QEMU-Devel Archive on lore.kernel.org
 help / color / Atom feed
From: LIU Zhiwei <zhiwei_liu@c-sky.com>
To: richard.henderson@linaro.org, alistair23@gmail.com,
	chihmin.chao@sifive.com, palmer@dabbelt.com
Cc: guoren@linux.alibaba.com, qemu-riscv@nongnu.org,
	qemu-devel@nongnu.org, wxy194768@alibaba-inc.com,
	wenmeng_zhang@c-sky.com, LIU Zhiwei <zhiwei_liu@c-sky.com>
Subject: [PATCH v6 24/61] target/riscv: vector single-width saturating add and subtract
Date: Tue, 17 Mar 2020 23:06:16 +0800
Message-ID: <20200317150653.9008-25-zhiwei_liu@c-sky.com> (raw)
In-Reply-To: <20200317150653.9008-1-zhiwei_liu@c-sky.com>

Signed-off-by: LIU Zhiwei <zhiwei_liu@c-sky.com>
---
 target/riscv/helper.h                   |  33 ++
 target/riscv/insn32.decode              |  10 +
 target/riscv/insn_trans/trans_rvv.inc.c |  16 +
 target/riscv/vector_helper.c            | 389 ++++++++++++++++++++++++
 4 files changed, 448 insertions(+)

diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index f378db9cbf..fd1c184852 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -682,3 +682,36 @@ DEF_HELPER_4(vmv_v_x_b, void, ptr, i64, env, i32)
 DEF_HELPER_4(vmv_v_x_h, void, ptr, i64, env, i32)
 DEF_HELPER_4(vmv_v_x_w, void, ptr, i64, env, i32)
 DEF_HELPER_4(vmv_v_x_d, void, ptr, i64, env, i32)
+
+DEF_HELPER_6(vsaddu_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsaddu_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsaddu_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsaddu_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsadd_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsadd_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsadd_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsadd_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vssubu_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vssubu_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vssubu_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vssubu_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vssub_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vssub_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vssub_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vssub_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsaddu_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsaddu_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsaddu_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsaddu_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsadd_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsadd_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsadd_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsadd_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vssubu_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vssubu_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vssubu_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vssubu_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vssub_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vssub_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vssub_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vssub_vx_d, void, ptr, ptr, tl, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index adb76956c9..c9a4050adc 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -407,6 +407,16 @@ vmv_v_i         010111 1 00000 ..... 011 ..... 1010111 @r2
 vmerge_vvm      010111 0 ..... ..... 000 ..... 1010111 @r_vm_0
 vmerge_vxm      010111 0 ..... ..... 100 ..... 1010111 @r_vm_0
 vmerge_vim      010111 0 ..... ..... 011 ..... 1010111 @r_vm_0
+vsaddu_vv       100000 . ..... ..... 000 ..... 1010111 @r_vm
+vsaddu_vx       100000 . ..... ..... 100 ..... 1010111 @r_vm
+vsaddu_vi       100000 . ..... ..... 011 ..... 1010111 @r_vm
+vsadd_vv        100001 . ..... ..... 000 ..... 1010111 @r_vm
+vsadd_vx        100001 . ..... ..... 100 ..... 1010111 @r_vm
+vsadd_vi        100001 . ..... ..... 011 ..... 1010111 @r_vm
+vssubu_vv       100010 . ..... ..... 000 ..... 1010111 @r_vm
+vssubu_vx       100010 . ..... ..... 100 ..... 1010111 @r_vm
+vssub_vv        100011 . ..... ..... 000 ..... 1010111 @r_vm
+vssub_vx        100011 . ..... ..... 100 ..... 1010111 @r_vm
 
 vsetvli         0 ........... ..... 111 ..... 1010111  @r2_zimm
 vsetvl          1000000 ..... ..... 111 ..... 1010111  @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_trans/trans_rvv.inc.c
index 42ef59364f..dd1a508a51 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -1620,3 +1620,19 @@ static bool trans_vmv_v_i(DisasContext *s, arg_vmv_v_i *a)
 GEN_OPIVV_TRANS(vmerge_vvm, opivv_vadc_check)
 GEN_OPIVX_TRANS(vmerge_vxm, opivx_vadc_check)
 GEN_OPIVI_TRANS(vmerge_vim, 0, vmerge_vxm, opivx_vadc_check)
+
+/*
+ *** Vector Fixed-Point Arithmetic Instructions
+ */
+
+/* Vector Single-Width Saturating Add and Subtract */
+GEN_OPIVV_TRANS(vsaddu_vv, opivv_check)
+GEN_OPIVV_TRANS(vsadd_vv,  opivv_check)
+GEN_OPIVV_TRANS(vssubu_vv, opivv_check)
+GEN_OPIVV_TRANS(vssub_vv,  opivv_check)
+GEN_OPIVX_TRANS(vsaddu_vx,  opivx_check)
+GEN_OPIVX_TRANS(vsadd_vx,  opivx_check)
+GEN_OPIVX_TRANS(vssubu_vx,  opivx_check)
+GEN_OPIVX_TRANS(vssub_vx,  opivx_check)
+GEN_OPIVI_TRANS(vsaddu_vi, 1, vsaddu_vx, opivx_check)
+GEN_OPIVI_TRANS(vsadd_vi, 0, vsadd_vx, opivx_check)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index e52a556484..b17cac7fd4 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -2099,3 +2099,392 @@ GEN_VEXT_VMERGE_VX(vmerge_vxm_b, int8_t,  H1, clearb)
 GEN_VEXT_VMERGE_VX(vmerge_vxm_h, int16_t, H2, clearh)
 GEN_VEXT_VMERGE_VX(vmerge_vxm_w, int32_t, H4, clearl)
 GEN_VEXT_VMERGE_VX(vmerge_vxm_d, int64_t, H8, clearq)
+
+/*
+ *** Vector Fixed-Point Arithmetic Instructions
+ */
+
+/* Vector Single-Width Saturating Add and Subtract */
+
+/*
+ * As fixed point instructions probably have round mode and saturation,
+ * define common macros for fixed point here.
+ */
+typedef void opivv2_rm_fn(void *vd, void *vs1, void *vs2, int i,
+                          CPURISCVState *env, int vxrm);
+
+#define OPIVV2_RM(NAME, TD, T1, T2, TX1, TX2, HD, HS1, HS2, OP)     \
+static inline void                                                  \
+do_##NAME(void *vd, void *vs1, void *vs2, int i,                    \
+          CPURISCVState *env, int vxrm)                             \
+{                                                                   \
+    TX1 s1 = *((T1 *)vs1 + HS1(i));                                 \
+    TX2 s2 = *((T2 *)vs2 + HS2(i));                                 \
+    *((TD *)vd + HD(i)) = OP(env, vxrm, s2, s1);                    \
+}
+
+static inline void
+vext_vv_rm_1(void *vd, void *v0, void *vs1, void *vs2,
+             CPURISCVState *env,
+             uint32_t vl, uint32_t vm, uint32_t mlen, int vxrm,
+             opivv2_rm_fn *fn)
+{
+    for (uint32_t i = 0; i < vl; i++) {
+        if (!vm && !vext_elem_mask(v0, mlen, i)) {
+            continue;
+        }
+        fn(vd, vs1, vs2, i, env, vxrm);
+    }
+}
+
+static inline void
+vext_vv_rm_2(void *vd, void *v0, void *vs1, void *vs2,
+             CPURISCVState *env,
+             uint32_t desc, uint32_t esz, uint32_t dsz,
+             opivv2_rm_fn *fn, clear_fn *clearfn)
+{
+    uint32_t vlmax = vext_maxsz(desc) / esz;
+    uint32_t mlen = vext_mlen(desc);
+    uint32_t vm = vext_vm(desc);
+    uint32_t vl = env->vl;
+
+    if (vl == 0) {
+        return;
+    }
+
+    switch (env->vxrm) {
+    case 0: /* rnu */
+        vext_vv_rm_1(vd, v0, vs1, vs2,
+                     env, vl, vm, mlen, 0, fn);
+        break;
+    case 1: /* rne */
+        vext_vv_rm_1(vd, v0, vs1, vs2,
+                     env, vl, vm, mlen, 1, fn);
+        break;
+    case 2: /* rdn */
+        vext_vv_rm_1(vd, v0, vs1, vs2,
+                     env, vl, vm, mlen, 2, fn);
+        break;
+    default: /* rod */
+        vext_vv_rm_1(vd, v0, vs1, vs2,
+                     env, vl, vm, mlen, 3, fn);
+        break;
+    }
+
+    clearfn(vd, vl, vl * dsz,  vlmax * dsz);
+}
+
+/* generate helpers for fixed point instructions with OPIVV format */
+#define GEN_VEXT_VV_RM(NAME, ESZ, DSZ, CLEAR_FN)                \
+void HELPER(NAME)(void *vd, void *v0, void *vs1, void *vs2,     \
+                  CPURISCVState *env, uint32_t desc)            \
+{                                                               \
+    vext_vv_rm_2(vd, v0, vs1, vs2, env, desc, ESZ, DSZ,         \
+                 do_##NAME, CLEAR_FN);                          \
+}
+
+static inline uint8_t saddu8(CPURISCVState *env, int vxrm, uint8_t a, uint8_t b)
+{
+    uint8_t res = a + b;
+    if (res < a) {
+        res = UINT8_MAX;
+        env->vxsat = 0x1;
+    }
+    return res;
+}
+
+static inline uint16_t saddu16(CPURISCVState *env, int vxrm, uint16_t a,
+                               uint16_t b)
+{
+    uint16_t res = a + b;
+    if (res < a) {
+        res = UINT16_MAX;
+        env->vxsat = 0x1;
+    }
+    return res;
+}
+
+static inline uint32_t saddu32(CPURISCVState *env, int vxrm, uint32_t a,
+                               uint32_t b)
+{
+    uint32_t res = a + b;
+    if (res < a) {
+        res = UINT32_MAX;
+        env->vxsat = 0x1;
+    }
+    return res;
+}
+
+static inline uint64_t saddu64(CPURISCVState *env, int vxrm, uint64_t a,
+                               uint64_t b)
+{
+    uint64_t res = a + b;
+    if (res < a) {
+        res = UINT64_MAX;
+        env->vxsat = 0x1;
+    }
+    return res;
+}
+
+RVVCALL(OPIVV2_RM, vsaddu_vv_b, OP_UUU_B, H1, H1, H1, saddu8)
+RVVCALL(OPIVV2_RM, vsaddu_vv_h, OP_UUU_H, H2, H2, H2, saddu16)
+RVVCALL(OPIVV2_RM, vsaddu_vv_w, OP_UUU_W, H4, H4, H4, saddu32)
+RVVCALL(OPIVV2_RM, vsaddu_vv_d, OP_UUU_D, H8, H8, H8, saddu64)
+GEN_VEXT_VV_RM(vsaddu_vv_b, 1, 1, clearb)
+GEN_VEXT_VV_RM(vsaddu_vv_h, 2, 2, clearh)
+GEN_VEXT_VV_RM(vsaddu_vv_w, 4, 4, clearl)
+GEN_VEXT_VV_RM(vsaddu_vv_d, 8, 8, clearq)
+
+typedef void opivx2_rm_fn(void *vd, target_long s1, void *vs2, int i,
+                          CPURISCVState *env, int vxrm);
+
+#define OPIVX2_RM(NAME, TD, T1, T2, TX1, TX2, HD, HS2, OP)          \
+static inline void                                                  \
+do_##NAME(void *vd, target_long s1, void *vs2, int i,               \
+          CPURISCVState *env, int vxrm)                             \
+{                                                                   \
+    TX2 s2 = *((T2 *)vs2 + HS2(i));                                 \
+    *((TD *)vd + HD(i)) = OP(env, vxrm, s2, (TX1)(T1)s1);           \
+}
+
+static inline void
+vext_vx_rm_1(void *vd, void *v0, target_long s1, void *vs2,
+             CPURISCVState *env,
+             uint32_t vl, uint32_t vm, uint32_t mlen, int vxrm,
+             opivx2_rm_fn *fn)
+{
+    for (uint32_t i = 0; i < vl; i++) {
+        if (!vm && !vext_elem_mask(v0, mlen, i)) {
+            continue;
+        }
+        fn(vd, s1, vs2, i, env, vxrm);
+    }
+}
+
+static inline void
+vext_vx_rm_2(void *vd, void *v0, target_long s1, void *vs2,
+             CPURISCVState *env,
+             uint32_t desc, uint32_t esz, uint32_t dsz,
+             opivx2_rm_fn *fn, clear_fn *clearfn)
+{
+    uint32_t vlmax = vext_maxsz(desc) / esz;
+    uint32_t mlen = vext_mlen(desc);
+    uint32_t vm = vext_vm(desc);
+    uint32_t vl = env->vl;
+
+    if (vl == 0) {
+        return;
+    }
+
+    switch (env->vxrm) {
+    case 0: /* rnu */
+        vext_vx_rm_1(vd, v0, s1, vs2,
+                     env, vl, vm, mlen, 0, fn);
+        break;
+    case 1: /* rne */
+        vext_vx_rm_1(vd, v0, s1, vs2,
+                     env, vl, vm, mlen, 1, fn);
+        break;
+    case 2: /* rdn */
+        vext_vx_rm_1(vd, v0, s1, vs2,
+                     env, vl, vm, mlen, 2, fn);
+        break;
+    default: /* rod */
+        vext_vx_rm_1(vd, v0, s1, vs2,
+                     env, vl, vm, mlen, 3, fn);
+        break;
+    }
+
+    clearfn(vd, vl, vl * dsz,  vlmax * dsz);
+}
+
+/* generate helpers for fixed point instructions with OPIVX format */
+#define GEN_VEXT_VX_RM(NAME, ESZ, DSZ, CLEAR_FN)          \
+void HELPER(NAME)(void *vd, void *v0, target_ulong s1,    \
+        void *vs2, CPURISCVState *env, uint32_t desc)     \
+{                                                         \
+    vext_vx_rm_2(vd, v0, s1, vs2, env, desc, ESZ, DSZ,    \
+                 do_##NAME, CLEAR_FN);                    \
+}
+
+RVVCALL(OPIVX2_RM, vsaddu_vx_b, OP_UUU_B, H1, H1, saddu8)
+RVVCALL(OPIVX2_RM, vsaddu_vx_h, OP_UUU_H, H2, H2, saddu16)
+RVVCALL(OPIVX2_RM, vsaddu_vx_w, OP_UUU_W, H4, H4, saddu32)
+RVVCALL(OPIVX2_RM, vsaddu_vx_d, OP_UUU_D, H8, H8, saddu64)
+GEN_VEXT_VX_RM(vsaddu_vx_b, 1, 1, clearb)
+GEN_VEXT_VX_RM(vsaddu_vx_h, 2, 2, clearh)
+GEN_VEXT_VX_RM(vsaddu_vx_w, 4, 4, clearl)
+GEN_VEXT_VX_RM(vsaddu_vx_d, 8, 8, clearq)
+
+static inline int8_t sadd8(CPURISCVState *env, int vxrm, int8_t a, int8_t b)
+{
+    int8_t res = a + b;
+    if ((res ^ a) & (res ^ b) & INT8_MIN) {
+        res = a > 0 ? INT8_MAX : INT8_MIN;
+        env->vxsat = 0x1;
+    }
+    return res;
+}
+static inline int16_t sadd16(CPURISCVState *env, int vxrm, int16_t a, int16_t b)
+{
+    int16_t res = a + b;
+    if ((res ^ a) & (res ^ b) & INT16_MIN) {
+        res = a > 0 ? INT16_MAX : INT16_MIN;
+        env->vxsat = 0x1;
+    }
+    return res;
+}
+static inline int32_t sadd32(CPURISCVState *env, int vxrm, int32_t a, int32_t b)
+{
+    int32_t res = a + b;
+    if ((res ^ a) & (res ^ b) & INT32_MIN) {
+        res = a > 0 ? INT32_MAX : INT32_MIN;
+        env->vxsat = 0x1;
+    }
+    return res;
+}
+static inline int64_t sadd64(CPURISCVState *env, int vxrm, int64_t a, int64_t b)
+{
+    int64_t res = a + b;
+    if ((res ^ a) & (res ^ b) & INT64_MIN) {
+        res = a > 0 ? INT64_MAX : INT64_MIN;
+        env->vxsat = 0x1;
+    }
+    return res;
+}
+RVVCALL(OPIVV2_RM, vsadd_vv_b, OP_SSS_B, H1, H1, H1, sadd8)
+RVVCALL(OPIVV2_RM, vsadd_vv_h, OP_SSS_H, H2, H2, H2, sadd16)
+RVVCALL(OPIVV2_RM, vsadd_vv_w, OP_SSS_W, H4, H4, H4, sadd32)
+RVVCALL(OPIVV2_RM, vsadd_vv_d, OP_SSS_D, H8, H8, H8, sadd64)
+GEN_VEXT_VV_RM(vsadd_vv_b, 1, 1, clearb)
+GEN_VEXT_VV_RM(vsadd_vv_h, 2, 2, clearh)
+GEN_VEXT_VV_RM(vsadd_vv_w, 4, 4, clearl)
+GEN_VEXT_VV_RM(vsadd_vv_d, 8, 8, clearq)
+
+RVVCALL(OPIVX2_RM, vsadd_vx_b, OP_SSS_B, H1, H1, sadd8)
+RVVCALL(OPIVX2_RM, vsadd_vx_h, OP_SSS_H, H2, H2, sadd16)
+RVVCALL(OPIVX2_RM, vsadd_vx_w, OP_SSS_W, H4, H4, sadd32)
+RVVCALL(OPIVX2_RM, vsadd_vx_d, OP_SSS_D, H8, H8, sadd64)
+GEN_VEXT_VX_RM(vsadd_vx_b, 1, 1, clearb)
+GEN_VEXT_VX_RM(vsadd_vx_h, 2, 2, clearh)
+GEN_VEXT_VX_RM(vsadd_vx_w, 4, 4, clearl)
+GEN_VEXT_VX_RM(vsadd_vx_d, 8, 8, clearq)
+
+static inline uint8_t ssubu8(CPURISCVState *env, int vxrm, uint8_t a, uint8_t b)
+{
+    uint8_t res = a - b;
+    if (res > a) {
+        res = 0;
+        env->vxsat = 0x1;
+    }
+    return res;
+}
+
+static inline uint16_t ssubu16(CPURISCVState *env, int vxrm, uint16_t a,
+                               uint16_t b)
+{
+    uint16_t res = a - b;
+    if (res > a) {
+        res = 0;
+        env->vxsat = 0x1;
+    }
+    return res;
+}
+
+static inline uint32_t ssubu32(CPURISCVState *env, int vxrm, uint32_t a,
+                               uint32_t b)
+{
+    uint32_t res = a - b;
+    if (res > a) {
+        res = 0;
+        env->vxsat = 0x1;
+    }
+    return res;
+}
+
+static inline uint64_t ssubu64(CPURISCVState *env, int vxrm, uint64_t a,
+                               uint64_t b)
+{
+    uint64_t res = a - b;
+    if (res > a) {
+        res = 0;
+        env->vxsat = 0x1;
+    }
+    return res;
+}
+
+RVVCALL(OPIVV2_RM, vssubu_vv_b, OP_UUU_B, H1, H1, H1, ssubu8)
+RVVCALL(OPIVV2_RM, vssubu_vv_h, OP_UUU_H, H2, H2, H2, ssubu16)
+RVVCALL(OPIVV2_RM, vssubu_vv_w, OP_UUU_W, H4, H4, H4, ssubu32)
+RVVCALL(OPIVV2_RM, vssubu_vv_d, OP_UUU_D, H8, H8, H8, ssubu64)
+GEN_VEXT_VV_RM(vssubu_vv_b, 1, 1, clearb)
+GEN_VEXT_VV_RM(vssubu_vv_h, 2, 2, clearh)
+GEN_VEXT_VV_RM(vssubu_vv_w, 4, 4, clearl)
+GEN_VEXT_VV_RM(vssubu_vv_d, 8, 8, clearq)
+
+RVVCALL(OPIVX2_RM, vssubu_vx_b, OP_UUU_B, H1, H1, ssubu8)
+RVVCALL(OPIVX2_RM, vssubu_vx_h, OP_UUU_H, H2, H2, ssubu16)
+RVVCALL(OPIVX2_RM, vssubu_vx_w, OP_UUU_W, H4, H4, ssubu32)
+RVVCALL(OPIVX2_RM, vssubu_vx_d, OP_UUU_D, H8, H8, ssubu64)
+GEN_VEXT_VX_RM(vssubu_vx_b, 1, 1, clearb)
+GEN_VEXT_VX_RM(vssubu_vx_h, 2, 2, clearh)
+GEN_VEXT_VX_RM(vssubu_vx_w, 4, 4, clearl)
+GEN_VEXT_VX_RM(vssubu_vx_d, 8, 8, clearq)
+
+static inline int8_t ssub8(CPURISCVState *env, int vxrm, int8_t a, int8_t b)
+{
+    int8_t res = a - b;
+    if ((res ^ a) & (a ^ b) & INT8_MIN) {
+        res = a > 0 ? INT8_MAX : INT8_MIN;
+        env->vxsat = 0x1;
+    }
+    return res;
+}
+
+static inline int16_t ssub16(CPURISCVState *env, int vxrm, int16_t a, int16_t b)
+{
+    int16_t res = a - b;
+    if ((res ^ a) & (a ^ b) & INT16_MIN) {
+        res = a > 0 ? INT16_MAX : INT16_MIN;
+        env->vxsat = 0x1;
+    }
+    return res;
+}
+
+static inline int32_t ssub32(CPURISCVState *env, int vxrm, int32_t a, int32_t b)
+{
+    int32_t res = a - b;
+    if ((res ^ a) & (a ^ b) & INT32_MIN) {
+        res = a > 0 ? INT32_MAX : INT32_MIN;
+        env->vxsat = 0x1;
+    }
+    return res;
+}
+
+static inline int64_t ssub64(CPURISCVState *env, int vxrm, int64_t a, int64_t b)
+{
+    int64_t res = a - b;
+    if ((res ^ a) & (a ^ b) & INT64_MIN) {
+        res = a > 0 ? INT64_MAX : INT64_MIN;
+        env->vxsat = 0x1;
+    }
+    return res;
+}
+
+RVVCALL(OPIVV2_RM, vssub_vv_b, OP_SSS_B, H1, H1, H1, ssub8)
+RVVCALL(OPIVV2_RM, vssub_vv_h, OP_SSS_H, H2, H2, H2, ssub16)
+RVVCALL(OPIVV2_RM, vssub_vv_w, OP_SSS_W, H4, H4, H4, ssub32)
+RVVCALL(OPIVV2_RM, vssub_vv_d, OP_SSS_D, H8, H8, H8, ssub64)
+GEN_VEXT_VV_RM(vssub_vv_b, 1, 1, clearb)
+GEN_VEXT_VV_RM(vssub_vv_h, 2, 2, clearh)
+GEN_VEXT_VV_RM(vssub_vv_w, 4, 4, clearl)
+GEN_VEXT_VV_RM(vssub_vv_d, 8, 8, clearq)
+
+RVVCALL(OPIVX2_RM, vssub_vx_b, OP_SSS_B, H1, H1, ssub8)
+RVVCALL(OPIVX2_RM, vssub_vx_h, OP_SSS_H, H2, H2, ssub16)
+RVVCALL(OPIVX2_RM, vssub_vx_w, OP_SSS_W, H4, H4, ssub32)
+RVVCALL(OPIVX2_RM, vssub_vx_d, OP_SSS_D, H8, H8, ssub64)
+GEN_VEXT_VX_RM(vssub_vx_b, 1, 1, clearb)
+GEN_VEXT_VX_RM(vssub_vx_h, 2, 2, clearh)
+GEN_VEXT_VX_RM(vssub_vx_w, 4, 4, clearl)
+GEN_VEXT_VX_RM(vssub_vx_d, 8, 8, clearq)
-- 
2.23.0



  parent reply index

Thread overview: 120+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-03-17 15:05 [PATCH v6 00/61] target/riscv: support vector extension v0.7.1 LIU Zhiwei
2020-03-17 15:05 ` [PATCH v6 01/61] target/riscv: add vector extension field in CPURISCVState LIU Zhiwei
2020-03-17 15:05 ` [PATCH v6 02/61] target/riscv: implementation-defined constant parameters LIU Zhiwei
2020-03-17 15:05 ` [PATCH v6 03/61] target/riscv: support vector extension csr LIU Zhiwei
2020-03-17 15:05 ` [PATCH v6 04/61] target/riscv: add vector configure instruction LIU Zhiwei
2020-03-23  6:51   ` Kito Cheng
2020-03-23  7:10     ` LIU Zhiwei
2020-03-17 15:05 ` [PATCH v6 05/61] target/riscv: add an internals.h header LIU Zhiwei
2020-03-18 23:45   ` Alistair Francis
2020-03-27 23:41   ` Richard Henderson
2020-03-17 15:05 ` [PATCH v6 06/61] target/riscv: add vector stride load and store instructions LIU Zhiwei
2020-03-18 23:54   ` Alistair Francis
2020-03-17 15:05 ` [PATCH v6 07/61] target/riscv: add vector index " LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 08/61] target/riscv: add fault-only-first unit stride load LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 09/61] target/riscv: add vector amo operations LIU Zhiwei
2020-03-19 17:01   ` Alistair Francis
2020-03-27 23:44   ` Richard Henderson
2020-03-17 15:06 ` [PATCH v6 10/61] target/riscv: vector single-width integer add and subtract LIU Zhiwei
2020-03-20 18:31   ` Alistair Francis
2020-03-27 23:54   ` Richard Henderson
2020-03-28 14:42     ` LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 11/61] target/riscv: vector widening " LIU Zhiwei
2020-03-19 16:28   ` Alistair Francis
2020-03-17 15:06 ` [PATCH v6 12/61] target/riscv: vector integer add-with-carry / subtract-with-borrow instructions LIU Zhiwei
2020-03-19 17:29   ` Alistair Francis
2020-03-28  0:00   ` Richard Henderson
2020-03-17 15:06 ` [PATCH v6 13/61] target/riscv: vector bitwise logical instructions LIU Zhiwei
2020-03-20 18:34   ` Alistair Francis
2020-03-17 15:06 ` [PATCH v6 14/61] target/riscv: vector single-width bit shift instructions LIU Zhiwei
2020-03-19 20:10   ` Alistair Francis
2020-03-17 15:06 ` [PATCH v6 15/61] target/riscv: vector narrowing integer right " LIU Zhiwei
2020-03-20 18:43   ` Alistair Francis
2020-03-17 15:06 ` [PATCH v6 16/61] target/riscv: vector integer comparison instructions LIU Zhiwei
2020-03-25 17:32   ` Alistair Francis
2020-03-17 15:06 ` [PATCH v6 17/61] target/riscv: vector integer min/max instructions LIU Zhiwei
2020-03-20 18:49   ` Alistair Francis
2020-03-17 15:06 ` [PATCH v6 18/61] target/riscv: vector single-width integer multiply instructions LIU Zhiwei
2020-03-25 17:36   ` Alistair Francis
2020-03-28  0:06   ` Richard Henderson
2020-03-28 15:17     ` LIU Zhiwei
2020-03-28 15:47       ` Richard Henderson
2020-03-28 16:13         ` LIU Zhiwei
2020-03-29  4:00           ` LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 19/61] target/riscv: vector integer divide instructions LIU Zhiwei
2020-03-20 18:51   ` Alistair Francis
2020-03-17 15:06 ` [PATCH v6 20/61] target/riscv: vector widening integer multiply instructions LIU Zhiwei
2020-03-25 17:25   ` Alistair Francis
2020-03-17 15:06 ` [PATCH v6 21/61] target/riscv: vector single-width integer multiply-add instructions LIU Zhiwei
2020-03-25 17:27   ` Alistair Francis
2020-03-17 15:06 ` [PATCH v6 22/61] target/riscv: vector widening " LIU Zhiwei
2020-03-25 17:42   ` Alistair Francis
2020-03-17 15:06 ` [PATCH v6 23/61] target/riscv: vector integer merge and move instructions LIU Zhiwei
2020-03-26 17:57   ` Alistair Francis
2020-03-28  0:18   ` Richard Henderson
2020-03-17 15:06 ` LIU Zhiwei [this message]
2020-03-28  0:20   ` [PATCH v6 24/61] target/riscv: vector single-width saturating add and subtract Richard Henderson
2020-03-17 15:06 ` [PATCH v6 25/61] target/riscv: vector single-width averaging " LIU Zhiwei
2020-03-19  3:46   ` LIU Zhiwei
2020-03-28  0:32     ` Richard Henderson
2020-03-28  1:07       ` LIU Zhiwei
2020-03-28  1:22         ` Richard Henderson
2020-03-28 15:37           ` LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 26/61] target/riscv: vector single-width fractional multiply with rounding and saturation LIU Zhiwei
2020-03-28  1:08   ` Richard Henderson
2020-03-28 15:41     ` LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 27/61] target/riscv: vector widening saturating scaled multiply-add LIU Zhiwei
2020-03-28  1:23   ` Richard Henderson
2020-03-17 15:06 ` [PATCH v6 28/61] target/riscv: vector single-width scaling shift instructions LIU Zhiwei
2020-03-28  1:24   ` Richard Henderson
2020-03-17 15:06 ` [PATCH v6 29/61] target/riscv: vector narrowing fixed-point clip instructions LIU Zhiwei
2020-03-28  1:50   ` Richard Henderson
2020-03-17 15:06 ` [PATCH v6 30/61] target/riscv: vector single-width floating-point add/subtract instructions LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 31/61] target/riscv: vector widening " LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 32/61] target/riscv: vector single-width floating-point multiply/divide instructions LIU Zhiwei
2020-03-25 17:46   ` Alistair Francis
2020-03-17 15:06 ` [PATCH v6 33/61] target/riscv: vector widening floating-point multiply LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 34/61] target/riscv: vector single-width floating-point fused multiply-add instructions LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 35/61] target/riscv: vector widening " LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 36/61] target/riscv: vector floating-point square-root instruction LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 37/61] target/riscv: vector floating-point min/max instructions LIU Zhiwei
2020-03-25 17:47   ` Alistair Francis
2020-03-17 15:06 ` [PATCH v6 38/61] target/riscv: vector floating-point sign-injection instructions LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 39/61] target/riscv: vector floating-point compare instructions LIU Zhiwei
2020-03-28  2:01   ` Richard Henderson
2020-03-28 15:44     ` LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 40/61] target/riscv: vector floating-point classify instructions LIU Zhiwei
2020-03-28  2:06   ` Richard Henderson
2020-03-17 15:06 ` [PATCH v6 41/61] target/riscv: vector floating-point merge instructions LIU Zhiwei
2020-03-28  3:23   ` Richard Henderson
2020-03-28 15:47     ` LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 42/61] target/riscv: vector floating-point/integer type-convert instructions LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 43/61] target/riscv: widening " LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 44/61] target/riscv: narrowing " LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 45/61] target/riscv: vector single-width integer reduction instructions LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 46/61] target/riscv: vector wideing " LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 47/61] target/riscv: vector single-width floating-point " LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 48/61] target/riscv: vector widening " LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 49/61] target/riscv: vector mask-register logical instructions LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 50/61] target/riscv: vector mask population count vmpopc LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 51/61] target/riscv: vmfirst find-first-set mask bit LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 52/61] target/riscv: set-X-first " LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 53/61] target/riscv: vector iota instruction LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 54/61] target/riscv: vector element index instruction LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 55/61] target/riscv: integer extract instruction LIU Zhiwei
2020-03-28  3:36   ` Richard Henderson
2020-03-28 16:23     ` LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 56/61] target/riscv: integer scalar move instruction LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 57/61] target/riscv: floating-point scalar move instructions LIU Zhiwei
2020-03-28  3:44   ` Richard Henderson
2020-03-28 16:31     ` LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 58/61] target/riscv: vector slide instructions LIU Zhiwei
2020-03-28  3:50   ` Richard Henderson
2020-03-28 13:40   ` LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 59/61] target/riscv: vector register gather instruction LIU Zhiwei
2020-03-28  3:57   ` Richard Henderson
2020-03-17 15:06 ` [PATCH v6 60/61] target/riscv: vector compress instruction LIU Zhiwei
2020-03-17 15:06 ` [PATCH v6 61/61] target/riscv: configure and turn on vector extension from command line LIU Zhiwei
2020-03-25 17:49   ` Alistair Francis
2020-03-28  4:00   ` Richard Henderson
2020-03-17 20:47 ` [PATCH v6 00/61] target/riscv: support vector extension v0.7.1 no-reply

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200317150653.9008-25-zhiwei_liu@c-sky.com \
    --to=zhiwei_liu@c-sky.com \
    --cc=alistair23@gmail.com \
    --cc=chihmin.chao@sifive.com \
    --cc=guoren@linux.alibaba.com \
    --cc=palmer@dabbelt.com \
    --cc=qemu-devel@nongnu.org \
    --cc=qemu-riscv@nongnu.org \
    --cc=richard.henderson@linaro.org \
    --cc=wenmeng_zhang@c-sky.com \
    --cc=wxy194768@alibaba-inc.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

QEMU-Devel Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/qemu-devel/0 qemu-devel/git/0.git
	git clone --mirror https://lore.kernel.org/qemu-devel/1 qemu-devel/git/1.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 qemu-devel qemu-devel/ https://lore.kernel.org/qemu-devel \
		qemu-devel@nongnu.org
	public-inbox-index qemu-devel

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.nongnu.qemu-devel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git