[PATCH RESEND v3 1/8] target/ppc: Implemented vector divide instructions

[PATCH RESEND v3 1/8] target/ppc: Implemented vector divide instructions

[Lucas Mateus Castro(alqotel)]

From: "Lucas Mateus Castro (alqotel)" <lucas.araujo@eldorado.org.br>

Implement the following PowerISA v3.1 instructions:
vdivsw: Vector Divide Signed Word
vdivuw: Vector Divide Unsigned Word
vdivsd: Vector Divide Signed Doubleword
vdivud: Vector Divide Unsigned Doubleword

Signed-off-by: Lucas Mateus Castro (alqotel) <lucas.araujo@eldorado.org.br>
---
 target/ppc/insn32.decode            |  7 +++
 target/ppc/translate/vmx-impl.c.inc | 85 +++++++++++++++++++++++++++++
 2 files changed, 92 insertions(+)

diff --git a/target/ppc/insn32.decode b/target/ppc/insn32.decode
index 18a94fa3b5..6df405e398 100644
--- a/target/ppc/insn32.decode
+++ b/target/ppc/insn32.decode
@@ -786,3 +786,10 @@ XVF64GERPP      111011 ... -- .... 0 ..... 00111010 ..-  @XX3_at xa=%xx_xa_pair
 XVF64GERPN      111011 ... -- .... 0 ..... 10111010 ..-  @XX3_at xa=%xx_xa_pair
 XVF64GERNP      111011 ... -- .... 0 ..... 01111010 ..-  @XX3_at xa=%xx_xa_pair
 XVF64GERNN      111011 ... -- .... 0 ..... 11111010 ..-  @XX3_at xa=%xx_xa_pair
+
+## Vector Division Instructions
+
+VDIVSW          000100 ..... ..... ..... 00110001011    @VX
+VDIVUW          000100 ..... ..... ..... 00010001011    @VX
+VDIVSD          000100 ..... ..... ..... 00111001011    @VX
+VDIVUD          000100 ..... ..... ..... 00011001011    @VX
diff --git a/target/ppc/translate/vmx-impl.c.inc b/target/ppc/translate/vmx-impl.c.inc
index d7524c3204..4c0b1a32ec 100644
--- a/target/ppc/translate/vmx-impl.c.inc
+++ b/target/ppc/translate/vmx-impl.c.inc
@@ -3238,6 +3238,91 @@ TRANS(VMULHSD, do_vx_mulh, true , do_vx_vmulhd_i64)
 TRANS(VMULHUW, do_vx_mulh, false, do_vx_vmulhw_i64)
 TRANS(VMULHUD, do_vx_mulh, false, do_vx_vmulhd_i64)
 
+static bool do_vdiv_vmod(DisasContext *ctx, arg_VX *a, const int vece,
+                         void (*func_32)(TCGv_i32 t, TCGv_i32 a, TCGv_i32 b),
+                         void (*func_64)(TCGv_i64 t, TCGv_i64 a, TCGv_i64 b))
+{
+    const GVecGen3 op = {
+        .fni4 = func_32,
+        .fni8 = func_64,
+        .vece = vece
+    };
+
+    REQUIRE_VECTOR(ctx);
+
+    tcg_gen_gvec_3(avr_full_offset(a->vrt), avr_full_offset(a->vra),
+                   avr_full_offset(a->vrb), 16, 16, &op);
+
+    return true;
+}
+
+#define DIVU32(NAME, DIV)                                               \
+static void NAME(TCGv_i32 t, TCGv_i32 a, TCGv_i32 b)                    \
+{                                                                       \
+    TCGv_i32 zero = tcg_constant_i32(0);                                \
+    TCGv_i32 one = tcg_constant_i32(1);                                 \
+    tcg_gen_movcond_i32(TCG_COND_EQ, b, b, zero, one, b);               \
+    DIV(t, a, b);                                                       \
+}
+
+#define DIVS32(NAME, DIV)                                               \
+static void NAME(TCGv_i32 t, TCGv_i32 a, TCGv_i32 b)                    \
+{                                                                       \
+    TCGv_i32 t0 = tcg_temp_new_i32();                                   \
+    TCGv_i32 t1 = tcg_temp_new_i32();                                   \
+    tcg_gen_setcondi_i32(TCG_COND_EQ, t0, a, INT32_MIN);                \
+    tcg_gen_setcondi_i32(TCG_COND_EQ, t1, b, -1);                       \
+    tcg_gen_and_i32(t0, t0, t1);                                        \
+    tcg_gen_setcondi_i32(TCG_COND_EQ, t1, b, 0);                        \
+    tcg_gen_or_i32(t0, t0, t1);                                         \
+    tcg_gen_movi_i32(t1, 0);                                            \
+    tcg_gen_movcond_i32(TCG_COND_NE, b, t0, t1, t0, b);                 \
+    DIV(t, a, b);                                                       \
+    tcg_temp_free_i32(t0);                                              \
+    tcg_temp_free_i32(t1);                                              \
+}
+
+#define DIVU64(NAME, DIV)                                               \
+static void NAME(TCGv_i64 t, TCGv_i64 a, TCGv_i64 b)                    \
+{                                                                       \
+    TCGv_i64 zero = tcg_constant_i64(0);                                \
+    TCGv_i64 one = tcg_constant_i64(1);                                 \
+    tcg_gen_movcond_i64(TCG_COND_EQ, b, b, zero, one, b);               \
+    DIV(t, a, b);                                                       \
+}
+
+#define DIVS64(NAME, DIV)                                               \
+static void NAME(TCGv_i64 t, TCGv_i64 a, TCGv_i64 b)                    \
+{                                                                       \
+    TCGv_i64 t0 = tcg_temp_new_i64();                                   \
+    TCGv_i64 t1 = tcg_temp_new_i64();                                   \
+    tcg_gen_setcondi_i64(TCG_COND_EQ, t0, a, INT64_MIN);                \
+    tcg_gen_setcondi_i64(TCG_COND_EQ, t1, b, -1);                       \
+    tcg_gen_and_i64(t0, t0, t1);                                        \
+    tcg_gen_setcondi_i64(TCG_COND_EQ, t1, b, 0);                        \
+    tcg_gen_or_i64(t0, t0, t1);                                         \
+    tcg_gen_movi_i64(t1, 0);                                            \
+    tcg_gen_movcond_i64(TCG_COND_NE, b, t0, t1, t0, b);                 \
+    DIV(t, a, b);                                                       \
+    tcg_temp_free_i64(t0);                                              \
+    tcg_temp_free_i64(t1);                                              \
+}
+
+DIVS32(do_divsw, tcg_gen_div_i32)
+DIVU32(do_divuw, tcg_gen_divu_i32)
+DIVS64(do_divsd, tcg_gen_div_i64)
+DIVU64(do_divud, tcg_gen_divu_i64)
+
+TRANS_FLAGS2(ISA310, VDIVSW, do_vdiv_vmod, MO_32, do_divsw, NULL)
+TRANS_FLAGS2(ISA310, VDIVUW, do_vdiv_vmod, MO_32, do_divuw, NULL)
+TRANS_FLAGS2(ISA310, VDIVSD, do_vdiv_vmod, MO_64, NULL, do_divsd)
+TRANS_FLAGS2(ISA310, VDIVUD, do_vdiv_vmod, MO_64, NULL, do_divud)
+
+#undef DIVS32
+#undef DIVU32
+#undef DIVS64
+#undef DIVU64
+
 #undef GEN_VR_LDX
 #undef GEN_VR_STX
 #undef GEN_VR_LVE
-- 
2.31.1

Re: [PATCH RESEND v3 1/8] target/ppc: Implemented vector divide instructions

[Richard Henderson]

On 5/25/22 06:49, Lucas Mateus Castro(alqotel) wrote:
> From: "Lucas Mateus Castro (alqotel)"<lucas.araujo@eldorado.org.br>
> 
> Implement the following PowerISA v3.1 instructions:
> vdivsw: Vector Divide Signed Word
> vdivuw: Vector Divide Unsigned Word
> vdivsd: Vector Divide Signed Doubleword
> vdivud: Vector Divide Unsigned Doubleword
> 
> Signed-off-by: Lucas Mateus Castro (alqotel)<lucas.araujo@eldorado.org.br>
> ---
>   target/ppc/insn32.decode            |  7 +++
>   target/ppc/translate/vmx-impl.c.inc | 85 +++++++++++++++++++++++++++++
>   2 files changed, 92 insertions(+)

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>

r~

[PATCH RESEND v3 2/8] target/ppc: Implemented vector divide quadword

[Lucas Mateus Castro(alqotel)]

From: "Lucas Mateus Castro (alqotel)" <lucas.araujo@eldorado.org.br>

Implement the following PowerISA v3.1 instructions:
vdivsq: Vector Divide Signed Quadword
vdivuq: Vector Divide Unsigned Quadword

Signed-off-by: Lucas Mateus Castro (alqotel) <lucas.araujo@eldorado.org.br>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/ppc/helper.h                 |  2 ++
 target/ppc/insn32.decode            |  2 ++
 target/ppc/int_helper.c             | 21 +++++++++++++++++++++
 target/ppc/translate/vmx-impl.c.inc |  2 ++
 4 files changed, 27 insertions(+)

diff --git a/target/ppc/helper.h b/target/ppc/helper.h
index 6233e28d85..9f33e589e0 100644
--- a/target/ppc/helper.h
+++ b/target/ppc/helper.h
@@ -175,6 +175,8 @@ DEF_HELPER_FLAGS_3(VMULOSW, TCG_CALL_NO_RWG, void, avr, avr, avr)
 DEF_HELPER_FLAGS_3(VMULOUB, TCG_CALL_NO_RWG, void, avr, avr, avr)
 DEF_HELPER_FLAGS_3(VMULOUH, TCG_CALL_NO_RWG, void, avr, avr, avr)
 DEF_HELPER_FLAGS_3(VMULOUW, TCG_CALL_NO_RWG, void, avr, avr, avr)
+DEF_HELPER_FLAGS_3(VDIVSQ, TCG_CALL_NO_RWG, void, avr, avr, avr)
+DEF_HELPER_FLAGS_3(VDIVUQ, TCG_CALL_NO_RWG, void, avr, avr, avr)
 DEF_HELPER_FLAGS_3(vslo, TCG_CALL_NO_RWG, void, avr, avr, avr)
 DEF_HELPER_FLAGS_3(vsro, TCG_CALL_NO_RWG, void, avr, avr, avr)
 DEF_HELPER_FLAGS_3(vsrv, TCG_CALL_NO_RWG, void, avr, avr, avr)
diff --git a/target/ppc/insn32.decode b/target/ppc/insn32.decode
index 6df405e398..01bfde8c5e 100644
--- a/target/ppc/insn32.decode
+++ b/target/ppc/insn32.decode
@@ -793,3 +793,5 @@ VDIVSW          000100 ..... ..... ..... 00110001011    @VX
 VDIVUW          000100 ..... ..... ..... 00010001011    @VX
 VDIVSD          000100 ..... ..... ..... 00111001011    @VX
 VDIVUD          000100 ..... ..... ..... 00011001011    @VX
+VDIVSQ          000100 ..... ..... ..... 00100001011    @VX
+VDIVUQ          000100 ..... ..... ..... 00000001011    @VX
diff --git a/target/ppc/int_helper.c b/target/ppc/int_helper.c
index 105b626d1b..033718dc0e 100644
--- a/target/ppc/int_helper.c
+++ b/target/ppc/int_helper.c
@@ -1162,6 +1162,27 @@ void helper_XXPERMX(ppc_vsr_t *t, ppc_vsr_t *s0, ppc_vsr_t *s1, ppc_vsr_t *pcv,
     *t = tmp;
 }
 
+void helper_VDIVSQ(ppc_avr_t *t, ppc_avr_t *a, ppc_avr_t *b)
+{
+    Int128 neg1 = int128_makes64(-1);
+    Int128 int128_min = int128_make128(0, INT64_MIN);
+    if (likely(int128_nz(b->s128) &&
+              (int128_ne(a->s128, int128_min) || int128_ne(b->s128, neg1)))) {
+        t->s128 = int128_divs(a->s128, b->s128);
+    } else {
+        t->s128 = a->s128; /* Undefined behavior */
+    }
+}
+
+void helper_VDIVUQ(ppc_avr_t *t, ppc_avr_t *a, ppc_avr_t *b)
+{
+    if (int128_nz(b->s128)) {
+        t->s128 = int128_divu(a->s128, b->s128);
+    } else {
+        t->s128 = a->s128; /* Undefined behavior */
+    }
+}
+
 void helper_VPERM(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, ppc_avr_t *c)
 {
     ppc_avr_t result;
diff --git a/target/ppc/translate/vmx-impl.c.inc b/target/ppc/translate/vmx-impl.c.inc
index 4c0b1a32ec..22572e6a79 100644
--- a/target/ppc/translate/vmx-impl.c.inc
+++ b/target/ppc/translate/vmx-impl.c.inc
@@ -3317,6 +3317,8 @@ TRANS_FLAGS2(ISA310, VDIVSW, do_vdiv_vmod, MO_32, do_divsw, NULL)
 TRANS_FLAGS2(ISA310, VDIVUW, do_vdiv_vmod, MO_32, do_divuw, NULL)
 TRANS_FLAGS2(ISA310, VDIVSD, do_vdiv_vmod, MO_64, NULL, do_divsd)
 TRANS_FLAGS2(ISA310, VDIVUD, do_vdiv_vmod, MO_64, NULL, do_divud)
+TRANS_FLAGS2(ISA310, VDIVSQ, do_vx_helper, gen_helper_VDIVSQ)
+TRANS_FLAGS2(ISA310, VDIVUQ, do_vx_helper, gen_helper_VDIVUQ)
 
 #undef DIVS32
 #undef DIVU32
-- 
2.31.1

[PATCH RESEND v3 3/8] target/ppc: Implemented vector divide extended word

[Lucas Mateus Castro(alqotel)]

From: "Lucas Mateus Castro (alqotel)" <lucas.araujo@eldorado.org.br>

Implement the following PowerISA v3.1 instructions:
vdivesw: Vector Divide Extended Signed Word
vdiveuw: Vector Divide Extended Unsigned Word

Signed-off-by: Lucas Mateus Castro (alqotel) <lucas.araujo@eldorado.org.br>
---
 target/ppc/insn32.decode            |  3 ++
 target/ppc/translate/vmx-impl.c.inc | 48 +++++++++++++++++++++++++++++
 2 files changed, 51 insertions(+)

diff --git a/target/ppc/insn32.decode b/target/ppc/insn32.decode
index 01bfde8c5e..f6d2d4b257 100644
--- a/target/ppc/insn32.decode
+++ b/target/ppc/insn32.decode
@@ -795,3 +795,6 @@ VDIVSD          000100 ..... ..... ..... 00111001011    @VX
 VDIVUD          000100 ..... ..... ..... 00011001011    @VX
 VDIVSQ          000100 ..... ..... ..... 00100001011    @VX
 VDIVUQ          000100 ..... ..... ..... 00000001011    @VX
+
+VDIVESW         000100 ..... ..... ..... 01110001011    @VX
+VDIVEUW         000100 ..... ..... ..... 01010001011    @VX
diff --git a/target/ppc/translate/vmx-impl.c.inc b/target/ppc/translate/vmx-impl.c.inc
index 22572e6a79..8c542bcb29 100644
--- a/target/ppc/translate/vmx-impl.c.inc
+++ b/target/ppc/translate/vmx-impl.c.inc
@@ -3320,6 +3320,54 @@ TRANS_FLAGS2(ISA310, VDIVUD, do_vdiv_vmod, MO_64, NULL, do_divud)
 TRANS_FLAGS2(ISA310, VDIVSQ, do_vx_helper, gen_helper_VDIVSQ)
 TRANS_FLAGS2(ISA310, VDIVUQ, do_vx_helper, gen_helper_VDIVUQ)
 
+static void do_dives_i32(TCGv_i32 t, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i64 val1, val2;
+
+    val1 = tcg_temp_new_i64();
+    val2 = tcg_temp_new_i64();
+
+    tcg_gen_ext_i32_i64(val1, a);
+    tcg_gen_ext_i32_i64(val2, b);
+
+    /* (a << 32)/b */
+    tcg_gen_shli_i64(val1, val1, 32);
+    tcg_gen_div_i64(val1, val1, val2);
+
+    /* if quotient doesn't fit in 32 bits the result is undefined */
+    tcg_gen_extrl_i64_i32(t, val1);
+
+    tcg_temp_free_i64(val1);
+    tcg_temp_free_i64(val2);
+}
+
+static void do_diveu_i32(TCGv_i32 t, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i64 val1, val2;
+
+    val1 = tcg_temp_new_i64();
+    val2 = tcg_temp_new_i64();
+
+    tcg_gen_extu_i32_i64(val1, a);
+    tcg_gen_extu_i32_i64(val2, b);
+
+    /* (a << 32)/b */
+    tcg_gen_shli_i64(val1, val1, 32);
+    tcg_gen_divu_i64(val1, val1, val2);
+
+    /* if quotient doesn't fit in 32 bits the result is undefined */
+    tcg_gen_extrl_i64_i32(t, val1);
+
+    tcg_temp_free_i64(val1);
+    tcg_temp_free_i64(val2);
+}
+
+DIVS32(do_divesw, do_dives_i32)
+DIVU32(do_diveuw, do_diveu_i32)
+
+TRANS_FLAGS2(ISA310, VDIVESW, do_vdiv_vmod, MO_32, do_divesw, NULL)
+TRANS_FLAGS2(ISA310, VDIVEUW, do_vdiv_vmod, MO_32, do_diveuw, NULL)
+
 #undef DIVS32
 #undef DIVU32
 #undef DIVS64
-- 
2.31.1

Re: [PATCH RESEND v3 3/8] target/ppc: Implemented vector divide extended word

[Richard Henderson]

On 5/25/22 06:49, Lucas Mateus Castro(alqotel) wrote:
> From: "Lucas Mateus Castro (alqotel)"<lucas.araujo@eldorado.org.br>
> 
> Implement the following PowerISA v3.1 instructions:
> vdivesw: Vector Divide Extended Signed Word
> vdiveuw: Vector Divide Extended Unsigned Word
> 
> Signed-off-by: Lucas Mateus Castro (alqotel)<lucas.araujo@eldorado.org.br>
> ---
>   target/ppc/insn32.decode            |  3 ++
>   target/ppc/translate/vmx-impl.c.inc | 48 +++++++++++++++++++++++++++++
>   2 files changed, 51 insertions(+)

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>

r~

[PATCH RESEND v3 4/8] host-utils: Implemented unsigned 256-by-128 division

[Lucas Mateus Castro(alqotel)]

From: "Lucas Mateus Castro (alqotel)" <lucas.araujo@eldorado.org.br>

Based on already existing QEMU implementation, created an unsigned 256
bit by 128 bit division needed to implement the vector divide extended
unsigned instruction from PowerISA3.1

Signed-off-by: Lucas Mateus Castro (alqotel) <lucas.araujo@eldorado.org.br>
---
This patch had received Reviewed-by by Richard Henderson pending on the
placemente of clz128 being moved to int128.h, but clz128 ended up being changed
to accommodate to int128.h (i.e. the lack of clz64), so out of precaution I'd
like to request a review of the clz128 implementation
---
 include/qemu/host-utils.h |   2 +
 include/qemu/int128.h     |  38 +++++++++++
 util/host-utils.c         | 129 ++++++++++++++++++++++++++++++++++++++
 3 files changed, 169 insertions(+)

diff --git a/include/qemu/host-utils.h b/include/qemu/host-utils.h
index f19bd29105..9767af7573 100644
--- a/include/qemu/host-utils.h
+++ b/include/qemu/host-utils.h
@@ -32,6 +32,7 @@
 
 #include "qemu/compiler.h"
 #include "qemu/bswap.h"
+#include "qemu/int128.h"
 
 #ifdef CONFIG_INT128
 static inline void mulu64(uint64_t *plow, uint64_t *phigh,
@@ -849,4 +850,5 @@ static inline uint64_t udiv_qrnnd(uint64_t *r, uint64_t n1,
 #endif
 }
 
+Int128 divu256(Int128 *plow, Int128 *phigh, Int128 divisor);
 #endif
diff --git a/include/qemu/int128.h b/include/qemu/int128.h
index ef71f56e3f..d2b76ca6ac 100644
--- a/include/qemu/int128.h
+++ b/include/qemu/int128.h
@@ -128,11 +128,21 @@ static inline bool int128_ge(Int128 a, Int128 b)
     return a >= b;
 }
 
+static inline bool int128_uge(Int128 a, Int128 b)
+{
+    return ((__uint128_t)a) >= ((__uint128_t)b);
+}
+
 static inline bool int128_lt(Int128 a, Int128 b)
 {
     return a < b;
 }
 
+static inline bool int128_ult(Int128 a, Int128 b)
+{
+    return (__uint128_t)a < (__uint128_t)b;
+}
+
 static inline bool int128_le(Int128 a, Int128 b)
 {
     return a <= b;
@@ -177,6 +187,15 @@ static inline Int128 bswap128(Int128 a)
 #endif
 }
 
+static inline int clz128(Int128 a)
+{
+    if (a >> 64) {
+        return __builtin_clzll(a >> 64);
+    } else {
+        return (a) ? __builtin_clzll((uint64_t)a) + 64 : 128;
+    }
+}
+
 static inline Int128 int128_divu(Int128 a, Int128 b)
 {
     return (__uint128_t)a / (__uint128_t)b;
@@ -373,11 +392,21 @@ static inline bool int128_ge(Int128 a, Int128 b)
     return a.hi > b.hi || (a.hi == b.hi && a.lo >= b.lo);
 }
 
+static inline bool int128_uge(Int128 a, Int128 b)
+{
+    return (uint64_t)a.hi > (uint64_t)b.hi || (a.hi == b.hi && a.lo >= b.lo);
+}
+
 static inline bool int128_lt(Int128 a, Int128 b)
 {
     return !int128_ge(a, b);
 }
 
+static inline bool int128_ult(Int128 a, Int128 b)
+{
+    return !int128_uge(a, b);
+}
+
 static inline bool int128_le(Int128 a, Int128 b)
 {
     return int128_ge(b, a);
@@ -418,6 +447,15 @@ static inline Int128 bswap128(Int128 a)
     return int128_make128(bswap64(a.hi), bswap64(a.lo));
 }
 
+static inline int clz128(Int128 a)
+{
+    if (a.hi) {
+        return __builtin_clzll(a.hi);
+    } else {
+        return (a.lo) ? __builtin_clzll(a.lo) + 64 : 128;
+    }
+}
+
 Int128 int128_divu(Int128, Int128);
 Int128 int128_remu(Int128, Int128);
 Int128 int128_divs(Int128, Int128);
diff --git a/util/host-utils.c b/util/host-utils.c
index 96d5dc0bed..93dfb1b6ab 100644
--- a/util/host-utils.c
+++ b/util/host-utils.c
@@ -266,3 +266,132 @@ void ulshift(uint64_t *plow, uint64_t *phigh, int32_t shift, bool *overflow)
         *plow = *plow << shift;
     }
 }
+
+/*
+ * Unsigned 256-by-128 division.
+ * Returns the remainder via r.
+ * Returns lower 128 bit of quotient.
+ * Needs a normalized divisor (most significant bit set to 1).
+ *
+ * Adapted from include/qemu/host-utils.h udiv_qrnnd,
+ * from the GNU Multi Precision Library - longlong.h __udiv_qrnnd
+ * (https://gmplib.org/repo/gmp/file/tip/longlong.h)
+ *
+ * Licensed under the GPLv2/LGPLv3
+ */
+static Int128 udiv256_qrnnd(Int128 *r, Int128 n1, Int128 n0, Int128 d)
+{
+    Int128 d0, d1, q0, q1, r1, r0, m;
+    uint64_t mp0, mp1;
+
+    d0 = int128_make64(int128_getlo(d));
+    d1 = int128_make64(int128_gethi(d));
+
+    r1 = int128_remu(n1, d1);
+    q1 = int128_divu(n1, d1);
+    mp0 = int128_getlo(q1);
+    mp1 = int128_gethi(q1);
+    mulu128(&mp0, &mp1, int128_getlo(d0));
+    m = int128_make128(mp0, mp1);
+    r1 = int128_make128(int128_gethi(n0), int128_getlo(r1));
+    if (int128_ult(r1, m)) {
+        q1 = int128_sub(q1, int128_one());
+        r1 = int128_add(r1, d);
+        if (int128_uge(r1, d)) {
+            if (int128_ult(r1, m)) {
+                q1 = int128_sub(q1, int128_one());
+                r1 = int128_add(r1, d);
+            }
+        }
+    }
+    r1 = int128_sub(r1, m);
+
+    r0 = int128_remu(r1, d1);
+    q0 = int128_divu(r1, d1);
+    mp0 = int128_getlo(q0);
+    mp1 = int128_gethi(q0);
+    mulu128(&mp0, &mp1, int128_getlo(d0));
+    m = int128_make128(mp0, mp1);
+    r0 = int128_make128(int128_getlo(n0), int128_getlo(r0));
+    if (int128_ult(r0, m)) {
+        q0 = int128_sub(q0, int128_one());
+        r0 = int128_add(r0, d);
+        if (int128_uge(r0, d)) {
+            if (int128_ult(r0, m)) {
+                q0 = int128_sub(q0, int128_one());
+                r0 = int128_add(r0, d);
+            }
+        }
+    }
+    r0 = int128_sub(r0, m);
+
+    *r = r0;
+    return int128_or(int128_lshift(q1, 64), q0);
+}
+
+/*
+ * Unsigned 256-by-128 division.
+ * Returns the remainder.
+ * Returns quotient via plow and phigh.
+ * Also returns the remainder via the function return value.
+ */
+Int128 divu256(Int128 *plow, Int128 *phigh, Int128 divisor)
+{
+    Int128 dhi = *phigh;
+    Int128 dlo = *plow;
+    Int128 rem, dhighest;
+    int sh;
+
+    if (!int128_nz(divisor) || !int128_nz(dhi)) {
+        *plow  = int128_divu(dlo, divisor);
+        *phigh = int128_zero();
+        return int128_remu(dlo, divisor);
+    } else {
+        sh = clz128(divisor);
+
+        if (int128_ult(dhi, divisor)) {
+            if (sh != 0) {
+                /* normalize the divisor, shifting the dividend accordingly */
+                divisor = int128_lshift(divisor, sh);
+                dhi = int128_or(int128_lshift(dhi, sh),
+                                int128_urshift(dlo, (128 - sh)));
+                dlo = int128_lshift(dlo, sh);
+            }
+
+            *phigh = int128_zero();
+            *plow = udiv256_qrnnd(&rem, dhi, dlo, divisor);
+        } else {
+            if (sh != 0) {
+                /* normalize the divisor, shifting the dividend accordingly */
+                divisor = int128_lshift(divisor, sh);
+                dhighest = int128_rshift(dhi, (128 - sh));
+                dhi = int128_or(int128_lshift(dhi, sh),
+                                int128_urshift(dlo, (128 - sh)));
+                dlo = int128_lshift(dlo, sh);
+
+                *phigh = udiv256_qrnnd(&dhi, dhighest, dhi, divisor);
+            } else {
+                /*
+                 * dhi >= divisor
+                 * Since the MSB of divisor is set (sh == 0),
+                 * (dhi - divisor) < divisor
+                 *
+                 * Thus, the high part of the quotient is 1, and we can
+                 * calculate the low part with a single call to udiv_qrnnd
+                 * after subtracting divisor from dhi
+                 */
+                dhi = int128_sub(dhi, divisor);
+                *phigh = int128_one();
+            }
+
+            *plow = udiv256_qrnnd(&rem, dhi, dlo, divisor);
+        }
+
+        /*
+         * since the dividend/divisor might have been normalized,
+         * the remainder might also have to be shifted back
+         */
+        rem = int128_urshift(rem, sh);
+        return rem;
+    }
+}
-- 
2.31.1

Re: [PATCH RESEND v3 4/8] host-utils: Implemented unsigned 256-by-128 division

[Richard Henderson]

On 5/25/22 06:49, Lucas Mateus Castro(alqotel) wrote:
> From: "Lucas Mateus Castro (alqotel)"<lucas.araujo@eldorado.org.br>
> 
> Based on already existing QEMU implementation, created an unsigned 256
> bit by 128 bit division needed to implement the vector divide extended
> unsigned instruction from PowerISA3.1
> 
> Signed-off-by: Lucas Mateus Castro (alqotel)<lucas.araujo@eldorado.org.br>
> ---
> This patch had received Reviewed-by by Richard Henderson pending on the
> placemente of clz128 being moved to int128.h, but clz128 ended up being changed
> to accommodate to int128.h (i.e. the lack of clz64), so out of precaution I'd
> like to request a review of the clz128 implementation
> ---
>   include/qemu/host-utils.h |   2 +
>   include/qemu/int128.h     |  38 +++++++++++
>   util/host-utils.c         | 129 ++++++++++++++++++++++++++++++++++++++
>   3 files changed, 169 insertions(+)

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>

r~

[PATCH RESEND v3 5/8] host-utils: Implemented signed 256-by-128 division

[Lucas Mateus Castro(alqotel)]

From: "Lucas Mateus Castro (alqotel)" <lucas.araujo@eldorado.org.br>

Based on already existing QEMU implementation created a signed
256 bit by 128 bit division needed to implement the vector divide
extended signed quadword instruction from PowerISA 3.1

Signed-off-by: Lucas Mateus Castro (alqotel) <lucas.araujo@eldorado.org.br>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
 include/qemu/host-utils.h |  1 +
 util/host-utils.c         | 51 +++++++++++++++++++++++++++++++++++++++
 2 files changed, 52 insertions(+)

diff --git a/include/qemu/host-utils.h b/include/qemu/host-utils.h
index 9767af7573..bc743f5e32 100644
--- a/include/qemu/host-utils.h
+++ b/include/qemu/host-utils.h
@@ -851,4 +851,5 @@ static inline uint64_t udiv_qrnnd(uint64_t *r, uint64_t n1,
 }
 
 Int128 divu256(Int128 *plow, Int128 *phigh, Int128 divisor);
+Int128 divs256(Int128 *plow, Int128 *phigh, Int128 divisor);
 #endif
diff --git a/util/host-utils.c b/util/host-utils.c
index 93dfb1b6ab..fb91bcba82 100644
--- a/util/host-utils.c
+++ b/util/host-utils.c
@@ -395,3 +395,54 @@ Int128 divu256(Int128 *plow, Int128 *phigh, Int128 divisor)
         return rem;
     }
 }
+
+/*
+ * Signed 256-by-128 division.
+ * Returns quotient via plow and phigh.
+ * Also returns the remainder via the function return value.
+ */
+Int128 divs256(Int128 *plow, Int128 *phigh, Int128 divisor)
+{
+    bool neg_quotient = false, neg_remainder = false;
+    Int128 unsig_hi = *phigh, unsig_lo = *plow;
+    Int128 rem;
+
+    if (!int128_nonneg(*phigh)) {
+        neg_quotient = !neg_quotient;
+        neg_remainder = !neg_remainder;
+
+        if (!int128_nz(unsig_lo)) {
+            unsig_hi = int128_neg(unsig_hi);
+        } else {
+            unsig_hi = int128_not(unsig_hi);
+            unsig_lo = int128_neg(unsig_lo);
+        }
+    }
+
+    if (!int128_nonneg(divisor)) {
+        neg_quotient = !neg_quotient;
+
+        divisor = int128_neg(divisor);
+    }
+
+    rem = divu256(&unsig_lo, &unsig_hi, divisor);
+
+    if (neg_quotient) {
+        if (!int128_nz(unsig_lo)) {
+            *phigh = int128_neg(unsig_hi);
+            *plow = int128_zero();
+        } else {
+            *phigh = int128_not(unsig_hi);
+            *plow = int128_neg(unsig_lo);
+        }
+    } else {
+        *phigh = unsig_hi;
+        *plow = unsig_lo;
+    }
+
+    if (neg_remainder) {
+        return int128_neg(rem);
+    } else {
+        return rem;
+    }
+}
-- 
2.31.1

[PATCH RESEND v3 6/8] target/ppc: Implemented remaining vector divide extended

[Lucas Mateus Castro(alqotel)]

From: "Lucas Mateus Castro (alqotel)" <lucas.araujo@eldorado.org.br>

Implement the following PowerISA v3.1 instructions:
vdivesd: Vector Divide Extended Signed Doubleword
vdiveud: Vector Divide Extended Unsigned Doubleword
vdivesq: Vector Divide Extended Signed Quadword
vdiveuq: Vector Divide Extended Unsigned Quadword

Signed-off-by: Lucas Mateus Castro (alqotel) <lucas.araujo@eldorado.org.br>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/ppc/helper.h                 |  4 ++
 target/ppc/insn32.decode            |  4 ++
 target/ppc/int_helper.c             | 64 +++++++++++++++++++++++++++++
 target/ppc/translate/vmx-impl.c.inc |  4 ++
 4 files changed, 76 insertions(+)

diff --git a/target/ppc/helper.h b/target/ppc/helper.h
index 9f33e589e0..e7624300df 100644
--- a/target/ppc/helper.h
+++ b/target/ppc/helper.h
@@ -177,6 +177,10 @@ DEF_HELPER_FLAGS_3(VMULOUH, TCG_CALL_NO_RWG, void, avr, avr, avr)
 DEF_HELPER_FLAGS_3(VMULOUW, TCG_CALL_NO_RWG, void, avr, avr, avr)
 DEF_HELPER_FLAGS_3(VDIVSQ, TCG_CALL_NO_RWG, void, avr, avr, avr)
 DEF_HELPER_FLAGS_3(VDIVUQ, TCG_CALL_NO_RWG, void, avr, avr, avr)
+DEF_HELPER_FLAGS_3(VDIVESD, TCG_CALL_NO_RWG, void, avr, avr, avr)
+DEF_HELPER_FLAGS_3(VDIVEUD, TCG_CALL_NO_RWG, void, avr, avr, avr)
+DEF_HELPER_FLAGS_3(VDIVESQ, TCG_CALL_NO_RWG, void, avr, avr, avr)
+DEF_HELPER_FLAGS_3(VDIVEUQ, TCG_CALL_NO_RWG, void, avr, avr, avr)
 DEF_HELPER_FLAGS_3(vslo, TCG_CALL_NO_RWG, void, avr, avr, avr)
 DEF_HELPER_FLAGS_3(vsro, TCG_CALL_NO_RWG, void, avr, avr, avr)
 DEF_HELPER_FLAGS_3(vsrv, TCG_CALL_NO_RWG, void, avr, avr, avr)
diff --git a/target/ppc/insn32.decode b/target/ppc/insn32.decode
index f6d2d4b257..5b2d7824a0 100644
--- a/target/ppc/insn32.decode
+++ b/target/ppc/insn32.decode
@@ -798,3 +798,7 @@ VDIVUQ          000100 ..... ..... ..... 00000001011    @VX
 
 VDIVESW         000100 ..... ..... ..... 01110001011    @VX
 VDIVEUW         000100 ..... ..... ..... 01010001011    @VX
+VDIVESD         000100 ..... ..... ..... 01111001011    @VX
+VDIVEUD         000100 ..... ..... ..... 01011001011    @VX
+VDIVESQ         000100 ..... ..... ..... 01100001011    @VX
+VDIVEUQ         000100 ..... ..... ..... 01000001011    @VX
diff --git a/target/ppc/int_helper.c b/target/ppc/int_helper.c
index 033718dc0e..42f0dcfc52 100644
--- a/target/ppc/int_helper.c
+++ b/target/ppc/int_helper.c
@@ -1183,6 +1183,70 @@ void helper_VDIVUQ(ppc_avr_t *t, ppc_avr_t *a, ppc_avr_t *b)
     }
 }
 
+void helper_VDIVESD(ppc_avr_t *t, ppc_avr_t *a, ppc_avr_t *b)
+{
+    int i;
+    int64_t high;
+    uint64_t low;
+    for (i = 0; i < 2; i++) {
+        high = a->s64[i];
+        low = 0;
+        if (unlikely((high == INT64_MIN && b->s64[i] == -1) || !b->s64[i])) {
+            t->s64[i] = a->s64[i]; /* Undefined behavior */
+        } else {
+            divs128(&low, &high, b->s64[i]);
+            t->s64[i] = low;
+        }
+    }
+}
+
+void helper_VDIVEUD(ppc_avr_t *t, ppc_avr_t *a, ppc_avr_t *b)
+{
+    int i;
+    uint64_t high, low;
+    for (i = 0; i < 2; i++) {
+        high = a->u64[i];
+        low = 0;
+        if (unlikely(!b->u64[i])) {
+            t->u64[i] = a->u64[i]; /* Undefined behavior */
+        } else {
+            divu128(&low, &high, b->u64[i]);
+            t->u64[i] = low;
+        }
+    }
+}
+
+void helper_VDIVESQ(ppc_avr_t *t, ppc_avr_t *a, ppc_avr_t *b)
+{
+    Int128 high, low;
+    Int128 int128_min = int128_make128(0, INT64_MIN);
+    Int128 neg1 = int128_makes64(-1);
+
+    high = a->s128;
+    low = int128_zero();
+    if (unlikely(!int128_nz(b->s128) ||
+                 (int128_eq(b->s128, neg1) && int128_eq(high, int128_min)))) {
+        t->s128 = a->s128; /* Undefined behavior */
+    } else {
+        divs256(&low, &high, b->s128);
+        t->s128 = low;
+    }
+}
+
+void helper_VDIVEUQ(ppc_avr_t *t, ppc_avr_t *a, ppc_avr_t *b)
+{
+    Int128 high, low;
+
+    high = a->s128;
+    low = int128_zero();
+    if (unlikely(!int128_nz(b->s128))) {
+        t->s128 = a->s128; /* Undefined behavior */
+    } else {
+        divu256(&low, &high, b->s128);
+        t->s128 = low;
+    }
+}
+
 void helper_VPERM(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, ppc_avr_t *c)
 {
     ppc_avr_t result;
diff --git a/target/ppc/translate/vmx-impl.c.inc b/target/ppc/translate/vmx-impl.c.inc
index 8c542bcb29..f00aa64bf9 100644
--- a/target/ppc/translate/vmx-impl.c.inc
+++ b/target/ppc/translate/vmx-impl.c.inc
@@ -3367,6 +3367,10 @@ DIVU32(do_diveuw, do_diveu_i32)
 
 TRANS_FLAGS2(ISA310, VDIVESW, do_vdiv_vmod, MO_32, do_divesw, NULL)
 TRANS_FLAGS2(ISA310, VDIVEUW, do_vdiv_vmod, MO_32, do_diveuw, NULL)
+TRANS_FLAGS2(ISA310, VDIVESD, do_vx_helper, gen_helper_VDIVESD)
+TRANS_FLAGS2(ISA310, VDIVEUD, do_vx_helper, gen_helper_VDIVEUD)
+TRANS_FLAGS2(ISA310, VDIVESQ, do_vx_helper, gen_helper_VDIVESQ)
+TRANS_FLAGS2(ISA310, VDIVEUQ, do_vx_helper, gen_helper_VDIVEUQ)
 
 #undef DIVS32
 #undef DIVU32
-- 
2.31.1

[PATCH RESEND v3 7/8] target/ppc: Implemented vector module word/doubleword

[Lucas Mateus Castro(alqotel)]

From: "Lucas Mateus Castro (alqotel)" <lucas.araujo@eldorado.org.br>

Implement the following PowerISA v3.1 instructions:
vmodsw: Vector Modulo Signed Word
vmoduw: Vector Modulo Unsigned Word
vmodsd: Vector Modulo Signed Doubleword
vmodud: Vector Modulo Unsigned Doubleword

Signed-off-by: Lucas Mateus Castro (alqotel) <lucas.araujo@eldorado.org.br>
---
 target/ppc/insn32.decode            |  5 +++++
 target/ppc/translate/vmx-impl.c.inc | 10 ++++++++++
 2 files changed, 15 insertions(+)

diff --git a/target/ppc/insn32.decode b/target/ppc/insn32.decode
index 5b2d7824a0..75fa206b39 100644
--- a/target/ppc/insn32.decode
+++ b/target/ppc/insn32.decode
@@ -802,3 +802,8 @@ VDIVESD         000100 ..... ..... ..... 01111001011    @VX
 VDIVEUD         000100 ..... ..... ..... 01011001011    @VX
 VDIVESQ         000100 ..... ..... ..... 01100001011    @VX
 VDIVEUQ         000100 ..... ..... ..... 01000001011    @VX
+
+VMODSW          000100 ..... ..... ..... 11110001011    @VX
+VMODUW          000100 ..... ..... ..... 11010001011    @VX
+VMODSD          000100 ..... ..... ..... 11111001011    @VX
+VMODUD          000100 ..... ..... ..... 11011001011    @VX
diff --git a/target/ppc/translate/vmx-impl.c.inc b/target/ppc/translate/vmx-impl.c.inc
index f00aa64bf9..78277fb018 100644
--- a/target/ppc/translate/vmx-impl.c.inc
+++ b/target/ppc/translate/vmx-impl.c.inc
@@ -3365,6 +3365,11 @@ static void do_diveu_i32(TCGv_i32 t, TCGv_i32 a, TCGv_i32 b)
 DIVS32(do_divesw, do_dives_i32)
 DIVU32(do_diveuw, do_diveu_i32)
 
+DIVS32(do_modsw, tcg_gen_rem_i32)
+DIVU32(do_moduw, tcg_gen_remu_i32)
+DIVS64(do_modsd, tcg_gen_rem_i64)
+DIVU64(do_modud, tcg_gen_remu_i64)
+
 TRANS_FLAGS2(ISA310, VDIVESW, do_vdiv_vmod, MO_32, do_divesw, NULL)
 TRANS_FLAGS2(ISA310, VDIVEUW, do_vdiv_vmod, MO_32, do_diveuw, NULL)
 TRANS_FLAGS2(ISA310, VDIVESD, do_vx_helper, gen_helper_VDIVESD)
@@ -3372,6 +3377,11 @@ TRANS_FLAGS2(ISA310, VDIVEUD, do_vx_helper, gen_helper_VDIVEUD)
 TRANS_FLAGS2(ISA310, VDIVESQ, do_vx_helper, gen_helper_VDIVESQ)
 TRANS_FLAGS2(ISA310, VDIVEUQ, do_vx_helper, gen_helper_VDIVEUQ)
 
+TRANS_FLAGS2(ISA310, VMODSW, do_vdiv_vmod, MO_32, do_modsw , NULL)
+TRANS_FLAGS2(ISA310, VMODUW, do_vdiv_vmod, MO_32, do_moduw, NULL)
+TRANS_FLAGS2(ISA310, VMODSD, do_vdiv_vmod, MO_64, NULL, do_modsd)
+TRANS_FLAGS2(ISA310, VMODUD, do_vdiv_vmod, MO_64, NULL, do_modud)
+
 #undef DIVS32
 #undef DIVU32
 #undef DIVS64
-- 
2.31.1

Re: [PATCH RESEND v3 7/8] target/ppc: Implemented vector module word/doubleword

[Richard Henderson]

On 5/25/22 06:49, Lucas Mateus Castro(alqotel) wrote:
> From: "Lucas Mateus Castro (alqotel)"<lucas.araujo@eldorado.org.br>
> 
> Implement the following PowerISA v3.1 instructions:
> vmodsw: Vector Modulo Signed Word
> vmoduw: Vector Modulo Unsigned Word
> vmodsd: Vector Modulo Signed Doubleword
> vmodud: Vector Modulo Unsigned Doubleword
> 
> Signed-off-by: Lucas Mateus Castro (alqotel)<lucas.araujo@eldorado.org.br>
> ---
>   target/ppc/insn32.decode            |  5 +++++
>   target/ppc/translate/vmx-impl.c.inc | 10 ++++++++++
>   2 files changed, 15 insertions(+)

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>

r~

[PATCH RESEND v3 8/8] target/ppc: Implemented vector module quadword

[Lucas Mateus Castro(alqotel)]

From: "Lucas Mateus Castro (alqotel)" <lucas.araujo@eldorado.org.br>

Implement the following PowerISA v3.1 instructions:
vmodsq: Vector Modulo Signed Quadword
vmoduq: Vector Modulo Unsigned Quadword

Signed-off-by: Lucas Mateus Castro (alqotel) <lucas.araujo@eldorado.org.br>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Resolves: https://gitlab.com/qemu-project/qemu/-/issues/744
---
 target/ppc/helper.h                 |  2 ++
 target/ppc/insn32.decode            |  2 ++
 target/ppc/int_helper.c             | 21 +++++++++++++++++++++
 target/ppc/translate/vmx-impl.c.inc |  2 ++
 4 files changed, 27 insertions(+)

diff --git a/target/ppc/helper.h b/target/ppc/helper.h
index e7624300df..d627cfe6ed 100644
--- a/target/ppc/helper.h
+++ b/target/ppc/helper.h
@@ -181,6 +181,8 @@ DEF_HELPER_FLAGS_3(VDIVESD, TCG_CALL_NO_RWG, void, avr, avr, avr)
 DEF_HELPER_FLAGS_3(VDIVEUD, TCG_CALL_NO_RWG, void, avr, avr, avr)
 DEF_HELPER_FLAGS_3(VDIVESQ, TCG_CALL_NO_RWG, void, avr, avr, avr)
 DEF_HELPER_FLAGS_3(VDIVEUQ, TCG_CALL_NO_RWG, void, avr, avr, avr)
+DEF_HELPER_FLAGS_3(VMODSQ, TCG_CALL_NO_RWG, void, avr, avr, avr)
+DEF_HELPER_FLAGS_3(VMODUQ, TCG_CALL_NO_RWG, void, avr, avr, avr)
 DEF_HELPER_FLAGS_3(vslo, TCG_CALL_NO_RWG, void, avr, avr, avr)
 DEF_HELPER_FLAGS_3(vsro, TCG_CALL_NO_RWG, void, avr, avr, avr)
 DEF_HELPER_FLAGS_3(vsrv, TCG_CALL_NO_RWG, void, avr, avr, avr)
diff --git a/target/ppc/insn32.decode b/target/ppc/insn32.decode
index 75fa206b39..6ea48d5163 100644
--- a/target/ppc/insn32.decode
+++ b/target/ppc/insn32.decode
@@ -807,3 +807,5 @@ VMODSW          000100 ..... ..... ..... 11110001011    @VX
 VMODUW          000100 ..... ..... ..... 11010001011    @VX
 VMODSD          000100 ..... ..... ..... 11111001011    @VX
 VMODUD          000100 ..... ..... ..... 11011001011    @VX
+VMODSQ          000100 ..... ..... ..... 11100001011    @VX
+VMODUQ          000100 ..... ..... ..... 11000001011    @VX
diff --git a/target/ppc/int_helper.c b/target/ppc/int_helper.c
index 42f0dcfc52..16357c0900 100644
--- a/target/ppc/int_helper.c
+++ b/target/ppc/int_helper.c
@@ -1247,6 +1247,27 @@ void helper_VDIVEUQ(ppc_avr_t *t, ppc_avr_t *a, ppc_avr_t *b)
     }
 }
 
+void helper_VMODSQ(ppc_avr_t *t, ppc_avr_t *a, ppc_avr_t *b)
+{
+    Int128 neg1 = int128_makes64(-1);
+    Int128 int128_min = int128_make128(0, INT64_MIN);
+    if (likely(int128_nz(b->s128) &&
+              (int128_ne(a->s128, int128_min) || int128_ne(b->s128, neg1)))) {
+        t->s128 = int128_rems(a->s128, b->s128);
+    } else {
+        t->s128 = int128_zero(); /* Undefined behavior */
+    }
+}
+
+void helper_VMODUQ(ppc_avr_t *t, ppc_avr_t *a, ppc_avr_t *b)
+{
+    if (likely(int128_nz(b->s128))) {
+        t->s128 = int128_remu(a->s128, b->s128);
+    } else {
+        t->s128 = int128_zero(); /* Undefined behavior */
+    }
+}
+
 void helper_VPERM(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, ppc_avr_t *c)
 {
     ppc_avr_t result;
diff --git a/target/ppc/translate/vmx-impl.c.inc b/target/ppc/translate/vmx-impl.c.inc
index 78277fb018..0b563bed37 100644
--- a/target/ppc/translate/vmx-impl.c.inc
+++ b/target/ppc/translate/vmx-impl.c.inc
@@ -3381,6 +3381,8 @@ TRANS_FLAGS2(ISA310, VMODSW, do_vdiv_vmod, MO_32, do_modsw , NULL)
 TRANS_FLAGS2(ISA310, VMODUW, do_vdiv_vmod, MO_32, do_moduw, NULL)
 TRANS_FLAGS2(ISA310, VMODSD, do_vdiv_vmod, MO_64, NULL, do_modsd)
 TRANS_FLAGS2(ISA310, VMODUD, do_vdiv_vmod, MO_64, NULL, do_modud)
+TRANS_FLAGS2(ISA310, VMODSQ, do_vx_helper, gen_helper_VMODSQ)
+TRANS_FLAGS2(ISA310, VMODUQ, do_vx_helper, gen_helper_VMODUQ)
 
 #undef DIVS32
 #undef DIVU32
-- 
2.31.1