[PULL 00/11] MIPS queue for October 24th, 2019

[PULL 00/11] MIPS queue for October 24th, 2019

[Aleksandar Markovic]

From: Aleksandar Markovic <amarkovic@wavecomp.com>

The following changes since commit ea0ec714d3109e0d0523b9dacb38030e4cb142a8:

  Merge remote-tracking branch 'remotes/xtensa/tags/20191023-xtensa' into staging (2019-10-24 09:55:01 +0100)

are available in the git repository at:

  https://github.com/AMarkovic/qemu tags/mips-queue-oct-24-2019

for you to fetch changes up to f4d200d0e55ebc4e9c9af50cb9317e2f6ebe9d0c:

  target/mips: Add support for emulation of CRC32 group of instructions (2019-10-24 13:00:37 +0200)

----------------------------------------------------------------

MIPS queue for October 24th, 2019

  - added emulation of R6 CRC32 instructions 
  - added several mostly cosmetic leanups
  - a checkpath warning is a false positive

----------------------------------------------------------------

Aleksandar Markovic (10):
  target/mips: Clean up helper.c
  target/mips: Clean up op_helper.c
  MAINTAINERS: Update mail address of Aleksandar Rikalo
  target/mips: msa: Split helpers for <MAX|MIN>_A.<B|H|W|D>
  target/mips: msa: Split helpers for <MAX|MIN>_<S|U>.<B|H|W|D>
  target/mips: msa: Split helpers for ILV<EV|OD|L|R>.<B|H|W|D>
  target/mips: msa: Split helpers for ADD<_A|S_A|S_S|S_U|V>.<B|H|W|D>
  target/mips: msa: Split helpers for HADD_<S|U>.<H|W|D>
  target/mips: msa: Split helpers for S<LL|RA|RAR|RL|RLR>.<B|H|W|D>
  target/mips: msa: Split helpers for PCK<EV|OD>.<B|H|W|D>

Yongbok Kim (1):
  target/mips: Add support for emulation of CRC32 group of instructions

 .mailmap                 |    5 +-
 MAINTAINERS              |   18 +-
 disas/mips.c             |    8 +
 target/mips/helper.c     |  123 +-
 target/mips/helper.h     |  135 +-
 target/mips/msa_helper.c | 4244 +++++++++++++++++++++++++++++-----------------
 target/mips/op_helper.c  | 1032 +++++++----
 target/mips/translate.c  |  483 +++++-
 8 files changed, 4039 insertions(+), 2009 deletions(-)

-- 
2.7.4

[PULL 01/11] target/mips: Clean up helper.c

[Aleksandar Markovic]

From: Aleksandar Markovic <amarkovic@wavecomp.com>

Mostly fix errors and warnings reported by 'checkpatch.pl -f'.

Cc: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Aleksandar Rikalo <aleksandar.rikalo@rt-rk.com>
Signed-off-by: Aleksandar Markovic <amarkovic@wavecomp.com>
Message-Id: <1571826227-10583-2-git-send-email-aleksandar.markovic@rt-rk.com>
---
 target/mips/helper.c | 123 +++++++++++++++++++++++++++++++--------------------
 1 file changed, 74 insertions(+), 49 deletions(-)

diff --git a/target/mips/helper.c b/target/mips/helper.c
index a2b6459..781930a 100644
--- a/target/mips/helper.c
+++ b/target/mips/helper.c
@@ -39,8 +39,8 @@ enum {
 #if !defined(CONFIG_USER_ONLY)
 
 /* no MMU emulation */
-int no_mmu_map_address (CPUMIPSState *env, hwaddr *physical, int *prot,
-                        target_ulong address, int rw, int access_type)
+int no_mmu_map_address(CPUMIPSState *env, hwaddr *physical, int *prot,
+                       target_ulong address, int rw, int access_type)
 {
     *physical = address;
     *prot = PAGE_READ | PAGE_WRITE | PAGE_EXEC;
@@ -48,26 +48,28 @@ int no_mmu_map_address (CPUMIPSState *env, hwaddr *physical, int *prot,
 }
 
 /* fixed mapping MMU emulation */
-int fixed_mmu_map_address (CPUMIPSState *env, hwaddr *physical, int *prot,
-                           target_ulong address, int rw, int access_type)
+int fixed_mmu_map_address(CPUMIPSState *env, hwaddr *physical, int *prot,
+                          target_ulong address, int rw, int access_type)
 {
     if (address <= (int32_t)0x7FFFFFFFUL) {
-        if (!(env->CP0_Status & (1 << CP0St_ERL)))
+        if (!(env->CP0_Status & (1 << CP0St_ERL))) {
             *physical = address + 0x40000000UL;
-        else
+        } else {
             *physical = address;
-    } else if (address <= (int32_t)0xBFFFFFFFUL)
+        }
+    } else if (address <= (int32_t)0xBFFFFFFFUL) {
         *physical = address & 0x1FFFFFFF;
-    else
+    } else {
         *physical = address;
+    }
 
     *prot = PAGE_READ | PAGE_WRITE | PAGE_EXEC;
     return TLBRET_MATCH;
 }
 
 /* MIPS32/MIPS64 R4000-style MMU emulation */
-int r4k_map_address (CPUMIPSState *env, hwaddr *physical, int *prot,
-                     target_ulong address, int rw, int access_type)
+int r4k_map_address(CPUMIPSState *env, hwaddr *physical, int *prot,
+                    target_ulong address, int rw, int access_type)
 {
     uint16_t ASID = env->CP0_EntryHi & env->CP0_EntryHi_ASID_mask;
     int i;
@@ -99,8 +101,9 @@ int r4k_map_address (CPUMIPSState *env, hwaddr *physical, int *prot,
             if (rw != MMU_DATA_STORE || (n ? tlb->D1 : tlb->D0)) {
                 *physical = tlb->PFN[n] | (address & (mask >> 1));
                 *prot = PAGE_READ;
-                if (n ? tlb->D1 : tlb->D0)
+                if (n ? tlb->D1 : tlb->D0) {
                     *prot |= PAGE_WRITE;
+                }
                 if (!(n ? tlb->XI1 : tlb->XI0)) {
                     *prot |= PAGE_EXEC;
                 }
@@ -130,7 +133,7 @@ static int is_seg_am_mapped(unsigned int am, bool eu, int mmu_idx)
     int32_t adetlb_mask;
 
     switch (mmu_idx) {
-    case 3 /* ERL */:
+    case 3: /* ERL */
         /* If EU is set, always unmapped */
         if (eu) {
             return 0;
@@ -204,7 +207,7 @@ static int get_segctl_physical_address(CPUMIPSState *env, hwaddr *physical,
                                     pa & ~(hwaddr)segmask);
 }
 
-static int get_physical_address (CPUMIPSState *env, hwaddr *physical,
+static int get_physical_address(CPUMIPSState *env, hwaddr *physical,
                                 int *prot, target_ulong real_address,
                                 int rw, int access_type, int mmu_idx)
 {
@@ -252,14 +255,15 @@ static int get_physical_address (CPUMIPSState *env, hwaddr *physical,
         } else {
             segctl = env->CP0_SegCtl2 >> 16;
         }
-        ret = get_segctl_physical_address(env, physical, prot, real_address, rw,
-                                          access_type, mmu_idx, segctl,
-                                          0x3FFFFFFF);
+        ret = get_segctl_physical_address(env, physical, prot,
+                                          real_address, rw, access_type,
+                                          mmu_idx, segctl, 0x3FFFFFFF);
 #if defined(TARGET_MIPS64)
     } else if (address < 0x4000000000000000ULL) {
         /* xuseg */
         if (UX && address <= (0x3FFFFFFFFFFFFFFFULL & env->SEGMask)) {
-            ret = env->tlb->map_address(env, physical, prot, real_address, rw, access_type);
+            ret = env->tlb->map_address(env, physical, prot,
+                                        real_address, rw, access_type);
         } else {
             ret = TLBRET_BADADDR;
         }
@@ -267,7 +271,8 @@ static int get_physical_address (CPUMIPSState *env, hwaddr *physical,
         /* xsseg */
         if ((supervisor_mode || kernel_mode) &&
             SX && address <= (0x7FFFFFFFFFFFFFFFULL & env->SEGMask)) {
-            ret = env->tlb->map_address(env, physical, prot, real_address, rw, access_type);
+            ret = env->tlb->map_address(env, physical, prot,
+                                        real_address, rw, access_type);
         } else {
             ret = TLBRET_BADADDR;
         }
@@ -307,7 +312,8 @@ static int get_physical_address (CPUMIPSState *env, hwaddr *physical,
         /* xkseg */
         if (kernel_mode && KX &&
             address <= (0xFFFFFFFF7FFFFFFFULL & env->SEGMask)) {
-            ret = env->tlb->map_address(env, physical, prot, real_address, rw, access_type);
+            ret = env->tlb->map_address(env, physical, prot,
+                                        real_address, rw, access_type);
         } else {
             ret = TLBRET_BADADDR;
         }
@@ -328,8 +334,10 @@ static int get_physical_address (CPUMIPSState *env, hwaddr *physical,
                                           access_type, mmu_idx,
                                           env->CP0_SegCtl0 >> 16, 0x1FFFFFFF);
     } else {
-        /* kseg3 */
-        /* XXX: debug segment is not emulated */
+        /*
+         * kseg3
+         * XXX: debug segment is not emulated
+         */
         ret = get_segctl_physical_address(env, physical, prot, real_address, rw,
                                           access_type, mmu_idx,
                                           env->CP0_SegCtl0, 0x1FFFFFFF);
@@ -515,9 +523,9 @@ static void raise_mmu_exception(CPUMIPSState *env, target_ulong address,
 #if defined(TARGET_MIPS64)
     env->CP0_EntryHi &= env->SEGMask;
     env->CP0_XContext =
-        /* PTEBase */   (env->CP0_XContext & ((~0ULL) << (env->SEGBITS - 7))) |
-        /* R */         (extract64(address, 62, 2) << (env->SEGBITS - 9)) |
-        /* BadVPN2 */   (extract64(address, 13, env->SEGBITS - 13) << 4);
+        (env->CP0_XContext & ((~0ULL) << (env->SEGBITS - 7))) | /* PTEBase */
+        (extract64(address, 62, 2) << (env->SEGBITS - 9)) |     /* R       */
+        (extract64(address, 13, env->SEGBITS - 13) << 4);       /* BadVPN2 */
 #endif
     cs->exception_index = exception;
     env->error_code = error_code;
@@ -945,7 +953,8 @@ bool mips_cpu_tlb_fill(CPUState *cs, vaddr address, int size,
 }
 
 #ifndef CONFIG_USER_ONLY
-hwaddr cpu_mips_translate_address(CPUMIPSState *env, target_ulong address, int rw)
+hwaddr cpu_mips_translate_address(CPUMIPSState *env, target_ulong address,
+                                  int rw)
 {
     hwaddr physical;
     int prot;
@@ -1005,7 +1014,7 @@ static const char * const excp_names[EXCP_LAST + 1] = {
 };
 #endif
 
-target_ulong exception_resume_pc (CPUMIPSState *env)
+target_ulong exception_resume_pc(CPUMIPSState *env)
 {
     target_ulong bad_pc;
     target_ulong isa_mode;
@@ -1013,8 +1022,10 @@ target_ulong exception_resume_pc (CPUMIPSState *env)
     isa_mode = !!(env->hflags & MIPS_HFLAG_M16);
     bad_pc = env->active_tc.PC | isa_mode;
     if (env->hflags & MIPS_HFLAG_BMASK) {
-        /* If the exception was raised from a delay slot, come back to
-           the jump.  */
+        /*
+         * If the exception was raised from a delay slot, come back to
+         * the jump.
+         */
         bad_pc -= (env->hflags & MIPS_HFLAG_B16 ? 2 : 4);
     }
 
@@ -1022,14 +1033,14 @@ target_ulong exception_resume_pc (CPUMIPSState *env)
 }
 
 #if !defined(CONFIG_USER_ONLY)
-static void set_hflags_for_handler (CPUMIPSState *env)
+static void set_hflags_for_handler(CPUMIPSState *env)
 {
     /* Exception handlers are entered in 32-bit mode.  */
     env->hflags &= ~(MIPS_HFLAG_M16);
     /* ...except that microMIPS lets you choose.  */
     if (env->insn_flags & ASE_MICROMIPS) {
-        env->hflags |= (!!(env->CP0_Config3
-                           & (1 << CP0C3_ISA_ON_EXC))
+        env->hflags |= (!!(env->CP0_Config3 &
+                           (1 << CP0C3_ISA_ON_EXC))
                         << MIPS_HFLAG_M16_SHIFT);
     }
 }
@@ -1096,10 +1107,12 @@ void mips_cpu_do_interrupt(CPUState *cs)
     switch (cs->exception_index) {
     case EXCP_DSS:
         env->CP0_Debug |= 1 << CP0DB_DSS;
-        /* Debug single step cannot be raised inside a delay slot and
-           resume will always occur on the next instruction
-           (but we assume the pc has always been updated during
-           code translation). */
+        /*
+         * Debug single step cannot be raised inside a delay slot and
+         * resume will always occur on the next instruction
+         * (but we assume the pc has always been updated during
+         * code translation).
+         */
         env->CP0_DEPC = env->active_tc.PC | !!(env->hflags & MIPS_HFLAG_M16);
         goto enter_debug_mode;
     case EXCP_DINT:
@@ -1111,7 +1124,8 @@ void mips_cpu_do_interrupt(CPUState *cs)
     case EXCP_DBp:
         env->CP0_Debug |= 1 << CP0DB_DBp;
         /* Setup DExcCode - SDBBP instruction */
-        env->CP0_Debug = (env->CP0_Debug & ~(0x1fULL << CP0DB_DEC)) | 9 << CP0DB_DEC;
+        env->CP0_Debug = (env->CP0_Debug & ~(0x1fULL << CP0DB_DEC)) |
+                         (9 << CP0DB_DEC);
         goto set_DEPC;
     case EXCP_DDBS:
         env->CP0_Debug |= 1 << CP0DB_DDBS;
@@ -1132,8 +1146,9 @@ void mips_cpu_do_interrupt(CPUState *cs)
         env->hflags |= MIPS_HFLAG_DM | MIPS_HFLAG_CP0;
         env->hflags &= ~(MIPS_HFLAG_KSU);
         /* EJTAG probe trap enable is not implemented... */
-        if (!(env->CP0_Status & (1 << CP0St_EXL)))
+        if (!(env->CP0_Status & (1 << CP0St_EXL))) {
             env->CP0_Cause &= ~(1U << CP0Ca_BD);
+        }
         env->active_tc.PC = env->exception_base + 0x480;
         set_hflags_for_handler(env);
         break;
@@ -1159,8 +1174,9 @@ void mips_cpu_do_interrupt(CPUState *cs)
         }
         env->hflags |= MIPS_HFLAG_CP0;
         env->hflags &= ~(MIPS_HFLAG_KSU);
-        if (!(env->CP0_Status & (1 << CP0St_EXL)))
+        if (!(env->CP0_Status & (1 << CP0St_EXL))) {
             env->CP0_Cause &= ~(1U << CP0Ca_BD);
+        }
         env->active_tc.PC = env->exception_base;
         set_hflags_for_handler(env);
         break;
@@ -1176,12 +1192,16 @@ void mips_cpu_do_interrupt(CPUState *cs)
                 uint32_t pending = (env->CP0_Cause & CP0Ca_IP_mask) >> CP0Ca_IP;
 
                 if (env->CP0_Config3 & (1 << CP0C3_VEIC)) {
-                    /* For VEIC mode, the external interrupt controller feeds
-                     * the vector through the CP0Cause IP lines.  */
+                    /*
+                     * For VEIC mode, the external interrupt controller feeds
+                     * the vector through the CP0Cause IP lines.
+                     */
                     vector = pending;
                 } else {
-                    /* Vectored Interrupts
-                     * Mask with Status.IM7-IM0 to get enabled interrupts. */
+                    /*
+                     * Vectored Interrupts
+                     * Mask with Status.IM7-IM0 to get enabled interrupts.
+                     */
                     pending &= (env->CP0_Status >> CP0St_IM) & 0xff;
                     /* Find the highest-priority interrupt. */
                     while (pending >>= 1) {
@@ -1354,7 +1374,8 @@ void mips_cpu_do_interrupt(CPUState *cs)
 
         env->active_tc.PC += offset;
         set_hflags_for_handler(env);
-        env->CP0_Cause = (env->CP0_Cause & ~(0x1f << CP0Ca_EC)) | (cause << CP0Ca_EC);
+        env->CP0_Cause = (env->CP0_Cause & ~(0x1f << CP0Ca_EC)) |
+                         (cause << CP0Ca_EC);
         break;
     default:
         abort();
@@ -1390,7 +1411,7 @@ bool mips_cpu_exec_interrupt(CPUState *cs, int interrupt_request)
 }
 
 #if !defined(CONFIG_USER_ONLY)
-void r4k_invalidate_tlb (CPUMIPSState *env, int idx, int use_extra)
+void r4k_invalidate_tlb(CPUMIPSState *env, int idx, int use_extra)
 {
     CPUState *cs = env_cpu(env);
     r4k_tlb_t *tlb;
@@ -1400,16 +1421,20 @@ void r4k_invalidate_tlb (CPUMIPSState *env, int idx, int use_extra)
     target_ulong mask;
 
     tlb = &env->tlb->mmu.r4k.tlb[idx];
-    /* The qemu TLB is flushed when the ASID changes, so no need to
-       flush these entries again.  */
+    /*
+     * The qemu TLB is flushed when the ASID changes, so no need to
+     * flush these entries again.
+     */
     if (tlb->G == 0 && tlb->ASID != ASID) {
         return;
     }
 
     if (use_extra && env->tlb->tlb_in_use < MIPS_TLB_MAX) {
-        /* For tlbwr, we can shadow the discarded entry into
-           a new (fake) TLB entry, as long as the guest can not
-           tell that it's there.  */
+        /*
+         * For tlbwr, we can shadow the discarded entry into
+         * a new (fake) TLB entry, as long as the guest can not
+         * tell that it's there.
+         */
         env->tlb->mmu.r4k.tlb[env->tlb->tlb_in_use] = *tlb;
         env->tlb->tlb_in_use++;
         return;
-- 
2.7.4

[PULL 02/11] target/mips: Clean up op_helper.c

[Aleksandar Markovic]

From: Aleksandar Markovic <amarkovic@wavecomp.com>

Mostly fix errors and warnings reported by 'checkpatch.pl -f'.

Reviewed-by: Aleksandar Rikalo <aleksandar.rikalo@rt-rk.com>
Signed-off-by: Aleksandar Markovic <amarkovic@wavecomp.com>
Message-Id: <1571826227-10583-3-git-send-email-aleksandar.markovic@rt-rk.com>
---
 target/mips/op_helper.c | 1010 +++++++++++++++++++++++++++++++----------------
 1 file changed, 663 insertions(+), 347 deletions(-)

diff --git a/target/mips/op_helper.c b/target/mips/op_helper.c
index 4de6465..18fcee4 100644
--- a/target/mips/op_helper.c
+++ b/target/mips/op_helper.c
@@ -64,8 +64,7 @@ static inline type do_##name(CPUMIPSState *env, target_ulong addr,      \
 static inline type do_##name(CPUMIPSState *env, target_ulong addr,      \
                              int mem_idx, uintptr_t retaddr)            \
 {                                                                       \
-    switch (mem_idx)                                                    \
-    {                                                                   \
+    switch (mem_idx) {                                                  \
     case 0: return (type) cpu_##insn##_kernel_ra(env, addr, retaddr);   \
     case 1: return (type) cpu_##insn##_super_ra(env, addr, retaddr);    \
     default:                                                            \
@@ -92,12 +91,17 @@ static inline void do_##name(CPUMIPSState *env, target_ulong addr,      \
 static inline void do_##name(CPUMIPSState *env, target_ulong addr,      \
                              type val, int mem_idx, uintptr_t retaddr)  \
 {                                                                       \
-    switch (mem_idx)                                                    \
-    {                                                                   \
-    case 0: cpu_##insn##_kernel_ra(env, addr, val, retaddr); break;     \
-    case 1: cpu_##insn##_super_ra(env, addr, val, retaddr); break;      \
+    switch (mem_idx) {                                                  \
+    case 0:                                                             \
+        cpu_##insn##_kernel_ra(env, addr, val, retaddr);                \
+        break;                                                          \
+    case 1:                                                             \
+        cpu_##insn##_super_ra(env, addr, val, retaddr);                 \
+        break;                                                          \
     default:                                                            \
-    case 2: cpu_##insn##_user_ra(env, addr, val, retaddr); break;       \
+    case 2:                                                             \
+        cpu_##insn##_user_ra(env, addr, val, retaddr);                  \
+        break;                                                          \
     case 3:                                                             \
         cpu_##insn##_error_ra(env, addr, val, retaddr);                 \
         break;                                                          \
@@ -114,7 +118,8 @@ HELPER_ST(sd, stq, uint64_t)
 /* 64 bits arithmetic for 32 bits hosts */
 static inline uint64_t get_HILO(CPUMIPSState *env)
 {
-    return ((uint64_t)(env->active_tc.HI[0]) << 32) | (uint32_t)env->active_tc.LO[0];
+    return ((uint64_t)(env->active_tc.HI[0]) << 32) |
+           (uint32_t)env->active_tc.LO[0];
 }
 
 static inline target_ulong set_HIT0_LO(CPUMIPSState *env, uint64_t HILO)
@@ -435,9 +440,10 @@ void helper_swr(CPUMIPSState *env, target_ulong arg1, target_ulong arg2,
 }
 
 #if defined(TARGET_MIPS64)
-/* "half" load and stores.  We must do the memory access inline,
-   or fault handling won't work.  */
-
+/*
+ * "half" load and stores.  We must do the memory access inline,
+ * or fault handling won't work.
+ */
 #ifdef TARGET_WORDS_BIGENDIAN
 #define GET_LMASK64(v) ((v) & 7)
 #else
@@ -535,7 +541,7 @@ void helper_lwm(CPUMIPSState *env, target_ulong addr, target_ulong reglist,
     target_ulong base_reglist = reglist & 0xf;
     target_ulong do_r31 = reglist & 0x10;
 
-    if (base_reglist > 0 && base_reglist <= ARRAY_SIZE (multiple_regs)) {
+    if (base_reglist > 0 && base_reglist <= ARRAY_SIZE(multiple_regs)) {
         target_ulong i;
 
         for (i = 0; i < base_reglist; i++) {
@@ -557,7 +563,7 @@ void helper_swm(CPUMIPSState *env, target_ulong addr, target_ulong reglist,
     target_ulong base_reglist = reglist & 0xf;
     target_ulong do_r31 = reglist & 0x10;
 
-    if (base_reglist > 0 && base_reglist <= ARRAY_SIZE (multiple_regs)) {
+    if (base_reglist > 0 && base_reglist <= ARRAY_SIZE(multiple_regs)) {
         target_ulong i;
 
         for (i = 0; i < base_reglist; i++) {
@@ -579,7 +585,7 @@ void helper_ldm(CPUMIPSState *env, target_ulong addr, target_ulong reglist,
     target_ulong base_reglist = reglist & 0xf;
     target_ulong do_r31 = reglist & 0x10;
 
-    if (base_reglist > 0 && base_reglist <= ARRAY_SIZE (multiple_regs)) {
+    if (base_reglist > 0 && base_reglist <= ARRAY_SIZE(multiple_regs)) {
         target_ulong i;
 
         for (i = 0; i < base_reglist; i++) {
@@ -600,7 +606,7 @@ void helper_sdm(CPUMIPSState *env, target_ulong addr, target_ulong reglist,
     target_ulong base_reglist = reglist & 0xf;
     target_ulong do_r31 = reglist & 0x10;
 
-    if (base_reglist > 0 && base_reglist <= ARRAY_SIZE (multiple_regs)) {
+    if (base_reglist > 0 && base_reglist <= ARRAY_SIZE(multiple_regs)) {
         target_ulong i;
 
         for (i = 0; i < base_reglist; i++) {
@@ -623,8 +629,10 @@ static bool mips_vpe_is_wfi(MIPSCPU *c)
     CPUState *cpu = CPU(c);
     CPUMIPSState *env = &c->env;
 
-    /* If the VPE is halted but otherwise active, it means it's waiting for
-       an interrupt.  */
+    /*
+     * If the VPE is halted but otherwise active, it means it's waiting for
+     * an interrupt.\
+     */
     return cpu->halted && mips_vpe_active(env);
 }
 
@@ -638,9 +646,11 @@ static bool mips_vp_is_wfi(MIPSCPU *c)
 
 static inline void mips_vpe_wake(MIPSCPU *c)
 {
-    /* Don't set ->halted = 0 directly, let it be done via cpu_has_work
-       because there might be other conditions that state that c should
-       be sleeping.  */
+    /*
+     * Don't set ->halted = 0 directly, let it be done via cpu_has_work
+     * because there might be other conditions that state that c should
+     * be sleeping.
+     */
     qemu_mutex_lock_iothread();
     cpu_interrupt(CPU(c), CPU_INTERRUPT_WAKE);
     qemu_mutex_unlock_iothread();
@@ -650,8 +660,10 @@ static inline void mips_vpe_sleep(MIPSCPU *cpu)
 {
     CPUState *cs = CPU(cpu);
 
-    /* The VPE was shut off, really go to bed.
-       Reset any old _WAKE requests.  */
+    /*
+     * The VPE was shut off, really go to bed.
+     * Reset any old _WAKE requests.
+     */
     cs->halted = 1;
     cpu_reset_interrupt(cs, CPU_INTERRUPT_WAKE);
 }
@@ -684,9 +696,12 @@ static inline void mips_tc_sleep(MIPSCPU *cpu, int tc)
  * This function will transform @tc into a local index within the
  * returned #CPUMIPSState.
  */
-/* FIXME: This code assumes that all VPEs have the same number of TCs,
-          which depends on runtime setup. Can probably be fixed by
-          walking the list of CPUMIPSStates.  */
+
+/*
+ * FIXME: This code assumes that all VPEs have the same number of TCs,
+ *        which depends on runtime setup. Can probably be fixed by
+ *        walking the list of CPUMIPSStates.
+ */
 static CPUMIPSState *mips_cpu_map_tc(CPUMIPSState *env, int *tc)
 {
     MIPSCPU *cpu;
@@ -712,17 +727,21 @@ static CPUMIPSState *mips_cpu_map_tc(CPUMIPSState *env, int *tc)
     return &cpu->env;
 }
 
-/* The per VPE CP0_Status register shares some fields with the per TC
-   CP0_TCStatus registers. These fields are wired to the same registers,
-   so changes to either of them should be reflected on both registers.
-
-   Also, EntryHi shares the bottom 8 bit ASID with TCStauts.
-
-   These helper call synchronizes the regs for a given cpu.  */
+/*
+ * The per VPE CP0_Status register shares some fields with the per TC
+ * CP0_TCStatus registers. These fields are wired to the same registers,
+ * so changes to either of them should be reflected on both registers.
+ *
+ * Also, EntryHi shares the bottom 8 bit ASID with TCStauts.
+ *
+ * These helper call synchronizes the regs for a given cpu.
+ */
 
-/* Called for updates to CP0_Status.  Defined in "cpu.h" for gdbstub.c.  */
-/* static inline void sync_c0_status(CPUMIPSState *env, CPUMIPSState *cpu,
-                                     int tc);  */
+/*
+ * Called for updates to CP0_Status.  Defined in "cpu.h" for gdbstub.c.
+ * static inline void sync_c0_status(CPUMIPSState *env, CPUMIPSState *cpu,
+ *                                   int tc);
+ */
 
 /* Called for updates to CP0_TCStatus.  */
 static void sync_c0_tcstatus(CPUMIPSState *cpu, int tc,
@@ -805,10 +824,11 @@ target_ulong helper_mftc0_tcstatus(CPUMIPSState *env)
     int other_tc = env->CP0_VPEControl & (0xff << CP0VPECo_TargTC);
     CPUMIPSState *other = mips_cpu_map_tc(env, &other_tc);
 
-    if (other_tc == other->current_tc)
+    if (other_tc == other->current_tc) {
         return other->active_tc.CP0_TCStatus;
-    else
+    } else {
         return other->tcs[other_tc].CP0_TCStatus;
+    }
 }
 
 target_ulong helper_mfc0_tcbind(CPUMIPSState *env)
@@ -821,10 +841,11 @@ target_ulong helper_mftc0_tcbind(CPUMIPSState *env)
     int other_tc = env->CP0_VPEControl & (0xff << CP0VPECo_TargTC);
     CPUMIPSState *other = mips_cpu_map_tc(env, &other_tc);
 
-    if (other_tc == other->current_tc)
+    if (other_tc == other->current_tc) {
         return other->active_tc.CP0_TCBind;
-    else
+    } else {
         return other->tcs[other_tc].CP0_TCBind;
+    }
 }
 
 target_ulong helper_mfc0_tcrestart(CPUMIPSState *env)
@@ -837,10 +858,11 @@ target_ulong helper_mftc0_tcrestart(CPUMIPSState *env)
     int other_tc = env->CP0_VPEControl & (0xff << CP0VPECo_TargTC);
     CPUMIPSState *other = mips_cpu_map_tc(env, &other_tc);
 
-    if (other_tc == other->current_tc)
+    if (other_tc == other->current_tc) {
         return other->active_tc.PC;
-    else
+    } else {
         return other->tcs[other_tc].PC;
+    }
 }
 
 target_ulong helper_mfc0_tchalt(CPUMIPSState *env)
@@ -853,10 +875,11 @@ target_ulong helper_mftc0_tchalt(CPUMIPSState *env)
     int other_tc = env->CP0_VPEControl & (0xff << CP0VPECo_TargTC);
     CPUMIPSState *other = mips_cpu_map_tc(env, &other_tc);
 
-    if (other_tc == other->current_tc)
+    if (other_tc == other->current_tc) {
         return other->active_tc.CP0_TCHalt;
-    else
+    } else {
         return other->tcs[other_tc].CP0_TCHalt;
+    }
 }
 
 target_ulong helper_mfc0_tccontext(CPUMIPSState *env)
@@ -869,10 +892,11 @@ target_ulong helper_mftc0_tccontext(CPUMIPSState *env)
     int other_tc = env->CP0_VPEControl & (0xff << CP0VPECo_TargTC);
     CPUMIPSState *other = mips_cpu_map_tc(env, &other_tc);
 
-    if (other_tc == other->current_tc)
+    if (other_tc == other->current_tc) {
         return other->active_tc.CP0_TCContext;
-    else
+    } else {
         return other->tcs[other_tc].CP0_TCContext;
+    }
 }
 
 target_ulong helper_mfc0_tcschedule(CPUMIPSState *env)
@@ -885,10 +909,11 @@ target_ulong helper_mftc0_tcschedule(CPUMIPSState *env)
     int other_tc = env->CP0_VPEControl & (0xff << CP0VPECo_TargTC);
     CPUMIPSState *other = mips_cpu_map_tc(env, &other_tc);
 
-    if (other_tc == other->current_tc)
+    if (other_tc == other->current_tc) {
         return other->active_tc.CP0_TCSchedule;
-    else
+    } else {
         return other->tcs[other_tc].CP0_TCSchedule;
+    }
 }
 
 target_ulong helper_mfc0_tcschefback(CPUMIPSState *env)
@@ -901,10 +926,11 @@ target_ulong helper_mftc0_tcschefback(CPUMIPSState *env)
     int other_tc = env->CP0_VPEControl & (0xff << CP0VPECo_TargTC);
     CPUMIPSState *other = mips_cpu_map_tc(env, &other_tc);
 
-    if (other_tc == other->current_tc)
+    if (other_tc == other->current_tc) {
         return other->active_tc.CP0_TCScheFBack;
-    else
+    } else {
         return other->tcs[other_tc].CP0_TCScheFBack;
+    }
 }
 
 target_ulong helper_mfc0_count(CPUMIPSState *env)
@@ -987,8 +1013,9 @@ target_ulong helper_mfc0_watchhi(CPUMIPSState *env, uint32_t sel)
 target_ulong helper_mfc0_debug(CPUMIPSState *env)
 {
     target_ulong t0 = env->CP0_Debug;
-    if (env->hflags & MIPS_HFLAG_DM)
+    if (env->hflags & MIPS_HFLAG_DM) {
         t0 |= 1 << CP0DB_DM;
+    }
 
     return t0;
 }
@@ -999,10 +1026,11 @@ target_ulong helper_mftc0_debug(CPUMIPSState *env)
     int32_t tcstatus;
     CPUMIPSState *other = mips_cpu_map_tc(env, &other_tc);
 
-    if (other_tc == other->current_tc)
+    if (other_tc == other->current_tc) {
         tcstatus = other->active_tc.CP0_Debug_tcstatus;
-    else
+    } else {
         tcstatus = other->tcs[other_tc].CP0_Debug_tcstatus;
+    }
 
     /* XXX: Might be wrong, check with EJTAG spec. */
     return (other->CP0_Debug & ~((1 << CP0DB_SSt) | (1 << CP0DB_Halt))) |
@@ -1076,14 +1104,16 @@ void helper_mtc0_mvpcontrol(CPUMIPSState *env, target_ulong arg1)
     uint32_t mask = 0;
     uint32_t newval;
 
-    if (env->CP0_VPEConf0 & (1 << CP0VPEC0_MVP))
+    if (env->CP0_VPEConf0 & (1 << CP0VPEC0_MVP)) {
         mask |= (1 << CP0MVPCo_CPA) | (1 << CP0MVPCo_VPC) |
                 (1 << CP0MVPCo_EVP);
-    if (env->mvp->CP0_MVPControl & (1 << CP0MVPCo_VPC))
+    }
+    if (env->mvp->CP0_MVPControl & (1 << CP0MVPCo_VPC)) {
         mask |= (1 << CP0MVPCo_STLB);
+    }
     newval = (env->mvp->CP0_MVPControl & ~mask) | (arg1 & mask);
 
-    // TODO: Enable/disable shared TLB, enable/disable VPEs.
+    /* TODO: Enable/disable shared TLB, enable/disable VPEs. */
 
     env->mvp->CP0_MVPControl = newval;
 }
@@ -1097,10 +1127,12 @@ void helper_mtc0_vpecontrol(CPUMIPSState *env, target_ulong arg1)
            (1 << CP0VPECo_TE) | (0xff << CP0VPECo_TargTC);
     newval = (env->CP0_VPEControl & ~mask) | (arg1 & mask);
 
-    /* Yield scheduler intercept not implemented. */
-    /* Gating storage scheduler intercept not implemented. */
+    /*
+     * Yield scheduler intercept not implemented.
+     * Gating storage scheduler intercept not implemented.
+     */
 
-    // TODO: Enable/disable TCs.
+    /* TODO: Enable/disable TCs. */
 
     env->CP0_VPEControl = newval;
 }
@@ -1143,13 +1175,14 @@ void helper_mtc0_vpeconf0(CPUMIPSState *env, target_ulong arg1)
     uint32_t newval;
 
     if (env->CP0_VPEConf0 & (1 << CP0VPEC0_MVP)) {
-        if (env->CP0_VPEConf0 & (1 << CP0VPEC0_VPA))
+        if (env->CP0_VPEConf0 & (1 << CP0VPEC0_VPA)) {
             mask |= (0xff << CP0VPEC0_XTC);
+        }
         mask |= (1 << CP0VPEC0_MVP) | (1 << CP0VPEC0_VPA);
     }
     newval = (env->CP0_VPEConf0 & ~mask) | (arg1 & mask);
 
-    // TODO: TC exclusive handling due to ERL/EXL.
+    /* TODO: TC exclusive handling due to ERL/EXL. */
 
     env->CP0_VPEConf0 = newval;
 }
@@ -1181,7 +1214,7 @@ void helper_mtc0_vpeconf1(CPUMIPSState *env, target_ulong arg1)
     /* UDI not implemented. */
     /* CP2 not implemented. */
 
-    // TODO: Handle FPU (CP1) binding.
+    /* TODO: Handle FPU (CP1) binding. */
 
     env->CP0_VPEConf1 = newval;
 }
@@ -1233,10 +1266,11 @@ void helper_mttc0_tcstatus(CPUMIPSState *env, target_ulong arg1)
     int other_tc = env->CP0_VPEControl & (0xff << CP0VPECo_TargTC);
     CPUMIPSState *other = mips_cpu_map_tc(env, &other_tc);
 
-    if (other_tc == other->current_tc)
+    if (other_tc == other->current_tc) {
         other->active_tc.CP0_TCStatus = arg1;
-    else
+    } else {
         other->tcs[other_tc].CP0_TCStatus = arg1;
+    }
     sync_c0_tcstatus(other, other_tc, arg1);
 }
 
@@ -1245,8 +1279,9 @@ void helper_mtc0_tcbind(CPUMIPSState *env, target_ulong arg1)
     uint32_t mask = (1 << CP0TCBd_TBE);
     uint32_t newval;
 
-    if (env->mvp->CP0_MVPControl & (1 << CP0MVPCo_VPC))
+    if (env->mvp->CP0_MVPControl & (1 << CP0MVPCo_VPC)) {
         mask |= (1 << CP0TCBd_CurVPE);
+    }
     newval = (env->active_tc.CP0_TCBind & ~mask) | (arg1 & mask);
     env->active_tc.CP0_TCBind = newval;
 }
@@ -1258,8 +1293,9 @@ void helper_mttc0_tcbind(CPUMIPSState *env, target_ulong arg1)
     uint32_t newval;
     CPUMIPSState *other = mips_cpu_map_tc(env, &other_tc);
 
-    if (other->mvp->CP0_MVPControl & (1 << CP0MVPCo_VPC))
+    if (other->mvp->CP0_MVPControl & (1 << CP0MVPCo_VPC)) {
         mask |= (1 << CP0TCBd_CurVPE);
+    }
     if (other_tc == other->current_tc) {
         newval = (other->active_tc.CP0_TCBind & ~mask) | (arg1 & mask);
         other->active_tc.CP0_TCBind = newval;
@@ -1304,7 +1340,7 @@ void helper_mtc0_tchalt(CPUMIPSState *env, target_ulong arg1)
 
     env->active_tc.CP0_TCHalt = arg1 & 0x1;
 
-    // TODO: Halt TC / Restart (if allocated+active) TC.
+    /* TODO: Halt TC / Restart (if allocated+active) TC. */
     if (env->active_tc.CP0_TCHalt & 1) {
         mips_tc_sleep(cpu, env->current_tc);
     } else {
@@ -1318,12 +1354,13 @@ void helper_mttc0_tchalt(CPUMIPSState *env, target_ulong arg1)
     CPUMIPSState *other = mips_cpu_map_tc(env, &other_tc);
     MIPSCPU *other_cpu = env_archcpu(other);
 
-    // TODO: Halt TC / Restart (if allocated+active) TC.
+    /* TODO: Halt TC / Restart (if allocated+active) TC. */
 
-    if (other_tc == other->current_tc)
+    if (other_tc == other->current_tc) {
         other->active_tc.CP0_TCHalt = arg1;
-    else
+    } else {
         other->tcs[other_tc].CP0_TCHalt = arg1;
+    }
 
     if (arg1 & 1) {
         mips_tc_sleep(other_cpu, other_tc);
@@ -1342,10 +1379,11 @@ void helper_mttc0_tccontext(CPUMIPSState *env, target_ulong arg1)
     int other_tc = env->CP0_VPEControl & (0xff << CP0VPECo_TargTC);
     CPUMIPSState *other = mips_cpu_map_tc(env, &other_tc);
 
-    if (other_tc == other->current_tc)
+    if (other_tc == other->current_tc) {
         other->active_tc.CP0_TCContext = arg1;
-    else
+    } else {
         other->tcs[other_tc].CP0_TCContext = arg1;
+    }
 }
 
 void helper_mtc0_tcschedule(CPUMIPSState *env, target_ulong arg1)
@@ -1358,10 +1396,11 @@ void helper_mttc0_tcschedule(CPUMIPSState *env, target_ulong arg1)
     int other_tc = env->CP0_VPEControl & (0xff << CP0VPECo_TargTC);
     CPUMIPSState *other = mips_cpu_map_tc(env, &other_tc);
 
-    if (other_tc == other->current_tc)
+    if (other_tc == other->current_tc) {
         other->active_tc.CP0_TCSchedule = arg1;
-    else
+    } else {
         other->tcs[other_tc].CP0_TCSchedule = arg1;
+    }
 }
 
 void helper_mtc0_tcschefback(CPUMIPSState *env, target_ulong arg1)
@@ -1374,10 +1413,11 @@ void helper_mttc0_tcschefback(CPUMIPSState *env, target_ulong arg1)
     int other_tc = env->CP0_VPEControl & (0xff << CP0VPECo_TargTC);
     CPUMIPSState *other = mips_cpu_map_tc(env, &other_tc);
 
-    if (other_tc == other->current_tc)
+    if (other_tc == other->current_tc) {
         other->active_tc.CP0_TCScheFBack = arg1;
-    else
+    } else {
         other->tcs[other_tc].CP0_TCScheFBack = arg1;
+    }
 }
 
 void helper_mtc0_entrylo1(CPUMIPSState *env, target_ulong arg1)
@@ -1703,9 +1743,15 @@ void helper_mtc0_status(CPUMIPSState *env, target_ulong arg1)
         case 3:
             qemu_log(", ERL\n");
             break;
-        case MIPS_HFLAG_UM: qemu_log(", UM\n"); break;
-        case MIPS_HFLAG_SM: qemu_log(", SM\n"); break;
-        case MIPS_HFLAG_KM: qemu_log("\n"); break;
+        case MIPS_HFLAG_UM:
+            qemu_log(", UM\n");
+            break;
+        case MIPS_HFLAG_SM:
+            qemu_log(", SM\n");
+            break;
+        case MIPS_HFLAG_KM:
+            qemu_log("\n");
+            break;
         default:
             cpu_abort(env_cpu(env), "Invalid MMU mode!\n");
             break;
@@ -1860,21 +1906,26 @@ void helper_mtc0_maari(CPUMIPSState *env, target_ulong arg1)
 {
     int index = arg1 & 0x3f;
     if (index == 0x3f) {
-        /* Software may write all ones to INDEX to determine the
-           maximum value supported. */
+        /*
+         * Software may write all ones to INDEX to determine the
+         *  maximum value supported.
+         */
         env->CP0_MAARI = MIPS_MAAR_MAX - 1;
     } else if (index < MIPS_MAAR_MAX) {
         env->CP0_MAARI = index;
     }
-    /* Other than the all ones, if the
-       value written is not supported, then INDEX is unchanged
-       from its previous value. */
+    /*
+     * Other than the all ones, if the value written is not supported,
+     * then INDEX is unchanged from its previous value.
+     */
 }
 
 void helper_mtc0_watchlo(CPUMIPSState *env, target_ulong arg1, uint32_t sel)
 {
-    /* Watch exceptions for instructions, data loads, data stores
-       not implemented. */
+    /*
+     * Watch exceptions for instructions, data loads, data stores
+     * not implemented.
+     */
     env->CP0_WatchLo[sel] = (arg1 & ~0x7);
 }
 
@@ -1899,10 +1950,11 @@ void helper_mtc0_framemask(CPUMIPSState *env, target_ulong arg1)
 void helper_mtc0_debug(CPUMIPSState *env, target_ulong arg1)
 {
     env->CP0_Debug = (env->CP0_Debug & 0x8C03FC1F) | (arg1 & 0x13300120);
-    if (arg1 & (1 << CP0DB_DM))
+    if (arg1 & (1 << CP0DB_DM)) {
         env->hflags |= MIPS_HFLAG_DM;
-    else
+    } else {
         env->hflags &= ~MIPS_HFLAG_DM;
+    }
 }
 
 void helper_mttc0_debug(CPUMIPSState *env, target_ulong arg1)
@@ -1912,10 +1964,11 @@ void helper_mttc0_debug(CPUMIPSState *env, target_ulong arg1)
     CPUMIPSState *other = mips_cpu_map_tc(env, &other_tc);
 
     /* XXX: Might be wrong, check with EJTAG spec. */
-    if (other_tc == other->current_tc)
+    if (other_tc == other->current_tc) {
         other->active_tc.CP0_Debug_tcstatus = val;
-    else
+    } else {
         other->tcs[other_tc].CP0_Debug_tcstatus = val;
+    }
     other->CP0_Debug = (other->CP0_Debug &
                      ((1 << CP0DB_SSt) | (1 << CP0DB_Halt))) |
                      (arg1 & ~((1 << CP0DB_SSt) | (1 << CP0DB_Halt)));
@@ -1944,9 +1997,11 @@ void helper_mtc0_errctl(CPUMIPSState *env, target_ulong arg1)
 void helper_mtc0_taglo(CPUMIPSState *env, target_ulong arg1)
 {
     if (env->hflags & MIPS_HFLAG_ITC_CACHE) {
-        /* If CACHE instruction is configured for ITC tags then make all
-           CP0.TagLo bits writable. The actual write to ITC Configuration
-           Tag will take care of the read-only bits. */
+        /*
+         * If CACHE instruction is configured for ITC tags then make all
+         * CP0.TagLo bits writable. The actual write to ITC Configuration
+         * Tag will take care of the read-only bits.
+         */
         env->CP0_TagLo = arg1;
     } else {
         env->CP0_TagLo = arg1 & 0xFFFFFCF6;
@@ -1974,10 +2029,11 @@ target_ulong helper_mftgpr(CPUMIPSState *env, uint32_t sel)
     int other_tc = env->CP0_VPEControl & (0xff << CP0VPECo_TargTC);
     CPUMIPSState *other = mips_cpu_map_tc(env, &other_tc);
 
-    if (other_tc == other->current_tc)
+    if (other_tc == other->current_tc) {
         return other->active_tc.gpr[sel];
-    else
+    } else {
         return other->tcs[other_tc].gpr[sel];
+    }
 }
 
 target_ulong helper_mftlo(CPUMIPSState *env, uint32_t sel)
@@ -1985,10 +2041,11 @@ target_ulong helper_mftlo(CPUMIPSState *env, uint32_t sel)
     int other_tc = env->CP0_VPEControl & (0xff << CP0VPECo_TargTC);
     CPUMIPSState *other = mips_cpu_map_tc(env, &other_tc);
 
-    if (other_tc == other->current_tc)
+    if (other_tc == other->current_tc) {
         return other->active_tc.LO[sel];
-    else
+    } else {
         return other->tcs[other_tc].LO[sel];
+    }
 }
 
 target_ulong helper_mfthi(CPUMIPSState *env, uint32_t sel)
@@ -1996,10 +2053,11 @@ target_ulong helper_mfthi(CPUMIPSState *env, uint32_t sel)
     int other_tc = env->CP0_VPEControl & (0xff << CP0VPECo_TargTC);
     CPUMIPSState *other = mips_cpu_map_tc(env, &other_tc);
 
-    if (other_tc == other->current_tc)
+    if (other_tc == other->current_tc) {
         return other->active_tc.HI[sel];
-    else
+    } else {
         return other->tcs[other_tc].HI[sel];
+    }
 }
 
 target_ulong helper_mftacx(CPUMIPSState *env, uint32_t sel)
@@ -2007,10 +2065,11 @@ target_ulong helper_mftacx(CPUMIPSState *env, uint32_t sel)
     int other_tc = env->CP0_VPEControl & (0xff << CP0VPECo_TargTC);
     CPUMIPSState *other = mips_cpu_map_tc(env, &other_tc);
 
-    if (other_tc == other->current_tc)
+    if (other_tc == other->current_tc) {
         return other->active_tc.ACX[sel];
-    else
+    } else {
         return other->tcs[other_tc].ACX[sel];
+    }
 }
 
 target_ulong helper_mftdsp(CPUMIPSState *env)
@@ -2018,10 +2077,11 @@ target_ulong helper_mftdsp(CPUMIPSState *env)
     int other_tc = env->CP0_VPEControl & (0xff << CP0VPECo_TargTC);
     CPUMIPSState *other = mips_cpu_map_tc(env, &other_tc);
 
-    if (other_tc == other->current_tc)
+    if (other_tc == other->current_tc) {
         return other->active_tc.DSPControl;
-    else
+    } else {
         return other->tcs[other_tc].DSPControl;
+    }
 }
 
 void helper_mttgpr(CPUMIPSState *env, target_ulong arg1, uint32_t sel)
@@ -2029,10 +2089,11 @@ void helper_mttgpr(CPUMIPSState *env, target_ulong arg1, uint32_t sel)
     int other_tc = env->CP0_VPEControl & (0xff << CP0VPECo_TargTC);
     CPUMIPSState *other = mips_cpu_map_tc(env, &other_tc);
 
-    if (other_tc == other->current_tc)
+    if (other_tc == other->current_tc) {
         other->active_tc.gpr[sel] = arg1;
-    else
+    } else {
         other->tcs[other_tc].gpr[sel] = arg1;
+    }
 }
 
 void helper_mttlo(CPUMIPSState *env, target_ulong arg1, uint32_t sel)
@@ -2040,10 +2101,11 @@ void helper_mttlo(CPUMIPSState *env, target_ulong arg1, uint32_t sel)
     int other_tc = env->CP0_VPEControl & (0xff << CP0VPECo_TargTC);
     CPUMIPSState *other = mips_cpu_map_tc(env, &other_tc);
 
-    if (other_tc == other->current_tc)
+    if (other_tc == other->current_tc) {
         other->active_tc.LO[sel] = arg1;
-    else
+    } else {
         other->tcs[other_tc].LO[sel] = arg1;
+    }
 }
 
 void helper_mtthi(CPUMIPSState *env, target_ulong arg1, uint32_t sel)
@@ -2051,10 +2113,11 @@ void helper_mtthi(CPUMIPSState *env, target_ulong arg1, uint32_t sel)
     int other_tc = env->CP0_VPEControl & (0xff << CP0VPECo_TargTC);
     CPUMIPSState *other = mips_cpu_map_tc(env, &other_tc);
 
-    if (other_tc == other->current_tc)
+    if (other_tc == other->current_tc) {
         other->active_tc.HI[sel] = arg1;
-    else
+    } else {
         other->tcs[other_tc].HI[sel] = arg1;
+    }
 }
 
 void helper_mttacx(CPUMIPSState *env, target_ulong arg1, uint32_t sel)
@@ -2062,10 +2125,11 @@ void helper_mttacx(CPUMIPSState *env, target_ulong arg1, uint32_t sel)
     int other_tc = env->CP0_VPEControl & (0xff << CP0VPECo_TargTC);
     CPUMIPSState *other = mips_cpu_map_tc(env, &other_tc);
 
-    if (other_tc == other->current_tc)
+    if (other_tc == other->current_tc) {
         other->active_tc.ACX[sel] = arg1;
-    else
+    } else {
         other->tcs[other_tc].ACX[sel] = arg1;
+    }
 }
 
 void helper_mttdsp(CPUMIPSState *env, target_ulong arg1)
@@ -2073,22 +2137,23 @@ void helper_mttdsp(CPUMIPSState *env, target_ulong arg1)
     int other_tc = env->CP0_VPEControl & (0xff << CP0VPECo_TargTC);
     CPUMIPSState *other = mips_cpu_map_tc(env, &other_tc);
 
-    if (other_tc == other->current_tc)
+    if (other_tc == other->current_tc) {
         other->active_tc.DSPControl = arg1;
-    else
+    } else {
         other->tcs[other_tc].DSPControl = arg1;
+    }
 }
 
 /* MIPS MT functions */
 target_ulong helper_dmt(void)
 {
-    // TODO
-     return 0;
+    /* TODO */
+    return 0;
 }
 
 target_ulong helper_emt(void)
 {
-    // TODO
+    /* TODO */
     return 0;
 }
 
@@ -2130,8 +2195,10 @@ target_ulong helper_evpe(CPUMIPSState *env)
 
 void helper_fork(target_ulong arg1, target_ulong arg2)
 {
-    // arg1 = rt, arg2 = rs
-    // TODO: store to TC register
+    /*
+     * arg1 = rt, arg2 = rs
+     * TODO: store to TC register
+     */
 }
 
 target_ulong helper_yield(CPUMIPSState *env, target_ulong arg)
@@ -2149,11 +2216,12 @@ target_ulong helper_yield(CPUMIPSState *env, target_ulong arg)
             }
         }
     } else if (arg1 == 0) {
-        if (0 /* TODO: TC underflow */) {
+        if (0) {
+            /* TODO: TC underflow */
             env->CP0_VPEControl &= ~(0x7 << CP0VPECo_EXCPT);
             do_raise_exception(env, EXCP_THREAD, GETPC());
         } else {
-            // TODO: Deallocate TC
+            /* TODO: Deallocate TC */
         }
     } else if (arg1 > 0) {
         /* Yield qualifier inputs not implemented. */
@@ -2193,8 +2261,10 @@ target_ulong helper_evp(CPUMIPSState *env)
         CPU_FOREACH(other_cs) {
             MIPSCPU *other_cpu = MIPS_CPU(other_cs);
             if ((&other_cpu->env != env) && !mips_vp_is_wfi(other_cpu)) {
-                /* If the VP is WFI, don't disturb its sleep.
-                 * Otherwise, wake it up. */
+                /*
+                 * If the VP is WFI, don't disturb its sleep.
+                 * Otherwise, wake it up.
+                 */
                 mips_vpe_wake(other_cpu);
             }
         }
@@ -2206,7 +2276,7 @@ target_ulong helper_evp(CPUMIPSState *env)
 
 #ifndef CONFIG_USER_ONLY
 /* TLB management */
-static void r4k_mips_tlb_flush_extra (CPUMIPSState *env, int first)
+static void r4k_mips_tlb_flush_extra(CPUMIPSState *env, int first)
 {
     /* Discard entries from env->tlb[first] onwards.  */
     while (env->tlb->tlb_in_use > first) {
@@ -2308,8 +2378,10 @@ void r4k_helper_tlbwi(CPUMIPSState *env)
     XI1 = (env->CP0_EntryLo1 >> CP0EnLo_XI) &1;
     RI1 = (env->CP0_EntryLo1 >> CP0EnLo_RI) &1;
 
-    /* Discard cached TLB entries, unless tlbwi is just upgrading access
-       permissions on the current entry. */
+    /*
+     * Discard cached TLB entries, unless tlbwi is just upgrading access
+     * permissions on the current entry.
+     */
     if (tlb->VPN != VPN || tlb->ASID != ASID || tlb->G != G ||
         (!tlb->EHINV && EHINV) ||
         (tlb->V0 && !V0) || (tlb->D0 && !D0) ||
@@ -2370,7 +2442,7 @@ void r4k_helper_tlbp(CPUMIPSState *env)
 #endif
             /* Check ASID, virtual page number & size */
             if ((tlb->G == 1 || tlb->ASID == ASID) && VPN == tag) {
-                r4k_mips_tlb_flush_extra (env, i);
+                r4k_mips_tlb_flush_extra(env, i);
                 break;
             }
         }
@@ -2400,8 +2472,9 @@ void r4k_helper_tlbr(CPUMIPSState *env)
     tlb = &env->tlb->mmu.r4k.tlb[idx];
 
     /* If this will change the current ASID, flush qemu's TLB.  */
-    if (ASID != tlb->ASID)
+    if (ASID != tlb->ASID) {
         cpu_mips_tlb_flush(env);
+    }
 
     r4k_mips_tlb_flush_extra(env, env->tlb->nb_tlb);
 
@@ -2476,10 +2549,12 @@ static void debug_pre_eret(CPUMIPSState *env)
     if (qemu_loglevel_mask(CPU_LOG_EXEC)) {
         qemu_log("ERET: PC " TARGET_FMT_lx " EPC " TARGET_FMT_lx,
                 env->active_tc.PC, env->CP0_EPC);
-        if (env->CP0_Status & (1 << CP0St_ERL))
+        if (env->CP0_Status & (1 << CP0St_ERL)) {
             qemu_log(" ErrorEPC " TARGET_FMT_lx, env->CP0_ErrorEPC);
-        if (env->hflags & MIPS_HFLAG_DM)
+        }
+        if (env->hflags & MIPS_HFLAG_DM) {
             qemu_log(" DEPC " TARGET_FMT_lx, env->CP0_DEPC);
+        }
         qemu_log("\n");
     }
 }
@@ -2489,17 +2564,25 @@ static void debug_post_eret(CPUMIPSState *env)
     if (qemu_loglevel_mask(CPU_LOG_EXEC)) {
         qemu_log("  =>  PC " TARGET_FMT_lx " EPC " TARGET_FMT_lx,
                 env->active_tc.PC, env->CP0_EPC);
-        if (env->CP0_Status & (1 << CP0St_ERL))
+        if (env->CP0_Status & (1 << CP0St_ERL)) {
             qemu_log(" ErrorEPC " TARGET_FMT_lx, env->CP0_ErrorEPC);
-        if (env->hflags & MIPS_HFLAG_DM)
+        }
+        if (env->hflags & MIPS_HFLAG_DM) {
             qemu_log(" DEPC " TARGET_FMT_lx, env->CP0_DEPC);
+        }
         switch (cpu_mmu_index(env, false)) {
         case 3:
             qemu_log(", ERL\n");
             break;
-        case MIPS_HFLAG_UM: qemu_log(", UM\n"); break;
-        case MIPS_HFLAG_SM: qemu_log(", SM\n"); break;
-        case MIPS_HFLAG_KM: qemu_log("\n"); break;
+        case MIPS_HFLAG_UM:
+            qemu_log(", UM\n");
+            break;
+        case MIPS_HFLAG_SM:
+            qemu_log(", SM\n");
+            break;
+        case MIPS_HFLAG_KM:
+            qemu_log("\n");
+            break;
         default:
             cpu_abort(env_cpu(env), "Invalid MMU mode!\n");
             break;
@@ -2609,8 +2692,9 @@ void helper_pmon(CPUMIPSState *env, int function)
     function /= 2;
     switch (function) {
     case 2: /* TODO: char inbyte(int waitflag); */
-        if (env->active_tc.gpr[4] == 0)
+        if (env->active_tc.gpr[4] == 0) {
             env->active_tc.gpr[2] = -1;
+        }
         /* Fall through */
     case 11: /* TODO: char inbyte (void); */
         env->active_tc.gpr[2] = -1;
@@ -2636,8 +2720,10 @@ void helper_wait(CPUMIPSState *env)
 
     cs->halted = 1;
     cpu_reset_interrupt(cs, CPU_INTERRUPT_WAKE);
-    /* Last instruction in the block, PC was updated before
-       - no need to recover PC and icount */
+    /*
+     * Last instruction in the block, PC was updated before
+     * - no need to recover PC and icount.
+     */
     raise_exception(env, EXCP_HLT);
 }
 
@@ -2731,13 +2817,15 @@ target_ulong helper_cfc1(CPUMIPSState *env, uint32_t reg)
         }
         break;
     case 25:
-        arg1 = ((env->active_fpu.fcr31 >> 24) & 0xfe) | ((env->active_fpu.fcr31 >> 23) & 0x1);
+        arg1 = ((env->active_fpu.fcr31 >> 24) & 0xfe) |
+               ((env->active_fpu.fcr31 >> 23) & 0x1);
         break;
     case 26:
         arg1 = env->active_fpu.fcr31 & 0x0003f07c;
         break;
     case 28:
-        arg1 = (env->active_fpu.fcr31 & 0x00000f83) | ((env->active_fpu.fcr31 >> 22) & 0x4);
+        arg1 = (env->active_fpu.fcr31 & 0x00000f83) |
+               ((env->active_fpu.fcr31 >> 22) & 0x4);
         break;
     default:
         arg1 = (int32_t)env->active_fpu.fcr31;
@@ -2802,19 +2890,24 @@ void helper_ctc1(CPUMIPSState *env, target_ulong arg1, uint32_t fs, uint32_t rt)
         if ((env->insn_flags & ISA_MIPS32R6) || (arg1 & 0xffffff00)) {
             return;
         }
-        env->active_fpu.fcr31 = (env->active_fpu.fcr31 & 0x017fffff) | ((arg1 & 0xfe) << 24) |
-                     ((arg1 & 0x1) << 23);
+        env->active_fpu.fcr31 = (env->active_fpu.fcr31 & 0x017fffff) |
+                                ((arg1 & 0xfe) << 24) |
+                                ((arg1 & 0x1) << 23);
         break;
     case 26:
-        if (arg1 & 0x007c0000)
+        if (arg1 & 0x007c0000) {
             return;
-        env->active_fpu.fcr31 = (env->active_fpu.fcr31 & 0xfffc0f83) | (arg1 & 0x0003f07c);
+        }
+        env->active_fpu.fcr31 = (env->active_fpu.fcr31 & 0xfffc0f83) |
+                                (arg1 & 0x0003f07c);
         break;
     case 28:
-        if (arg1 & 0x007c0000)
+        if (arg1 & 0x007c0000) {
             return;
-        env->active_fpu.fcr31 = (env->active_fpu.fcr31 & 0xfefff07c) | (arg1 & 0x00000f83) |
-                     ((arg1 & 0x4) << 22);
+        }
+        env->active_fpu.fcr31 = (env->active_fpu.fcr31 & 0xfefff07c) |
+                                (arg1 & 0x00000f83) |
+                                ((arg1 & 0x4) << 22);
         break;
     case 31:
         env->active_fpu.fcr31 = (arg1 & env->active_fpu.fcr31_rw_bitmask) |
@@ -2828,8 +2921,10 @@ void helper_ctc1(CPUMIPSState *env, target_ulong arg1, uint32_t fs, uint32_t rt)
     }
     restore_fp_status(env);
     set_float_exception_flags(0, &env->active_fpu.fp_status);
-    if ((GET_FP_ENABLE(env->active_fpu.fcr31) | 0x20) & GET_FP_CAUSE(env->active_fpu.fcr31))
+    if ((GET_FP_ENABLE(env->active_fpu.fcr31) | 0x20) &
+        GET_FP_CAUSE(env->active_fpu.fcr31)) {
         do_raise_exception(env, EXCP_FPE, GETPC());
+    }
 }
 
 int ieee_ex_to_mips(int xcpt)
@@ -2857,7 +2952,8 @@ int ieee_ex_to_mips(int xcpt)
 
 static inline void update_fcr31(CPUMIPSState *env, uintptr_t pc)
 {
-    int tmp = ieee_ex_to_mips(get_float_exception_flags(&env->active_fpu.fp_status));
+    int tmp = ieee_ex_to_mips(get_float_exception_flags(
+                                  &env->active_fpu.fp_status));
 
     SET_FP_CAUSE(env->active_fpu.fcr31, tmp);
 
@@ -2872,10 +2968,12 @@ static inline void update_fcr31(CPUMIPSState *env, uintptr_t pc)
     }
 }
 
-/* Float support.
-   Single precition routines have a "s" suffix, double precision a
-   "d" suffix, 32bit integer "w", 64bit integer "l", paired single "ps",
-   paired single lower "pl", paired single upper "pu".  */
+/*
+ * Float support.
+ * Single precition routines have a "s" suffix, double precision a
+ * "d" suffix, 32bit integer "w", 64bit integer "l", paired single "ps",
+ * paired single lower "pl", paired single upper "pu".
+ */
 
 /* unary operations, modifying fp status  */
 uint64_t helper_float_sqrt_d(CPUMIPSState *env, uint64_t fdt0)
@@ -3056,7 +3154,8 @@ uint64_t helper_float_round_l_d(CPUMIPSState *env, uint64_t fdt0)
 {
     uint64_t dt2;
 
-    set_float_rounding_mode(float_round_nearest_even, &env->active_fpu.fp_status);
+    set_float_rounding_mode(float_round_nearest_even,
+                            &env->active_fpu.fp_status);
     dt2 = float64_to_int64(fdt0, &env->active_fpu.fp_status);
     restore_rounding_mode(env);
     if (get_float_exception_flags(&env->active_fpu.fp_status)
@@ -3071,7 +3170,8 @@ uint64_t helper_float_round_l_s(CPUMIPSState *env, uint32_t fst0)
 {
     uint64_t dt2;
 
-    set_float_rounding_mode(float_round_nearest_even, &env->active_fpu.fp_status);
+    set_float_rounding_mode(float_round_nearest_even,
+                            &env->active_fpu.fp_status);
     dt2 = float32_to_int64(fst0, &env->active_fpu.fp_status);
     restore_rounding_mode(env);
     if (get_float_exception_flags(&env->active_fpu.fp_status)
@@ -3086,7 +3186,8 @@ uint32_t helper_float_round_w_d(CPUMIPSState *env, uint64_t fdt0)
 {
     uint32_t wt2;
 
-    set_float_rounding_mode(float_round_nearest_even, &env->active_fpu.fp_status);
+    set_float_rounding_mode(float_round_nearest_even,
+                            &env->active_fpu.fp_status);
     wt2 = float64_to_int32(fdt0, &env->active_fpu.fp_status);
     restore_rounding_mode(env);
     if (get_float_exception_flags(&env->active_fpu.fp_status)
@@ -3101,7 +3202,8 @@ uint32_t helper_float_round_w_s(CPUMIPSState *env, uint32_t fst0)
 {
     uint32_t wt2;
 
-    set_float_rounding_mode(float_round_nearest_even, &env->active_fpu.fp_status);
+    set_float_rounding_mode(float_round_nearest_even,
+                            &env->active_fpu.fp_status);
     wt2 = float32_to_int32(fst0, &env->active_fpu.fp_status);
     restore_rounding_mode(env);
     if (get_float_exception_flags(&env->active_fpu.fp_status)
@@ -3116,7 +3218,8 @@ uint64_t helper_float_trunc_l_d(CPUMIPSState *env, uint64_t fdt0)
 {
     uint64_t dt2;
 
-    dt2 = float64_to_int64_round_to_zero(fdt0, &env->active_fpu.fp_status);
+    dt2 = float64_to_int64_round_to_zero(fdt0,
+                                         &env->active_fpu.fp_status);
     if (get_float_exception_flags(&env->active_fpu.fp_status)
         & (float_flag_invalid | float_flag_overflow)) {
         dt2 = FP_TO_INT64_OVERFLOW;
@@ -3697,7 +3800,8 @@ uint64_t helper_float_recip1_ps(CPUMIPSState *env, uint64_t fdt0)
     uint32_t fst2;
     uint32_t fsth2;
 
-    fst2 = float32_div(float32_one, fdt0 & 0XFFFFFFFF, &env->active_fpu.fp_status);
+    fst2 = float32_div(float32_one, fdt0 & 0XFFFFFFFF,
+                       &env->active_fpu.fp_status);
     fsth2 = float32_div(float32_one, fdt0 >> 32, &env->active_fpu.fp_status);
     update_fcr31(env, GETPC());
     return ((uint64_t)fsth2 << 32) | fst2;
@@ -3737,8 +3841,8 @@ uint64_t helper_float_rsqrt1_ps(CPUMIPSState *env, uint64_t fdt0)
 }
 
 #define FLOAT_RINT(name, bits)                                              \
-uint ## bits ## _t helper_float_ ## name (CPUMIPSState *env,                \
-                                          uint ## bits ## _t fs)            \
+uint ## bits ## _t helper_float_ ## name(CPUMIPSState *env,                 \
+                                         uint ## bits ## _t fs)             \
 {                                                                           \
     uint ## bits ## _t fdret;                                               \
                                                                             \
@@ -3763,8 +3867,8 @@ FLOAT_RINT(rint_d, 64)
 #define FLOAT_CLASS_POSITIVE_ZERO      0x200
 
 #define FLOAT_CLASS(name, bits)                                      \
-uint ## bits ## _t float_ ## name (uint ## bits ## _t arg,           \
-                                   float_status *status)             \
+uint ## bits ## _t float_ ## name(uint ## bits ## _t arg,            \
+                                  float_status *status)              \
 {                                                                    \
     if (float ## bits ## _is_signaling_nan(arg, status)) {           \
         return FLOAT_CLASS_SIGNALING_NAN;                            \
@@ -3793,8 +3897,8 @@ uint ## bits ## _t float_ ## name (uint ## bits ## _t arg,           \
     }                                                                \
 }                                                                    \
                                                                      \
-uint ## bits ## _t helper_float_ ## name (CPUMIPSState *env,         \
-                                          uint ## bits ## _t arg)    \
+uint ## bits ## _t helper_float_ ## name(CPUMIPSState *env,          \
+                                         uint ## bits ## _t arg)     \
 {                                                                    \
     return float_ ## name(arg, &env->active_fpu.fp_status);          \
 }
@@ -3810,7 +3914,7 @@ uint64_t helper_float_ ## name ## _d(CPUMIPSState *env,            \
 {                                                                  \
     uint64_t dt2;                                                  \
                                                                    \
-    dt2 = float64_ ## name (fdt0, fdt1, &env->active_fpu.fp_status);     \
+    dt2 = float64_ ## name(fdt0, fdt1, &env->active_fpu.fp_status);\
     update_fcr31(env, GETPC());                                    \
     return dt2;                                                    \
 }                                                                  \
@@ -3820,7 +3924,7 @@ uint32_t helper_float_ ## name ## _s(CPUMIPSState *env,            \
 {                                                                  \
     uint32_t wt2;                                                  \
                                                                    \
-    wt2 = float32_ ## name (fst0, fst1, &env->active_fpu.fp_status);     \
+    wt2 = float32_ ## name(fst0, fst1, &env->active_fpu.fp_status);\
     update_fcr31(env, GETPC());                                    \
     return wt2;                                                    \
 }                                                                  \
@@ -3836,8 +3940,8 @@ uint64_t helper_float_ ## name ## _ps(CPUMIPSState *env,           \
     uint32_t wt2;                                                  \
     uint32_t wth2;                                                 \
                                                                    \
-    wt2 = float32_ ## name (fst0, fst1, &env->active_fpu.fp_status);     \
-    wth2 = float32_ ## name (fsth0, fsth1, &env->active_fpu.fp_status);  \
+    wt2 = float32_ ## name(fst0, fst1, &env->active_fpu.fp_status);     \
+    wth2 = float32_ ## name(fsth0, fsth1, &env->active_fpu.fp_status);  \
     update_fcr31(env, GETPC());                                    \
     return ((uint64_t)wth2 << 32) | wt2;                           \
 }
@@ -3852,7 +3956,8 @@ FLOAT_BINOP(div)
 uint64_t helper_float_recip2_d(CPUMIPSState *env, uint64_t fdt0, uint64_t fdt2)
 {
     fdt2 = float64_mul(fdt0, fdt2, &env->active_fpu.fp_status);
-    fdt2 = float64_chs(float64_sub(fdt2, float64_one, &env->active_fpu.fp_status));
+    fdt2 = float64_chs(float64_sub(fdt2, float64_one,
+                                   &env->active_fpu.fp_status));
     update_fcr31(env, GETPC());
     return fdt2;
 }
@@ -3860,7 +3965,8 @@ uint64_t helper_float_recip2_d(CPUMIPSState *env, uint64_t fdt0, uint64_t fdt2)
 uint32_t helper_float_recip2_s(CPUMIPSState *env, uint32_t fst0, uint32_t fst2)
 {
     fst2 = float32_mul(fst0, fst2, &env->active_fpu.fp_status);
-    fst2 = float32_chs(float32_sub(fst2, float32_one, &env->active_fpu.fp_status));
+    fst2 = float32_chs(float32_sub(fst2, float32_one,
+                                       &env->active_fpu.fp_status));
     update_fcr31(env, GETPC());
     return fst2;
 }
@@ -3874,8 +3980,10 @@ uint64_t helper_float_recip2_ps(CPUMIPSState *env, uint64_t fdt0, uint64_t fdt2)
 
     fst2 = float32_mul(fst0, fst2, &env->active_fpu.fp_status);
     fsth2 = float32_mul(fsth0, fsth2, &env->active_fpu.fp_status);
-    fst2 = float32_chs(float32_sub(fst2, float32_one, &env->active_fpu.fp_status));
-    fsth2 = float32_chs(float32_sub(fsth2, float32_one, &env->active_fpu.fp_status));
+    fst2 = float32_chs(float32_sub(fst2, float32_one,
+                                       &env->active_fpu.fp_status));
+    fsth2 = float32_chs(float32_sub(fsth2, float32_one,
+                                       &env->active_fpu.fp_status));
     update_fcr31(env, GETPC());
     return ((uint64_t)fsth2 << 32) | fst2;
 }
@@ -3884,7 +3992,8 @@ uint64_t helper_float_rsqrt2_d(CPUMIPSState *env, uint64_t fdt0, uint64_t fdt2)
 {
     fdt2 = float64_mul(fdt0, fdt2, &env->active_fpu.fp_status);
     fdt2 = float64_sub(fdt2, float64_one, &env->active_fpu.fp_status);
-    fdt2 = float64_chs(float64_div(fdt2, FLOAT_TWO64, &env->active_fpu.fp_status));
+    fdt2 = float64_chs(float64_div(fdt2, FLOAT_TWO64,
+                                       &env->active_fpu.fp_status));
     update_fcr31(env, GETPC());
     return fdt2;
 }
@@ -3893,7 +4002,8 @@ uint32_t helper_float_rsqrt2_s(CPUMIPSState *env, uint32_t fst0, uint32_t fst2)
 {
     fst2 = float32_mul(fst0, fst2, &env->active_fpu.fp_status);
     fst2 = float32_sub(fst2, float32_one, &env->active_fpu.fp_status);
-    fst2 = float32_chs(float32_div(fst2, FLOAT_TWO32, &env->active_fpu.fp_status));
+    fst2 = float32_chs(float32_div(fst2, FLOAT_TWO32,
+                                       &env->active_fpu.fp_status));
     update_fcr31(env, GETPC());
     return fst2;
 }
@@ -3909,8 +4019,10 @@ uint64_t helper_float_rsqrt2_ps(CPUMIPSState *env, uint64_t fdt0, uint64_t fdt2)
     fsth2 = float32_mul(fsth0, fsth2, &env->active_fpu.fp_status);
     fst2 = float32_sub(fst2, float32_one, &env->active_fpu.fp_status);
     fsth2 = float32_sub(fsth2, float32_one, &env->active_fpu.fp_status);
-    fst2 = float32_chs(float32_div(fst2, FLOAT_TWO32, &env->active_fpu.fp_status));
-    fsth2 = float32_chs(float32_div(fsth2, FLOAT_TWO32, &env->active_fpu.fp_status));
+    fst2 = float32_chs(float32_div(fst2, FLOAT_TWO32,
+                                       &env->active_fpu.fp_status));
+    fsth2 = float32_chs(float32_div(fsth2, FLOAT_TWO32,
+                                       &env->active_fpu.fp_status));
     update_fcr31(env, GETPC());
     return ((uint64_t)fsth2 << 32) | fst2;
 }
@@ -3924,8 +4036,8 @@ uint64_t helper_float_addr_ps(CPUMIPSState *env, uint64_t fdt0, uint64_t fdt1)
     uint32_t fst2;
     uint32_t fsth2;
 
-    fst2 = float32_add (fst0, fsth0, &env->active_fpu.fp_status);
-    fsth2 = float32_add (fst1, fsth1, &env->active_fpu.fp_status);
+    fst2 = float32_add(fst0, fsth0, &env->active_fpu.fp_status);
+    fsth2 = float32_add(fst1, fsth1, &env->active_fpu.fp_status);
     update_fcr31(env, GETPC());
     return ((uint64_t)fsth2 << 32) | fst2;
 }
@@ -3939,16 +4051,16 @@ uint64_t helper_float_mulr_ps(CPUMIPSState *env, uint64_t fdt0, uint64_t fdt1)
     uint32_t fst2;
     uint32_t fsth2;
 
-    fst2 = float32_mul (fst0, fsth0, &env->active_fpu.fp_status);
-    fsth2 = float32_mul (fst1, fsth1, &env->active_fpu.fp_status);
+    fst2 = float32_mul(fst0, fsth0, &env->active_fpu.fp_status);
+    fsth2 = float32_mul(fst1, fsth1, &env->active_fpu.fp_status);
     update_fcr31(env, GETPC());
     return ((uint64_t)fsth2 << 32) | fst2;
 }
 
 #define FLOAT_MINMAX(name, bits, minmaxfunc)                            \
-uint ## bits ## _t helper_float_ ## name (CPUMIPSState *env,            \
-                                          uint ## bits ## _t fs,        \
-                                          uint ## bits ## _t ft)        \
+uint ## bits ## _t helper_float_ ## name(CPUMIPSState *env,             \
+                                         uint ## bits ## _t fs,         \
+                                         uint ## bits ## _t ft)         \
 {                                                                       \
     uint ## bits ## _t fdret;                                           \
                                                                         \
@@ -4026,10 +4138,10 @@ FLOAT_FMA(nmsub, float_muladd_negate_result | float_muladd_negate_c)
 #undef FLOAT_FMA
 
 #define FLOAT_FMADDSUB(name, bits, muladd_arg)                          \
-uint ## bits ## _t helper_float_ ## name (CPUMIPSState *env,            \
-                                          uint ## bits ## _t fs,        \
-                                          uint ## bits ## _t ft,        \
-                                          uint ## bits ## _t fd)        \
+uint ## bits ## _t helper_float_ ## name(CPUMIPSState *env,             \
+                                         uint ## bits ## _t fs,         \
+                                         uint ## bits ## _t ft,         \
+                                         uint ## bits ## _t fd)         \
 {                                                                       \
     uint ## bits ## _t fdret;                                           \
                                                                         \
@@ -4072,26 +4184,58 @@ void helper_cmpabs_d_ ## op(CPUMIPSState *env, uint64_t fdt0,  \
         CLEAR_FP_COND(cc, env->active_fpu);                    \
 }
 
-/* NOTE: the comma operator will make "cond" to eval to false,
- * but float64_unordered_quiet() is still called. */
-FOP_COND_D(f,   (float64_unordered_quiet(fdt1, fdt0, &env->active_fpu.fp_status), 0))
-FOP_COND_D(un,  float64_unordered_quiet(fdt1, fdt0, &env->active_fpu.fp_status))
-FOP_COND_D(eq,  float64_eq_quiet(fdt0, fdt1, &env->active_fpu.fp_status))
-FOP_COND_D(ueq, float64_unordered_quiet(fdt1, fdt0, &env->active_fpu.fp_status)  || float64_eq_quiet(fdt0, fdt1, &env->active_fpu.fp_status))
-FOP_COND_D(olt, float64_lt_quiet(fdt0, fdt1, &env->active_fpu.fp_status))
-FOP_COND_D(ult, float64_unordered_quiet(fdt1, fdt0, &env->active_fpu.fp_status)  || float64_lt_quiet(fdt0, fdt1, &env->active_fpu.fp_status))
-FOP_COND_D(ole, float64_le_quiet(fdt0, fdt1, &env->active_fpu.fp_status))
-FOP_COND_D(ule, float64_unordered_quiet(fdt1, fdt0, &env->active_fpu.fp_status)  || float64_le_quiet(fdt0, fdt1, &env->active_fpu.fp_status))
-/* NOTE: the comma operator will make "cond" to eval to false,
- * but float64_unordered() is still called. */
-FOP_COND_D(sf,  (float64_unordered(fdt1, fdt0, &env->active_fpu.fp_status), 0))
-FOP_COND_D(ngle,float64_unordered(fdt1, fdt0, &env->active_fpu.fp_status))
-FOP_COND_D(seq, float64_eq(fdt0, fdt1, &env->active_fpu.fp_status))
-FOP_COND_D(ngl, float64_unordered(fdt1, fdt0, &env->active_fpu.fp_status)  || float64_eq(fdt0, fdt1, &env->active_fpu.fp_status))
-FOP_COND_D(lt,  float64_lt(fdt0, fdt1, &env->active_fpu.fp_status))
-FOP_COND_D(nge, float64_unordered(fdt1, fdt0, &env->active_fpu.fp_status)  || float64_lt(fdt0, fdt1, &env->active_fpu.fp_status))
-FOP_COND_D(le,  float64_le(fdt0, fdt1, &env->active_fpu.fp_status))
-FOP_COND_D(ngt, float64_unordered(fdt1, fdt0, &env->active_fpu.fp_status)  || float64_le(fdt0, fdt1, &env->active_fpu.fp_status))
+/*
+ * NOTE: the comma operator will make "cond" to eval to false,
+ * but float64_unordered_quiet() is still called.
+ */
+FOP_COND_D(f,    (float64_unordered_quiet(fdt1, fdt0,
+                                       &env->active_fpu.fp_status), 0))
+FOP_COND_D(un,   float64_unordered_quiet(fdt1, fdt0,
+                                       &env->active_fpu.fp_status))
+FOP_COND_D(eq,   float64_eq_quiet(fdt0, fdt1,
+                                       &env->active_fpu.fp_status))
+FOP_COND_D(ueq,  float64_unordered_quiet(fdt1, fdt0,
+                                       &env->active_fpu.fp_status)
+                 || float64_eq_quiet(fdt0, fdt1,
+                                       &env->active_fpu.fp_status))
+FOP_COND_D(olt,  float64_lt_quiet(fdt0, fdt1,
+                                       &env->active_fpu.fp_status))
+FOP_COND_D(ult,  float64_unordered_quiet(fdt1, fdt0,
+                                       &env->active_fpu.fp_status)
+                 || float64_lt_quiet(fdt0, fdt1,
+                                       &env->active_fpu.fp_status))
+FOP_COND_D(ole,  float64_le_quiet(fdt0, fdt1,
+                                       &env->active_fpu.fp_status))
+FOP_COND_D(ule,  float64_unordered_quiet(fdt1, fdt0,
+                                       &env->active_fpu.fp_status)
+                 || float64_le_quiet(fdt0, fdt1,
+                                       &env->active_fpu.fp_status))
+/*
+ * NOTE: the comma operator will make "cond" to eval to false,
+ * but float64_unordered() is still called.
+ */
+FOP_COND_D(sf,   (float64_unordered(fdt1, fdt0,
+                                       &env->active_fpu.fp_status), 0))
+FOP_COND_D(ngle, float64_unordered(fdt1, fdt0,
+                                       &env->active_fpu.fp_status))
+FOP_COND_D(seq,  float64_eq(fdt0, fdt1,
+                                       &env->active_fpu.fp_status))
+FOP_COND_D(ngl,  float64_unordered(fdt1, fdt0,
+                                       &env->active_fpu.fp_status)
+                 || float64_eq(fdt0, fdt1,
+                                       &env->active_fpu.fp_status))
+FOP_COND_D(lt,   float64_lt(fdt0, fdt1,
+                                       &env->active_fpu.fp_status))
+FOP_COND_D(nge,  float64_unordered(fdt1, fdt0,
+                                       &env->active_fpu.fp_status)
+                 || float64_lt(fdt0, fdt1,
+                                       &env->active_fpu.fp_status))
+FOP_COND_D(le,   float64_le(fdt0, fdt1,
+                                       &env->active_fpu.fp_status))
+FOP_COND_D(ngt,  float64_unordered(fdt1, fdt0,
+                                       &env->active_fpu.fp_status)
+                 || float64_le(fdt0, fdt1,
+                                       &env->active_fpu.fp_status))
 
 #define FOP_COND_S(op, cond)                                   \
 void helper_cmp_s_ ## op(CPUMIPSState *env, uint32_t fst0,     \
@@ -4119,26 +4263,58 @@ void helper_cmpabs_s_ ## op(CPUMIPSState *env, uint32_t fst0,  \
         CLEAR_FP_COND(cc, env->active_fpu);                    \
 }
 
-/* NOTE: the comma operator will make "cond" to eval to false,
- * but float32_unordered_quiet() is still called. */
-FOP_COND_S(f,   (float32_unordered_quiet(fst1, fst0, &env->active_fpu.fp_status), 0))
-FOP_COND_S(un,  float32_unordered_quiet(fst1, fst0, &env->active_fpu.fp_status))
-FOP_COND_S(eq,  float32_eq_quiet(fst0, fst1, &env->active_fpu.fp_status))
-FOP_COND_S(ueq, float32_unordered_quiet(fst1, fst0, &env->active_fpu.fp_status)  || float32_eq_quiet(fst0, fst1, &env->active_fpu.fp_status))
-FOP_COND_S(olt, float32_lt_quiet(fst0, fst1, &env->active_fpu.fp_status))
-FOP_COND_S(ult, float32_unordered_quiet(fst1, fst0, &env->active_fpu.fp_status)  || float32_lt_quiet(fst0, fst1, &env->active_fpu.fp_status))
-FOP_COND_S(ole, float32_le_quiet(fst0, fst1, &env->active_fpu.fp_status))
-FOP_COND_S(ule, float32_unordered_quiet(fst1, fst0, &env->active_fpu.fp_status)  || float32_le_quiet(fst0, fst1, &env->active_fpu.fp_status))
-/* NOTE: the comma operator will make "cond" to eval to false,
- * but float32_unordered() is still called. */
-FOP_COND_S(sf,  (float32_unordered(fst1, fst0, &env->active_fpu.fp_status), 0))
-FOP_COND_S(ngle,float32_unordered(fst1, fst0, &env->active_fpu.fp_status))
-FOP_COND_S(seq, float32_eq(fst0, fst1, &env->active_fpu.fp_status))
-FOP_COND_S(ngl, float32_unordered(fst1, fst0, &env->active_fpu.fp_status)  || float32_eq(fst0, fst1, &env->active_fpu.fp_status))
-FOP_COND_S(lt,  float32_lt(fst0, fst1, &env->active_fpu.fp_status))
-FOP_COND_S(nge, float32_unordered(fst1, fst0, &env->active_fpu.fp_status)  || float32_lt(fst0, fst1, &env->active_fpu.fp_status))
-FOP_COND_S(le,  float32_le(fst0, fst1, &env->active_fpu.fp_status))
-FOP_COND_S(ngt, float32_unordered(fst1, fst0, &env->active_fpu.fp_status)  || float32_le(fst0, fst1, &env->active_fpu.fp_status))
+/*
+ * NOTE: the comma operator will make "cond" to eval to false,
+ * but float32_unordered_quiet() is still called.
+ */
+FOP_COND_S(f,    (float32_unordered_quiet(fst1, fst0,
+                                       &env->active_fpu.fp_status), 0))
+FOP_COND_S(un,   float32_unordered_quiet(fst1, fst0,
+                                       &env->active_fpu.fp_status))
+FOP_COND_S(eq,   float32_eq_quiet(fst0, fst1,
+                                       &env->active_fpu.fp_status))
+FOP_COND_S(ueq,  float32_unordered_quiet(fst1, fst0,
+                                       &env->active_fpu.fp_status)
+                 || float32_eq_quiet(fst0, fst1,
+                                       &env->active_fpu.fp_status))
+FOP_COND_S(olt,  float32_lt_quiet(fst0, fst1,
+                                       &env->active_fpu.fp_status))
+FOP_COND_S(ult,  float32_unordered_quiet(fst1, fst0,
+                                       &env->active_fpu.fp_status)
+                 || float32_lt_quiet(fst0, fst1,
+                                       &env->active_fpu.fp_status))
+FOP_COND_S(ole,  float32_le_quiet(fst0, fst1,
+                                       &env->active_fpu.fp_status))
+FOP_COND_S(ule,  float32_unordered_quiet(fst1, fst0,
+                                       &env->active_fpu.fp_status)
+                 || float32_le_quiet(fst0, fst1,
+                                       &env->active_fpu.fp_status))
+/*
+ * NOTE: the comma operator will make "cond" to eval to false,
+ * but float32_unordered() is still called.
+ */
+FOP_COND_S(sf,   (float32_unordered(fst1, fst0,
+                                       &env->active_fpu.fp_status), 0))
+FOP_COND_S(ngle, float32_unordered(fst1, fst0,
+                                       &env->active_fpu.fp_status))
+FOP_COND_S(seq,  float32_eq(fst0, fst1,
+                                       &env->active_fpu.fp_status))
+FOP_COND_S(ngl,  float32_unordered(fst1, fst0,
+                                       &env->active_fpu.fp_status)
+                 || float32_eq(fst0, fst1,
+                                       &env->active_fpu.fp_status))
+FOP_COND_S(lt,   float32_lt(fst0, fst1,
+                                       &env->active_fpu.fp_status))
+FOP_COND_S(nge,  float32_unordered(fst1, fst0,
+                                       &env->active_fpu.fp_status)
+                 || float32_lt(fst0, fst1,
+                                       &env->active_fpu.fp_status))
+FOP_COND_S(le,   float32_le(fst0, fst1,
+                                       &env->active_fpu.fp_status))
+FOP_COND_S(ngt,  float32_unordered(fst1, fst0,
+                                       &env->active_fpu.fp_status)
+                 || float32_le(fst0, fst1,
+                                       &env->active_fpu.fp_status))
 
 #define FOP_COND_PS(op, condl, condh)                           \
 void helper_cmp_ps_ ## op(CPUMIPSState *env, uint64_t fdt0,     \
@@ -4184,47 +4360,107 @@ void helper_cmpabs_ps_ ## op(CPUMIPSState *env, uint64_t fdt0,  \
         CLEAR_FP_COND(cc + 1, env->active_fpu);                 \
 }
 
-/* NOTE: the comma operator will make "cond" to eval to false,
- * but float32_unordered_quiet() is still called. */
-FOP_COND_PS(f,   (float32_unordered_quiet(fst1, fst0, &env->active_fpu.fp_status), 0),
-                 (float32_unordered_quiet(fsth1, fsth0, &env->active_fpu.fp_status), 0))
-FOP_COND_PS(un,  float32_unordered_quiet(fst1, fst0, &env->active_fpu.fp_status),
-                 float32_unordered_quiet(fsth1, fsth0, &env->active_fpu.fp_status))
-FOP_COND_PS(eq,  float32_eq_quiet(fst0, fst1, &env->active_fpu.fp_status),
-                 float32_eq_quiet(fsth0, fsth1, &env->active_fpu.fp_status))
-FOP_COND_PS(ueq, float32_unordered_quiet(fst1, fst0, &env->active_fpu.fp_status)    || float32_eq_quiet(fst0, fst1, &env->active_fpu.fp_status),
-                 float32_unordered_quiet(fsth1, fsth0, &env->active_fpu.fp_status)  || float32_eq_quiet(fsth0, fsth1, &env->active_fpu.fp_status))
-FOP_COND_PS(olt, float32_lt_quiet(fst0, fst1, &env->active_fpu.fp_status),
-                 float32_lt_quiet(fsth0, fsth1, &env->active_fpu.fp_status))
-FOP_COND_PS(ult, float32_unordered_quiet(fst1, fst0, &env->active_fpu.fp_status)    || float32_lt_quiet(fst0, fst1, &env->active_fpu.fp_status),
-                 float32_unordered_quiet(fsth1, fsth0, &env->active_fpu.fp_status)  || float32_lt_quiet(fsth0, fsth1, &env->active_fpu.fp_status))
-FOP_COND_PS(ole, float32_le_quiet(fst0, fst1, &env->active_fpu.fp_status),
-                 float32_le_quiet(fsth0, fsth1, &env->active_fpu.fp_status))
-FOP_COND_PS(ule, float32_unordered_quiet(fst1, fst0, &env->active_fpu.fp_status)    || float32_le_quiet(fst0, fst1, &env->active_fpu.fp_status),
-                 float32_unordered_quiet(fsth1, fsth0, &env->active_fpu.fp_status)  || float32_le_quiet(fsth0, fsth1, &env->active_fpu.fp_status))
-/* NOTE: the comma operator will make "cond" to eval to false,
- * but float32_unordered() is still called. */
-FOP_COND_PS(sf,  (float32_unordered(fst1, fst0, &env->active_fpu.fp_status), 0),
-                 (float32_unordered(fsth1, fsth0, &env->active_fpu.fp_status), 0))
-FOP_COND_PS(ngle,float32_unordered(fst1, fst0, &env->active_fpu.fp_status),
-                 float32_unordered(fsth1, fsth0, &env->active_fpu.fp_status))
-FOP_COND_PS(seq, float32_eq(fst0, fst1, &env->active_fpu.fp_status),
-                 float32_eq(fsth0, fsth1, &env->active_fpu.fp_status))
-FOP_COND_PS(ngl, float32_unordered(fst1, fst0, &env->active_fpu.fp_status)    || float32_eq(fst0, fst1, &env->active_fpu.fp_status),
-                 float32_unordered(fsth1, fsth0, &env->active_fpu.fp_status)  || float32_eq(fsth0, fsth1, &env->active_fpu.fp_status))
-FOP_COND_PS(lt,  float32_lt(fst0, fst1, &env->active_fpu.fp_status),
-                 float32_lt(fsth0, fsth1, &env->active_fpu.fp_status))
-FOP_COND_PS(nge, float32_unordered(fst1, fst0, &env->active_fpu.fp_status)    || float32_lt(fst0, fst1, &env->active_fpu.fp_status),
-                 float32_unordered(fsth1, fsth0, &env->active_fpu.fp_status)  || float32_lt(fsth0, fsth1, &env->active_fpu.fp_status))
-FOP_COND_PS(le,  float32_le(fst0, fst1, &env->active_fpu.fp_status),
-                 float32_le(fsth0, fsth1, &env->active_fpu.fp_status))
-FOP_COND_PS(ngt, float32_unordered(fst1, fst0, &env->active_fpu.fp_status)    || float32_le(fst0, fst1, &env->active_fpu.fp_status),
-                 float32_unordered(fsth1, fsth0, &env->active_fpu.fp_status)  || float32_le(fsth0, fsth1, &env->active_fpu.fp_status))
+/*
+ * NOTE: the comma operator will make "cond" to eval to false,
+ * but float32_unordered_quiet() is still called.
+ */
+FOP_COND_PS(f,    (float32_unordered_quiet(fst1, fst0,
+                                       &env->active_fpu.fp_status), 0),
+                  (float32_unordered_quiet(fsth1, fsth0,
+                                       &env->active_fpu.fp_status), 0))
+FOP_COND_PS(un,   float32_unordered_quiet(fst1, fst0,
+                                       &env->active_fpu.fp_status),
+                  float32_unordered_quiet(fsth1, fsth0,
+                                       &env->active_fpu.fp_status))
+FOP_COND_PS(eq,   float32_eq_quiet(fst0, fst1,
+                                       &env->active_fpu.fp_status),
+                  float32_eq_quiet(fsth0, fsth1,
+                                       &env->active_fpu.fp_status))
+FOP_COND_PS(ueq,  float32_unordered_quiet(fst1, fst0,
+                                       &env->active_fpu.fp_status)
+                  || float32_eq_quiet(fst0, fst1,
+                                       &env->active_fpu.fp_status),
+                  float32_unordered_quiet(fsth1, fsth0,
+                                       &env->active_fpu.fp_status)
+                  || float32_eq_quiet(fsth0, fsth1,
+                                       &env->active_fpu.fp_status))
+FOP_COND_PS(olt,  float32_lt_quiet(fst0, fst1,
+                                       &env->active_fpu.fp_status),
+                  float32_lt_quiet(fsth0, fsth1,
+                                       &env->active_fpu.fp_status))
+FOP_COND_PS(ult,  float32_unordered_quiet(fst1, fst0,
+                                       &env->active_fpu.fp_status)
+                  || float32_lt_quiet(fst0, fst1,
+                                       &env->active_fpu.fp_status),
+                  float32_unordered_quiet(fsth1, fsth0,
+                                       &env->active_fpu.fp_status)
+                  || float32_lt_quiet(fsth0, fsth1,
+                                       &env->active_fpu.fp_status))
+FOP_COND_PS(ole,  float32_le_quiet(fst0, fst1,
+                                       &env->active_fpu.fp_status),
+                  float32_le_quiet(fsth0, fsth1,
+                                       &env->active_fpu.fp_status))
+FOP_COND_PS(ule,  float32_unordered_quiet(fst1, fst0,
+                                       &env->active_fpu.fp_status)
+                  || float32_le_quiet(fst0, fst1,
+                                       &env->active_fpu.fp_status),
+                  float32_unordered_quiet(fsth1, fsth0,
+                                       &env->active_fpu.fp_status)
+                  || float32_le_quiet(fsth0, fsth1,
+                                       &env->active_fpu.fp_status))
+/*
+ * NOTE: the comma operator will make "cond" to eval to false,
+ * but float32_unordered() is still called.
+ */
+FOP_COND_PS(sf,   (float32_unordered(fst1, fst0,
+                                       &env->active_fpu.fp_status), 0),
+                  (float32_unordered(fsth1, fsth0,
+                                       &env->active_fpu.fp_status), 0))
+FOP_COND_PS(ngle, float32_unordered(fst1, fst0,
+                                       &env->active_fpu.fp_status),
+                  float32_unordered(fsth1, fsth0,
+                                       &env->active_fpu.fp_status))
+FOP_COND_PS(seq,  float32_eq(fst0, fst1,
+                                       &env->active_fpu.fp_status),
+                  float32_eq(fsth0, fsth1,
+                                       &env->active_fpu.fp_status))
+FOP_COND_PS(ngl,  float32_unordered(fst1, fst0,
+                                       &env->active_fpu.fp_status)
+                  || float32_eq(fst0, fst1,
+                                       &env->active_fpu.fp_status),
+                  float32_unordered(fsth1, fsth0,
+                                       &env->active_fpu.fp_status)
+                  || float32_eq(fsth0, fsth1,
+                                       &env->active_fpu.fp_status))
+FOP_COND_PS(lt,   float32_lt(fst0, fst1,
+                                       &env->active_fpu.fp_status),
+                  float32_lt(fsth0, fsth1,
+                                       &env->active_fpu.fp_status))
+FOP_COND_PS(nge,  float32_unordered(fst1, fst0,
+                                       &env->active_fpu.fp_status)
+                  || float32_lt(fst0, fst1,
+                                       &env->active_fpu.fp_status),
+                  float32_unordered(fsth1, fsth0,
+                                       &env->active_fpu.fp_status)
+                  || float32_lt(fsth0, fsth1,
+                                       &env->active_fpu.fp_status))
+FOP_COND_PS(le,   float32_le(fst0, fst1,
+                                       &env->active_fpu.fp_status),
+                  float32_le(fsth0, fsth1,
+                                       &env->active_fpu.fp_status))
+FOP_COND_PS(ngt,  float32_unordered(fst1, fst0,
+                                       &env->active_fpu.fp_status)
+                  || float32_le(fst0, fst1,
+                                       &env->active_fpu.fp_status),
+                  float32_unordered(fsth1, fsth0,
+                                       &env->active_fpu.fp_status)
+                  || float32_le(fsth0, fsth1,
+                                       &env->active_fpu.fp_status))
 
 /* R6 compare operations */
 #define FOP_CONDN_D(op, cond)                                       \
-uint64_t helper_r6_cmp_d_ ## op(CPUMIPSState * env, uint64_t fdt0,  \
-                         uint64_t fdt1)                             \
+uint64_t helper_r6_cmp_d_ ## op(CPUMIPSState *env, uint64_t fdt0,   \
+                                uint64_t fdt1)                      \
 {                                                                   \
     uint64_t c;                                                     \
     c = cond;                                                       \
@@ -4236,50 +4472,90 @@ uint64_t helper_r6_cmp_d_ ## op(CPUMIPSState * env, uint64_t fdt0,  \
     }                                                               \
 }
 
-/* NOTE: the comma operator will make "cond" to eval to false,
- * but float64_unordered_quiet() is still called. */
-FOP_CONDN_D(af,  (float64_unordered_quiet(fdt1, fdt0, &env->active_fpu.fp_status), 0))
-FOP_CONDN_D(un,  (float64_unordered_quiet(fdt1, fdt0, &env->active_fpu.fp_status)))
-FOP_CONDN_D(eq,  (float64_eq_quiet(fdt0, fdt1, &env->active_fpu.fp_status)))
-FOP_CONDN_D(ueq, (float64_unordered_quiet(fdt1, fdt0, &env->active_fpu.fp_status)
-                  || float64_eq_quiet(fdt0, fdt1, &env->active_fpu.fp_status)))
-FOP_CONDN_D(lt,  (float64_lt_quiet(fdt0, fdt1, &env->active_fpu.fp_status)))
-FOP_CONDN_D(ult, (float64_unordered_quiet(fdt1, fdt0, &env->active_fpu.fp_status)
-                  || float64_lt_quiet(fdt0, fdt1, &env->active_fpu.fp_status)))
-FOP_CONDN_D(le,  (float64_le_quiet(fdt0, fdt1, &env->active_fpu.fp_status)))
-FOP_CONDN_D(ule, (float64_unordered_quiet(fdt1, fdt0, &env->active_fpu.fp_status)
-                  || float64_le_quiet(fdt0, fdt1, &env->active_fpu.fp_status)))
-/* NOTE: the comma operator will make "cond" to eval to false,
- * but float64_unordered() is still called. */
-FOP_CONDN_D(saf,  (float64_unordered(fdt1, fdt0, &env->active_fpu.fp_status), 0))
-FOP_CONDN_D(sun,  (float64_unordered(fdt1, fdt0, &env->active_fpu.fp_status)))
-FOP_CONDN_D(seq,  (float64_eq(fdt0, fdt1, &env->active_fpu.fp_status)))
-FOP_CONDN_D(sueq, (float64_unordered(fdt1, fdt0, &env->active_fpu.fp_status)
-                   || float64_eq(fdt0, fdt1, &env->active_fpu.fp_status)))
-FOP_CONDN_D(slt,  (float64_lt(fdt0, fdt1, &env->active_fpu.fp_status)))
-FOP_CONDN_D(sult, (float64_unordered(fdt1, fdt0, &env->active_fpu.fp_status)
-                   || float64_lt(fdt0, fdt1, &env->active_fpu.fp_status)))
-FOP_CONDN_D(sle,  (float64_le(fdt0, fdt1, &env->active_fpu.fp_status)))
-FOP_CONDN_D(sule, (float64_unordered(fdt1, fdt0, &env->active_fpu.fp_status)
-                   || float64_le(fdt0, fdt1, &env->active_fpu.fp_status)))
-FOP_CONDN_D(or,   (float64_le_quiet(fdt1, fdt0, &env->active_fpu.fp_status)
-                   || float64_le_quiet(fdt0, fdt1, &env->active_fpu.fp_status)))
-FOP_CONDN_D(une,  (float64_unordered_quiet(fdt1, fdt0, &env->active_fpu.fp_status)
-                   || float64_lt_quiet(fdt1, fdt0, &env->active_fpu.fp_status)
-                   || float64_lt_quiet(fdt0, fdt1, &env->active_fpu.fp_status)))
-FOP_CONDN_D(ne,   (float64_lt_quiet(fdt1, fdt0, &env->active_fpu.fp_status)
-                   || float64_lt_quiet(fdt0, fdt1, &env->active_fpu.fp_status)))
-FOP_CONDN_D(sor,  (float64_le(fdt1, fdt0, &env->active_fpu.fp_status)
-                   || float64_le(fdt0, fdt1, &env->active_fpu.fp_status)))
-FOP_CONDN_D(sune, (float64_unordered(fdt1, fdt0, &env->active_fpu.fp_status)
-                   || float64_lt(fdt1, fdt0, &env->active_fpu.fp_status)
-                   || float64_lt(fdt0, fdt1, &env->active_fpu.fp_status)))
-FOP_CONDN_D(sne,  (float64_lt(fdt1, fdt0, &env->active_fpu.fp_status)
-                   || float64_lt(fdt0, fdt1, &env->active_fpu.fp_status)))
+/*
+ * NOTE: the comma operator will make "cond" to eval to false,
+ * but float64_unordered_quiet() is still called.
+ */
+FOP_CONDN_D(af,  (float64_unordered_quiet(fdt1, fdt0,
+                                       &env->active_fpu.fp_status), 0))
+FOP_CONDN_D(un,  (float64_unordered_quiet(fdt1, fdt0,
+                                       &env->active_fpu.fp_status)))
+FOP_CONDN_D(eq,  (float64_eq_quiet(fdt0, fdt1,
+                                       &env->active_fpu.fp_status)))
+FOP_CONDN_D(ueq, (float64_unordered_quiet(fdt1, fdt0,
+                                       &env->active_fpu.fp_status)
+                 || float64_eq_quiet(fdt0, fdt1,
+                                       &env->active_fpu.fp_status)))
+FOP_CONDN_D(lt,  (float64_lt_quiet(fdt0, fdt1,
+                                       &env->active_fpu.fp_status)))
+FOP_CONDN_D(ult, (float64_unordered_quiet(fdt1, fdt0,
+                                       &env->active_fpu.fp_status)
+                 || float64_lt_quiet(fdt0, fdt1,
+                                       &env->active_fpu.fp_status)))
+FOP_CONDN_D(le,  (float64_le_quiet(fdt0, fdt1,
+                                       &env->active_fpu.fp_status)))
+FOP_CONDN_D(ule, (float64_unordered_quiet(fdt1, fdt0,
+                                       &env->active_fpu.fp_status)
+                 || float64_le_quiet(fdt0, fdt1,
+                                       &env->active_fpu.fp_status)))
+/*
+ * NOTE: the comma operator will make "cond" to eval to false,
+ * but float64_unordered() is still called.\
+ */
+FOP_CONDN_D(saf,  (float64_unordered(fdt1, fdt0,
+                                       &env->active_fpu.fp_status), 0))
+FOP_CONDN_D(sun,  (float64_unordered(fdt1, fdt0,
+                                       &env->active_fpu.fp_status)))
+FOP_CONDN_D(seq,  (float64_eq(fdt0, fdt1,
+                                       &env->active_fpu.fp_status)))
+FOP_CONDN_D(sueq, (float64_unordered(fdt1, fdt0,
+                                       &env->active_fpu.fp_status)
+                   || float64_eq(fdt0, fdt1,
+                                       &env->active_fpu.fp_status)))
+FOP_CONDN_D(slt,  (float64_lt(fdt0, fdt1,
+                                       &env->active_fpu.fp_status)))
+FOP_CONDN_D(sult, (float64_unordered(fdt1, fdt0,
+                                       &env->active_fpu.fp_status)
+                   || float64_lt(fdt0, fdt1,
+                                       &env->active_fpu.fp_status)))
+FOP_CONDN_D(sle,  (float64_le(fdt0, fdt1,
+                                       &env->active_fpu.fp_status)))
+FOP_CONDN_D(sule, (float64_unordered(fdt1, fdt0,
+                                       &env->active_fpu.fp_status)
+                   || float64_le(fdt0, fdt1,
+                                       &env->active_fpu.fp_status)))
+FOP_CONDN_D(or,   (float64_le_quiet(fdt1, fdt0,
+                                       &env->active_fpu.fp_status)
+                   || float64_le_quiet(fdt0, fdt1,
+                                       &env->active_fpu.fp_status)))
+FOP_CONDN_D(une,  (float64_unordered_quiet(fdt1, fdt0,
+                                       &env->active_fpu.fp_status)
+                   || float64_lt_quiet(fdt1, fdt0,
+                                       &env->active_fpu.fp_status)
+                   || float64_lt_quiet(fdt0, fdt1,
+                                       &env->active_fpu.fp_status)))
+FOP_CONDN_D(ne,   (float64_lt_quiet(fdt1, fdt0,
+                                       &env->active_fpu.fp_status)
+                   || float64_lt_quiet(fdt0, fdt1,
+                                       &env->active_fpu.fp_status)))
+FOP_CONDN_D(sor,  (float64_le(fdt1, fdt0,
+                                       &env->active_fpu.fp_status)
+                   || float64_le(fdt0, fdt1,
+                                       &env->active_fpu.fp_status)))
+FOP_CONDN_D(sune, (float64_unordered(fdt1, fdt0,
+                                       &env->active_fpu.fp_status)
+                   || float64_lt(fdt1, fdt0,
+                                       &env->active_fpu.fp_status)
+                   || float64_lt(fdt0, fdt1,
+                                       &env->active_fpu.fp_status)))
+FOP_CONDN_D(sne,  (float64_lt(fdt1, fdt0,
+                                       &env->active_fpu.fp_status)
+                   || float64_lt(fdt0, fdt1,
+                                       &env->active_fpu.fp_status)))
 
 #define FOP_CONDN_S(op, cond)                                       \
-uint32_t helper_r6_cmp_s_ ## op(CPUMIPSState * env, uint32_t fst0,  \
-                         uint32_t fst1)                             \
+uint32_t helper_r6_cmp_s_ ## op(CPUMIPSState *env, uint32_t fst0,   \
+                                uint32_t fst1)                      \
 {                                                                   \
     uint64_t c;                                                     \
     c = cond;                                                       \
@@ -4291,46 +4567,86 @@ uint32_t helper_r6_cmp_s_ ## op(CPUMIPSState * env, uint32_t fst0,  \
     }                                                               \
 }
 
-/* NOTE: the comma operator will make "cond" to eval to false,
- * but float32_unordered_quiet() is still called. */
-FOP_CONDN_S(af,   (float32_unordered_quiet(fst1, fst0, &env->active_fpu.fp_status), 0))
-FOP_CONDN_S(un,   (float32_unordered_quiet(fst1, fst0, &env->active_fpu.fp_status)))
-FOP_CONDN_S(eq,   (float32_eq_quiet(fst0, fst1, &env->active_fpu.fp_status)))
-FOP_CONDN_S(ueq,  (float32_unordered_quiet(fst1, fst0, &env->active_fpu.fp_status)
-                   || float32_eq_quiet(fst0, fst1, &env->active_fpu.fp_status)))
-FOP_CONDN_S(lt,   (float32_lt_quiet(fst0, fst1, &env->active_fpu.fp_status)))
-FOP_CONDN_S(ult,  (float32_unordered_quiet(fst1, fst0, &env->active_fpu.fp_status)
-                   || float32_lt_quiet(fst0, fst1, &env->active_fpu.fp_status)))
-FOP_CONDN_S(le,   (float32_le_quiet(fst0, fst1, &env->active_fpu.fp_status)))
-FOP_CONDN_S(ule,  (float32_unordered_quiet(fst1, fst0, &env->active_fpu.fp_status)
-                   || float32_le_quiet(fst0, fst1, &env->active_fpu.fp_status)))
-/* NOTE: the comma operator will make "cond" to eval to false,
- * but float32_unordered() is still called. */
-FOP_CONDN_S(saf,  (float32_unordered(fst1, fst0, &env->active_fpu.fp_status), 0))
-FOP_CONDN_S(sun,  (float32_unordered(fst1, fst0, &env->active_fpu.fp_status)))
-FOP_CONDN_S(seq,  (float32_eq(fst0, fst1, &env->active_fpu.fp_status)))
-FOP_CONDN_S(sueq, (float32_unordered(fst1, fst0, &env->active_fpu.fp_status)
-                   || float32_eq(fst0, fst1, &env->active_fpu.fp_status)))
-FOP_CONDN_S(slt,  (float32_lt(fst0, fst1, &env->active_fpu.fp_status)))
-FOP_CONDN_S(sult, (float32_unordered(fst1, fst0, &env->active_fpu.fp_status)
-                   || float32_lt(fst0, fst1, &env->active_fpu.fp_status)))
-FOP_CONDN_S(sle,  (float32_le(fst0, fst1, &env->active_fpu.fp_status)))
-FOP_CONDN_S(sule, (float32_unordered(fst1, fst0, &env->active_fpu.fp_status)
-                   || float32_le(fst0, fst1, &env->active_fpu.fp_status)))
-FOP_CONDN_S(or,   (float32_le_quiet(fst1, fst0, &env->active_fpu.fp_status)
-                   || float32_le_quiet(fst0, fst1, &env->active_fpu.fp_status)))
-FOP_CONDN_S(une,  (float32_unordered_quiet(fst1, fst0, &env->active_fpu.fp_status)
-                   || float32_lt_quiet(fst1, fst0, &env->active_fpu.fp_status)
-                   || float32_lt_quiet(fst0, fst1, &env->active_fpu.fp_status)))
-FOP_CONDN_S(ne,   (float32_lt_quiet(fst1, fst0, &env->active_fpu.fp_status)
-                   || float32_lt_quiet(fst0, fst1, &env->active_fpu.fp_status)))
-FOP_CONDN_S(sor,  (float32_le(fst1, fst0, &env->active_fpu.fp_status)
-                   || float32_le(fst0, fst1, &env->active_fpu.fp_status)))
-FOP_CONDN_S(sune, (float32_unordered(fst1, fst0, &env->active_fpu.fp_status)
-                   || float32_lt(fst1, fst0, &env->active_fpu.fp_status)
-                   || float32_lt(fst0, fst1, &env->active_fpu.fp_status)))
-FOP_CONDN_S(sne,  (float32_lt(fst1, fst0, &env->active_fpu.fp_status)
-                   || float32_lt(fst0, fst1, &env->active_fpu.fp_status)))
+/*
+ * NOTE: the comma operator will make "cond" to eval to false,
+ * but float32_unordered_quiet() is still called.
+ */
+FOP_CONDN_S(af,   (float32_unordered_quiet(fst1, fst0,
+                                       &env->active_fpu.fp_status), 0))
+FOP_CONDN_S(un,   (float32_unordered_quiet(fst1, fst0,
+                                       &env->active_fpu.fp_status)))
+FOP_CONDN_S(eq,   (float32_eq_quiet(fst0, fst1,
+                                       &env->active_fpu.fp_status)))
+FOP_CONDN_S(ueq,  (float32_unordered_quiet(fst1, fst0,
+                                       &env->active_fpu.fp_status)
+                   || float32_eq_quiet(fst0, fst1,
+                                       &env->active_fpu.fp_status)))
+FOP_CONDN_S(lt,   (float32_lt_quiet(fst0, fst1,
+                                       &env->active_fpu.fp_status)))
+FOP_CONDN_S(ult,  (float32_unordered_quiet(fst1, fst0,
+                                       &env->active_fpu.fp_status)
+                   || float32_lt_quiet(fst0, fst1,
+                                       &env->active_fpu.fp_status)))
+FOP_CONDN_S(le,   (float32_le_quiet(fst0, fst1,
+                                       &env->active_fpu.fp_status)))
+FOP_CONDN_S(ule,  (float32_unordered_quiet(fst1, fst0,
+                                       &env->active_fpu.fp_status)
+                   || float32_le_quiet(fst0, fst1,
+                                       &env->active_fpu.fp_status)))
+/*
+ * NOTE: the comma operator will make "cond" to eval to false,
+ * but float32_unordered() is still called.
+ */
+FOP_CONDN_S(saf,  (float32_unordered(fst1, fst0,
+                                       &env->active_fpu.fp_status), 0))
+FOP_CONDN_S(sun,  (float32_unordered(fst1, fst0,
+                                       &env->active_fpu.fp_status)))
+FOP_CONDN_S(seq,  (float32_eq(fst0, fst1,
+                                       &env->active_fpu.fp_status)))
+FOP_CONDN_S(sueq, (float32_unordered(fst1, fst0,
+                                       &env->active_fpu.fp_status)
+                   || float32_eq(fst0, fst1,
+                                       &env->active_fpu.fp_status)))
+FOP_CONDN_S(slt,  (float32_lt(fst0, fst1,
+                                       &env->active_fpu.fp_status)))
+FOP_CONDN_S(sult, (float32_unordered(fst1, fst0,
+                                       &env->active_fpu.fp_status)
+                   || float32_lt(fst0, fst1,
+                                       &env->active_fpu.fp_status)))
+FOP_CONDN_S(sle,  (float32_le(fst0, fst1,
+                                       &env->active_fpu.fp_status)))
+FOP_CONDN_S(sule, (float32_unordered(fst1, fst0,
+                                       &env->active_fpu.fp_status)
+                   || float32_le(fst0, fst1,
+                                       &env->active_fpu.fp_status)))
+FOP_CONDN_S(or,   (float32_le_quiet(fst1, fst0,
+                                       &env->active_fpu.fp_status)
+                   || float32_le_quiet(fst0, fst1,
+                                       &env->active_fpu.fp_status)))
+FOP_CONDN_S(une,  (float32_unordered_quiet(fst1, fst0,
+                                       &env->active_fpu.fp_status)
+                   || float32_lt_quiet(fst1, fst0,
+                                       &env->active_fpu.fp_status)
+                   || float32_lt_quiet(fst0, fst1,
+                                       &env->active_fpu.fp_status)))
+FOP_CONDN_S(ne,   (float32_lt_quiet(fst1, fst0,
+                                       &env->active_fpu.fp_status)
+                   || float32_lt_quiet(fst0, fst1,
+                                       &env->active_fpu.fp_status)))
+FOP_CONDN_S(sor,  (float32_le(fst1, fst0,
+                                       &env->active_fpu.fp_status)
+                   || float32_le(fst0, fst1,
+                                       &env->active_fpu.fp_status)))
+FOP_CONDN_S(sune, (float32_unordered(fst1, fst0,
+                                       &env->active_fpu.fp_status)
+                   || float32_lt(fst1, fst0,
+                                       &env->active_fpu.fp_status)
+                   || float32_lt(fst0, fst1,
+                                       &env->active_fpu.fp_status)))
+FOP_CONDN_S(sne,  (float32_lt(fst1, fst0,
+                                       &env->active_fpu.fp_status)
+                   || float32_lt(fst0, fst1,
+                                       &env->active_fpu.fp_status)))
 
 /* MSA */
 /* Data format min and max values */
@@ -4522,7 +4838,7 @@ void helper_msa_ld_d(CPUMIPSState *env, uint32_t wd,
 }
 
 #define MSA_PAGESPAN(x) \
-        ((((x) & ~TARGET_PAGE_MASK) + MSA_WRLEN/8 - 1) >= TARGET_PAGE_SIZE)
+        ((((x) & ~TARGET_PAGE_MASK) + MSA_WRLEN / 8 - 1) >= TARGET_PAGE_SIZE)
 
 static inline void ensure_writable_pages(CPUMIPSState *env,
                                          target_ulong addr,
-- 
2.7.4

[PULL 03/11] MAINTAINERS: Update mail address of Aleksandar Rikalo

[Aleksandar Markovic]

From: Aleksandar Markovic <amarkovic@wavecomp.com>

Aleksandar Rikalo wishes to change his primary mail address for QEMU.
Some minor line order is corrected in .mailmap to be alphabetical,
too.

Reviewed-by: Aleksandar Rikalo <aleksandar.rikalo@rt-rk.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Signed-off-by: Aleksandar Markovic <amarkovic@wavecomp.com>
Message-Id: <1571826227-10583-4-git-send-email-aleksandar.markovic@rt-rk.com>
---
 .mailmap    |  5 +++--
 MAINTAINERS | 18 +++++++++---------
 2 files changed, 12 insertions(+), 11 deletions(-)

diff --git a/.mailmap b/.mailmap
index 0756a0b..3816e4e 100644
--- a/.mailmap
+++ b/.mailmap
@@ -39,10 +39,11 @@ Julia Suvorova <jusual@mail.ru> Julia Suvorova via Qemu-devel <qemu-devel@nongnu
 Justin Terry (VM) <juterry@microsoft.com> Justin Terry (VM) via Qemu-devel <qemu-devel@nongnu.org>
 
 # Next, replace old addresses by a more recent one.
-Anthony Liguori <anthony@codemonkey.ws> Anthony Liguori <aliguori@us.ibm.com>
-James Hogan <jhogan@kernel.org> <james.hogan@imgtec.com>
 Aleksandar Markovic <amarkovic@wavecomp.com> <aleksandar.markovic@mips.com>
 Aleksandar Markovic <amarkovic@wavecomp.com> <aleksandar.markovic@imgtec.com>
+Aleksandar Rikalo <aleksandar.rikalo@rt-rk.com> <arikalo@wavecomp.com>
+Anthony Liguori <anthony@codemonkey.ws> Anthony Liguori <aliguori@us.ibm.com>
+James Hogan <jhogan@kernel.org> <james.hogan@imgtec.com>
 Paul Burton <pburton@wavecomp.com> <paul.burton@mips.com>
 Paul Burton <pburton@wavecomp.com> <paul.burton@imgtec.com>
 Paul Burton <pburton@wavecomp.com> <paul@archlinuxmips.org>
diff --git a/MAINTAINERS b/MAINTAINERS
index ed41d7d..92cec69 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -208,7 +208,7 @@ F: disas/microblaze.c
 MIPS TCG CPUs
 M: Aurelien Jarno <aurelien@aurel32.net>
 M: Aleksandar Markovic <amarkovic@wavecomp.com>
-R: Aleksandar Rikalo <arikalo@wavecomp.com>
+R: Aleksandar Rikalo <aleksandar.rikalo@rt-rk.com>
 S: Maintained
 F: target/mips/
 F: default-configs/*mips*
@@ -363,7 +363,7 @@ F: target/arm/kvm.c
 
 MIPS KVM CPUs
 M: James Hogan <jhogan@kernel.org>
-R: Aleksandar Rikalo <arikalo@wavecomp.com>
+R: Aleksandar Rikalo <aleksandar.rikalo@rt-rk.com>
 S: Maintained
 F: target/mips/kvm.c
 
@@ -934,7 +934,7 @@ MIPS Machines
 -------------
 Jazz
 M: Hervé Poussineau <hpoussin@reactos.org>
-R: Aleksandar Rikalo <arikalo@wavecomp.com>
+R: Aleksandar Rikalo <aleksandar.rikalo@rt-rk.com>
 S: Maintained
 F: hw/mips/mips_jazz.c
 F: hw/display/jazz_led.c
@@ -942,7 +942,7 @@ F: hw/dma/rc4030.c
 
 Malta
 M: Aurelien Jarno <aurelien@aurel32.net>
-R: Aleksandar Rikalo <arikalo@wavecomp.com>
+R: Aleksandar Rikalo <aleksandar.rikalo@rt-rk.com>
 S: Maintained
 F: hw/mips/mips_malta.c
 F: hw/mips/gt64xxx_pci.c
@@ -950,20 +950,20 @@ F: tests/acceptance/linux_ssh_mips_malta.py
 
 Mipssim
 M: Aleksandar Markovic <amarkovic@wavecomp.com>
-R: Aleksandar Rikalo <arikalo@wavecomp.com>
+R: Aleksandar Rikalo <aleksandar.rikalo@rt-rk.com>
 S: Odd Fixes
 F: hw/mips/mips_mipssim.c
 F: hw/net/mipsnet.c
 
 R4000
 M: Aurelien Jarno <aurelien@aurel32.net>
-R: Aleksandar Rikalo <arikalo@wavecomp.com>
+R: Aleksandar Rikalo <aleksandar.rikalo@rt-rk.com>
 S: Maintained
 F: hw/mips/mips_r4k.c
 
 Fulong 2E
 M: Aleksandar Markovic <amarkovic@wavecomp.com>
-R: Aleksandar Rikalo <arikalo@wavecomp.com>
+R: Aleksandar Rikalo <aleksandar.rikalo@rt-rk.com>
 S: Odd Fixes
 F: hw/mips/mips_fulong2e.c
 F: hw/isa/vt82c686.c
@@ -972,7 +972,7 @@ F: include/hw/isa/vt82c686.h
 
 Boston
 M: Paul Burton <pburton@wavecomp.com>
-R: Aleksandar Rikalo <arikalo@wavecomp.com>
+R: Aleksandar Rikalo <aleksandar.rikalo@rt-rk.com>
 S: Maintained
 F: hw/core/loader-fit.c
 F: hw/mips/boston.c
@@ -2352,7 +2352,7 @@ F: disas/i386.c
 
 MIPS TCG target
 M: Aurelien Jarno <aurelien@aurel32.net>
-R: Aleksandar Rikalo <arikalo@wavecomp.com>
+R: Aleksandar Rikalo <aleksandar.rikalo@rt-rk.com>
 S: Maintained
 F: tcg/mips/
 
-- 
2.7.4

[PULL 04/11] target/mips: msa: Split helpers for <MAX|MIN>_A.<B|H|W|D>

[Aleksandar Markovic]

From: Aleksandar Markovic <amarkovic@wavecomp.com>

Achieves clearer code and slightly better performance.

Reviewed-by: Aleksandar Rikalo <aleksandar.rikalo@rt-rk.com>
Signed-off-by: Aleksandar Markovic <amarkovic@wavecomp.com>
Message-Id: <1571826227-10583-5-git-send-email-aleksandar.markovic@rt-rk.com>
---
 target/mips/helper.h     |  11 +++-
 target/mips/msa_helper.c | 163 ++++++++++++++++++++++++++++++++++++++++++-----
 target/mips/translate.c  |  38 +++++++++--
 3 files changed, 187 insertions(+), 25 deletions(-)

diff --git a/target/mips/helper.h b/target/mips/helper.h
index d615c83..cef4de6 100644
--- a/target/mips/helper.h
+++ b/target/mips/helper.h
@@ -877,6 +877,15 @@ DEF_HELPER_4(msa_div_u_h, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_div_u_w, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_div_u_d, void, env, i32, i32, i32)
 
+DEF_HELPER_4(msa_max_a_b, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_max_a_h, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_max_a_w, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_max_a_d, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_min_a_b, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_min_a_h, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_min_a_w, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_min_a_d, void, env, i32, i32, i32)
+
 DEF_HELPER_4(msa_mod_u_b, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_mod_u_h, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_mod_u_w, void, env, i32, i32, i32)
@@ -940,8 +949,6 @@ DEF_HELPER_5(msa_max_s_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_max_u_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_min_s_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_min_u_df, void, env, i32, i32, i32, i32)
-DEF_HELPER_5(msa_max_a_df, void, env, i32, i32, i32, i32)
-DEF_HELPER_5(msa_min_a_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_add_a_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_adds_a_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_adds_s_df, void, env, i32, i32, i32, i32)
diff --git a/target/mips/msa_helper.c b/target/mips/msa_helper.c
index a2052ba..3eb0ab1 100644
--- a/target/mips/msa_helper.c
+++ b/target/mips/msa_helper.c
@@ -1736,7 +1736,152 @@ void helper_msa_div_u_d(CPUMIPSState *env,
  * +---------------+----------------------------------------------------------+
  */
 
-/* TODO: insert Int Max Min group helpers here */
+static inline int64_t msa_max_a_df(uint32_t df, int64_t arg1, int64_t arg2)
+{
+    uint64_t abs_arg1 = arg1 >= 0 ? arg1 : -arg1;
+    uint64_t abs_arg2 = arg2 >= 0 ? arg2 : -arg2;
+    return abs_arg1 > abs_arg2 ? arg1 : arg2;
+}
+
+void helper_msa_max_a_b(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->b[0]  = msa_max_a_df(DF_BYTE, pws->b[0],  pwt->b[0]);
+    pwd->b[1]  = msa_max_a_df(DF_BYTE, pws->b[1],  pwt->b[1]);
+    pwd->b[2]  = msa_max_a_df(DF_BYTE, pws->b[2],  pwt->b[2]);
+    pwd->b[3]  = msa_max_a_df(DF_BYTE, pws->b[3],  pwt->b[3]);
+    pwd->b[4]  = msa_max_a_df(DF_BYTE, pws->b[4],  pwt->b[4]);
+    pwd->b[5]  = msa_max_a_df(DF_BYTE, pws->b[5],  pwt->b[5]);
+    pwd->b[6]  = msa_max_a_df(DF_BYTE, pws->b[6],  pwt->b[6]);
+    pwd->b[7]  = msa_max_a_df(DF_BYTE, pws->b[7],  pwt->b[7]);
+    pwd->b[8]  = msa_max_a_df(DF_BYTE, pws->b[8],  pwt->b[8]);
+    pwd->b[9]  = msa_max_a_df(DF_BYTE, pws->b[9],  pwt->b[9]);
+    pwd->b[10] = msa_max_a_df(DF_BYTE, pws->b[10], pwt->b[10]);
+    pwd->b[11] = msa_max_a_df(DF_BYTE, pws->b[11], pwt->b[11]);
+    pwd->b[12] = msa_max_a_df(DF_BYTE, pws->b[12], pwt->b[12]);
+    pwd->b[13] = msa_max_a_df(DF_BYTE, pws->b[13], pwt->b[13]);
+    pwd->b[14] = msa_max_a_df(DF_BYTE, pws->b[14], pwt->b[14]);
+    pwd->b[15] = msa_max_a_df(DF_BYTE, pws->b[15], pwt->b[15]);
+}
+
+void helper_msa_max_a_h(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->h[0]  = msa_max_a_df(DF_HALF, pws->h[0],  pwt->h[0]);
+    pwd->h[1]  = msa_max_a_df(DF_HALF, pws->h[1],  pwt->h[1]);
+    pwd->h[2]  = msa_max_a_df(DF_HALF, pws->h[2],  pwt->h[2]);
+    pwd->h[3]  = msa_max_a_df(DF_HALF, pws->h[3],  pwt->h[3]);
+    pwd->h[4]  = msa_max_a_df(DF_HALF, pws->h[4],  pwt->h[4]);
+    pwd->h[5]  = msa_max_a_df(DF_HALF, pws->h[5],  pwt->h[5]);
+    pwd->h[6]  = msa_max_a_df(DF_HALF, pws->h[6],  pwt->h[6]);
+    pwd->h[7]  = msa_max_a_df(DF_HALF, pws->h[7],  pwt->h[7]);
+}
+
+void helper_msa_max_a_w(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->w[0]  = msa_max_a_df(DF_WORD, pws->w[0],  pwt->w[0]);
+    pwd->w[1]  = msa_max_a_df(DF_WORD, pws->w[1],  pwt->w[1]);
+    pwd->w[2]  = msa_max_a_df(DF_WORD, pws->w[2],  pwt->w[2]);
+    pwd->w[3]  = msa_max_a_df(DF_WORD, pws->w[3],  pwt->w[3]);
+}
+
+void helper_msa_max_a_d(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->d[0]  = msa_max_a_df(DF_DOUBLE, pws->d[0],  pwt->d[0]);
+    pwd->d[1]  = msa_max_a_df(DF_DOUBLE, pws->d[1],  pwt->d[1]);
+}
+
+
+static inline int64_t msa_min_a_df(uint32_t df, int64_t arg1, int64_t arg2)
+{
+    uint64_t abs_arg1 = arg1 >= 0 ? arg1 : -arg1;
+    uint64_t abs_arg2 = arg2 >= 0 ? arg2 : -arg2;
+    return abs_arg1 < abs_arg2 ? arg1 : arg2;
+}
+
+void helper_msa_min_a_b(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->b[0]  = msa_min_a_df(DF_BYTE, pws->b[0],  pwt->b[0]);
+    pwd->b[1]  = msa_min_a_df(DF_BYTE, pws->b[1],  pwt->b[1]);
+    pwd->b[2]  = msa_min_a_df(DF_BYTE, pws->b[2],  pwt->b[2]);
+    pwd->b[3]  = msa_min_a_df(DF_BYTE, pws->b[3],  pwt->b[3]);
+    pwd->b[4]  = msa_min_a_df(DF_BYTE, pws->b[4],  pwt->b[4]);
+    pwd->b[5]  = msa_min_a_df(DF_BYTE, pws->b[5],  pwt->b[5]);
+    pwd->b[6]  = msa_min_a_df(DF_BYTE, pws->b[6],  pwt->b[6]);
+    pwd->b[7]  = msa_min_a_df(DF_BYTE, pws->b[7],  pwt->b[7]);
+    pwd->b[8]  = msa_min_a_df(DF_BYTE, pws->b[8],  pwt->b[8]);
+    pwd->b[9]  = msa_min_a_df(DF_BYTE, pws->b[9],  pwt->b[9]);
+    pwd->b[10] = msa_min_a_df(DF_BYTE, pws->b[10], pwt->b[10]);
+    pwd->b[11] = msa_min_a_df(DF_BYTE, pws->b[11], pwt->b[11]);
+    pwd->b[12] = msa_min_a_df(DF_BYTE, pws->b[12], pwt->b[12]);
+    pwd->b[13] = msa_min_a_df(DF_BYTE, pws->b[13], pwt->b[13]);
+    pwd->b[14] = msa_min_a_df(DF_BYTE, pws->b[14], pwt->b[14]);
+    pwd->b[15] = msa_min_a_df(DF_BYTE, pws->b[15], pwt->b[15]);
+}
+
+void helper_msa_min_a_h(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->h[0]  = msa_min_a_df(DF_HALF, pws->h[0],  pwt->h[0]);
+    pwd->h[1]  = msa_min_a_df(DF_HALF, pws->h[1],  pwt->h[1]);
+    pwd->h[2]  = msa_min_a_df(DF_HALF, pws->h[2],  pwt->h[2]);
+    pwd->h[3]  = msa_min_a_df(DF_HALF, pws->h[3],  pwt->h[3]);
+    pwd->h[4]  = msa_min_a_df(DF_HALF, pws->h[4],  pwt->h[4]);
+    pwd->h[5]  = msa_min_a_df(DF_HALF, pws->h[5],  pwt->h[5]);
+    pwd->h[6]  = msa_min_a_df(DF_HALF, pws->h[6],  pwt->h[6]);
+    pwd->h[7]  = msa_min_a_df(DF_HALF, pws->h[7],  pwt->h[7]);
+}
+
+void helper_msa_min_a_w(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->w[0]  = msa_min_a_df(DF_WORD, pws->w[0],  pwt->w[0]);
+    pwd->w[1]  = msa_min_a_df(DF_WORD, pws->w[1],  pwt->w[1]);
+    pwd->w[2]  = msa_min_a_df(DF_WORD, pws->w[2],  pwt->w[2]);
+    pwd->w[3]  = msa_min_a_df(DF_WORD, pws->w[3],  pwt->w[3]);
+}
+
+void helper_msa_min_a_d(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->d[0]  = msa_min_a_df(DF_DOUBLE, pws->d[0],  pwt->d[0]);
+    pwd->d[1]  = msa_min_a_df(DF_DOUBLE, pws->d[1],  pwt->d[1]);
+}
 
 
 /*
@@ -2456,20 +2601,6 @@ MSA_TEROP_IMMU_DF(binsli, binsl)
 MSA_TEROP_IMMU_DF(binsri, binsr)
 #undef MSA_TEROP_IMMU_DF
 
-static inline int64_t msa_max_a_df(uint32_t df, int64_t arg1, int64_t arg2)
-{
-    uint64_t abs_arg1 = arg1 >= 0 ? arg1 : -arg1;
-    uint64_t abs_arg2 = arg2 >= 0 ? arg2 : -arg2;
-    return abs_arg1 > abs_arg2 ? arg1 : arg2;
-}
-
-static inline int64_t msa_min_a_df(uint32_t df, int64_t arg1, int64_t arg2)
-{
-    uint64_t abs_arg1 = arg1 >= 0 ? arg1 : -arg1;
-    uint64_t abs_arg2 = arg2 >= 0 ? arg2 : -arg2;
-    return abs_arg1 < abs_arg2 ? arg1 : arg2;
-}
-
 static inline int64_t msa_add_a_df(uint32_t df, int64_t arg1, int64_t arg2)
 {
     uint64_t abs_arg1 = arg1 >= 0 ? arg1 : -arg1;
@@ -2773,8 +2904,6 @@ MSA_BINOP_DF(max_s)
 MSA_BINOP_DF(max_u)
 MSA_BINOP_DF(min_s)
 MSA_BINOP_DF(min_u)
-MSA_BINOP_DF(max_a)
-MSA_BINOP_DF(min_a)
 MSA_BINOP_DF(add_a)
 MSA_BINOP_DF(adds_a)
 MSA_BINOP_DF(adds_s)
diff --git a/target/mips/translate.c b/target/mips/translate.c
index 5039716..8e26548 100644
--- a/target/mips/translate.c
+++ b/target/mips/translate.c
@@ -28642,6 +28642,38 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx)
             break;
         }
         break;
+    case OPC_MAX_A_df:
+        switch (df) {
+        case DF_BYTE:
+            gen_helper_msa_max_a_b(cpu_env, twd, tws, twt);
+            break;
+        case DF_HALF:
+            gen_helper_msa_max_a_h(cpu_env, twd, tws, twt);
+            break;
+        case DF_WORD:
+            gen_helper_msa_max_a_w(cpu_env, twd, tws, twt);
+            break;
+        case DF_DOUBLE:
+            gen_helper_msa_max_a_d(cpu_env, twd, tws, twt);
+            break;
+        }
+        break;
+    case OPC_MIN_A_df:
+        switch (df) {
+        case DF_BYTE:
+            gen_helper_msa_min_a_b(cpu_env, twd, tws, twt);
+            break;
+        case DF_HALF:
+            gen_helper_msa_min_a_h(cpu_env, twd, tws, twt);
+            break;
+        case DF_WORD:
+            gen_helper_msa_min_a_w(cpu_env, twd, tws, twt);
+            break;
+        case DF_DOUBLE:
+            gen_helper_msa_min_a_d(cpu_env, twd, tws, twt);
+            break;
+        }
+        break;
     case OPC_MOD_S_df:
         switch (df) {
         case DF_BYTE:
@@ -28767,15 +28799,9 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx)
     case OPC_ILVR_df:
         gen_helper_msa_ilvr_df(cpu_env, tdf, twd, tws, twt);
         break;
-    case OPC_MAX_A_df:
-        gen_helper_msa_max_a_df(cpu_env, tdf, twd, tws, twt);
-        break;
     case OPC_ILVEV_df:
         gen_helper_msa_ilvev_df(cpu_env, tdf, twd, tws, twt);
         break;
-    case OPC_MIN_A_df:
-        gen_helper_msa_min_a_df(cpu_env, tdf, twd, tws, twt);
-        break;
     case OPC_ILVOD_df:
         gen_helper_msa_ilvod_df(cpu_env, tdf, twd, tws, twt);
         break;
-- 
2.7.4

[PULL 05/11] target/mips: msa: Split helpers for <MAX|MIN>_<S|U>.<B|H|W|D>

[Aleksandar Markovic]

From: Aleksandar Markovic <amarkovic@wavecomp.com>

Achieves clearer code and slightly better performance.

Reviewed-by: Aleksandar Rikalo <aleksandar.rikalo@rt-rk.com>
Signed-off-by: Aleksandar Markovic <amarkovic@wavecomp.com>
Message-Id: <1571826227-10583-6-git-send-email-aleksandar.markovic@rt-rk.com>
---
 target/mips/helper.h     |  20 ++-
 target/mips/msa_helper.c | 320 ++++++++++++++++++++++++++++++++++++++++++-----
 target/mips/translate.c  |  76 +++++++++--
 3 files changed, 372 insertions(+), 44 deletions(-)

diff --git a/target/mips/helper.h b/target/mips/helper.h
index cef4de6..6419bb8 100644
--- a/target/mips/helper.h
+++ b/target/mips/helper.h
@@ -881,10 +881,26 @@ DEF_HELPER_4(msa_max_a_b, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_max_a_h, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_max_a_w, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_max_a_d, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_max_s_b, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_max_s_h, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_max_s_w, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_max_s_d, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_max_u_b, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_max_u_h, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_max_u_w, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_max_u_d, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_min_a_b, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_min_a_h, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_min_a_w, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_min_a_d, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_min_s_b, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_min_s_h, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_min_s_w, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_min_s_d, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_min_u_b, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_min_u_h, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_min_u_w, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_min_u_d, void, env, i32, i32, i32)
 
 DEF_HELPER_4(msa_mod_u_b, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_mod_u_h, void, env, i32, i32, i32)
@@ -945,10 +961,6 @@ DEF_HELPER_5(msa_binsl_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_binsr_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_addv_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_subv_df, void, env, i32, i32, i32, i32)
-DEF_HELPER_5(msa_max_s_df, void, env, i32, i32, i32, i32)
-DEF_HELPER_5(msa_max_u_df, void, env, i32, i32, i32, i32)
-DEF_HELPER_5(msa_min_s_df, void, env, i32, i32, i32, i32)
-DEF_HELPER_5(msa_min_u_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_add_a_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_adds_a_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_adds_s_df, void, env, i32, i32, i32, i32)
diff --git a/target/mips/msa_helper.c b/target/mips/msa_helper.c
index 3eb0ab1..65df15d 100644
--- a/target/mips/msa_helper.c
+++ b/target/mips/msa_helper.c
@@ -1810,6 +1810,152 @@ void helper_msa_max_a_d(CPUMIPSState *env,
 }
 
 
+static inline int64_t msa_max_s_df(uint32_t df, int64_t arg1, int64_t arg2)
+{
+    return arg1 > arg2 ? arg1 : arg2;
+}
+
+void helper_msa_max_s_b(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->b[0]  = msa_max_s_df(DF_BYTE, pws->b[0],  pwt->b[0]);
+    pwd->b[1]  = msa_max_s_df(DF_BYTE, pws->b[1],  pwt->b[1]);
+    pwd->b[2]  = msa_max_s_df(DF_BYTE, pws->b[2],  pwt->b[2]);
+    pwd->b[3]  = msa_max_s_df(DF_BYTE, pws->b[3],  pwt->b[3]);
+    pwd->b[4]  = msa_max_s_df(DF_BYTE, pws->b[4],  pwt->b[4]);
+    pwd->b[5]  = msa_max_s_df(DF_BYTE, pws->b[5],  pwt->b[5]);
+    pwd->b[6]  = msa_max_s_df(DF_BYTE, pws->b[6],  pwt->b[6]);
+    pwd->b[7]  = msa_max_s_df(DF_BYTE, pws->b[7],  pwt->b[7]);
+    pwd->b[8]  = msa_max_s_df(DF_BYTE, pws->b[8],  pwt->b[8]);
+    pwd->b[9]  = msa_max_s_df(DF_BYTE, pws->b[9],  pwt->b[9]);
+    pwd->b[10] = msa_max_s_df(DF_BYTE, pws->b[10], pwt->b[10]);
+    pwd->b[11] = msa_max_s_df(DF_BYTE, pws->b[11], pwt->b[11]);
+    pwd->b[12] = msa_max_s_df(DF_BYTE, pws->b[12], pwt->b[12]);
+    pwd->b[13] = msa_max_s_df(DF_BYTE, pws->b[13], pwt->b[13]);
+    pwd->b[14] = msa_max_s_df(DF_BYTE, pws->b[14], pwt->b[14]);
+    pwd->b[15] = msa_max_s_df(DF_BYTE, pws->b[15], pwt->b[15]);
+}
+
+void helper_msa_max_s_h(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->h[0]  = msa_max_s_df(DF_HALF, pws->h[0],  pwt->h[0]);
+    pwd->h[1]  = msa_max_s_df(DF_HALF, pws->h[1],  pwt->h[1]);
+    pwd->h[2]  = msa_max_s_df(DF_HALF, pws->h[2],  pwt->h[2]);
+    pwd->h[3]  = msa_max_s_df(DF_HALF, pws->h[3],  pwt->h[3]);
+    pwd->h[4]  = msa_max_s_df(DF_HALF, pws->h[4],  pwt->h[4]);
+    pwd->h[5]  = msa_max_s_df(DF_HALF, pws->h[5],  pwt->h[5]);
+    pwd->h[6]  = msa_max_s_df(DF_HALF, pws->h[6],  pwt->h[6]);
+    pwd->h[7]  = msa_max_s_df(DF_HALF, pws->h[7],  pwt->h[7]);
+}
+
+void helper_msa_max_s_w(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->w[0]  = msa_max_s_df(DF_WORD, pws->w[0],  pwt->w[0]);
+    pwd->w[1]  = msa_max_s_df(DF_WORD, pws->w[1],  pwt->w[1]);
+    pwd->w[2]  = msa_max_s_df(DF_WORD, pws->w[2],  pwt->w[2]);
+    pwd->w[3]  = msa_max_s_df(DF_WORD, pws->w[3],  pwt->w[3]);
+}
+
+void helper_msa_max_s_d(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->d[0]  = msa_max_s_df(DF_DOUBLE, pws->d[0],  pwt->d[0]);
+    pwd->d[1]  = msa_max_s_df(DF_DOUBLE, pws->d[1],  pwt->d[1]);
+}
+
+
+static inline int64_t msa_max_u_df(uint32_t df, int64_t arg1, int64_t arg2)
+{
+    uint64_t u_arg1 = UNSIGNED(arg1, df);
+    uint64_t u_arg2 = UNSIGNED(arg2, df);
+    return u_arg1 > u_arg2 ? arg1 : arg2;
+}
+
+void helper_msa_max_u_b(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->b[0]  = msa_max_u_df(DF_BYTE, pws->b[0],  pwt->b[0]);
+    pwd->b[1]  = msa_max_u_df(DF_BYTE, pws->b[1],  pwt->b[1]);
+    pwd->b[2]  = msa_max_u_df(DF_BYTE, pws->b[2],  pwt->b[2]);
+    pwd->b[3]  = msa_max_u_df(DF_BYTE, pws->b[3],  pwt->b[3]);
+    pwd->b[4]  = msa_max_u_df(DF_BYTE, pws->b[4],  pwt->b[4]);
+    pwd->b[5]  = msa_max_u_df(DF_BYTE, pws->b[5],  pwt->b[5]);
+    pwd->b[6]  = msa_max_u_df(DF_BYTE, pws->b[6],  pwt->b[6]);
+    pwd->b[7]  = msa_max_u_df(DF_BYTE, pws->b[7],  pwt->b[7]);
+    pwd->b[8]  = msa_max_u_df(DF_BYTE, pws->b[8],  pwt->b[8]);
+    pwd->b[9]  = msa_max_u_df(DF_BYTE, pws->b[9],  pwt->b[9]);
+    pwd->b[10] = msa_max_u_df(DF_BYTE, pws->b[10], pwt->b[10]);
+    pwd->b[11] = msa_max_u_df(DF_BYTE, pws->b[11], pwt->b[11]);
+    pwd->b[12] = msa_max_u_df(DF_BYTE, pws->b[12], pwt->b[12]);
+    pwd->b[13] = msa_max_u_df(DF_BYTE, pws->b[13], pwt->b[13]);
+    pwd->b[14] = msa_max_u_df(DF_BYTE, pws->b[14], pwt->b[14]);
+    pwd->b[15] = msa_max_u_df(DF_BYTE, pws->b[15], pwt->b[15]);
+}
+
+void helper_msa_max_u_h(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->h[0]  = msa_max_u_df(DF_HALF, pws->h[0],  pwt->h[0]);
+    pwd->h[1]  = msa_max_u_df(DF_HALF, pws->h[1],  pwt->h[1]);
+    pwd->h[2]  = msa_max_u_df(DF_HALF, pws->h[2],  pwt->h[2]);
+    pwd->h[3]  = msa_max_u_df(DF_HALF, pws->h[3],  pwt->h[3]);
+    pwd->h[4]  = msa_max_u_df(DF_HALF, pws->h[4],  pwt->h[4]);
+    pwd->h[5]  = msa_max_u_df(DF_HALF, pws->h[5],  pwt->h[5]);
+    pwd->h[6]  = msa_max_u_df(DF_HALF, pws->h[6],  pwt->h[6]);
+    pwd->h[7]  = msa_max_u_df(DF_HALF, pws->h[7],  pwt->h[7]);
+}
+
+void helper_msa_max_u_w(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->w[0]  = msa_max_u_df(DF_WORD, pws->w[0],  pwt->w[0]);
+    pwd->w[1]  = msa_max_u_df(DF_WORD, pws->w[1],  pwt->w[1]);
+    pwd->w[2]  = msa_max_u_df(DF_WORD, pws->w[2],  pwt->w[2]);
+    pwd->w[3]  = msa_max_u_df(DF_WORD, pws->w[3],  pwt->w[3]);
+}
+
+void helper_msa_max_u_d(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->d[0]  = msa_max_u_df(DF_DOUBLE, pws->d[0],  pwt->d[0]);
+    pwd->d[1]  = msa_max_u_df(DF_DOUBLE, pws->d[1],  pwt->d[1]);
+}
+
+
 static inline int64_t msa_min_a_df(uint32_t df, int64_t arg1, int64_t arg2)
 {
     uint64_t abs_arg1 = arg1 >= 0 ? arg1 : -arg1;
@@ -1884,6 +2030,152 @@ void helper_msa_min_a_d(CPUMIPSState *env,
 }
 
 
+static inline int64_t msa_min_s_df(uint32_t df, int64_t arg1, int64_t arg2)
+{
+    return arg1 < arg2 ? arg1 : arg2;
+}
+
+void helper_msa_min_s_b(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->b[0]  = msa_min_s_df(DF_BYTE, pws->b[0],  pwt->b[0]);
+    pwd->b[1]  = msa_min_s_df(DF_BYTE, pws->b[1],  pwt->b[1]);
+    pwd->b[2]  = msa_min_s_df(DF_BYTE, pws->b[2],  pwt->b[2]);
+    pwd->b[3]  = msa_min_s_df(DF_BYTE, pws->b[3],  pwt->b[3]);
+    pwd->b[4]  = msa_min_s_df(DF_BYTE, pws->b[4],  pwt->b[4]);
+    pwd->b[5]  = msa_min_s_df(DF_BYTE, pws->b[5],  pwt->b[5]);
+    pwd->b[6]  = msa_min_s_df(DF_BYTE, pws->b[6],  pwt->b[6]);
+    pwd->b[7]  = msa_min_s_df(DF_BYTE, pws->b[7],  pwt->b[7]);
+    pwd->b[8]  = msa_min_s_df(DF_BYTE, pws->b[8],  pwt->b[8]);
+    pwd->b[9]  = msa_min_s_df(DF_BYTE, pws->b[9],  pwt->b[9]);
+    pwd->b[10] = msa_min_s_df(DF_BYTE, pws->b[10], pwt->b[10]);
+    pwd->b[11] = msa_min_s_df(DF_BYTE, pws->b[11], pwt->b[11]);
+    pwd->b[12] = msa_min_s_df(DF_BYTE, pws->b[12], pwt->b[12]);
+    pwd->b[13] = msa_min_s_df(DF_BYTE, pws->b[13], pwt->b[13]);
+    pwd->b[14] = msa_min_s_df(DF_BYTE, pws->b[14], pwt->b[14]);
+    pwd->b[15] = msa_min_s_df(DF_BYTE, pws->b[15], pwt->b[15]);
+}
+
+void helper_msa_min_s_h(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->h[0]  = msa_min_s_df(DF_HALF, pws->h[0],  pwt->h[0]);
+    pwd->h[1]  = msa_min_s_df(DF_HALF, pws->h[1],  pwt->h[1]);
+    pwd->h[2]  = msa_min_s_df(DF_HALF, pws->h[2],  pwt->h[2]);
+    pwd->h[3]  = msa_min_s_df(DF_HALF, pws->h[3],  pwt->h[3]);
+    pwd->h[4]  = msa_min_s_df(DF_HALF, pws->h[4],  pwt->h[4]);
+    pwd->h[5]  = msa_min_s_df(DF_HALF, pws->h[5],  pwt->h[5]);
+    pwd->h[6]  = msa_min_s_df(DF_HALF, pws->h[6],  pwt->h[6]);
+    pwd->h[7]  = msa_min_s_df(DF_HALF, pws->h[7],  pwt->h[7]);
+}
+
+void helper_msa_min_s_w(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->w[0]  = msa_min_s_df(DF_WORD, pws->w[0],  pwt->w[0]);
+    pwd->w[1]  = msa_min_s_df(DF_WORD, pws->w[1],  pwt->w[1]);
+    pwd->w[2]  = msa_min_s_df(DF_WORD, pws->w[2],  pwt->w[2]);
+    pwd->w[3]  = msa_min_s_df(DF_WORD, pws->w[3],  pwt->w[3]);
+}
+
+void helper_msa_min_s_d(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->d[0]  = msa_min_s_df(DF_DOUBLE, pws->d[0],  pwt->d[0]);
+    pwd->d[1]  = msa_min_s_df(DF_DOUBLE, pws->d[1],  pwt->d[1]);
+}
+
+
+static inline int64_t msa_min_u_df(uint32_t df, int64_t arg1, int64_t arg2)
+{
+    uint64_t u_arg1 = UNSIGNED(arg1, df);
+    uint64_t u_arg2 = UNSIGNED(arg2, df);
+    return u_arg1 < u_arg2 ? arg1 : arg2;
+}
+
+void helper_msa_min_u_b(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->b[0]  = msa_min_u_df(DF_BYTE, pws->b[0],  pwt->b[0]);
+    pwd->b[1]  = msa_min_u_df(DF_BYTE, pws->b[1],  pwt->b[1]);
+    pwd->b[2]  = msa_min_u_df(DF_BYTE, pws->b[2],  pwt->b[2]);
+    pwd->b[3]  = msa_min_u_df(DF_BYTE, pws->b[3],  pwt->b[3]);
+    pwd->b[4]  = msa_min_u_df(DF_BYTE, pws->b[4],  pwt->b[4]);
+    pwd->b[5]  = msa_min_u_df(DF_BYTE, pws->b[5],  pwt->b[5]);
+    pwd->b[6]  = msa_min_u_df(DF_BYTE, pws->b[6],  pwt->b[6]);
+    pwd->b[7]  = msa_min_u_df(DF_BYTE, pws->b[7],  pwt->b[7]);
+    pwd->b[8]  = msa_min_u_df(DF_BYTE, pws->b[8],  pwt->b[8]);
+    pwd->b[9]  = msa_min_u_df(DF_BYTE, pws->b[9],  pwt->b[9]);
+    pwd->b[10] = msa_min_u_df(DF_BYTE, pws->b[10], pwt->b[10]);
+    pwd->b[11] = msa_min_u_df(DF_BYTE, pws->b[11], pwt->b[11]);
+    pwd->b[12] = msa_min_u_df(DF_BYTE, pws->b[12], pwt->b[12]);
+    pwd->b[13] = msa_min_u_df(DF_BYTE, pws->b[13], pwt->b[13]);
+    pwd->b[14] = msa_min_u_df(DF_BYTE, pws->b[14], pwt->b[14]);
+    pwd->b[15] = msa_min_u_df(DF_BYTE, pws->b[15], pwt->b[15]);
+}
+
+void helper_msa_min_u_h(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->h[0]  = msa_min_u_df(DF_HALF, pws->h[0],  pwt->h[0]);
+    pwd->h[1]  = msa_min_u_df(DF_HALF, pws->h[1],  pwt->h[1]);
+    pwd->h[2]  = msa_min_u_df(DF_HALF, pws->h[2],  pwt->h[2]);
+    pwd->h[3]  = msa_min_u_df(DF_HALF, pws->h[3],  pwt->h[3]);
+    pwd->h[4]  = msa_min_u_df(DF_HALF, pws->h[4],  pwt->h[4]);
+    pwd->h[5]  = msa_min_u_df(DF_HALF, pws->h[5],  pwt->h[5]);
+    pwd->h[6]  = msa_min_u_df(DF_HALF, pws->h[6],  pwt->h[6]);
+    pwd->h[7]  = msa_min_u_df(DF_HALF, pws->h[7],  pwt->h[7]);
+}
+
+void helper_msa_min_u_w(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->w[0]  = msa_min_u_df(DF_WORD, pws->w[0],  pwt->w[0]);
+    pwd->w[1]  = msa_min_u_df(DF_WORD, pws->w[1],  pwt->w[1]);
+    pwd->w[2]  = msa_min_u_df(DF_WORD, pws->w[2],  pwt->w[2]);
+    pwd->w[3]  = msa_min_u_df(DF_WORD, pws->w[3],  pwt->w[3]);
+}
+
+void helper_msa_min_u_d(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->d[0]  = msa_min_u_df(DF_DOUBLE, pws->d[0],  pwt->d[0]);
+    pwd->d[1]  = msa_min_u_df(DF_DOUBLE, pws->d[1],  pwt->d[1]);
+}
+
+
 /*
  * Int Modulo
  * ----------
@@ -2354,30 +2646,6 @@ static inline int64_t msa_subv_df(uint32_t df, int64_t arg1, int64_t arg2)
     return arg1 - arg2;
 }
 
-static inline int64_t msa_max_s_df(uint32_t df, int64_t arg1, int64_t arg2)
-{
-    return arg1 > arg2 ? arg1 : arg2;
-}
-
-static inline int64_t msa_max_u_df(uint32_t df, int64_t arg1, int64_t arg2)
-{
-    uint64_t u_arg1 = UNSIGNED(arg1, df);
-    uint64_t u_arg2 = UNSIGNED(arg2, df);
-    return u_arg1 > u_arg2 ? arg1 : arg2;
-}
-
-static inline int64_t msa_min_s_df(uint32_t df, int64_t arg1, int64_t arg2)
-{
-    return arg1 < arg2 ? arg1 : arg2;
-}
-
-static inline int64_t msa_min_u_df(uint32_t df, int64_t arg1, int64_t arg2)
-{
-    uint64_t u_arg1 = UNSIGNED(arg1, df);
-    uint64_t u_arg2 = UNSIGNED(arg2, df);
-    return u_arg1 < u_arg2 ? arg1 : arg2;
-}
-
 #define MSA_BINOP_IMM_DF(helper, func)                                  \
 void helper_msa_ ## helper ## _df(CPUMIPSState *env, uint32_t df,       \
                         uint32_t wd, uint32_t ws, int32_t u5)           \
@@ -2900,10 +3168,6 @@ MSA_BINOP_DF(sra)
 MSA_BINOP_DF(srl)
 MSA_BINOP_DF(addv)
 MSA_BINOP_DF(subv)
-MSA_BINOP_DF(max_s)
-MSA_BINOP_DF(max_u)
-MSA_BINOP_DF(min_s)
-MSA_BINOP_DF(min_u)
 MSA_BINOP_DF(add_a)
 MSA_BINOP_DF(adds_a)
 MSA_BINOP_DF(adds_s)
diff --git a/target/mips/translate.c b/target/mips/translate.c
index 8e26548..7a35c26 100644
--- a/target/mips/translate.c
+++ b/target/mips/translate.c
@@ -28658,6 +28658,38 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx)
             break;
         }
         break;
+    case OPC_MAX_S_df:
+        switch (df) {
+        case DF_BYTE:
+            gen_helper_msa_max_s_b(cpu_env, twd, tws, twt);
+            break;
+        case DF_HALF:
+            gen_helper_msa_max_s_h(cpu_env, twd, tws, twt);
+            break;
+        case DF_WORD:
+            gen_helper_msa_max_s_w(cpu_env, twd, tws, twt);
+            break;
+        case DF_DOUBLE:
+            gen_helper_msa_max_s_d(cpu_env, twd, tws, twt);
+            break;
+        }
+        break;
+    case OPC_MAX_U_df:
+        switch (df) {
+        case DF_BYTE:
+            gen_helper_msa_max_u_b(cpu_env, twd, tws, twt);
+            break;
+        case DF_HALF:
+            gen_helper_msa_max_u_h(cpu_env, twd, tws, twt);
+            break;
+        case DF_WORD:
+            gen_helper_msa_max_u_w(cpu_env, twd, tws, twt);
+            break;
+        case DF_DOUBLE:
+            gen_helper_msa_max_u_d(cpu_env, twd, tws, twt);
+            break;
+        }
+        break;
     case OPC_MIN_A_df:
         switch (df) {
         case DF_BYTE:
@@ -28674,6 +28706,38 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx)
             break;
         }
         break;
+    case OPC_MIN_S_df:
+        switch (df) {
+        case DF_BYTE:
+            gen_helper_msa_min_s_b(cpu_env, twd, tws, twt);
+            break;
+        case DF_HALF:
+            gen_helper_msa_min_s_h(cpu_env, twd, tws, twt);
+            break;
+        case DF_WORD:
+            gen_helper_msa_min_s_w(cpu_env, twd, tws, twt);
+            break;
+        case DF_DOUBLE:
+            gen_helper_msa_min_s_d(cpu_env, twd, tws, twt);
+            break;
+        }
+        break;
+    case OPC_MIN_U_df:
+        switch (df) {
+        case DF_BYTE:
+            gen_helper_msa_min_u_b(cpu_env, twd, tws, twt);
+            break;
+        case DF_HALF:
+            gen_helper_msa_min_u_h(cpu_env, twd, tws, twt);
+            break;
+        case DF_WORD:
+            gen_helper_msa_min_u_w(cpu_env, twd, tws, twt);
+            break;
+        case DF_DOUBLE:
+            gen_helper_msa_min_u_d(cpu_env, twd, tws, twt);
+            break;
+        }
+        break;
     case OPC_MOD_S_df:
         switch (df) {
         case DF_BYTE:
@@ -28751,9 +28815,6 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx)
     case OPC_SRL_df:
         gen_helper_msa_srl_df(cpu_env, tdf, twd, tws, twt);
         break;
-    case OPC_MAX_S_df:
-        gen_helper_msa_max_s_df(cpu_env, tdf, twd, tws, twt);
-        break;
     case OPC_ADDS_S_df:
         gen_helper_msa_adds_s_df(cpu_env, tdf, twd, tws, twt);
         break;
@@ -28769,9 +28830,6 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx)
     case OPC_SRLR_df:
         gen_helper_msa_srlr_df(cpu_env, tdf, twd, tws, twt);
         break;
-    case OPC_MAX_U_df:
-        gen_helper_msa_max_u_df(cpu_env, tdf, twd, tws, twt);
-        break;
     case OPC_ADDS_U_df:
         gen_helper_msa_adds_u_df(cpu_env, tdf, twd, tws, twt);
         break;
@@ -28781,18 +28839,12 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx)
     case OPC_PCKOD_df:
         gen_helper_msa_pckod_df(cpu_env, tdf, twd, tws, twt);
         break;
-    case OPC_MIN_S_df:
-        gen_helper_msa_min_s_df(cpu_env, tdf, twd, tws, twt);
-        break;
     case OPC_ASUB_S_df:
         gen_helper_msa_asub_s_df(cpu_env, tdf, twd, tws, twt);
         break;
     case OPC_ILVL_df:
         gen_helper_msa_ilvl_df(cpu_env, tdf, twd, tws, twt);
         break;
-    case OPC_MIN_U_df:
-        gen_helper_msa_min_u_df(cpu_env, tdf, twd, tws, twt);
-        break;
     case OPC_ASUB_U_df:
         gen_helper_msa_asub_u_df(cpu_env, tdf, twd, tws, twt);
         break;
-- 
2.7.4

[PULL 06/11] target/mips: msa: Split helpers for ILV<EV|OD|L|R>.<B|H|W|D>

[Aleksandar Markovic]

From: Aleksandar Markovic <amarkovic@wavecomp.com>

Achieves clearer code and slightly better performance.

Reviewed-by: Aleksandar Rikalo <aleksandar.rikalo@rt-rk.com>
Signed-off-by: Aleksandar Markovic <amarkovic@wavecomp.com>
Message-Id: <1571826227-10583-7-git-send-email-aleksandar.markovic@rt-rk.com>
---
 target/mips/helper.h     |  21 +-
 target/mips/msa_helper.c | 768 +++++++++++++++++++++++++----------------------
 target/mips/translate.c  |  76 ++++-
 3 files changed, 496 insertions(+), 369 deletions(-)

diff --git a/target/mips/helper.h b/target/mips/helper.h
index 6419bb8..f3df187 100644
--- a/target/mips/helper.h
+++ b/target/mips/helper.h
@@ -912,6 +912,23 @@ DEF_HELPER_4(msa_mod_s_h, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_mod_s_w, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_mod_s_d, void, env, i32, i32, i32)
 
+DEF_HELPER_4(msa_ilvev_b, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_ilvev_h, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_ilvev_w, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_ilvev_d, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_ilvod_b, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_ilvod_h, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_ilvod_w, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_ilvod_d, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_ilvl_b, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_ilvl_h, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_ilvl_w, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_ilvl_d, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_ilvr_b, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_ilvr_h, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_ilvr_w, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_ilvr_d, void, env, i32, i32, i32)
+
 DEF_HELPER_4(msa_and_v, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_nor_v, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_or_v, void, env, i32, i32, i32)
@@ -984,10 +1001,6 @@ DEF_HELPER_5(msa_sld_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_splat_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_pckev_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_pckod_df, void, env, i32, i32, i32, i32)
-DEF_HELPER_5(msa_ilvl_df, void, env, i32, i32, i32, i32)
-DEF_HELPER_5(msa_ilvr_df, void, env, i32, i32, i32, i32)
-DEF_HELPER_5(msa_ilvev_df, void, env, i32, i32, i32, i32)
-DEF_HELPER_5(msa_ilvod_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_vshf_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_srar_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_srlr_df, void, env, i32, i32, i32, i32)
diff --git a/target/mips/msa_helper.c b/target/mips/msa_helper.c
index 65df15d..499fcde 100644
--- a/target/mips/msa_helper.c
+++ b/target/mips/msa_helper.c
@@ -2432,7 +2432,421 @@ void helper_msa_mod_u_d(CPUMIPSState *env,
  * +---------------+----------------------------------------------------------+
  */
 
-/* TODO: insert Interleave group helpers here */
+
+void helper_msa_ilvev_b(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+#if defined(HOST_WORDS_BIGENDIAN)
+    pwd->b[8]  = pws->b[9];
+    pwd->b[9]  = pwt->b[9];
+    pwd->b[10] = pws->b[11];
+    pwd->b[11] = pwt->b[11];
+    pwd->b[12] = pws->b[13];
+    pwd->b[13] = pwt->b[13];
+    pwd->b[14] = pws->b[15];
+    pwd->b[15] = pwt->b[15];
+    pwd->b[0]  = pws->b[1];
+    pwd->b[1]  = pwt->b[1];
+    pwd->b[2]  = pws->b[3];
+    pwd->b[3]  = pwt->b[3];
+    pwd->b[4]  = pws->b[5];
+    pwd->b[5]  = pwt->b[5];
+    pwd->b[6]  = pws->b[7];
+    pwd->b[7]  = pwt->b[7];
+#else
+    pwd->b[15] = pws->b[14];
+    pwd->b[14] = pwt->b[14];
+    pwd->b[13] = pws->b[12];
+    pwd->b[12] = pwt->b[12];
+    pwd->b[11] = pws->b[10];
+    pwd->b[10] = pwt->b[10];
+    pwd->b[9]  = pws->b[8];
+    pwd->b[8]  = pwt->b[8];
+    pwd->b[7]  = pws->b[6];
+    pwd->b[6]  = pwt->b[6];
+    pwd->b[5]  = pws->b[4];
+    pwd->b[4]  = pwt->b[4];
+    pwd->b[3]  = pws->b[2];
+    pwd->b[2]  = pwt->b[2];
+    pwd->b[1]  = pws->b[0];
+    pwd->b[0]  = pwt->b[0];
+#endif
+}
+
+void helper_msa_ilvev_h(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+#if defined(HOST_WORDS_BIGENDIAN)
+    pwd->h[4] = pws->h[5];
+    pwd->h[5] = pwt->h[5];
+    pwd->h[6] = pws->h[7];
+    pwd->h[7] = pwt->h[7];
+    pwd->h[0] = pws->h[1];
+    pwd->h[1] = pwt->h[1];
+    pwd->h[2] = pws->h[3];
+    pwd->h[3] = pwt->h[3];
+#else
+    pwd->h[7] = pws->h[6];
+    pwd->h[6] = pwt->h[6];
+    pwd->h[5] = pws->h[4];
+    pwd->h[4] = pwt->h[4];
+    pwd->h[3] = pws->h[2];
+    pwd->h[2] = pwt->h[2];
+    pwd->h[1] = pws->h[0];
+    pwd->h[0] = pwt->h[0];
+#endif
+}
+
+void helper_msa_ilvev_w(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+#if defined(HOST_WORDS_BIGENDIAN)
+    pwd->w[2] = pws->w[3];
+    pwd->w[3] = pwt->w[3];
+    pwd->w[0] = pws->w[1];
+    pwd->w[1] = pwt->w[1];
+#else
+    pwd->w[3] = pws->w[2];
+    pwd->w[2] = pwt->w[2];
+    pwd->w[1] = pws->w[0];
+    pwd->w[0] = pwt->w[0];
+#endif
+}
+
+void helper_msa_ilvev_d(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->d[1] = pws->d[0];
+    pwd->d[0] = pwt->d[0];
+}
+
+
+void helper_msa_ilvod_b(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+#if defined(HOST_WORDS_BIGENDIAN)
+    pwd->b[7]  = pwt->b[6];
+    pwd->b[6]  = pws->b[6];
+    pwd->b[5]  = pwt->b[4];
+    pwd->b[4]  = pws->b[4];
+    pwd->b[3]  = pwt->b[2];
+    pwd->b[2]  = pws->b[2];
+    pwd->b[1]  = pwt->b[0];
+    pwd->b[0]  = pws->b[0];
+    pwd->b[15] = pwt->b[14];
+    pwd->b[14] = pws->b[14];
+    pwd->b[13] = pwt->b[12];
+    pwd->b[12] = pws->b[12];
+    pwd->b[11] = pwt->b[10];
+    pwd->b[10] = pws->b[10];
+    pwd->b[9]  = pwt->b[8];
+    pwd->b[8]  = pws->b[8];
+#else
+    pwd->b[0]  = pwt->b[1];
+    pwd->b[1]  = pws->b[1];
+    pwd->b[2]  = pwt->b[3];
+    pwd->b[3]  = pws->b[3];
+    pwd->b[4]  = pwt->b[5];
+    pwd->b[5]  = pws->b[5];
+    pwd->b[6]  = pwt->b[7];
+    pwd->b[7]  = pws->b[7];
+    pwd->b[8]  = pwt->b[9];
+    pwd->b[9]  = pws->b[9];
+    pwd->b[10] = pwt->b[11];
+    pwd->b[11] = pws->b[11];
+    pwd->b[12] = pwt->b[13];
+    pwd->b[13] = pws->b[13];
+    pwd->b[14] = pwt->b[15];
+    pwd->b[15] = pws->b[15];
+#endif
+}
+
+void helper_msa_ilvod_h(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+#if defined(HOST_WORDS_BIGENDIAN)
+    pwd->h[3] = pwt->h[2];
+    pwd->h[2] = pws->h[2];
+    pwd->h[1] = pwt->h[0];
+    pwd->h[0] = pws->h[0];
+    pwd->h[7] = pwt->h[6];
+    pwd->h[6] = pws->h[6];
+    pwd->h[5] = pwt->h[4];
+    pwd->h[4] = pws->h[4];
+#else
+    pwd->h[0] = pwt->h[1];
+    pwd->h[1] = pws->h[1];
+    pwd->h[2] = pwt->h[3];
+    pwd->h[3] = pws->h[3];
+    pwd->h[4] = pwt->h[5];
+    pwd->h[5] = pws->h[5];
+    pwd->h[6] = pwt->h[7];
+    pwd->h[7] = pws->h[7];
+#endif
+}
+
+void helper_msa_ilvod_w(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+#if defined(HOST_WORDS_BIGENDIAN)
+    pwd->w[1] = pwt->w[0];
+    pwd->w[0] = pws->w[0];
+    pwd->w[3] = pwt->w[2];
+    pwd->w[2] = pws->w[2];
+#else
+    pwd->w[0] = pwt->w[1];
+    pwd->w[1] = pws->w[1];
+    pwd->w[2] = pwt->w[3];
+    pwd->w[3] = pws->w[3];
+#endif
+}
+
+void helper_msa_ilvod_d(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->d[0] = pwt->d[1];
+    pwd->d[1] = pws->d[1];
+}
+
+
+void helper_msa_ilvl_b(CPUMIPSState *env,
+                       uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+#if defined(HOST_WORDS_BIGENDIAN)
+    pwd->b[7]  = pwt->b[15];
+    pwd->b[6]  = pws->b[15];
+    pwd->b[5]  = pwt->b[14];
+    pwd->b[4]  = pws->b[14];
+    pwd->b[3]  = pwt->b[13];
+    pwd->b[2]  = pws->b[13];
+    pwd->b[1]  = pwt->b[12];
+    pwd->b[0]  = pws->b[12];
+    pwd->b[15] = pwt->b[11];
+    pwd->b[14] = pws->b[11];
+    pwd->b[13] = pwt->b[10];
+    pwd->b[12] = pws->b[10];
+    pwd->b[11] = pwt->b[9];
+    pwd->b[10] = pws->b[9];
+    pwd->b[9]  = pwt->b[8];
+    pwd->b[8]  = pws->b[8];
+#else
+    pwd->b[0]  = pwt->b[8];
+    pwd->b[1]  = pws->b[8];
+    pwd->b[2]  = pwt->b[9];
+    pwd->b[3]  = pws->b[9];
+    pwd->b[4]  = pwt->b[10];
+    pwd->b[5]  = pws->b[10];
+    pwd->b[6]  = pwt->b[11];
+    pwd->b[7]  = pws->b[11];
+    pwd->b[8]  = pwt->b[12];
+    pwd->b[9]  = pws->b[12];
+    pwd->b[10] = pwt->b[13];
+    pwd->b[11] = pws->b[13];
+    pwd->b[12] = pwt->b[14];
+    pwd->b[13] = pws->b[14];
+    pwd->b[14] = pwt->b[15];
+    pwd->b[15] = pws->b[15];
+#endif
+}
+
+void helper_msa_ilvl_h(CPUMIPSState *env,
+                       uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+#if defined(HOST_WORDS_BIGENDIAN)
+    pwd->h[3] = pwt->h[7];
+    pwd->h[2] = pws->h[7];
+    pwd->h[1] = pwt->h[6];
+    pwd->h[0] = pws->h[6];
+    pwd->h[7] = pwt->h[5];
+    pwd->h[6] = pws->h[5];
+    pwd->h[5] = pwt->h[4];
+    pwd->h[4] = pws->h[4];
+#else
+    pwd->h[0] = pwt->h[4];
+    pwd->h[1] = pws->h[4];
+    pwd->h[2] = pwt->h[5];
+    pwd->h[3] = pws->h[5];
+    pwd->h[4] = pwt->h[6];
+    pwd->h[5] = pws->h[6];
+    pwd->h[6] = pwt->h[7];
+    pwd->h[7] = pws->h[7];
+#endif
+}
+
+void helper_msa_ilvl_w(CPUMIPSState *env,
+                       uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+#if defined(HOST_WORDS_BIGENDIAN)
+    pwd->w[1] = pwt->w[3];
+    pwd->w[0] = pws->w[3];
+    pwd->w[3] = pwt->w[2];
+    pwd->w[2] = pws->w[2];
+#else
+    pwd->w[0] = pwt->w[2];
+    pwd->w[1] = pws->w[2];
+    pwd->w[2] = pwt->w[3];
+    pwd->w[3] = pws->w[3];
+#endif
+}
+
+void helper_msa_ilvl_d(CPUMIPSState *env,
+                       uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->d[0] = pwt->d[1];
+    pwd->d[1] = pws->d[1];
+}
+
+
+void helper_msa_ilvr_b(CPUMIPSState *env,
+                       uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+#if defined(HOST_WORDS_BIGENDIAN)
+    pwd->b[8]  = pws->b[0];
+    pwd->b[9]  = pwt->b[0];
+    pwd->b[10] = pws->b[1];
+    pwd->b[11] = pwt->b[1];
+    pwd->b[12] = pws->b[2];
+    pwd->b[13] = pwt->b[2];
+    pwd->b[14] = pws->b[3];
+    pwd->b[15] = pwt->b[3];
+    pwd->b[0]  = pws->b[4];
+    pwd->b[1]  = pwt->b[4];
+    pwd->b[2]  = pws->b[5];
+    pwd->b[3]  = pwt->b[5];
+    pwd->b[4]  = pws->b[6];
+    pwd->b[5]  = pwt->b[6];
+    pwd->b[6]  = pws->b[7];
+    pwd->b[7]  = pwt->b[7];
+#else
+    pwd->b[15] = pws->b[7];
+    pwd->b[14] = pwt->b[7];
+    pwd->b[13] = pws->b[6];
+    pwd->b[12] = pwt->b[6];
+    pwd->b[11] = pws->b[5];
+    pwd->b[10] = pwt->b[5];
+    pwd->b[9]  = pws->b[4];
+    pwd->b[8]  = pwt->b[4];
+    pwd->b[7]  = pws->b[3];
+    pwd->b[6]  = pwt->b[3];
+    pwd->b[5]  = pws->b[2];
+    pwd->b[4]  = pwt->b[2];
+    pwd->b[3]  = pws->b[1];
+    pwd->b[2]  = pwt->b[1];
+    pwd->b[1]  = pws->b[0];
+    pwd->b[0]  = pwt->b[0];
+#endif
+}
+
+void helper_msa_ilvr_h(CPUMIPSState *env,
+                       uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+#if defined(HOST_WORDS_BIGENDIAN)
+    pwd->h[4] = pws->h[0];
+    pwd->h[5] = pwt->h[0];
+    pwd->h[6] = pws->h[1];
+    pwd->h[7] = pwt->h[1];
+    pwd->h[0] = pws->h[2];
+    pwd->h[1] = pwt->h[2];
+    pwd->h[2] = pws->h[3];
+    pwd->h[3] = pwt->h[3];
+#else
+    pwd->h[7] = pws->h[3];
+    pwd->h[6] = pwt->h[3];
+    pwd->h[5] = pws->h[2];
+    pwd->h[4] = pwt->h[2];
+    pwd->h[3] = pws->h[1];
+    pwd->h[2] = pwt->h[1];
+    pwd->h[1] = pws->h[0];
+    pwd->h[0] = pwt->h[0];
+#endif
+}
+
+void helper_msa_ilvr_w(CPUMIPSState *env,
+                       uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+#if defined(HOST_WORDS_BIGENDIAN)
+    pwd->w[2] = pws->w[0];
+    pwd->w[3] = pwt->w[0];
+    pwd->w[0] = pws->w[1];
+    pwd->w[1] = pwt->w[1];
+#else
+    pwd->w[3] = pws->w[1];
+    pwd->w[2] = pwt->w[1];
+    pwd->w[1] = pws->w[0];
+    pwd->w[0] = pwt->w[0];
+#endif
+}
+
+void helper_msa_ilvr_d(CPUMIPSState *env,
+                       uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->d[1] = pws->d[0];
+    pwd->d[0] = pwt->d[0];
+}
 
 
 /*
@@ -3522,358 +3936,6 @@ MSA_FN_DF(vshf_df)
 #undef MSA_FN_DF
 
 
-void helper_msa_ilvev_df(CPUMIPSState *env, uint32_t df, uint32_t wd,
-                         uint32_t ws, uint32_t wt)
-{
-    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
-    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
-    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
-
-    switch (df) {
-    case DF_BYTE:
-#if defined(HOST_WORDS_BIGENDIAN)
-        pwd->b[8]  = pws->b[9];
-        pwd->b[9]  = pwt->b[9];
-        pwd->b[10] = pws->b[11];
-        pwd->b[11] = pwt->b[11];
-        pwd->b[12] = pws->b[13];
-        pwd->b[13] = pwt->b[13];
-        pwd->b[14] = pws->b[15];
-        pwd->b[15] = pwt->b[15];
-        pwd->b[0]  = pws->b[1];
-        pwd->b[1]  = pwt->b[1];
-        pwd->b[2]  = pws->b[3];
-        pwd->b[3]  = pwt->b[3];
-        pwd->b[4]  = pws->b[5];
-        pwd->b[5]  = pwt->b[5];
-        pwd->b[6]  = pws->b[7];
-        pwd->b[7]  = pwt->b[7];
-#else
-        pwd->b[15] = pws->b[14];
-        pwd->b[14] = pwt->b[14];
-        pwd->b[13] = pws->b[12];
-        pwd->b[12] = pwt->b[12];
-        pwd->b[11] = pws->b[10];
-        pwd->b[10] = pwt->b[10];
-        pwd->b[9]  = pws->b[8];
-        pwd->b[8]  = pwt->b[8];
-        pwd->b[7]  = pws->b[6];
-        pwd->b[6]  = pwt->b[6];
-        pwd->b[5]  = pws->b[4];
-        pwd->b[4]  = pwt->b[4];
-        pwd->b[3]  = pws->b[2];
-        pwd->b[2]  = pwt->b[2];
-        pwd->b[1]  = pws->b[0];
-        pwd->b[0]  = pwt->b[0];
-#endif
-        break;
-    case DF_HALF:
-#if defined(HOST_WORDS_BIGENDIAN)
-        pwd->h[4] = pws->h[5];
-        pwd->h[5] = pwt->h[5];
-        pwd->h[6] = pws->h[7];
-        pwd->h[7] = pwt->h[7];
-        pwd->h[0] = pws->h[1];
-        pwd->h[1] = pwt->h[1];
-        pwd->h[2] = pws->h[3];
-        pwd->h[3] = pwt->h[3];
-#else
-        pwd->h[7] = pws->h[6];
-        pwd->h[6] = pwt->h[6];
-        pwd->h[5] = pws->h[4];
-        pwd->h[4] = pwt->h[4];
-        pwd->h[3] = pws->h[2];
-        pwd->h[2] = pwt->h[2];
-        pwd->h[1] = pws->h[0];
-        pwd->h[0] = pwt->h[0];
-#endif
-        break;
-    case DF_WORD:
-#if defined(HOST_WORDS_BIGENDIAN)
-        pwd->w[2] = pws->w[3];
-        pwd->w[3] = pwt->w[3];
-        pwd->w[0] = pws->w[1];
-        pwd->w[1] = pwt->w[1];
-#else
-        pwd->w[3] = pws->w[2];
-        pwd->w[2] = pwt->w[2];
-        pwd->w[1] = pws->w[0];
-        pwd->w[0] = pwt->w[0];
-#endif
-        break;
-    case DF_DOUBLE:
-        pwd->d[1] = pws->d[0];
-        pwd->d[0] = pwt->d[0];
-        break;
-    default:
-        assert(0);
-    }
-}
-
-void helper_msa_ilvod_df(CPUMIPSState *env, uint32_t df, uint32_t wd,
-                         uint32_t ws, uint32_t wt)
-{
-    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
-    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
-    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
-
-    switch (df) {
-    case DF_BYTE:
-#if defined(HOST_WORDS_BIGENDIAN)
-        pwd->b[7]  = pwt->b[6];
-        pwd->b[6]  = pws->b[6];
-        pwd->b[5]  = pwt->b[4];
-        pwd->b[4]  = pws->b[4];
-        pwd->b[3]  = pwt->b[2];
-        pwd->b[2]  = pws->b[2];
-        pwd->b[1]  = pwt->b[0];
-        pwd->b[0]  = pws->b[0];
-        pwd->b[15] = pwt->b[14];
-        pwd->b[14] = pws->b[14];
-        pwd->b[13] = pwt->b[12];
-        pwd->b[12] = pws->b[12];
-        pwd->b[11] = pwt->b[10];
-        pwd->b[10] = pws->b[10];
-        pwd->b[9]  = pwt->b[8];
-        pwd->b[8]  = pws->b[8];
-#else
-        pwd->b[0]  = pwt->b[1];
-        pwd->b[1]  = pws->b[1];
-        pwd->b[2]  = pwt->b[3];
-        pwd->b[3]  = pws->b[3];
-        pwd->b[4]  = pwt->b[5];
-        pwd->b[5]  = pws->b[5];
-        pwd->b[6]  = pwt->b[7];
-        pwd->b[7]  = pws->b[7];
-        pwd->b[8]  = pwt->b[9];
-        pwd->b[9]  = pws->b[9];
-        pwd->b[10] = pwt->b[11];
-        pwd->b[11] = pws->b[11];
-        pwd->b[12] = pwt->b[13];
-        pwd->b[13] = pws->b[13];
-        pwd->b[14] = pwt->b[15];
-        pwd->b[15] = pws->b[15];
-#endif
-        break;
-    case DF_HALF:
-#if defined(HOST_WORDS_BIGENDIAN)
-        pwd->h[3] = pwt->h[2];
-        pwd->h[2] = pws->h[2];
-        pwd->h[1] = pwt->h[0];
-        pwd->h[0] = pws->h[0];
-        pwd->h[7] = pwt->h[6];
-        pwd->h[6] = pws->h[6];
-        pwd->h[5] = pwt->h[4];
-        pwd->h[4] = pws->h[4];
-#else
-        pwd->h[0] = pwt->h[1];
-        pwd->h[1] = pws->h[1];
-        pwd->h[2] = pwt->h[3];
-        pwd->h[3] = pws->h[3];
-        pwd->h[4] = pwt->h[5];
-        pwd->h[5] = pws->h[5];
-        pwd->h[6] = pwt->h[7];
-        pwd->h[7] = pws->h[7];
-#endif
-        break;
-    case DF_WORD:
-#if defined(HOST_WORDS_BIGENDIAN)
-        pwd->w[1] = pwt->w[0];
-        pwd->w[0] = pws->w[0];
-        pwd->w[3] = pwt->w[2];
-        pwd->w[2] = pws->w[2];
-#else
-        pwd->w[0] = pwt->w[1];
-        pwd->w[1] = pws->w[1];
-        pwd->w[2] = pwt->w[3];
-        pwd->w[3] = pws->w[3];
-#endif
-        break;
-    case DF_DOUBLE:
-        pwd->d[0] = pwt->d[1];
-        pwd->d[1] = pws->d[1];
-        break;
-    default:
-        assert(0);
-    }
-}
-
-void helper_msa_ilvl_df(CPUMIPSState *env, uint32_t df, uint32_t wd,
-                        uint32_t ws, uint32_t wt)
-{
-    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
-    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
-    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
-
-    switch (df) {
-    case DF_BYTE:
-#if defined(HOST_WORDS_BIGENDIAN)
-        pwd->b[7]  = pwt->b[15];
-        pwd->b[6]  = pws->b[15];
-        pwd->b[5]  = pwt->b[14];
-        pwd->b[4]  = pws->b[14];
-        pwd->b[3]  = pwt->b[13];
-        pwd->b[2]  = pws->b[13];
-        pwd->b[1]  = pwt->b[12];
-        pwd->b[0]  = pws->b[12];
-        pwd->b[15] = pwt->b[11];
-        pwd->b[14] = pws->b[11];
-        pwd->b[13] = pwt->b[10];
-        pwd->b[12] = pws->b[10];
-        pwd->b[11] = pwt->b[9];
-        pwd->b[10] = pws->b[9];
-        pwd->b[9]  = pwt->b[8];
-        pwd->b[8]  = pws->b[8];
-#else
-        pwd->b[0]  = pwt->b[8];
-        pwd->b[1]  = pws->b[8];
-        pwd->b[2]  = pwt->b[9];
-        pwd->b[3]  = pws->b[9];
-        pwd->b[4]  = pwt->b[10];
-        pwd->b[5]  = pws->b[10];
-        pwd->b[6]  = pwt->b[11];
-        pwd->b[7]  = pws->b[11];
-        pwd->b[8]  = pwt->b[12];
-        pwd->b[9]  = pws->b[12];
-        pwd->b[10] = pwt->b[13];
-        pwd->b[11] = pws->b[13];
-        pwd->b[12] = pwt->b[14];
-        pwd->b[13] = pws->b[14];
-        pwd->b[14] = pwt->b[15];
-        pwd->b[15] = pws->b[15];
-#endif
-        break;
-    case DF_HALF:
-#if defined(HOST_WORDS_BIGENDIAN)
-        pwd->h[3] = pwt->h[7];
-        pwd->h[2] = pws->h[7];
-        pwd->h[1] = pwt->h[6];
-        pwd->h[0] = pws->h[6];
-        pwd->h[7] = pwt->h[5];
-        pwd->h[6] = pws->h[5];
-        pwd->h[5] = pwt->h[4];
-        pwd->h[4] = pws->h[4];
-#else
-        pwd->h[0] = pwt->h[4];
-        pwd->h[1] = pws->h[4];
-        pwd->h[2] = pwt->h[5];
-        pwd->h[3] = pws->h[5];
-        pwd->h[4] = pwt->h[6];
-        pwd->h[5] = pws->h[6];
-        pwd->h[6] = pwt->h[7];
-        pwd->h[7] = pws->h[7];
-#endif
-        break;
-    case DF_WORD:
-#if defined(HOST_WORDS_BIGENDIAN)
-        pwd->w[1] = pwt->w[3];
-        pwd->w[0] = pws->w[3];
-        pwd->w[3] = pwt->w[2];
-        pwd->w[2] = pws->w[2];
-#else
-        pwd->w[0] = pwt->w[2];
-        pwd->w[1] = pws->w[2];
-        pwd->w[2] = pwt->w[3];
-        pwd->w[3] = pws->w[3];
-#endif
-        break;
-    case DF_DOUBLE:
-        pwd->d[0] = pwt->d[1];
-        pwd->d[1] = pws->d[1];
-        break;
-    default:
-        assert(0);
-    }
-}
-
-void helper_msa_ilvr_df(CPUMIPSState *env, uint32_t df, uint32_t wd,
-                        uint32_t ws, uint32_t wt)
-{
-    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
-    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
-    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
-
-    switch (df) {
-    case DF_BYTE:
-#if defined(HOST_WORDS_BIGENDIAN)
-        pwd->b[8]  = pws->b[0];
-        pwd->b[9]  = pwt->b[0];
-        pwd->b[10] = pws->b[1];
-        pwd->b[11] = pwt->b[1];
-        pwd->b[12] = pws->b[2];
-        pwd->b[13] = pwt->b[2];
-        pwd->b[14] = pws->b[3];
-        pwd->b[15] = pwt->b[3];
-        pwd->b[0]  = pws->b[4];
-        pwd->b[1]  = pwt->b[4];
-        pwd->b[2]  = pws->b[5];
-        pwd->b[3]  = pwt->b[5];
-        pwd->b[4]  = pws->b[6];
-        pwd->b[5]  = pwt->b[6];
-        pwd->b[6]  = pws->b[7];
-        pwd->b[7]  = pwt->b[7];
-#else
-        pwd->b[15] = pws->b[7];
-        pwd->b[14] = pwt->b[7];
-        pwd->b[13] = pws->b[6];
-        pwd->b[12] = pwt->b[6];
-        pwd->b[11] = pws->b[5];
-        pwd->b[10] = pwt->b[5];
-        pwd->b[9]  = pws->b[4];
-        pwd->b[8]  = pwt->b[4];
-        pwd->b[7]  = pws->b[3];
-        pwd->b[6]  = pwt->b[3];
-        pwd->b[5]  = pws->b[2];
-        pwd->b[4]  = pwt->b[2];
-        pwd->b[3]  = pws->b[1];
-        pwd->b[2]  = pwt->b[1];
-        pwd->b[1]  = pws->b[0];
-        pwd->b[0]  = pwt->b[0];
-#endif
-        break;
-    case DF_HALF:
-#if defined(HOST_WORDS_BIGENDIAN)
-        pwd->h[4] = pws->h[0];
-        pwd->h[5] = pwt->h[0];
-        pwd->h[6] = pws->h[1];
-        pwd->h[7] = pwt->h[1];
-        pwd->h[0] = pws->h[2];
-        pwd->h[1] = pwt->h[2];
-        pwd->h[2] = pws->h[3];
-        pwd->h[3] = pwt->h[3];
-#else
-        pwd->h[7] = pws->h[3];
-        pwd->h[6] = pwt->h[3];
-        pwd->h[5] = pws->h[2];
-        pwd->h[4] = pwt->h[2];
-        pwd->h[3] = pws->h[1];
-        pwd->h[2] = pwt->h[1];
-        pwd->h[1] = pws->h[0];
-        pwd->h[0] = pwt->h[0];
-#endif
-        break;
-    case DF_WORD:
-#if defined(HOST_WORDS_BIGENDIAN)
-        pwd->w[2] = pws->w[0];
-        pwd->w[3] = pwt->w[0];
-        pwd->w[0] = pws->w[1];
-        pwd->w[1] = pwt->w[1];
-#else
-        pwd->w[3] = pws->w[1];
-        pwd->w[2] = pwt->w[1];
-        pwd->w[1] = pws->w[0];
-        pwd->w[0] = pwt->w[0];
-#endif
-        break;
-    case DF_DOUBLE:
-        pwd->d[1] = pws->d[0];
-        pwd->d[0] = pwt->d[0];
-        break;
-    default:
-        assert(0);
-    }
-}
-
 void helper_msa_pckev_df(CPUMIPSState *env, uint32_t df, uint32_t wd,
                          uint32_t ws, uint32_t wt)
 {
diff --git a/target/mips/translate.c b/target/mips/translate.c
index 7a35c26..ea8b8f4 100644
--- a/target/mips/translate.c
+++ b/target/mips/translate.c
@@ -28770,6 +28770,70 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx)
             break;
         }
         break;
+    case OPC_ILVEV_df:
+        switch (df) {
+        case DF_BYTE:
+            gen_helper_msa_ilvev_b(cpu_env, twd, tws, twt);
+            break;
+        case DF_HALF:
+            gen_helper_msa_ilvev_h(cpu_env, twd, tws, twt);
+            break;
+        case DF_WORD:
+            gen_helper_msa_ilvev_w(cpu_env, twd, tws, twt);
+            break;
+        case DF_DOUBLE:
+            gen_helper_msa_ilvev_d(cpu_env, twd, tws, twt);
+            break;
+        }
+        break;
+    case OPC_ILVOD_df:
+        switch (df) {
+        case DF_BYTE:
+            gen_helper_msa_ilvod_b(cpu_env, twd, tws, twt);
+            break;
+        case DF_HALF:
+            gen_helper_msa_ilvod_h(cpu_env, twd, tws, twt);
+            break;
+        case DF_WORD:
+            gen_helper_msa_ilvod_w(cpu_env, twd, tws, twt);
+            break;
+        case DF_DOUBLE:
+            gen_helper_msa_ilvod_d(cpu_env, twd, tws, twt);
+            break;
+        }
+        break;
+    case OPC_ILVL_df:
+        switch (df) {
+        case DF_BYTE:
+            gen_helper_msa_ilvl_b(cpu_env, twd, tws, twt);
+            break;
+        case DF_HALF:
+            gen_helper_msa_ilvl_h(cpu_env, twd, tws, twt);
+            break;
+        case DF_WORD:
+            gen_helper_msa_ilvl_w(cpu_env, twd, tws, twt);
+            break;
+        case DF_DOUBLE:
+            gen_helper_msa_ilvl_d(cpu_env, twd, tws, twt);
+            break;
+        }
+        break;
+    case OPC_ILVR_df:
+        switch (df) {
+        case DF_BYTE:
+            gen_helper_msa_ilvr_b(cpu_env, twd, tws, twt);
+            break;
+        case DF_HALF:
+            gen_helper_msa_ilvr_h(cpu_env, twd, tws, twt);
+            break;
+        case DF_WORD:
+            gen_helper_msa_ilvr_w(cpu_env, twd, tws, twt);
+            break;
+        case DF_DOUBLE:
+            gen_helper_msa_ilvr_d(cpu_env, twd, tws, twt);
+            break;
+        }
+        break;
     case OPC_SLL_df:
         gen_helper_msa_sll_df(cpu_env, tdf, twd, tws, twt);
         break;
@@ -28842,21 +28906,9 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx)
     case OPC_ASUB_S_df:
         gen_helper_msa_asub_s_df(cpu_env, tdf, twd, tws, twt);
         break;
-    case OPC_ILVL_df:
-        gen_helper_msa_ilvl_df(cpu_env, tdf, twd, tws, twt);
-        break;
     case OPC_ASUB_U_df:
         gen_helper_msa_asub_u_df(cpu_env, tdf, twd, tws, twt);
         break;
-    case OPC_ILVR_df:
-        gen_helper_msa_ilvr_df(cpu_env, tdf, twd, tws, twt);
-        break;
-    case OPC_ILVEV_df:
-        gen_helper_msa_ilvev_df(cpu_env, tdf, twd, tws, twt);
-        break;
-    case OPC_ILVOD_df:
-        gen_helper_msa_ilvod_df(cpu_env, tdf, twd, tws, twt);
-        break;
 
     case OPC_DOTP_S_df:
     case OPC_DOTP_U_df:
-- 
2.7.4

[PULL 07/11] target/mips: msa: Split helpers for ADD<_A|S_A|S_S|S_U|V>.<B|H|W|D>

[Aleksandar Markovic]

From: Aleksandar Markovic <amarkovic@wavecomp.com>

Achieves clearer code and slightly better performance.

Reviewed-by: Aleksandar Rikalo <aleksandar.rikalo@rt-rk.com>
Signed-off-by: Aleksandar Markovic <amarkovic@wavecomp.com>
Message-Id: <1571826227-10583-8-git-send-email-aleksandar.markovic@rt-rk.com>
---
 target/mips/helper.h     |  30 +++-
 target/mips/msa_helper.c | 426 +++++++++++++++++++++++++++++++++++++++++------
 target/mips/translate.c  |  95 +++++++++--
 3 files changed, 482 insertions(+), 69 deletions(-)

diff --git a/target/mips/helper.h b/target/mips/helper.h
index f3df187..ce01e97 100644
--- a/target/mips/helper.h
+++ b/target/mips/helper.h
@@ -822,6 +822,31 @@ DEF_HELPER_4(msa_bset_h, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_bset_w, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_bset_d, void, env, i32, i32, i32)
 
+DEF_HELPER_4(msa_add_a_b, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_add_a_h, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_add_a_w, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_add_a_d, void, env, i32, i32, i32)
+
+DEF_HELPER_4(msa_adds_a_b, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_adds_a_h, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_adds_a_w, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_adds_a_d, void, env, i32, i32, i32)
+
+DEF_HELPER_4(msa_adds_s_b, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_adds_s_h, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_adds_s_w, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_adds_s_d, void, env, i32, i32, i32)
+
+DEF_HELPER_4(msa_adds_u_b, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_adds_u_h, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_adds_u_w, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_adds_u_d, void, env, i32, i32, i32)
+
+DEF_HELPER_4(msa_addv_b, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_addv_h, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_addv_w, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_addv_d, void, env, i32, i32, i32)
+
 DEF_HELPER_4(msa_ave_s_b, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_ave_s_h, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_ave_s_w, void, env, i32, i32, i32)
@@ -976,12 +1001,7 @@ DEF_HELPER_5(msa_sra_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_srl_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_binsl_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_binsr_df, void, env, i32, i32, i32, i32)
-DEF_HELPER_5(msa_addv_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_subv_df, void, env, i32, i32, i32, i32)
-DEF_HELPER_5(msa_add_a_df, void, env, i32, i32, i32, i32)
-DEF_HELPER_5(msa_adds_a_df, void, env, i32, i32, i32, i32)
-DEF_HELPER_5(msa_adds_s_df, void, env, i32, i32, i32, i32)
-DEF_HELPER_5(msa_adds_u_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_subs_s_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_subs_u_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_subsus_u_df, void, env, i32, i32, i32, i32)
diff --git a/target/mips/msa_helper.c b/target/mips/msa_helper.c
index 499fcde..c31f46c 100644
--- a/target/mips/msa_helper.c
+++ b/target/mips/msa_helper.c
@@ -805,7 +805,383 @@ void helper_msa_bset_d(CPUMIPSState *env, uint32_t wd, uint32_t ws, uint32_t wt)
  * +---------------+----------------------------------------------------------+
  */
 
-/* TODO: insert Int Add group helpers here */
+
+static inline int64_t msa_add_a_df(uint32_t df, int64_t arg1, int64_t arg2)
+{
+    uint64_t abs_arg1 = arg1 >= 0 ? arg1 : -arg1;
+    uint64_t abs_arg2 = arg2 >= 0 ? arg2 : -arg2;
+    return abs_arg1 + abs_arg2;
+}
+
+void helper_msa_add_a_b(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->b[0]  = msa_add_a_df(DF_BYTE, pws->b[0],  pwt->b[0]);
+    pwd->b[1]  = msa_add_a_df(DF_BYTE, pws->b[1],  pwt->b[1]);
+    pwd->b[2]  = msa_add_a_df(DF_BYTE, pws->b[2],  pwt->b[2]);
+    pwd->b[3]  = msa_add_a_df(DF_BYTE, pws->b[3],  pwt->b[3]);
+    pwd->b[4]  = msa_add_a_df(DF_BYTE, pws->b[4],  pwt->b[4]);
+    pwd->b[5]  = msa_add_a_df(DF_BYTE, pws->b[5],  pwt->b[5]);
+    pwd->b[6]  = msa_add_a_df(DF_BYTE, pws->b[6],  pwt->b[6]);
+    pwd->b[7]  = msa_add_a_df(DF_BYTE, pws->b[7],  pwt->b[7]);
+    pwd->b[8]  = msa_add_a_df(DF_BYTE, pws->b[8],  pwt->b[8]);
+    pwd->b[9]  = msa_add_a_df(DF_BYTE, pws->b[9],  pwt->b[9]);
+    pwd->b[10] = msa_add_a_df(DF_BYTE, pws->b[10], pwt->b[10]);
+    pwd->b[11] = msa_add_a_df(DF_BYTE, pws->b[11], pwt->b[11]);
+    pwd->b[12] = msa_add_a_df(DF_BYTE, pws->b[12], pwt->b[12]);
+    pwd->b[13] = msa_add_a_df(DF_BYTE, pws->b[13], pwt->b[13]);
+    pwd->b[14] = msa_add_a_df(DF_BYTE, pws->b[14], pwt->b[14]);
+    pwd->b[15] = msa_add_a_df(DF_BYTE, pws->b[15], pwt->b[15]);
+}
+
+void helper_msa_add_a_h(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->h[0]  = msa_add_a_df(DF_HALF, pws->h[0],  pwt->h[0]);
+    pwd->h[1]  = msa_add_a_df(DF_HALF, pws->h[1],  pwt->h[1]);
+    pwd->h[2]  = msa_add_a_df(DF_HALF, pws->h[2],  pwt->h[2]);
+    pwd->h[3]  = msa_add_a_df(DF_HALF, pws->h[3],  pwt->h[3]);
+    pwd->h[4]  = msa_add_a_df(DF_HALF, pws->h[4],  pwt->h[4]);
+    pwd->h[5]  = msa_add_a_df(DF_HALF, pws->h[5],  pwt->h[5]);
+    pwd->h[6]  = msa_add_a_df(DF_HALF, pws->h[6],  pwt->h[6]);
+    pwd->h[7]  = msa_add_a_df(DF_HALF, pws->h[7],  pwt->h[7]);
+}
+
+void helper_msa_add_a_w(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->w[0]  = msa_add_a_df(DF_WORD, pws->w[0],  pwt->w[0]);
+    pwd->w[1]  = msa_add_a_df(DF_WORD, pws->w[1],  pwt->w[1]);
+    pwd->w[2]  = msa_add_a_df(DF_WORD, pws->w[2],  pwt->w[2]);
+    pwd->w[3]  = msa_add_a_df(DF_WORD, pws->w[3],  pwt->w[3]);
+}
+
+void helper_msa_add_a_d(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->d[0]  = msa_add_a_df(DF_DOUBLE, pws->d[0],  pwt->d[0]);
+    pwd->d[1]  = msa_add_a_df(DF_DOUBLE, pws->d[1],  pwt->d[1]);
+}
+
+
+static inline int64_t msa_adds_a_df(uint32_t df, int64_t arg1, int64_t arg2)
+{
+    uint64_t max_int = (uint64_t)DF_MAX_INT(df);
+    uint64_t abs_arg1 = arg1 >= 0 ? arg1 : -arg1;
+    uint64_t abs_arg2 = arg2 >= 0 ? arg2 : -arg2;
+    if (abs_arg1 > max_int || abs_arg2 > max_int) {
+        return (int64_t)max_int;
+    } else {
+        return (abs_arg1 < max_int - abs_arg2) ? abs_arg1 + abs_arg2 : max_int;
+    }
+}
+
+void helper_msa_adds_a_b(CPUMIPSState *env,
+                         uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->b[0]  = msa_adds_a_df(DF_BYTE, pws->b[0],  pwt->b[0]);
+    pwd->b[1]  = msa_adds_a_df(DF_BYTE, pws->b[1],  pwt->b[1]);
+    pwd->b[2]  = msa_adds_a_df(DF_BYTE, pws->b[2],  pwt->b[2]);
+    pwd->b[3]  = msa_adds_a_df(DF_BYTE, pws->b[3],  pwt->b[3]);
+    pwd->b[4]  = msa_adds_a_df(DF_BYTE, pws->b[4],  pwt->b[4]);
+    pwd->b[5]  = msa_adds_a_df(DF_BYTE, pws->b[5],  pwt->b[5]);
+    pwd->b[6]  = msa_adds_a_df(DF_BYTE, pws->b[6],  pwt->b[6]);
+    pwd->b[7]  = msa_adds_a_df(DF_BYTE, pws->b[7],  pwt->b[7]);
+    pwd->b[8]  = msa_adds_a_df(DF_BYTE, pws->b[8],  pwt->b[8]);
+    pwd->b[9]  = msa_adds_a_df(DF_BYTE, pws->b[9],  pwt->b[9]);
+    pwd->b[10] = msa_adds_a_df(DF_BYTE, pws->b[10], pwt->b[10]);
+    pwd->b[11] = msa_adds_a_df(DF_BYTE, pws->b[11], pwt->b[11]);
+    pwd->b[12] = msa_adds_a_df(DF_BYTE, pws->b[12], pwt->b[12]);
+    pwd->b[13] = msa_adds_a_df(DF_BYTE, pws->b[13], pwt->b[13]);
+    pwd->b[14] = msa_adds_a_df(DF_BYTE, pws->b[14], pwt->b[14]);
+    pwd->b[15] = msa_adds_a_df(DF_BYTE, pws->b[15], pwt->b[15]);
+}
+
+void helper_msa_adds_a_h(CPUMIPSState *env,
+                         uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->h[0]  = msa_adds_a_df(DF_HALF, pws->h[0],  pwt->h[0]);
+    pwd->h[1]  = msa_adds_a_df(DF_HALF, pws->h[1],  pwt->h[1]);
+    pwd->h[2]  = msa_adds_a_df(DF_HALF, pws->h[2],  pwt->h[2]);
+    pwd->h[3]  = msa_adds_a_df(DF_HALF, pws->h[3],  pwt->h[3]);
+    pwd->h[4]  = msa_adds_a_df(DF_HALF, pws->h[4],  pwt->h[4]);
+    pwd->h[5]  = msa_adds_a_df(DF_HALF, pws->h[5],  pwt->h[5]);
+    pwd->h[6]  = msa_adds_a_df(DF_HALF, pws->h[6],  pwt->h[6]);
+    pwd->h[7]  = msa_adds_a_df(DF_HALF, pws->h[7],  pwt->h[7]);
+}
+
+void helper_msa_adds_a_w(CPUMIPSState *env,
+                         uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->w[0]  = msa_adds_a_df(DF_WORD, pws->w[0],  pwt->w[0]);
+    pwd->w[1]  = msa_adds_a_df(DF_WORD, pws->w[1],  pwt->w[1]);
+    pwd->w[2]  = msa_adds_a_df(DF_WORD, pws->w[2],  pwt->w[2]);
+    pwd->w[3]  = msa_adds_a_df(DF_WORD, pws->w[3],  pwt->w[3]);
+}
+
+void helper_msa_adds_a_d(CPUMIPSState *env,
+                         uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->d[0]  = msa_adds_a_df(DF_DOUBLE, pws->d[0],  pwt->d[0]);
+    pwd->d[1]  = msa_adds_a_df(DF_DOUBLE, pws->d[1],  pwt->d[1]);
+}
+
+
+static inline int64_t msa_adds_s_df(uint32_t df, int64_t arg1, int64_t arg2)
+{
+    int64_t max_int = DF_MAX_INT(df);
+    int64_t min_int = DF_MIN_INT(df);
+    if (arg1 < 0) {
+        return (min_int - arg1 < arg2) ? arg1 + arg2 : min_int;
+    } else {
+        return (arg2 < max_int - arg1) ? arg1 + arg2 : max_int;
+    }
+}
+
+void helper_msa_adds_s_b(CPUMIPSState *env,
+                         uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->b[0]  = msa_adds_s_df(DF_BYTE, pws->b[0],  pwt->b[0]);
+    pwd->b[1]  = msa_adds_s_df(DF_BYTE, pws->b[1],  pwt->b[1]);
+    pwd->b[2]  = msa_adds_s_df(DF_BYTE, pws->b[2],  pwt->b[2]);
+    pwd->b[3]  = msa_adds_s_df(DF_BYTE, pws->b[3],  pwt->b[3]);
+    pwd->b[4]  = msa_adds_s_df(DF_BYTE, pws->b[4],  pwt->b[4]);
+    pwd->b[5]  = msa_adds_s_df(DF_BYTE, pws->b[5],  pwt->b[5]);
+    pwd->b[6]  = msa_adds_s_df(DF_BYTE, pws->b[6],  pwt->b[6]);
+    pwd->b[7]  = msa_adds_s_df(DF_BYTE, pws->b[7],  pwt->b[7]);
+    pwd->b[8]  = msa_adds_s_df(DF_BYTE, pws->b[8],  pwt->b[8]);
+    pwd->b[9]  = msa_adds_s_df(DF_BYTE, pws->b[9],  pwt->b[9]);
+    pwd->b[10] = msa_adds_s_df(DF_BYTE, pws->b[10], pwt->b[10]);
+    pwd->b[11] = msa_adds_s_df(DF_BYTE, pws->b[11], pwt->b[11]);
+    pwd->b[12] = msa_adds_s_df(DF_BYTE, pws->b[12], pwt->b[12]);
+    pwd->b[13] = msa_adds_s_df(DF_BYTE, pws->b[13], pwt->b[13]);
+    pwd->b[14] = msa_adds_s_df(DF_BYTE, pws->b[14], pwt->b[14]);
+    pwd->b[15] = msa_adds_s_df(DF_BYTE, pws->b[15], pwt->b[15]);
+}
+
+void helper_msa_adds_s_h(CPUMIPSState *env,
+                         uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->h[0]  = msa_adds_s_df(DF_HALF, pws->h[0],  pwt->h[0]);
+    pwd->h[1]  = msa_adds_s_df(DF_HALF, pws->h[1],  pwt->h[1]);
+    pwd->h[2]  = msa_adds_s_df(DF_HALF, pws->h[2],  pwt->h[2]);
+    pwd->h[3]  = msa_adds_s_df(DF_HALF, pws->h[3],  pwt->h[3]);
+    pwd->h[4]  = msa_adds_s_df(DF_HALF, pws->h[4],  pwt->h[4]);
+    pwd->h[5]  = msa_adds_s_df(DF_HALF, pws->h[5],  pwt->h[5]);
+    pwd->h[6]  = msa_adds_s_df(DF_HALF, pws->h[6],  pwt->h[6]);
+    pwd->h[7]  = msa_adds_s_df(DF_HALF, pws->h[7],  pwt->h[7]);
+}
+
+void helper_msa_adds_s_w(CPUMIPSState *env,
+                         uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->w[0]  = msa_adds_s_df(DF_WORD, pws->w[0],  pwt->w[0]);
+    pwd->w[1]  = msa_adds_s_df(DF_WORD, pws->w[1],  pwt->w[1]);
+    pwd->w[2]  = msa_adds_s_df(DF_WORD, pws->w[2],  pwt->w[2]);
+    pwd->w[3]  = msa_adds_s_df(DF_WORD, pws->w[3],  pwt->w[3]);
+}
+
+void helper_msa_adds_s_d(CPUMIPSState *env,
+                         uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->d[0]  = msa_adds_s_df(DF_DOUBLE, pws->d[0],  pwt->d[0]);
+    pwd->d[1]  = msa_adds_s_df(DF_DOUBLE, pws->d[1],  pwt->d[1]);
+}
+
+
+static inline uint64_t msa_adds_u_df(uint32_t df, uint64_t arg1, uint64_t arg2)
+{
+    uint64_t max_uint = DF_MAX_UINT(df);
+    uint64_t u_arg1 = UNSIGNED(arg1, df);
+    uint64_t u_arg2 = UNSIGNED(arg2, df);
+    return (u_arg1 < max_uint - u_arg2) ? u_arg1 + u_arg2 : max_uint;
+}
+
+void helper_msa_adds_u_b(CPUMIPSState *env,
+                         uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->b[0]  = msa_adds_u_df(DF_BYTE, pws->b[0],  pwt->b[0]);
+    pwd->b[1]  = msa_adds_u_df(DF_BYTE, pws->b[1],  pwt->b[1]);
+    pwd->b[2]  = msa_adds_u_df(DF_BYTE, pws->b[2],  pwt->b[2]);
+    pwd->b[3]  = msa_adds_u_df(DF_BYTE, pws->b[3],  pwt->b[3]);
+    pwd->b[4]  = msa_adds_u_df(DF_BYTE, pws->b[4],  pwt->b[4]);
+    pwd->b[5]  = msa_adds_u_df(DF_BYTE, pws->b[5],  pwt->b[5]);
+    pwd->b[6]  = msa_adds_u_df(DF_BYTE, pws->b[6],  pwt->b[6]);
+    pwd->b[7]  = msa_adds_u_df(DF_BYTE, pws->b[7],  pwt->b[7]);
+    pwd->b[8]  = msa_adds_u_df(DF_BYTE, pws->b[8],  pwt->b[8]);
+    pwd->b[9]  = msa_adds_u_df(DF_BYTE, pws->b[9],  pwt->b[9]);
+    pwd->b[10] = msa_adds_u_df(DF_BYTE, pws->b[10], pwt->b[10]);
+    pwd->b[11] = msa_adds_u_df(DF_BYTE, pws->b[11], pwt->b[11]);
+    pwd->b[12] = msa_adds_u_df(DF_BYTE, pws->b[12], pwt->b[12]);
+    pwd->b[13] = msa_adds_u_df(DF_BYTE, pws->b[13], pwt->b[13]);
+    pwd->b[14] = msa_adds_u_df(DF_BYTE, pws->b[14], pwt->b[14]);
+    pwd->b[15] = msa_adds_u_df(DF_BYTE, pws->b[15], pwt->b[15]);
+}
+
+void helper_msa_adds_u_h(CPUMIPSState *env,
+                         uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->h[0]  = msa_adds_u_df(DF_HALF, pws->h[0],  pwt->h[0]);
+    pwd->h[1]  = msa_adds_u_df(DF_HALF, pws->h[1],  pwt->h[1]);
+    pwd->h[2]  = msa_adds_u_df(DF_HALF, pws->h[2],  pwt->h[2]);
+    pwd->h[3]  = msa_adds_u_df(DF_HALF, pws->h[3],  pwt->h[3]);
+    pwd->h[4]  = msa_adds_u_df(DF_HALF, pws->h[4],  pwt->h[4]);
+    pwd->h[5]  = msa_adds_u_df(DF_HALF, pws->h[5],  pwt->h[5]);
+    pwd->h[6]  = msa_adds_u_df(DF_HALF, pws->h[6],  pwt->h[6]);
+    pwd->h[7]  = msa_adds_u_df(DF_HALF, pws->h[7],  pwt->h[7]);
+}
+
+void helper_msa_adds_u_w(CPUMIPSState *env,
+                         uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->w[0]  = msa_adds_u_df(DF_WORD, pws->w[0],  pwt->w[0]);
+    pwd->w[1]  = msa_adds_u_df(DF_WORD, pws->w[1],  pwt->w[1]);
+    pwd->w[2]  = msa_adds_u_df(DF_WORD, pws->w[2],  pwt->w[2]);
+    pwd->w[3]  = msa_adds_u_df(DF_WORD, pws->w[3],  pwt->w[3]);
+}
+
+void helper_msa_adds_u_d(CPUMIPSState *env,
+                         uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->d[0]  = msa_adds_u_df(DF_DOUBLE, pws->d[0],  pwt->d[0]);
+    pwd->d[1]  = msa_adds_u_df(DF_DOUBLE, pws->d[1],  pwt->d[1]);
+}
+
+
+static inline int64_t msa_addv_df(uint32_t df, int64_t arg1, int64_t arg2)
+{
+    return arg1 + arg2;
+}
+
+void helper_msa_addv_b(CPUMIPSState *env,
+                       uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->b[0]  = msa_addv_df(DF_BYTE, pws->b[0],  pwt->b[0]);
+    pwd->b[1]  = msa_addv_df(DF_BYTE, pws->b[1],  pwt->b[1]);
+    pwd->b[2]  = msa_addv_df(DF_BYTE, pws->b[2],  pwt->b[2]);
+    pwd->b[3]  = msa_addv_df(DF_BYTE, pws->b[3],  pwt->b[3]);
+    pwd->b[4]  = msa_addv_df(DF_BYTE, pws->b[4],  pwt->b[4]);
+    pwd->b[5]  = msa_addv_df(DF_BYTE, pws->b[5],  pwt->b[5]);
+    pwd->b[6]  = msa_addv_df(DF_BYTE, pws->b[6],  pwt->b[6]);
+    pwd->b[7]  = msa_addv_df(DF_BYTE, pws->b[7],  pwt->b[7]);
+    pwd->b[8]  = msa_addv_df(DF_BYTE, pws->b[8],  pwt->b[8]);
+    pwd->b[9]  = msa_addv_df(DF_BYTE, pws->b[9],  pwt->b[9]);
+    pwd->b[10] = msa_addv_df(DF_BYTE, pws->b[10], pwt->b[10]);
+    pwd->b[11] = msa_addv_df(DF_BYTE, pws->b[11], pwt->b[11]);
+    pwd->b[12] = msa_addv_df(DF_BYTE, pws->b[12], pwt->b[12]);
+    pwd->b[13] = msa_addv_df(DF_BYTE, pws->b[13], pwt->b[13]);
+    pwd->b[14] = msa_addv_df(DF_BYTE, pws->b[14], pwt->b[14]);
+    pwd->b[15] = msa_addv_df(DF_BYTE, pws->b[15], pwt->b[15]);
+}
+
+void helper_msa_addv_h(CPUMIPSState *env,
+                       uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->h[0]  = msa_addv_df(DF_HALF, pws->h[0],  pwt->h[0]);
+    pwd->h[1]  = msa_addv_df(DF_HALF, pws->h[1],  pwt->h[1]);
+    pwd->h[2]  = msa_addv_df(DF_HALF, pws->h[2],  pwt->h[2]);
+    pwd->h[3]  = msa_addv_df(DF_HALF, pws->h[3],  pwt->h[3]);
+    pwd->h[4]  = msa_addv_df(DF_HALF, pws->h[4],  pwt->h[4]);
+    pwd->h[5]  = msa_addv_df(DF_HALF, pws->h[5],  pwt->h[5]);
+    pwd->h[6]  = msa_addv_df(DF_HALF, pws->h[6],  pwt->h[6]);
+    pwd->h[7]  = msa_addv_df(DF_HALF, pws->h[7],  pwt->h[7]);
+}
+
+void helper_msa_addv_w(CPUMIPSState *env,
+                       uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->w[0]  = msa_addv_df(DF_WORD, pws->w[0],  pwt->w[0]);
+    pwd->w[1]  = msa_addv_df(DF_WORD, pws->w[1],  pwt->w[1]);
+    pwd->w[2]  = msa_addv_df(DF_WORD, pws->w[2],  pwt->w[2]);
+    pwd->w[3]  = msa_addv_df(DF_WORD, pws->w[3],  pwt->w[3]);
+}
+
+void helper_msa_addv_d(CPUMIPSState *env,
+                       uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->d[0]  = msa_addv_df(DF_DOUBLE, pws->d[0],  pwt->d[0]);
+    pwd->d[1]  = msa_addv_df(DF_DOUBLE, pws->d[1],  pwt->d[1]);
+}
 
 
 /*
@@ -3050,11 +3426,6 @@ void helper_msa_shf_df(CPUMIPSState *env, uint32_t df, uint32_t wd,
     msa_move_v(pwd, pwx);
 }
 
-static inline int64_t msa_addv_df(uint32_t df, int64_t arg1, int64_t arg2)
-{
-    return arg1 + arg2;
-}
-
 static inline int64_t msa_subv_df(uint32_t df, int64_t arg1, int64_t arg2)
 {
     return arg1 - arg2;
@@ -3283,44 +3654,6 @@ MSA_TEROP_IMMU_DF(binsli, binsl)
 MSA_TEROP_IMMU_DF(binsri, binsr)
 #undef MSA_TEROP_IMMU_DF
 
-static inline int64_t msa_add_a_df(uint32_t df, int64_t arg1, int64_t arg2)
-{
-    uint64_t abs_arg1 = arg1 >= 0 ? arg1 : -arg1;
-    uint64_t abs_arg2 = arg2 >= 0 ? arg2 : -arg2;
-    return abs_arg1 + abs_arg2;
-}
-
-static inline int64_t msa_adds_a_df(uint32_t df, int64_t arg1, int64_t arg2)
-{
-    uint64_t max_int = (uint64_t)DF_MAX_INT(df);
-    uint64_t abs_arg1 = arg1 >= 0 ? arg1 : -arg1;
-    uint64_t abs_arg2 = arg2 >= 0 ? arg2 : -arg2;
-    if (abs_arg1 > max_int || abs_arg2 > max_int) {
-        return (int64_t)max_int;
-    } else {
-        return (abs_arg1 < max_int - abs_arg2) ? abs_arg1 + abs_arg2 : max_int;
-    }
-}
-
-static inline int64_t msa_adds_s_df(uint32_t df, int64_t arg1, int64_t arg2)
-{
-    int64_t max_int = DF_MAX_INT(df);
-    int64_t min_int = DF_MIN_INT(df);
-    if (arg1 < 0) {
-        return (min_int - arg1 < arg2) ? arg1 + arg2 : min_int;
-    } else {
-        return (arg2 < max_int - arg1) ? arg1 + arg2 : max_int;
-    }
-}
-
-static inline uint64_t msa_adds_u_df(uint32_t df, uint64_t arg1, uint64_t arg2)
-{
-    uint64_t max_uint = DF_MAX_UINT(df);
-    uint64_t u_arg1 = UNSIGNED(arg1, df);
-    uint64_t u_arg2 = UNSIGNED(arg2, df);
-    return (u_arg1 < max_uint - u_arg2) ? u_arg1 + u_arg2 : max_uint;
-}
-
 static inline int64_t msa_subs_s_df(uint32_t df, int64_t arg1, int64_t arg2)
 {
     int64_t max_int = DF_MAX_INT(df);
@@ -3580,12 +3913,7 @@ void helper_msa_ ## func ## _df(CPUMIPSState *env, uint32_t df,         \
 MSA_BINOP_DF(sll)
 MSA_BINOP_DF(sra)
 MSA_BINOP_DF(srl)
-MSA_BINOP_DF(addv)
 MSA_BINOP_DF(subv)
-MSA_BINOP_DF(add_a)
-MSA_BINOP_DF(adds_a)
-MSA_BINOP_DF(adds_s)
-MSA_BINOP_DF(adds_u)
 MSA_BINOP_DF(subs_s)
 MSA_BINOP_DF(subs_u)
 MSA_BINOP_DF(subsus_u)
diff --git a/target/mips/translate.c b/target/mips/translate.c
index ea8b8f4..14f9891 100644
--- a/target/mips/translate.c
+++ b/target/mips/translate.c
@@ -28466,6 +28466,86 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx)
             break;
         }
         break;
+    case OPC_ADD_A_df:
+        switch (df) {
+        case DF_BYTE:
+            gen_helper_msa_add_a_b(cpu_env, twd, tws, twt);
+            break;
+        case DF_HALF:
+            gen_helper_msa_add_a_h(cpu_env, twd, tws, twt);
+            break;
+        case DF_WORD:
+            gen_helper_msa_add_a_w(cpu_env, twd, tws, twt);
+            break;
+        case DF_DOUBLE:
+            gen_helper_msa_add_a_d(cpu_env, twd, tws, twt);
+            break;
+        }
+        break;
+    case OPC_ADDS_A_df:
+        switch (df) {
+        case DF_BYTE:
+            gen_helper_msa_adds_a_b(cpu_env, twd, tws, twt);
+            break;
+        case DF_HALF:
+            gen_helper_msa_adds_a_h(cpu_env, twd, tws, twt);
+            break;
+        case DF_WORD:
+            gen_helper_msa_adds_a_w(cpu_env, twd, tws, twt);
+            break;
+        case DF_DOUBLE:
+            gen_helper_msa_adds_a_d(cpu_env, twd, tws, twt);
+            break;
+        }
+        break;
+    case OPC_ADDS_S_df:
+        switch (df) {
+        case DF_BYTE:
+            gen_helper_msa_adds_s_b(cpu_env, twd, tws, twt);
+            break;
+        case DF_HALF:
+            gen_helper_msa_adds_s_h(cpu_env, twd, tws, twt);
+            break;
+        case DF_WORD:
+            gen_helper_msa_adds_s_w(cpu_env, twd, tws, twt);
+            break;
+        case DF_DOUBLE:
+            gen_helper_msa_adds_s_d(cpu_env, twd, tws, twt);
+            break;
+        }
+        break;
+    case OPC_ADDS_U_df:
+        switch (df) {
+        case DF_BYTE:
+            gen_helper_msa_adds_u_b(cpu_env, twd, tws, twt);
+            break;
+        case DF_HALF:
+            gen_helper_msa_adds_u_h(cpu_env, twd, tws, twt);
+            break;
+        case DF_WORD:
+            gen_helper_msa_adds_u_w(cpu_env, twd, tws, twt);
+            break;
+        case DF_DOUBLE:
+            gen_helper_msa_adds_u_d(cpu_env, twd, tws, twt);
+            break;
+        }
+        break;
+    case OPC_ADDV_df:
+        switch (df) {
+        case DF_BYTE:
+            gen_helper_msa_addv_b(cpu_env, twd, tws, twt);
+            break;
+        case DF_HALF:
+            gen_helper_msa_addv_h(cpu_env, twd, tws, twt);
+            break;
+        case DF_WORD:
+            gen_helper_msa_addv_w(cpu_env, twd, tws, twt);
+            break;
+        case DF_DOUBLE:
+            gen_helper_msa_addv_d(cpu_env, twd, tws, twt);
+            break;
+        }
+        break;
     case OPC_AVE_S_df:
         switch (df) {
         case DF_BYTE:
@@ -28837,12 +28917,6 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx)
     case OPC_SLL_df:
         gen_helper_msa_sll_df(cpu_env, tdf, twd, tws, twt);
         break;
-    case OPC_ADDV_df:
-        gen_helper_msa_addv_df(cpu_env, tdf, twd, tws, twt);
-        break;
-    case OPC_ADD_A_df:
-        gen_helper_msa_add_a_df(cpu_env, tdf, twd, tws, twt);
-        break;
     case OPC_SUBS_S_df:
         gen_helper_msa_subs_s_df(cpu_env, tdf, twd, tws, twt);
         break;
@@ -28861,9 +28935,6 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx)
     case OPC_SUBV_df:
         gen_helper_msa_subv_df(cpu_env, tdf, twd, tws, twt);
         break;
-    case OPC_ADDS_A_df:
-        gen_helper_msa_adds_a_df(cpu_env, tdf, twd, tws, twt);
-        break;
     case OPC_SUBS_U_df:
         gen_helper_msa_subs_u_df(cpu_env, tdf, twd, tws, twt);
         break;
@@ -28879,9 +28950,6 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx)
     case OPC_SRL_df:
         gen_helper_msa_srl_df(cpu_env, tdf, twd, tws, twt);
         break;
-    case OPC_ADDS_S_df:
-        gen_helper_msa_adds_s_df(cpu_env, tdf, twd, tws, twt);
-        break;
     case OPC_SUBSUS_U_df:
         gen_helper_msa_subsus_u_df(cpu_env, tdf, twd, tws, twt);
         break;
@@ -28894,9 +28962,6 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx)
     case OPC_SRLR_df:
         gen_helper_msa_srlr_df(cpu_env, tdf, twd, tws, twt);
         break;
-    case OPC_ADDS_U_df:
-        gen_helper_msa_adds_u_df(cpu_env, tdf, twd, tws, twt);
-        break;
     case OPC_SUBSUU_S_df:
         gen_helper_msa_subsuu_s_df(cpu_env, tdf, twd, tws, twt);
         break;
-- 
2.7.4

[PULL 08/11] target/mips: msa: Split helpers for HADD_<S|U>.<H|W|D>

[Aleksandar Markovic]

From: Aleksandar Markovic <amarkovic@wavecomp.com>

Achieves clearer code and slightly better performance.

Reviewed-by: Aleksandar Rikalo <aleksandar.rikalo@rt-rk.com>
Signed-off-by: Aleksandar Markovic <amarkovic@wavecomp.com>
Message-Id: <1571826227-10583-9-git-send-email-aleksandar.markovic@rt-rk.com>
---
 target/mips/helper.h     |  10 +++-
 target/mips/msa_helper.c | 131 ++++++++++++++++++++++++++++++++++++++---------
 target/mips/translate.c  |  32 +++++++++---
 3 files changed, 141 insertions(+), 32 deletions(-)

diff --git a/target/mips/helper.h b/target/mips/helper.h
index ce01e97..f25ba90 100644
--- a/target/mips/helper.h
+++ b/target/mips/helper.h
@@ -847,6 +847,14 @@ DEF_HELPER_4(msa_addv_h, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_addv_w, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_addv_d, void, env, i32, i32, i32)
 
+DEF_HELPER_4(msa_hadd_s_h, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_hadd_s_w, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_hadd_s_d, void, env, i32, i32, i32)
+
+DEF_HELPER_4(msa_hadd_u_h, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_hadd_u_w, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_hadd_u_d, void, env, i32, i32, i32)
+
 DEF_HELPER_4(msa_ave_s_b, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_ave_s_h, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_ave_s_w, void, env, i32, i32, i32)
@@ -1024,8 +1032,6 @@ DEF_HELPER_5(msa_pckod_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_vshf_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_srar_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_srlr_df, void, env, i32, i32, i32, i32)
-DEF_HELPER_5(msa_hadd_s_df, void, env, i32, i32, i32, i32)
-DEF_HELPER_5(msa_hadd_u_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_hsub_s_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_hsub_u_df, void, env, i32, i32, i32, i32)
 
diff --git a/target/mips/msa_helper.c b/target/mips/msa_helper.c
index c31f46c..f5d3737 100644
--- a/target/mips/msa_helper.c
+++ b/target/mips/msa_helper.c
@@ -1184,6 +1184,113 @@ void helper_msa_addv_d(CPUMIPSState *env,
 }
 
 
+#define SIGNED_EVEN(a, df) \
+        ((((int64_t)(a)) << (64 - DF_BITS(df) / 2)) >> (64 - DF_BITS(df) / 2))
+
+#define UNSIGNED_EVEN(a, df) \
+        ((((uint64_t)(a)) << (64 - DF_BITS(df) / 2)) >> (64 - DF_BITS(df) / 2))
+
+#define SIGNED_ODD(a, df) \
+        ((((int64_t)(a)) << (64 - DF_BITS(df))) >> (64 - DF_BITS(df) / 2))
+
+#define UNSIGNED_ODD(a, df) \
+        ((((uint64_t)(a)) << (64 - DF_BITS(df))) >> (64 - DF_BITS(df) / 2))
+
+
+static inline int64_t msa_hadd_s_df(uint32_t df, int64_t arg1, int64_t arg2)
+{
+    return SIGNED_ODD(arg1, df) + SIGNED_EVEN(arg2, df);
+}
+
+void helper_msa_hadd_s_h(CPUMIPSState *env,
+                         uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->h[0]  = msa_hadd_s_df(DF_HALF, pws->h[0],  pwt->h[0]);
+    pwd->h[1]  = msa_hadd_s_df(DF_HALF, pws->h[1],  pwt->h[1]);
+    pwd->h[2]  = msa_hadd_s_df(DF_HALF, pws->h[2],  pwt->h[2]);
+    pwd->h[3]  = msa_hadd_s_df(DF_HALF, pws->h[3],  pwt->h[3]);
+    pwd->h[4]  = msa_hadd_s_df(DF_HALF, pws->h[4],  pwt->h[4]);
+    pwd->h[5]  = msa_hadd_s_df(DF_HALF, pws->h[5],  pwt->h[5]);
+    pwd->h[6]  = msa_hadd_s_df(DF_HALF, pws->h[6],  pwt->h[6]);
+    pwd->h[7]  = msa_hadd_s_df(DF_HALF, pws->h[7],  pwt->h[7]);
+}
+
+void helper_msa_hadd_s_w(CPUMIPSState *env,
+                         uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->w[0]  = msa_hadd_s_df(DF_WORD, pws->w[0],  pwt->w[0]);
+    pwd->w[1]  = msa_hadd_s_df(DF_WORD, pws->w[1],  pwt->w[1]);
+    pwd->w[2]  = msa_hadd_s_df(DF_WORD, pws->w[2],  pwt->w[2]);
+    pwd->w[3]  = msa_hadd_s_df(DF_WORD, pws->w[3],  pwt->w[3]);
+}
+
+void helper_msa_hadd_s_d(CPUMIPSState *env,
+                         uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->d[0]  = msa_hadd_s_df(DF_DOUBLE, pws->d[0],  pwt->d[0]);
+    pwd->d[1]  = msa_hadd_s_df(DF_DOUBLE, pws->d[1],  pwt->d[1]);
+}
+
+
+static inline int64_t msa_hadd_u_df(uint32_t df, int64_t arg1, int64_t arg2)
+{
+    return UNSIGNED_ODD(arg1, df) + UNSIGNED_EVEN(arg2, df);
+}
+
+void helper_msa_hadd_u_h(CPUMIPSState *env,
+                         uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->h[0]  = msa_hadd_u_df(DF_HALF, pws->h[0],  pwt->h[0]);
+    pwd->h[1]  = msa_hadd_u_df(DF_HALF, pws->h[1],  pwt->h[1]);
+    pwd->h[2]  = msa_hadd_u_df(DF_HALF, pws->h[2],  pwt->h[2]);
+    pwd->h[3]  = msa_hadd_u_df(DF_HALF, pws->h[3],  pwt->h[3]);
+    pwd->h[4]  = msa_hadd_u_df(DF_HALF, pws->h[4],  pwt->h[4]);
+    pwd->h[5]  = msa_hadd_u_df(DF_HALF, pws->h[5],  pwt->h[5]);
+    pwd->h[6]  = msa_hadd_u_df(DF_HALF, pws->h[6],  pwt->h[6]);
+    pwd->h[7]  = msa_hadd_u_df(DF_HALF, pws->h[7],  pwt->h[7]);
+}
+
+void helper_msa_hadd_u_w(CPUMIPSState *env,
+                         uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->w[0]  = msa_hadd_u_df(DF_WORD, pws->w[0],  pwt->w[0]);
+    pwd->w[1]  = msa_hadd_u_df(DF_WORD, pws->w[1],  pwt->w[1]);
+    pwd->w[2]  = msa_hadd_u_df(DF_WORD, pws->w[2],  pwt->w[2]);
+    pwd->w[3]  = msa_hadd_u_df(DF_WORD, pws->w[3],  pwt->w[3]);
+}
+
+void helper_msa_hadd_u_d(CPUMIPSState *env,
+                         uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->d[0]  = msa_hadd_u_df(DF_DOUBLE, pws->d[0],  pwt->d[0]);
+    pwd->d[1]  = msa_hadd_u_df(DF_DOUBLE, pws->d[1],  pwt->d[1]);
+}
+
+
 /*
  * Int Average
  * -----------
@@ -3727,18 +3834,6 @@ static inline int64_t msa_mulv_df(uint32_t df, int64_t arg1, int64_t arg2)
     return arg1 * arg2;
 }
 
-#define SIGNED_EVEN(a, df) \
-        ((((int64_t)(a)) << (64 - DF_BITS(df) / 2)) >> (64 - DF_BITS(df) / 2))
-
-#define UNSIGNED_EVEN(a, df) \
-        ((((uint64_t)(a)) << (64 - DF_BITS(df) / 2)) >> (64 - DF_BITS(df) / 2))
-
-#define SIGNED_ODD(a, df) \
-        ((((int64_t)(a)) << (64 - DF_BITS(df))) >> (64 - DF_BITS(df) / 2))
-
-#define UNSIGNED_ODD(a, df) \
-        ((((uint64_t)(a)) << (64 - DF_BITS(df))) >> (64 - DF_BITS(df) / 2))
-
 #define SIGNED_EXTRACT(e, o, a, df)     \
     do {                                \
         e = SIGNED_EVEN(a, df);         \
@@ -3815,16 +3910,6 @@ static inline void msa_sld_df(uint32_t df, wr_t *pwd,
     }
 }
 
-static inline int64_t msa_hadd_s_df(uint32_t df, int64_t arg1, int64_t arg2)
-{
-    return SIGNED_ODD(arg1, df) + SIGNED_EVEN(arg2, df);
-}
-
-static inline int64_t msa_hadd_u_df(uint32_t df, int64_t arg1, int64_t arg2)
-{
-    return UNSIGNED_ODD(arg1, df) + UNSIGNED_EVEN(arg2, df);
-}
-
 static inline int64_t msa_hsub_s_df(uint32_t df, int64_t arg1, int64_t arg2)
 {
     return SIGNED_ODD(arg1, df) - SIGNED_EVEN(arg2, df);
@@ -3925,8 +4010,6 @@ MSA_BINOP_DF(dotp_s)
 MSA_BINOP_DF(dotp_u)
 MSA_BINOP_DF(srar)
 MSA_BINOP_DF(srlr)
-MSA_BINOP_DF(hadd_s)
-MSA_BINOP_DF(hadd_u)
 MSA_BINOP_DF(hsub_s)
 MSA_BINOP_DF(hsub_u)
 
diff --git a/target/mips/translate.c b/target/mips/translate.c
index 14f9891..9e8e973 100644
--- a/target/mips/translate.c
+++ b/target/mips/translate.c
@@ -28990,6 +28990,32 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx)
             break;
         }
         switch (MASK_MSA_3R(ctx->opcode)) {
+        case OPC_HADD_S_df:
+            switch (df) {
+            case DF_HALF:
+                gen_helper_msa_hadd_s_h(cpu_env, twd, tws, twt);
+                break;
+            case DF_WORD:
+                gen_helper_msa_hadd_s_w(cpu_env, twd, tws, twt);
+                break;
+            case DF_DOUBLE:
+                gen_helper_msa_hadd_s_d(cpu_env, twd, tws, twt);
+                break;
+            }
+            break;
+        case OPC_HADD_U_df:
+            switch (df) {
+            case DF_HALF:
+                gen_helper_msa_hadd_u_h(cpu_env, twd, tws, twt);
+                break;
+            case DF_WORD:
+                gen_helper_msa_hadd_u_w(cpu_env, twd, tws, twt);
+                break;
+            case DF_DOUBLE:
+                gen_helper_msa_hadd_u_d(cpu_env, twd, tws, twt);
+                break;
+            }
+            break;
         case OPC_DOTP_S_df:
             gen_helper_msa_dotp_s_df(cpu_env, tdf, twd, tws, twt);
             break;
@@ -29005,15 +29031,9 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx)
         case OPC_DPSUB_S_df:
             gen_helper_msa_dpsub_s_df(cpu_env, tdf, twd, tws, twt);
             break;
-        case OPC_HADD_S_df:
-            gen_helper_msa_hadd_s_df(cpu_env, tdf, twd, tws, twt);
-            break;
         case OPC_DPSUB_U_df:
             gen_helper_msa_dpsub_u_df(cpu_env, tdf, twd, tws, twt);
             break;
-        case OPC_HADD_U_df:
-            gen_helper_msa_hadd_u_df(cpu_env, tdf, twd, tws, twt);
-            break;
         case OPC_HSUB_S_df:
             gen_helper_msa_hsub_s_df(cpu_env, tdf, twd, tws, twt);
             break;
-- 
2.7.4

[PULL 09/11] target/mips: msa: Split helpers for S<LL|RA|RAR|RL|RLR>.<B|H|W|D>

[Aleksandar Markovic]

From: Aleksandar Markovic <amarkovic@wavecomp.com>

Achieves clearer code and slightly better performance.

Reviewed-by: Aleksandar Rikalo <aleksandar.rikalo@rt-rk.com>
Signed-off-by: Aleksandar Markovic <amarkovic@wavecomp.com>
Message-Id: <1571826227-10583-10-git-send-email-aleksandar.markovic@rt-rk.com>
---
 target/mips/helper.h     |  30 +++-
 target/mips/msa_helper.c | 424 +++++++++++++++++++++++++++++++++++++++++------
 target/mips/translate.c  |  91 ++++++++--
 3 files changed, 479 insertions(+), 66 deletions(-)

diff --git a/target/mips/helper.h b/target/mips/helper.h
index f25ba90..f779404 100644
--- a/target/mips/helper.h
+++ b/target/mips/helper.h
@@ -967,6 +967,31 @@ DEF_HELPER_4(msa_nor_v, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_or_v, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_xor_v, void, env, i32, i32, i32)
 
+DEF_HELPER_4(msa_sll_b, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_sll_h, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_sll_w, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_sll_d, void, env, i32, i32, i32)
+
+DEF_HELPER_4(msa_sra_b, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_sra_h, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_sra_w, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_sra_d, void, env, i32, i32, i32)
+
+DEF_HELPER_4(msa_srar_b, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_srar_h, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_srar_w, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_srar_d, void, env, i32, i32, i32)
+
+DEF_HELPER_4(msa_srl_b, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_srl_h, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_srl_w, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_srl_d, void, env, i32, i32, i32)
+
+DEF_HELPER_4(msa_srlr_b, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_srlr_h, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_srlr_w, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_srlr_d, void, env, i32, i32, i32)
+
 DEF_HELPER_3(msa_move_v, void, env, i32, i32)
 
 DEF_HELPER_4(msa_andi_b, void, env, i32, i32, i32)
@@ -1004,9 +1029,6 @@ DEF_HELPER_5(msa_sat_u_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_srari_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_srlri_df, void, env, i32, i32, i32, i32)
 
-DEF_HELPER_5(msa_sll_df, void, env, i32, i32, i32, i32)
-DEF_HELPER_5(msa_sra_df, void, env, i32, i32, i32, i32)
-DEF_HELPER_5(msa_srl_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_binsl_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_binsr_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_subv_df, void, env, i32, i32, i32, i32)
@@ -1030,8 +1052,6 @@ DEF_HELPER_5(msa_splat_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_pckev_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_pckod_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_vshf_df, void, env, i32, i32, i32, i32)
-DEF_HELPER_5(msa_srar_df, void, env, i32, i32, i32, i32)
-DEF_HELPER_5(msa_srlr_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_hsub_s_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_hsub_u_df, void, env, i32, i32, i32, i32)
 
diff --git a/target/mips/msa_helper.c b/target/mips/msa_helper.c
index f5d3737..38ff1da 100644
--- a/target/mips/msa_helper.c
+++ b/target/mips/msa_helper.c
@@ -3461,7 +3461,382 @@ void helper_msa_move_v(CPUMIPSState *env, uint32_t wd, uint32_t ws)
  * +---------------+----------------------------------------------------------+
  */
 
-/* TODO: insert Shift group helpers here */
+
+static inline int64_t msa_sll_df(uint32_t df, int64_t arg1, int64_t arg2)
+{
+    int32_t b_arg2 = BIT_POSITION(arg2, df);
+    return arg1 << b_arg2;
+}
+
+void helper_msa_sll_b(CPUMIPSState *env,
+                      uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->b[0]  = msa_sll_df(DF_BYTE, pws->b[0],  pwt->b[0]);
+    pwd->b[1]  = msa_sll_df(DF_BYTE, pws->b[1],  pwt->b[1]);
+    pwd->b[2]  = msa_sll_df(DF_BYTE, pws->b[2],  pwt->b[2]);
+    pwd->b[3]  = msa_sll_df(DF_BYTE, pws->b[3],  pwt->b[3]);
+    pwd->b[4]  = msa_sll_df(DF_BYTE, pws->b[4],  pwt->b[4]);
+    pwd->b[5]  = msa_sll_df(DF_BYTE, pws->b[5],  pwt->b[5]);
+    pwd->b[6]  = msa_sll_df(DF_BYTE, pws->b[6],  pwt->b[6]);
+    pwd->b[7]  = msa_sll_df(DF_BYTE, pws->b[7],  pwt->b[7]);
+    pwd->b[8]  = msa_sll_df(DF_BYTE, pws->b[8],  pwt->b[8]);
+    pwd->b[9]  = msa_sll_df(DF_BYTE, pws->b[9],  pwt->b[9]);
+    pwd->b[10] = msa_sll_df(DF_BYTE, pws->b[10], pwt->b[10]);
+    pwd->b[11] = msa_sll_df(DF_BYTE, pws->b[11], pwt->b[11]);
+    pwd->b[12] = msa_sll_df(DF_BYTE, pws->b[12], pwt->b[12]);
+    pwd->b[13] = msa_sll_df(DF_BYTE, pws->b[13], pwt->b[13]);
+    pwd->b[14] = msa_sll_df(DF_BYTE, pws->b[14], pwt->b[14]);
+    pwd->b[15] = msa_sll_df(DF_BYTE, pws->b[15], pwt->b[15]);
+}
+
+void helper_msa_sll_h(CPUMIPSState *env,
+                      uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->h[0]  = msa_sll_df(DF_HALF, pws->h[0],  pwt->h[0]);
+    pwd->h[1]  = msa_sll_df(DF_HALF, pws->h[1],  pwt->h[1]);
+    pwd->h[2]  = msa_sll_df(DF_HALF, pws->h[2],  pwt->h[2]);
+    pwd->h[3]  = msa_sll_df(DF_HALF, pws->h[3],  pwt->h[3]);
+    pwd->h[4]  = msa_sll_df(DF_HALF, pws->h[4],  pwt->h[4]);
+    pwd->h[5]  = msa_sll_df(DF_HALF, pws->h[5],  pwt->h[5]);
+    pwd->h[6]  = msa_sll_df(DF_HALF, pws->h[6],  pwt->h[6]);
+    pwd->h[7]  = msa_sll_df(DF_HALF, pws->h[7],  pwt->h[7]);
+}
+
+void helper_msa_sll_w(CPUMIPSState *env,
+                      uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->w[0]  = msa_sll_df(DF_WORD, pws->w[0],  pwt->w[0]);
+    pwd->w[1]  = msa_sll_df(DF_WORD, pws->w[1],  pwt->w[1]);
+    pwd->w[2]  = msa_sll_df(DF_WORD, pws->w[2],  pwt->w[2]);
+    pwd->w[3]  = msa_sll_df(DF_WORD, pws->w[3],  pwt->w[3]);
+}
+
+void helper_msa_sll_d(CPUMIPSState *env,
+                      uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->d[0]  = msa_sll_df(DF_DOUBLE, pws->d[0],  pwt->d[0]);
+    pwd->d[1]  = msa_sll_df(DF_DOUBLE, pws->d[1],  pwt->d[1]);
+}
+
+
+static inline int64_t msa_sra_df(uint32_t df, int64_t arg1, int64_t arg2)
+{
+    int32_t b_arg2 = BIT_POSITION(arg2, df);
+    return arg1 >> b_arg2;
+}
+
+void helper_msa_sra_b(CPUMIPSState *env,
+                      uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->b[0]  = msa_sra_df(DF_BYTE, pws->b[0],  pwt->b[0]);
+    pwd->b[1]  = msa_sra_df(DF_BYTE, pws->b[1],  pwt->b[1]);
+    pwd->b[2]  = msa_sra_df(DF_BYTE, pws->b[2],  pwt->b[2]);
+    pwd->b[3]  = msa_sra_df(DF_BYTE, pws->b[3],  pwt->b[3]);
+    pwd->b[4]  = msa_sra_df(DF_BYTE, pws->b[4],  pwt->b[4]);
+    pwd->b[5]  = msa_sra_df(DF_BYTE, pws->b[5],  pwt->b[5]);
+    pwd->b[6]  = msa_sra_df(DF_BYTE, pws->b[6],  pwt->b[6]);
+    pwd->b[7]  = msa_sra_df(DF_BYTE, pws->b[7],  pwt->b[7]);
+    pwd->b[8]  = msa_sra_df(DF_BYTE, pws->b[8],  pwt->b[8]);
+    pwd->b[9]  = msa_sra_df(DF_BYTE, pws->b[9],  pwt->b[9]);
+    pwd->b[10] = msa_sra_df(DF_BYTE, pws->b[10], pwt->b[10]);
+    pwd->b[11] = msa_sra_df(DF_BYTE, pws->b[11], pwt->b[11]);
+    pwd->b[12] = msa_sra_df(DF_BYTE, pws->b[12], pwt->b[12]);
+    pwd->b[13] = msa_sra_df(DF_BYTE, pws->b[13], pwt->b[13]);
+    pwd->b[14] = msa_sra_df(DF_BYTE, pws->b[14], pwt->b[14]);
+    pwd->b[15] = msa_sra_df(DF_BYTE, pws->b[15], pwt->b[15]);
+}
+
+void helper_msa_sra_h(CPUMIPSState *env,
+                      uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->h[0]  = msa_sra_df(DF_HALF, pws->h[0],  pwt->h[0]);
+    pwd->h[1]  = msa_sra_df(DF_HALF, pws->h[1],  pwt->h[1]);
+    pwd->h[2]  = msa_sra_df(DF_HALF, pws->h[2],  pwt->h[2]);
+    pwd->h[3]  = msa_sra_df(DF_HALF, pws->h[3],  pwt->h[3]);
+    pwd->h[4]  = msa_sra_df(DF_HALF, pws->h[4],  pwt->h[4]);
+    pwd->h[5]  = msa_sra_df(DF_HALF, pws->h[5],  pwt->h[5]);
+    pwd->h[6]  = msa_sra_df(DF_HALF, pws->h[6],  pwt->h[6]);
+    pwd->h[7]  = msa_sra_df(DF_HALF, pws->h[7],  pwt->h[7]);
+}
+
+void helper_msa_sra_w(CPUMIPSState *env,
+                      uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->w[0]  = msa_sra_df(DF_WORD, pws->w[0],  pwt->w[0]);
+    pwd->w[1]  = msa_sra_df(DF_WORD, pws->w[1],  pwt->w[1]);
+    pwd->w[2]  = msa_sra_df(DF_WORD, pws->w[2],  pwt->w[2]);
+    pwd->w[3]  = msa_sra_df(DF_WORD, pws->w[3],  pwt->w[3]);
+}
+
+void helper_msa_sra_d(CPUMIPSState *env,
+                      uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->d[0]  = msa_sra_df(DF_DOUBLE, pws->d[0],  pwt->d[0]);
+    pwd->d[1]  = msa_sra_df(DF_DOUBLE, pws->d[1],  pwt->d[1]);
+}
+
+
+static inline int64_t msa_srar_df(uint32_t df, int64_t arg1, int64_t arg2)
+{
+    int32_t b_arg2 = BIT_POSITION(arg2, df);
+    if (b_arg2 == 0) {
+        return arg1;
+    } else {
+        int64_t r_bit = (arg1 >> (b_arg2 - 1)) & 1;
+        return (arg1 >> b_arg2) + r_bit;
+    }
+}
+
+void helper_msa_srar_b(CPUMIPSState *env,
+                       uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->b[0]  = msa_srar_df(DF_BYTE, pws->b[0],  pwt->b[0]);
+    pwd->b[1]  = msa_srar_df(DF_BYTE, pws->b[1],  pwt->b[1]);
+    pwd->b[2]  = msa_srar_df(DF_BYTE, pws->b[2],  pwt->b[2]);
+    pwd->b[3]  = msa_srar_df(DF_BYTE, pws->b[3],  pwt->b[3]);
+    pwd->b[4]  = msa_srar_df(DF_BYTE, pws->b[4],  pwt->b[4]);
+    pwd->b[5]  = msa_srar_df(DF_BYTE, pws->b[5],  pwt->b[5]);
+    pwd->b[6]  = msa_srar_df(DF_BYTE, pws->b[6],  pwt->b[6]);
+    pwd->b[7]  = msa_srar_df(DF_BYTE, pws->b[7],  pwt->b[7]);
+    pwd->b[8]  = msa_srar_df(DF_BYTE, pws->b[8],  pwt->b[8]);
+    pwd->b[9]  = msa_srar_df(DF_BYTE, pws->b[9],  pwt->b[9]);
+    pwd->b[10] = msa_srar_df(DF_BYTE, pws->b[10], pwt->b[10]);
+    pwd->b[11] = msa_srar_df(DF_BYTE, pws->b[11], pwt->b[11]);
+    pwd->b[12] = msa_srar_df(DF_BYTE, pws->b[12], pwt->b[12]);
+    pwd->b[13] = msa_srar_df(DF_BYTE, pws->b[13], pwt->b[13]);
+    pwd->b[14] = msa_srar_df(DF_BYTE, pws->b[14], pwt->b[14]);
+    pwd->b[15] = msa_srar_df(DF_BYTE, pws->b[15], pwt->b[15]);
+}
+
+void helper_msa_srar_h(CPUMIPSState *env,
+                       uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->h[0]  = msa_srar_df(DF_HALF, pws->h[0],  pwt->h[0]);
+    pwd->h[1]  = msa_srar_df(DF_HALF, pws->h[1],  pwt->h[1]);
+    pwd->h[2]  = msa_srar_df(DF_HALF, pws->h[2],  pwt->h[2]);
+    pwd->h[3]  = msa_srar_df(DF_HALF, pws->h[3],  pwt->h[3]);
+    pwd->h[4]  = msa_srar_df(DF_HALF, pws->h[4],  pwt->h[4]);
+    pwd->h[5]  = msa_srar_df(DF_HALF, pws->h[5],  pwt->h[5]);
+    pwd->h[6]  = msa_srar_df(DF_HALF, pws->h[6],  pwt->h[6]);
+    pwd->h[7]  = msa_srar_df(DF_HALF, pws->h[7],  pwt->h[7]);
+}
+
+void helper_msa_srar_w(CPUMIPSState *env,
+                       uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->w[0]  = msa_srar_df(DF_WORD, pws->w[0],  pwt->w[0]);
+    pwd->w[1]  = msa_srar_df(DF_WORD, pws->w[1],  pwt->w[1]);
+    pwd->w[2]  = msa_srar_df(DF_WORD, pws->w[2],  pwt->w[2]);
+    pwd->w[3]  = msa_srar_df(DF_WORD, pws->w[3],  pwt->w[3]);
+}
+
+void helper_msa_srar_d(CPUMIPSState *env,
+                       uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->d[0]  = msa_srar_df(DF_DOUBLE, pws->d[0],  pwt->d[0]);
+    pwd->d[1]  = msa_srar_df(DF_DOUBLE, pws->d[1],  pwt->d[1]);
+}
+
+
+static inline int64_t msa_srl_df(uint32_t df, int64_t arg1, int64_t arg2)
+{
+    uint64_t u_arg1 = UNSIGNED(arg1, df);
+    int32_t b_arg2 = BIT_POSITION(arg2, df);
+    return u_arg1 >> b_arg2;
+}
+
+void helper_msa_srl_b(CPUMIPSState *env,
+                      uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->b[0]  = msa_srl_df(DF_BYTE, pws->b[0],  pwt->b[0]);
+    pwd->b[1]  = msa_srl_df(DF_BYTE, pws->b[1],  pwt->b[1]);
+    pwd->b[2]  = msa_srl_df(DF_BYTE, pws->b[2],  pwt->b[2]);
+    pwd->b[3]  = msa_srl_df(DF_BYTE, pws->b[3],  pwt->b[3]);
+    pwd->b[4]  = msa_srl_df(DF_BYTE, pws->b[4],  pwt->b[4]);
+    pwd->b[5]  = msa_srl_df(DF_BYTE, pws->b[5],  pwt->b[5]);
+    pwd->b[6]  = msa_srl_df(DF_BYTE, pws->b[6],  pwt->b[6]);
+    pwd->b[7]  = msa_srl_df(DF_BYTE, pws->b[7],  pwt->b[7]);
+    pwd->b[8]  = msa_srl_df(DF_BYTE, pws->b[8],  pwt->b[8]);
+    pwd->b[9]  = msa_srl_df(DF_BYTE, pws->b[9],  pwt->b[9]);
+    pwd->b[10] = msa_srl_df(DF_BYTE, pws->b[10], pwt->b[10]);
+    pwd->b[11] = msa_srl_df(DF_BYTE, pws->b[11], pwt->b[11]);
+    pwd->b[12] = msa_srl_df(DF_BYTE, pws->b[12], pwt->b[12]);
+    pwd->b[13] = msa_srl_df(DF_BYTE, pws->b[13], pwt->b[13]);
+    pwd->b[14] = msa_srl_df(DF_BYTE, pws->b[14], pwt->b[14]);
+    pwd->b[15] = msa_srl_df(DF_BYTE, pws->b[15], pwt->b[15]);
+}
+
+void helper_msa_srl_h(CPUMIPSState *env,
+                      uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->h[0]  = msa_srl_df(DF_HALF, pws->h[0],  pwt->h[0]);
+    pwd->h[1]  = msa_srl_df(DF_HALF, pws->h[1],  pwt->h[1]);
+    pwd->h[2]  = msa_srl_df(DF_HALF, pws->h[2],  pwt->h[2]);
+    pwd->h[3]  = msa_srl_df(DF_HALF, pws->h[3],  pwt->h[3]);
+    pwd->h[4]  = msa_srl_df(DF_HALF, pws->h[4],  pwt->h[4]);
+    pwd->h[5]  = msa_srl_df(DF_HALF, pws->h[5],  pwt->h[5]);
+    pwd->h[6]  = msa_srl_df(DF_HALF, pws->h[6],  pwt->h[6]);
+    pwd->h[7]  = msa_srl_df(DF_HALF, pws->h[7],  pwt->h[7]);
+}
+
+void helper_msa_srl_w(CPUMIPSState *env,
+                      uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->w[0]  = msa_srl_df(DF_WORD, pws->w[0],  pwt->w[0]);
+    pwd->w[1]  = msa_srl_df(DF_WORD, pws->w[1],  pwt->w[1]);
+    pwd->w[2]  = msa_srl_df(DF_WORD, pws->w[2],  pwt->w[2]);
+    pwd->w[3]  = msa_srl_df(DF_WORD, pws->w[3],  pwt->w[3]);
+}
+
+void helper_msa_srl_d(CPUMIPSState *env,
+                      uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->d[0]  = msa_srl_df(DF_DOUBLE, pws->d[0],  pwt->d[0]);
+    pwd->d[1]  = msa_srl_df(DF_DOUBLE, pws->d[1],  pwt->d[1]);
+}
+
+
+static inline int64_t msa_srlr_df(uint32_t df, int64_t arg1, int64_t arg2)
+{
+    uint64_t u_arg1 = UNSIGNED(arg1, df);
+    int32_t b_arg2 = BIT_POSITION(arg2, df);
+    if (b_arg2 == 0) {
+        return u_arg1;
+    } else {
+        uint64_t r_bit = (u_arg1 >> (b_arg2 - 1)) & 1;
+        return (u_arg1 >> b_arg2) + r_bit;
+    }
+}
+
+void helper_msa_srlr_b(CPUMIPSState *env,
+                       uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->b[0]  = msa_srlr_df(DF_BYTE, pws->b[0],  pwt->b[0]);
+    pwd->b[1]  = msa_srlr_df(DF_BYTE, pws->b[1],  pwt->b[1]);
+    pwd->b[2]  = msa_srlr_df(DF_BYTE, pws->b[2],  pwt->b[2]);
+    pwd->b[3]  = msa_srlr_df(DF_BYTE, pws->b[3],  pwt->b[3]);
+    pwd->b[4]  = msa_srlr_df(DF_BYTE, pws->b[4],  pwt->b[4]);
+    pwd->b[5]  = msa_srlr_df(DF_BYTE, pws->b[5],  pwt->b[5]);
+    pwd->b[6]  = msa_srlr_df(DF_BYTE, pws->b[6],  pwt->b[6]);
+    pwd->b[7]  = msa_srlr_df(DF_BYTE, pws->b[7],  pwt->b[7]);
+    pwd->b[8]  = msa_srlr_df(DF_BYTE, pws->b[8],  pwt->b[8]);
+    pwd->b[9]  = msa_srlr_df(DF_BYTE, pws->b[9],  pwt->b[9]);
+    pwd->b[10] = msa_srlr_df(DF_BYTE, pws->b[10], pwt->b[10]);
+    pwd->b[11] = msa_srlr_df(DF_BYTE, pws->b[11], pwt->b[11]);
+    pwd->b[12] = msa_srlr_df(DF_BYTE, pws->b[12], pwt->b[12]);
+    pwd->b[13] = msa_srlr_df(DF_BYTE, pws->b[13], pwt->b[13]);
+    pwd->b[14] = msa_srlr_df(DF_BYTE, pws->b[14], pwt->b[14]);
+    pwd->b[15] = msa_srlr_df(DF_BYTE, pws->b[15], pwt->b[15]);
+}
+
+void helper_msa_srlr_h(CPUMIPSState *env,
+                       uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->h[0]  = msa_srlr_df(DF_HALF, pws->h[0],  pwt->h[0]);
+    pwd->h[1]  = msa_srlr_df(DF_HALF, pws->h[1],  pwt->h[1]);
+    pwd->h[2]  = msa_srlr_df(DF_HALF, pws->h[2],  pwt->h[2]);
+    pwd->h[3]  = msa_srlr_df(DF_HALF, pws->h[3],  pwt->h[3]);
+    pwd->h[4]  = msa_srlr_df(DF_HALF, pws->h[4],  pwt->h[4]);
+    pwd->h[5]  = msa_srlr_df(DF_HALF, pws->h[5],  pwt->h[5]);
+    pwd->h[6]  = msa_srlr_df(DF_HALF, pws->h[6],  pwt->h[6]);
+    pwd->h[7]  = msa_srlr_df(DF_HALF, pws->h[7],  pwt->h[7]);
+}
+
+void helper_msa_srlr_w(CPUMIPSState *env,
+                       uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->w[0]  = msa_srlr_df(DF_WORD, pws->w[0],  pwt->w[0]);
+    pwd->w[1]  = msa_srlr_df(DF_WORD, pws->w[1],  pwt->w[1]);
+    pwd->w[2]  = msa_srlr_df(DF_WORD, pws->w[2],  pwt->w[2]);
+    pwd->w[3]  = msa_srlr_df(DF_WORD, pws->w[3],  pwt->w[3]);
+}
+
+void helper_msa_srlr_d(CPUMIPSState *env,
+                       uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->d[0]  = msa_srlr_df(DF_DOUBLE, pws->d[0],  pwt->d[0]);
+    pwd->d[1]  = msa_srlr_df(DF_DOUBLE, pws->d[1],  pwt->d[1]);
+}
 
 
 #define MSA_FN_IMM8(FUNC, DEST, OPERATION)                              \
@@ -3617,25 +3992,6 @@ void helper_msa_ldi_df(CPUMIPSState *env, uint32_t df, uint32_t wd,
     }
 }
 
-static inline int64_t msa_sll_df(uint32_t df, int64_t arg1, int64_t arg2)
-{
-    int32_t b_arg2 = BIT_POSITION(arg2, df);
-    return arg1 << b_arg2;
-}
-
-static inline int64_t msa_sra_df(uint32_t df, int64_t arg1, int64_t arg2)
-{
-    int32_t b_arg2 = BIT_POSITION(arg2, df);
-    return arg1 >> b_arg2;
-}
-
-static inline int64_t msa_srl_df(uint32_t df, int64_t arg1, int64_t arg2)
-{
-    uint64_t u_arg1 = UNSIGNED(arg1, df);
-    int32_t b_arg2 = BIT_POSITION(arg2, df);
-    return u_arg1 >> b_arg2;
-}
-
 static inline int64_t msa_sat_s_df(uint32_t df, int64_t arg, uint32_t m)
 {
     return arg < M_MIN_INT(m + 1) ? M_MIN_INT(m + 1) :
@@ -3650,29 +4006,6 @@ static inline int64_t msa_sat_u_df(uint32_t df, int64_t arg, uint32_t m)
                                         M_MAX_UINT(m + 1);
 }
 
-static inline int64_t msa_srar_df(uint32_t df, int64_t arg1, int64_t arg2)
-{
-    int32_t b_arg2 = BIT_POSITION(arg2, df);
-    if (b_arg2 == 0) {
-        return arg1;
-    } else {
-        int64_t r_bit = (arg1 >> (b_arg2 - 1)) & 1;
-        return (arg1 >> b_arg2) + r_bit;
-    }
-}
-
-static inline int64_t msa_srlr_df(uint32_t df, int64_t arg1, int64_t arg2)
-{
-    uint64_t u_arg1 = UNSIGNED(arg1, df);
-    int32_t b_arg2 = BIT_POSITION(arg2, df);
-    if (b_arg2 == 0) {
-        return u_arg1;
-    } else {
-        uint64_t r_bit = (u_arg1 >> (b_arg2 - 1)) & 1;
-        return (u_arg1 >> b_arg2) + r_bit;
-    }
-}
-
 #define MSA_BINOP_IMMU_DF(helper, func)                                  \
 void helper_msa_ ## helper ## _df(CPUMIPSState *env, uint32_t df, uint32_t wd, \
                        uint32_t ws, uint32_t u5)                        \
@@ -3995,9 +4328,6 @@ void helper_msa_ ## func ## _df(CPUMIPSState *env, uint32_t df,         \
     }                                                                   \
 }
 
-MSA_BINOP_DF(sll)
-MSA_BINOP_DF(sra)
-MSA_BINOP_DF(srl)
 MSA_BINOP_DF(subv)
 MSA_BINOP_DF(subs_s)
 MSA_BINOP_DF(subs_u)
@@ -4008,8 +4338,6 @@ MSA_BINOP_DF(asub_u)
 MSA_BINOP_DF(mulv)
 MSA_BINOP_DF(dotp_s)
 MSA_BINOP_DF(dotp_u)
-MSA_BINOP_DF(srar)
-MSA_BINOP_DF(srlr)
 MSA_BINOP_DF(hsub_s)
 MSA_BINOP_DF(hsub_u)
 
diff --git a/target/mips/translate.c b/target/mips/translate.c
index 9e8e973..7cdf68d 100644
--- a/target/mips/translate.c
+++ b/target/mips/translate.c
@@ -28915,7 +28915,84 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx)
         }
         break;
     case OPC_SLL_df:
-        gen_helper_msa_sll_df(cpu_env, tdf, twd, tws, twt);
+        switch (df) {
+        case DF_BYTE:
+            gen_helper_msa_sll_b(cpu_env, twd, tws, twt);
+            break;
+        case DF_HALF:
+            gen_helper_msa_sll_h(cpu_env, twd, tws, twt);
+            break;
+        case DF_WORD:
+            gen_helper_msa_sll_w(cpu_env, twd, tws, twt);
+            break;
+        case DF_DOUBLE:
+            gen_helper_msa_sll_d(cpu_env, twd, tws, twt);
+            break;
+        }
+        break;
+    case OPC_SRA_df:
+        switch (df) {
+        case DF_BYTE:
+            gen_helper_msa_sra_b(cpu_env, twd, tws, twt);
+            break;
+        case DF_HALF:
+            gen_helper_msa_sra_h(cpu_env, twd, tws, twt);
+            break;
+        case DF_WORD:
+            gen_helper_msa_sra_w(cpu_env, twd, tws, twt);
+            break;
+        case DF_DOUBLE:
+            gen_helper_msa_sra_d(cpu_env, twd, tws, twt);
+            break;
+        }
+        break;
+    case OPC_SRAR_df:
+        switch (df) {
+        case DF_BYTE:
+            gen_helper_msa_srar_b(cpu_env, twd, tws, twt);
+            break;
+        case DF_HALF:
+            gen_helper_msa_srar_h(cpu_env, twd, tws, twt);
+            break;
+        case DF_WORD:
+            gen_helper_msa_srar_w(cpu_env, twd, tws, twt);
+            break;
+        case DF_DOUBLE:
+            gen_helper_msa_srar_d(cpu_env, twd, tws, twt);
+            break;
+        }
+        break;
+    case OPC_SRL_df:
+        switch (df) {
+        case DF_BYTE:
+            gen_helper_msa_srl_b(cpu_env, twd, tws, twt);
+            break;
+        case DF_HALF:
+            gen_helper_msa_srl_h(cpu_env, twd, tws, twt);
+            break;
+        case DF_WORD:
+            gen_helper_msa_srl_w(cpu_env, twd, tws, twt);
+            break;
+        case DF_DOUBLE:
+            gen_helper_msa_srl_d(cpu_env, twd, tws, twt);
+            break;
+        }
+        break;
+    case OPC_SRLR_df:
+        switch (df) {
+        case DF_BYTE:
+            gen_helper_msa_srlr_b(cpu_env, twd, tws, twt);
+            break;
+        case DF_HALF:
+            gen_helper_msa_srlr_h(cpu_env, twd, tws, twt);
+            break;
+        case DF_WORD:
+            gen_helper_msa_srlr_w(cpu_env, twd, tws, twt);
+            break;
+        case DF_DOUBLE:
+            gen_helper_msa_srlr_d(cpu_env, twd, tws, twt);
+            break;
+        }
         break;
     case OPC_SUBS_S_df:
         gen_helper_msa_subs_s_df(cpu_env, tdf, twd, tws, twt);
@@ -28929,9 +29006,6 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx)
     case OPC_VSHF_df:
         gen_helper_msa_vshf_df(cpu_env, tdf, twd, tws, twt);
         break;
-    case OPC_SRA_df:
-        gen_helper_msa_sra_df(cpu_env, tdf, twd, tws, twt);
-        break;
     case OPC_SUBV_df:
         gen_helper_msa_subv_df(cpu_env, tdf, twd, tws, twt);
         break;
@@ -28944,12 +29018,6 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx)
     case OPC_SPLAT_df:
         gen_helper_msa_splat_df(cpu_env, tdf, twd, tws, twt);
         break;
-    case OPC_SRAR_df:
-        gen_helper_msa_srar_df(cpu_env, tdf, twd, tws, twt);
-        break;
-    case OPC_SRL_df:
-        gen_helper_msa_srl_df(cpu_env, tdf, twd, tws, twt);
-        break;
     case OPC_SUBSUS_U_df:
         gen_helper_msa_subsus_u_df(cpu_env, tdf, twd, tws, twt);
         break;
@@ -28959,9 +29027,6 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx)
     case OPC_PCKEV_df:
         gen_helper_msa_pckev_df(cpu_env, tdf, twd, tws, twt);
         break;
-    case OPC_SRLR_df:
-        gen_helper_msa_srlr_df(cpu_env, tdf, twd, tws, twt);
-        break;
     case OPC_SUBSUU_S_df:
         gen_helper_msa_subsuu_s_df(cpu_env, tdf, twd, tws, twt);
         break;
-- 
2.7.4

[PULL 10/11] target/mips: msa: Split helpers for PCK<EV|OD>.<B|H|W|D>

[Aleksandar Markovic]

From: Aleksandar Markovic <amarkovic@wavecomp.com>

Achieves clearer code and slightly better performance.

Reviewed-by: Aleksandar Rikalo <aleksandar.rikalo@rt-rk.com>
Signed-off-by: Aleksandar Markovic <amarkovic@wavecomp.com>
Message-Id: <1571826227-10583-11-git-send-email-aleksandar.markovic@rt-rk.com>
---
 target/mips/helper.h     |  11 +-
 target/mips/msa_helper.c | 386 +++++++++++++++++++++++++----------------------
 target/mips/translate.c  |  38 ++++-
 3 files changed, 249 insertions(+), 186 deletions(-)

diff --git a/target/mips/helper.h b/target/mips/helper.h
index f779404..7bb13d5 100644
--- a/target/mips/helper.h
+++ b/target/mips/helper.h
@@ -967,6 +967,15 @@ DEF_HELPER_4(msa_nor_v, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_or_v, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_xor_v, void, env, i32, i32, i32)
 
+DEF_HELPER_4(msa_pckev_b, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_pckev_h, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_pckev_w, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_pckev_d, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_pckod_b, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_pckod_h, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_pckod_w, void, env, i32, i32, i32)
+DEF_HELPER_4(msa_pckod_d, void, env, i32, i32, i32)
+
 DEF_HELPER_4(msa_sll_b, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_sll_h, void, env, i32, i32, i32)
 DEF_HELPER_4(msa_sll_w, void, env, i32, i32, i32)
@@ -1049,8 +1058,6 @@ DEF_HELPER_5(msa_dpsub_s_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_dpsub_u_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_sld_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_splat_df, void, env, i32, i32, i32, i32)
-DEF_HELPER_5(msa_pckev_df, void, env, i32, i32, i32, i32)
-DEF_HELPER_5(msa_pckod_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_vshf_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_hsub_s_df, void, env, i32, i32, i32, i32)
 DEF_HELPER_5(msa_hsub_u_df, void, env, i32, i32, i32, i32)
diff --git a/target/mips/msa_helper.c b/target/mips/msa_helper.c
index 38ff1da..2400632 100644
--- a/target/mips/msa_helper.c
+++ b/target/mips/msa_helper.c
@@ -3430,7 +3430,214 @@ void helper_msa_move_v(CPUMIPSState *env, uint32_t wd, uint32_t ws)
  * +---------------+----------------------------------------------------------+
  */
 
-/* TODO: insert Pack group helpers here */
+
+void helper_msa_pckev_b(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+#if defined(HOST_WORDS_BIGENDIAN)
+    pwd->b[8]  = pws->b[9];
+    pwd->b[10] = pws->b[13];
+    pwd->b[12] = pws->b[1];
+    pwd->b[14] = pws->b[5];
+    pwd->b[0]  = pwt->b[9];
+    pwd->b[2]  = pwt->b[13];
+    pwd->b[4]  = pwt->b[1];
+    pwd->b[6]  = pwt->b[5];
+    pwd->b[9]  = pws->b[11];
+    pwd->b[13] = pws->b[3];
+    pwd->b[1]  = pwt->b[11];
+    pwd->b[5]  = pwt->b[3];
+    pwd->b[11] = pws->b[15];
+    pwd->b[3]  = pwt->b[15];
+    pwd->b[15] = pws->b[7];
+    pwd->b[7]  = pwt->b[7];
+#else
+    pwd->b[15] = pws->b[14];
+    pwd->b[13] = pws->b[10];
+    pwd->b[11] = pws->b[6];
+    pwd->b[9]  = pws->b[2];
+    pwd->b[7]  = pwt->b[14];
+    pwd->b[5]  = pwt->b[10];
+    pwd->b[3]  = pwt->b[6];
+    pwd->b[1]  = pwt->b[2];
+    pwd->b[14] = pws->b[12];
+    pwd->b[10] = pws->b[4];
+    pwd->b[6]  = pwt->b[12];
+    pwd->b[2]  = pwt->b[4];
+    pwd->b[12] = pws->b[8];
+    pwd->b[4]  = pwt->b[8];
+    pwd->b[8]  = pws->b[0];
+    pwd->b[0]  = pwt->b[0];
+#endif
+}
+
+void helper_msa_pckev_h(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+#if defined(HOST_WORDS_BIGENDIAN)
+    pwd->h[4] = pws->h[5];
+    pwd->h[6] = pws->h[1];
+    pwd->h[0] = pwt->h[5];
+    pwd->h[2] = pwt->h[1];
+    pwd->h[5] = pws->h[7];
+    pwd->h[1] = pwt->h[7];
+    pwd->h[7] = pws->h[3];
+    pwd->h[3] = pwt->h[3];
+#else
+    pwd->h[7] = pws->h[6];
+    pwd->h[5] = pws->h[2];
+    pwd->h[3] = pwt->h[6];
+    pwd->h[1] = pwt->h[2];
+    pwd->h[6] = pws->h[4];
+    pwd->h[2] = pwt->h[4];
+    pwd->h[4] = pws->h[0];
+    pwd->h[0] = pwt->h[0];
+#endif
+}
+
+void helper_msa_pckev_w(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+#if defined(HOST_WORDS_BIGENDIAN)
+    pwd->w[2] = pws->w[3];
+    pwd->w[0] = pwt->w[3];
+    pwd->w[3] = pws->w[1];
+    pwd->w[1] = pwt->w[1];
+#else
+    pwd->w[3] = pws->w[2];
+    pwd->w[1] = pwt->w[2];
+    pwd->w[2] = pws->w[0];
+    pwd->w[0] = pwt->w[0];
+#endif
+}
+
+void helper_msa_pckev_d(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->d[1] = pws->d[0];
+    pwd->d[0] = pwt->d[0];
+}
+
+
+void helper_msa_pckod_b(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+#if defined(HOST_WORDS_BIGENDIAN)
+    pwd->b[7]  = pwt->b[6];
+    pwd->b[5]  = pwt->b[2];
+    pwd->b[3]  = pwt->b[14];
+    pwd->b[1]  = pwt->b[10];
+    pwd->b[15] = pws->b[6];
+    pwd->b[13] = pws->b[2];
+    pwd->b[11] = pws->b[14];
+    pwd->b[9]  = pws->b[10];
+    pwd->b[6]  = pwt->b[4];
+    pwd->b[2]  = pwt->b[12];
+    pwd->b[14] = pws->b[4];
+    pwd->b[10] = pws->b[12];
+    pwd->b[4]  = pwt->b[0];
+    pwd->b[12] = pws->b[0];
+    pwd->b[0]  = pwt->b[8];
+    pwd->b[8]  = pws->b[8];
+#else
+    pwd->b[0]  = pwt->b[1];
+    pwd->b[2]  = pwt->b[5];
+    pwd->b[4]  = pwt->b[9];
+    pwd->b[6]  = pwt->b[13];
+    pwd->b[8]  = pws->b[1];
+    pwd->b[10] = pws->b[5];
+    pwd->b[12] = pws->b[9];
+    pwd->b[14] = pws->b[13];
+    pwd->b[1]  = pwt->b[3];
+    pwd->b[5]  = pwt->b[11];
+    pwd->b[9]  = pws->b[3];
+    pwd->b[13] = pws->b[11];
+    pwd->b[3]  = pwt->b[7];
+    pwd->b[11] = pws->b[7];
+    pwd->b[7]  = pwt->b[15];
+    pwd->b[15] = pws->b[15];
+#endif
+
+}
+
+void helper_msa_pckod_h(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+#if defined(HOST_WORDS_BIGENDIAN)
+    pwd->h[3] = pwt->h[2];
+    pwd->h[1] = pwt->h[6];
+    pwd->h[7] = pws->h[2];
+    pwd->h[5] = pws->h[6];
+    pwd->h[2] = pwt->h[0];
+    pwd->h[6] = pws->h[0];
+    pwd->h[0] = pwt->h[4];
+    pwd->h[4] = pws->h[4];
+#else
+    pwd->h[0] = pwt->h[1];
+    pwd->h[2] = pwt->h[5];
+    pwd->h[4] = pws->h[1];
+    pwd->h[6] = pws->h[5];
+    pwd->h[1] = pwt->h[3];
+    pwd->h[5] = pws->h[3];
+    pwd->h[3] = pwt->h[7];
+    pwd->h[7] = pws->h[7];
+#endif
+}
+
+void helper_msa_pckod_w(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+#if defined(HOST_WORDS_BIGENDIAN)
+    pwd->w[1] = pwt->w[0];
+    pwd->w[3] = pws->w[0];
+    pwd->w[0] = pwt->w[2];
+    pwd->w[2] = pws->w[2];
+#else
+    pwd->w[0] = pwt->w[1];
+    pwd->w[2] = pws->w[1];
+    pwd->w[1] = pwt->w[3];
+    pwd->w[3] = pws->w[3];
+#endif
+}
+
+void helper_msa_pckod_d(CPUMIPSState *env,
+                        uint32_t wd, uint32_t ws, uint32_t wt)
+{
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
+    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
+
+    pwd->d[0] = pwt->d[1];
+    pwd->d[1] = pws->d[1];
+}
 
 
 /*
@@ -4675,183 +4882,6 @@ MSA_FN_DF(vshf_df)
 #undef MSA_FN_DF
 
 
-void helper_msa_pckev_df(CPUMIPSState *env, uint32_t df, uint32_t wd,
-                         uint32_t ws, uint32_t wt)
-{
-    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
-    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
-    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
-
-    switch (df) {
-    case DF_BYTE:
-#if defined(HOST_WORDS_BIGENDIAN)
-        pwd->b[8]  = pws->b[9];
-        pwd->b[10] = pws->b[13];
-        pwd->b[12] = pws->b[1];
-        pwd->b[14] = pws->b[5];
-        pwd->b[0]  = pwt->b[9];
-        pwd->b[2]  = pwt->b[13];
-        pwd->b[4]  = pwt->b[1];
-        pwd->b[6]  = pwt->b[5];
-        pwd->b[9]  = pws->b[11];
-        pwd->b[13] = pws->b[3];
-        pwd->b[1]  = pwt->b[11];
-        pwd->b[5]  = pwt->b[3];
-        pwd->b[11] = pws->b[15];
-        pwd->b[3]  = pwt->b[15];
-        pwd->b[15] = pws->b[7];
-        pwd->b[7]  = pwt->b[7];
-#else
-        pwd->b[15] = pws->b[14];
-        pwd->b[13] = pws->b[10];
-        pwd->b[11] = pws->b[6];
-        pwd->b[9]  = pws->b[2];
-        pwd->b[7]  = pwt->b[14];
-        pwd->b[5]  = pwt->b[10];
-        pwd->b[3]  = pwt->b[6];
-        pwd->b[1]  = pwt->b[2];
-        pwd->b[14] = pws->b[12];
-        pwd->b[10] = pws->b[4];
-        pwd->b[6]  = pwt->b[12];
-        pwd->b[2]  = pwt->b[4];
-        pwd->b[12] = pws->b[8];
-        pwd->b[4]  = pwt->b[8];
-        pwd->b[8]  = pws->b[0];
-        pwd->b[0]  = pwt->b[0];
-#endif
-        break;
-    case DF_HALF:
-#if defined(HOST_WORDS_BIGENDIAN)
-        pwd->h[4] = pws->h[5];
-        pwd->h[6] = pws->h[1];
-        pwd->h[0] = pwt->h[5];
-        pwd->h[2] = pwt->h[1];
-        pwd->h[5] = pws->h[7];
-        pwd->h[1] = pwt->h[7];
-        pwd->h[7] = pws->h[3];
-        pwd->h[3] = pwt->h[3];
-#else
-        pwd->h[7] = pws->h[6];
-        pwd->h[5] = pws->h[2];
-        pwd->h[3] = pwt->h[6];
-        pwd->h[1] = pwt->h[2];
-        pwd->h[6] = pws->h[4];
-        pwd->h[2] = pwt->h[4];
-        pwd->h[4] = pws->h[0];
-        pwd->h[0] = pwt->h[0];
-#endif
-        break;
-    case DF_WORD:
-#if defined(HOST_WORDS_BIGENDIAN)
-        pwd->w[2] = pws->w[3];
-        pwd->w[0] = pwt->w[3];
-        pwd->w[3] = pws->w[1];
-        pwd->w[1] = pwt->w[1];
-#else
-        pwd->w[3] = pws->w[2];
-        pwd->w[1] = pwt->w[2];
-        pwd->w[2] = pws->w[0];
-        pwd->w[0] = pwt->w[0];
-#endif
-        break;
-    case DF_DOUBLE:
-        pwd->d[1] = pws->d[0];
-        pwd->d[0] = pwt->d[0];
-        break;
-    default:
-        assert(0);
-    }
-}
-
-void helper_msa_pckod_df(CPUMIPSState *env, uint32_t df, uint32_t wd,
-                         uint32_t ws, uint32_t wt)
-{
-    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);
-    wr_t *pws = &(env->active_fpu.fpr[ws].wr);
-    wr_t *pwt = &(env->active_fpu.fpr[wt].wr);
-
-    switch (df) {
-    case DF_BYTE:
-#if defined(HOST_WORDS_BIGENDIAN)
-        pwd->b[7]  = pwt->b[6];
-        pwd->b[5]  = pwt->b[2];
-        pwd->b[3]  = pwt->b[14];
-        pwd->b[1]  = pwt->b[10];
-        pwd->b[15] = pws->b[6];
-        pwd->b[13] = pws->b[2];
-        pwd->b[11] = pws->b[14];
-        pwd->b[9]  = pws->b[10];
-        pwd->b[6]  = pwt->b[4];
-        pwd->b[2]  = pwt->b[12];
-        pwd->b[14] = pws->b[4];
-        pwd->b[10] = pws->b[12];
-        pwd->b[4]  = pwt->b[0];
-        pwd->b[12] = pws->b[0];
-        pwd->b[0]  = pwt->b[8];
-        pwd->b[8]  = pws->b[8];
-#else
-        pwd->b[0]  = pwt->b[1];
-        pwd->b[2]  = pwt->b[5];
-        pwd->b[4]  = pwt->b[9];
-        pwd->b[6]  = pwt->b[13];
-        pwd->b[8]  = pws->b[1];
-        pwd->b[10] = pws->b[5];
-        pwd->b[12] = pws->b[9];
-        pwd->b[14] = pws->b[13];
-        pwd->b[1]  = pwt->b[3];
-        pwd->b[5]  = pwt->b[11];
-        pwd->b[9]  = pws->b[3];
-        pwd->b[13] = pws->b[11];
-        pwd->b[3]  = pwt->b[7];
-        pwd->b[11] = pws->b[7];
-        pwd->b[7]  = pwt->b[15];
-        pwd->b[15] = pws->b[15];
-#endif
-        break;
-    case DF_HALF:
-#if defined(HOST_WORDS_BIGENDIAN)
-        pwd->h[3] = pwt->h[2];
-        pwd->h[1] = pwt->h[6];
-        pwd->h[7] = pws->h[2];
-        pwd->h[5] = pws->h[6];
-        pwd->h[2] = pwt->h[0];
-        pwd->h[6] = pws->h[0];
-        pwd->h[0] = pwt->h[4];
-        pwd->h[4] = pws->h[4];
-#else
-        pwd->h[0] = pwt->h[1];
-        pwd->h[2] = pwt->h[5];
-        pwd->h[4] = pws->h[1];
-        pwd->h[6] = pws->h[5];
-        pwd->h[1] = pwt->h[3];
-        pwd->h[5] = pws->h[3];
-        pwd->h[3] = pwt->h[7];
-        pwd->h[7] = pws->h[7];
-#endif
-        break;
-    case DF_WORD:
-#if defined(HOST_WORDS_BIGENDIAN)
-        pwd->w[1] = pwt->w[0];
-        pwd->w[3] = pws->w[0];
-        pwd->w[0] = pwt->w[2];
-        pwd->w[2] = pws->w[2];
-#else
-        pwd->w[0] = pwt->w[1];
-        pwd->w[2] = pws->w[1];
-        pwd->w[1] = pwt->w[3];
-        pwd->w[3] = pws->w[3];
-#endif
-        break;
-    case DF_DOUBLE:
-        pwd->d[0] = pwt->d[1];
-        pwd->d[1] = pws->d[1];
-        break;
-    default:
-        assert(0);
-    }
-}
-
-
 void helper_msa_sldi_df(CPUMIPSState *env, uint32_t df, uint32_t wd,
                         uint32_t ws, uint32_t n)
 {
diff --git a/target/mips/translate.c b/target/mips/translate.c
index 7cdf68d..a57e0da 100644
--- a/target/mips/translate.c
+++ b/target/mips/translate.c
@@ -28914,6 +28914,38 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx)
             break;
         }
         break;
+    case OPC_PCKEV_df:
+        switch (df) {
+        case DF_BYTE:
+            gen_helper_msa_pckev_b(cpu_env, twd, tws, twt);
+            break;
+        case DF_HALF:
+            gen_helper_msa_pckev_h(cpu_env, twd, tws, twt);
+            break;
+        case DF_WORD:
+            gen_helper_msa_pckev_w(cpu_env, twd, tws, twt);
+            break;
+        case DF_DOUBLE:
+            gen_helper_msa_pckev_d(cpu_env, twd, tws, twt);
+            break;
+        }
+        break;
+    case OPC_PCKOD_df:
+        switch (df) {
+        case DF_BYTE:
+            gen_helper_msa_pckod_b(cpu_env, twd, tws, twt);
+            break;
+        case DF_HALF:
+            gen_helper_msa_pckod_h(cpu_env, twd, tws, twt);
+            break;
+        case DF_WORD:
+            gen_helper_msa_pckod_w(cpu_env, twd, tws, twt);
+            break;
+        case DF_DOUBLE:
+            gen_helper_msa_pckod_d(cpu_env, twd, tws, twt);
+            break;
+        }
+        break;
     case OPC_SLL_df:
         switch (df) {
         case DF_BYTE:
@@ -29024,15 +29056,9 @@ static void gen_msa_3r(CPUMIPSState *env, DisasContext *ctx)
     case OPC_MSUBV_df:
         gen_helper_msa_msubv_df(cpu_env, tdf, twd, tws, twt);
         break;
-    case OPC_PCKEV_df:
-        gen_helper_msa_pckev_df(cpu_env, tdf, twd, tws, twt);
-        break;
     case OPC_SUBSUU_S_df:
         gen_helper_msa_subsuu_s_df(cpu_env, tdf, twd, tws, twt);
         break;
-    case OPC_PCKOD_df:
-        gen_helper_msa_pckod_df(cpu_env, tdf, twd, tws, twt);
-        break;
     case OPC_ASUB_S_df:
         gen_helper_msa_asub_s_df(cpu_env, tdf, twd, tws, twt);
         break;
-- 
2.7.4

[PULL 11/11] target/mips: Add support for emulation of CRC32 group of instructions

[Aleksandar Markovic]

From: Yongbok Kim <yongbok.kim@imgtec.com>

Add emulation of MIPS' CRC32 (Cyclic Redundancy Check) instructions.
Reuse zlib crc32() and Linux crc32c(). Note that, at the time being,
there is no MIPS CPU that supports CRC32 instructions (they are an
optional part of MIPS64/32 R6 anf nanoMIPS ISAs).

Signed-off-by: Yongbok Kim <yongbok.kim@mips.com>
Signed-off-by: Aleksandar Markovic <amarkovic@wavecomp.com>
Reviewed-by: Aleksandar Markovic <amarkovic@wavecomp.com>
Message-Id: <1571826227-10583-14-git-send-email-aleksandar.markovic@rt-rk.com>
---
 disas/mips.c            |  8 ++++++++
 target/mips/helper.h    |  2 ++
 target/mips/op_helper.c | 22 ++++++++++++++++++++++
 target/mips/translate.c | 41 +++++++++++++++++++++++++++++++++++++++++
 4 files changed, 73 insertions(+)

diff --git a/disas/mips.c b/disas/mips.c
index dfefe5e..75c48b3 100644
--- a/disas/mips.c
+++ b/disas/mips.c
@@ -1409,6 +1409,14 @@ const struct mips_opcode mips_builtin_opcodes[] =
 {"dvp",        "t",     0x41600024, 0xffe0ffff, TRAP|WR_t,            0, I32R6},
 {"evp",        "",      0x41600004, 0xffffffff, TRAP,                 0, I32R6},
 {"evp",        "t",     0x41600004, 0xffe0ffff, TRAP|WR_t,            0, I32R6},
+{"crc32b",     "t,v,t", 0x7c00000f, 0xfc00ff3f, WR_d | RD_s | RD_t,   0, I32R6},
+{"crc32h",     "t,v,t", 0x7c00004f, 0xfc00ff3f, WR_d | RD_s | RD_t,   0, I32R6},
+{"crc32w",     "t,v,t", 0x7c00008f, 0xfc00ff3f, WR_d | RD_s | RD_t,   0, I32R6},
+{"crc32d",     "t,v,t", 0x7c0000cf, 0xfc00ff3f, WR_d | RD_s | RD_t,   0, I64R6},
+{"crc32cb",    "t,v,t", 0x7c00010f, 0xfc00ff3f, WR_d | RD_s | RD_t,   0, I32R6},
+{"crc32ch",    "t,v,t", 0x7c00014f, 0xfc00ff3f, WR_d | RD_s | RD_t,   0, I32R6},
+{"crc32cw",    "t,v,t", 0x7c00018f, 0xfc00ff3f, WR_d | RD_s | RD_t,   0, I32R6},
+{"crc32cd",    "t,v,t", 0x7c0001cf, 0xfc00ff3f, WR_d | RD_s | RD_t,   0, I64R6},
 
 /* MSA */
 {"sll.b",   "+d,+e,+f", 0x7800000d, 0xffe0003f, WR_VD|RD_VS|RD_VT,  0, MSA},
diff --git a/target/mips/helper.h b/target/mips/helper.h
index 7bb13d5..abaf503 100644
--- a/target/mips/helper.h
+++ b/target/mips/helper.h
@@ -40,6 +40,8 @@ DEF_HELPER_FLAGS_1(bitswap, TCG_CALL_NO_RWG_SE, tl, tl)
 DEF_HELPER_FLAGS_1(dbitswap, TCG_CALL_NO_RWG_SE, tl, tl)
 #endif
 
+DEF_HELPER_3(crc32, tl, tl, tl, i32)
+DEF_HELPER_3(crc32c, tl, tl, tl, i32)
 DEF_HELPER_FLAGS_4(rotx, TCG_CALL_NO_RWG_SE, tl, tl, i32, i32, i32)
 
 #ifndef CONFIG_USER_ONLY
diff --git a/target/mips/op_helper.c b/target/mips/op_helper.c
index 18fcee4..3298980 100644
--- a/target/mips/op_helper.c
+++ b/target/mips/op_helper.c
@@ -27,6 +27,8 @@
 #include "exec/memop.h"
 #include "sysemu/kvm.h"
 #include "fpu/softfloat.h"
+#include "qemu/crc32c.h"
+#include <zlib.h>
 
 /*****************************************************************************/
 /* Exceptions processing helpers */
@@ -350,6 +352,26 @@ target_ulong helper_rotx(target_ulong rs, uint32_t shift, uint32_t shiftx,
     return (int64_t)(int32_t)(uint32_t)tmp5;
 }
 
+/* these crc32 functions are based on target/arm/helper-a64.c */
+target_ulong helper_crc32(target_ulong val, target_ulong m, uint32_t sz)
+{
+    uint8_t buf[8];
+    target_ulong mask = ((sz * 8) == 64) ? -1ULL : ((1ULL << (sz * 8)) - 1);
+
+    m &= mask;
+    stq_le_p(buf, m);
+    return (int32_t) (crc32(val ^ 0xffffffff, buf, sz) ^ 0xffffffff);
+}
+
+target_ulong helper_crc32c(target_ulong val, target_ulong m, uint32_t sz)
+{
+    uint8_t buf[8];
+    target_ulong mask = ((sz * 8) == 64) ? -1ULL : ((1ULL << (sz * 8)) - 1);
+    m &= mask;
+    stq_le_p(buf, m);
+    return (int32_t) (crc32c(val, buf, sz) ^ 0xffffffff);
+}
+
 #ifndef CONFIG_USER_ONLY
 
 static inline hwaddr do_translate_address(CPUMIPSState *env,
diff --git a/target/mips/translate.c b/target/mips/translate.c
index a57e0da..f0aa743 100644
--- a/target/mips/translate.c
+++ b/target/mips/translate.c
@@ -451,6 +451,7 @@ enum {
     OPC_LWE            = 0x2F | OPC_SPECIAL3,
 
     /* R6 */
+    OPC_CRC32          = 0x0F | OPC_SPECIAL3,
     R6_OPC_PREF        = 0x35 | OPC_SPECIAL3,
     R6_OPC_CACHE       = 0x25 | OPC_SPECIAL3,
     R6_OPC_LL          = 0x36 | OPC_SPECIAL3,
@@ -2547,6 +2548,7 @@ typedef struct DisasContext {
     bool nan2008;
     bool abs2008;
     bool saar;
+    bool crcp;
 } DisasContext;
 
 #define DISAS_STOP       DISAS_TARGET_0
@@ -27017,6 +27019,33 @@ static void decode_opc_special2_legacy(CPUMIPSState *env, DisasContext *ctx)
     }
 }
 
+static void gen_crc32(DisasContext *ctx, int rd, int rs, int rt, int sz,
+                      int crc32c)
+{
+    TCGv t0;
+    TCGv t1;
+    TCGv_i32 tsz = tcg_const_i32(1 << sz);
+    if (rd == 0) {
+        /* Treat as NOP. */
+        return;
+    }
+    t0 = tcg_temp_new();
+    t1 = tcg_temp_new();
+
+    gen_load_gpr(t0, rt);
+    gen_load_gpr(t1, rs);
+
+    if (crc32c) {
+        gen_helper_crc32c(cpu_gpr[rd], t0, t1, tsz);
+    } else {
+        gen_helper_crc32(cpu_gpr[rd], t0, t1, tsz);
+    }
+
+    tcg_temp_free(t0);
+    tcg_temp_free(t1);
+    tcg_temp_free_i32(tsz);
+}
+
 static void decode_opc_special3_r6(CPUMIPSState *env, DisasContext *ctx)
 {
     int rs, rt, rd, sa;
@@ -27031,6 +27060,17 @@ static void decode_opc_special3_r6(CPUMIPSState *env, DisasContext *ctx)
 
     op1 = MASK_SPECIAL3(ctx->opcode);
     switch (op1) {
+    case OPC_CRC32:
+        if (unlikely(!ctx->crcp) ||
+            unlikely((extract32(ctx->opcode, 6, 2) == 3) &&
+                     (!(ctx->hflags & MIPS_HFLAG_64))) ||
+            unlikely((extract32(ctx->opcode, 8, 3) >= 2))) {
+            generate_exception_end(ctx, EXCP_RI);
+        }
+        gen_crc32(ctx, rt, rs, rt,
+                  extract32(ctx->opcode, 6, 2),
+                  extract32(ctx->opcode, 8, 3));
+        break;
     case R6_OPC_PREF:
         if (rt >= 24) {
             /* hint codes 24-31 are reserved and signal RI */
@@ -30581,6 +30621,7 @@ static void mips_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs)
     ctx->mrp = (env->CP0_Config5 >> CP0C5_MRP) & 1;
     ctx->nan2008 = (env->active_fpu.fcr31 >> FCR31_NAN2008) & 1;
     ctx->abs2008 = (env->active_fpu.fcr31 >> FCR31_ABS2008) & 1;
+    ctx->crcp = (env->CP0_Config5 >> CP0C5_CRCP) & 1;
     restore_cpu_state(env, ctx);
 #ifdef CONFIG_USER_ONLY
         ctx->mem_idx = MIPS_HFLAG_UM;
-- 
2.7.4

Re: [PULL 00/11] MIPS queue for October 24th, 2019

[no-reply]

Patchew URL: https://patchew.org/QEMU/1571915195-4381-1-git-send-email-aleksandar.markovic@rt-rk.com/



Hi,

This series seems to have some coding style problems. See output below for
more information:

Subject: [PULL 00/11] MIPS queue for October 24th, 2019
Type: series
Message-id: 1571915195-4381-1-git-send-email-aleksandar.markovic@rt-rk.com

=== TEST SCRIPT BEGIN ===
#!/bin/bash
git rev-parse base > /dev/null || exit 0
git config --local diff.renamelimit 0
git config --local diff.renames True
git config --local diff.algorithm histogram
./scripts/checkpatch.pl --mailback base..
=== TEST SCRIPT END ===

Switched to a new branch 'test'
54710a8 target/mips: Add support for emulation of CRC32 group of instructions
d8645d0 target/mips: msa: Split helpers for PCK<EV|OD>.<B|H|W|D>
e3c1ee9 target/mips: msa: Split helpers for S<LL|RA|RAR|RL|RLR>.<B|H|W|D>
6bb4421 target/mips: msa: Split helpers for HADD_<S|U>.<H|W|D>
0f4cc5e target/mips: msa: Split helpers for ADD<_A|S_A|S_S|S_U|V>.<B|H|W|D>
009d120 target/mips: msa: Split helpers for ILV<EV|OD|L|R>.<B|H|W|D>
cfe231b target/mips: msa: Split helpers for <MAX|MIN>_<S|U>.<B|H|W|D>
34a0fab target/mips: msa: Split helpers for <MAX|MIN>_A.<B|H|W|D>
c169d7e MAINTAINERS: Update mail address of Aleksandar Rikalo
832615f target/mips: Clean up op_helper.c
d177c65 target/mips: Clean up helper.c

=== OUTPUT BEGIN ===
1/11 Checking commit d177c65047a3 (target/mips: Clean up helper.c)
2/11 Checking commit 832615f56fef (target/mips: Clean up op_helper.c)
ERROR: spaces required around that '*' (ctx:WxV)
#1060: FILE: target/mips/op_helper.c:3871:
+                                  float_status *status)              \
                                                ^

total: 1 errors, 0 warnings, 1681 lines checked

Patch 2/11 has style problems, please review.  If any of these errors
are false positives report them to the maintainer, see
CHECKPATCH in MAINTAINERS.

3/11 Checking commit c169d7e49e4c (MAINTAINERS: Update mail address of Aleksandar Rikalo)
4/11 Checking commit 34a0fabb8579 (target/mips: msa: Split helpers for <MAX|MIN>_A.<B|H|W|D>)
5/11 Checking commit cfe231b2ea70 (target/mips: msa: Split helpers for <MAX|MIN>_<S|U>.<B|H|W|D>)
6/11 Checking commit 009d120710e1 (target/mips: msa: Split helpers for ILV<EV|OD|L|R>.<B|H|W|D>)
7/11 Checking commit 0f4cc5edd2d0 (target/mips: msa: Split helpers for ADD<_A|S_A|S_S|S_U|V>.<B|H|W|D>)
8/11 Checking commit 6bb44211f0a5 (target/mips: msa: Split helpers for HADD_<S|U>.<H|W|D>)
9/11 Checking commit e3c1ee9fd9b7 (target/mips: msa: Split helpers for S<LL|RA|RAR|RL|RLR>.<B|H|W|D>)
10/11 Checking commit d8645d096706 (target/mips: msa: Split helpers for PCK<EV|OD>.<B|H|W|D>)
11/11 Checking commit 54710a87852c (target/mips: Add support for emulation of CRC32 group of instructions)
=== OUTPUT END ===

Test command exited with code: 1


The full log is available at
http://patchew.org/logs/1571915195-4381-1-git-send-email-aleksandar.markovic@rt-rk.com/testing.checkpatch/?type=message.
---
Email generated automatically by Patchew [https://patchew.org/].
Please send your feedback to patchew-devel@redhat.com

Re: [PULL 00/11] MIPS queue for October 24th, 2019

[Peter Maydell]

On Thu, 24 Oct 2019 at 12:07, Aleksandar Markovic
<aleksandar.markovic@rt-rk.com> wrote:
>
> From: Aleksandar Markovic <amarkovic@wavecomp.com>
>
> The following changes since commit ea0ec714d3109e0d0523b9dacb38030e4cb142a8:
>
>   Merge remote-tracking branch 'remotes/xtensa/tags/20191023-xtensa' into staging (2019-10-24 09:55:01 +0100)
>
> are available in the git repository at:
>
>   https://github.com/AMarkovic/qemu tags/mips-queue-oct-24-2019
>
> for you to fetch changes up to f4d200d0e55ebc4e9c9af50cb9317e2f6ebe9d0c:
>
>   target/mips: Add support for emulation of CRC32 group of instructions (2019-10-24 13:00:37 +0200)
>
> ----------------------------------------------------------------
>
> MIPS queue for October 24th, 2019
>
>   - added emulation of R6 CRC32 instructions
>   - added several mostly cosmetic leanups
>   - a checkpath warning is a false positive
>

Hi; this fails to compile with 'implicit conversion' errors
on clang (OSX, freebsd, openbsd, and linux):


/home/petmay01/linaro/qemu-for-merges/target/mips/op_helper.c:359:44:
error: implicit conversion from 'unsigned long long' to 'target_ulong'
(aka 'unsigned int') changes value from 18446744073709551615 to
4294967295 [-Werror,-Wconstant-conversion]
    target_ulong mask = ((sz * 8) == 64) ? -1ULL : ((1ULL << (sz * 8)) - 1);
                 ~~~~                      ^~~~~
/home/petmay01/linaro/qemu-for-merges/target/mips/op_helper.c:369:44:
error: implicit conversion from 'unsigned long long' to 'target_ulong'
(aka 'unsigned int') changes value from 18446744073709551615 to
4294967295 [-Werror,-Wconstant-conversion]
    target_ulong mask = ((sz * 8) == 64) ? -1ULL : ((1ULL << (sz * 8)) - 1);
                 ~~~~                      ^~~~~
2 errors generated.


thanks
-- PMM

Re: [EXTERNAL]Re: [PULL 00/11] MIPS queue for October 24th, 2019

[Aleksandar Markovic]

> Hi; this fails to compile with 'implicit conversion' errors
> on clang (OSX, freebsd, openbsd, and linux):


I am going to send v2 shortly, that will not contain the offending patch.

Sorry about this.

Aleksandar