[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[PATCH v5 25/60] target/riscv: vector single-width fractional multiply w
From: |
LIU Zhiwei |
Subject: |
[PATCH v5 25/60] target/riscv: vector single-width fractional multiply with rounding and saturation |
Date: |
Thu, 12 Mar 2020 22:58:25 +0800 |
Signed-off-by: LIU Zhiwei <address@hidden>
---
target/riscv/helper.h | 9 +++
target/riscv/insn32.decode | 2 +
target/riscv/insn_trans/trans_rvv.inc.c | 4 +
target/riscv/vector_helper.c | 103 ++++++++++++++++++++++++
4 files changed, 118 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index d3837d2ca4..333eccca57 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -724,3 +724,12 @@ DEF_HELPER_6(vasub_vx_b, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vasub_vx_h, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vasub_vx_w, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vasub_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+
+DEF_HELPER_6(vsmul_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsmul_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsmul_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsmul_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vsmul_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsmul_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsmul_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vsmul_vx_d, void, ptr, ptr, tl, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 0227a16b16..99f70924d6 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -417,6 +417,8 @@ vaadd_vx 100100 . ..... ..... 100 ..... 1010111 @r_vm
vaadd_vi 100100 . ..... ..... 011 ..... 1010111 @r_vm
vasub_vv 100110 . ..... ..... 000 ..... 1010111 @r_vm
vasub_vx 100110 . ..... ..... 100 ..... 1010111 @r_vm
+vsmul_vv 100111 . ..... ..... 000 ..... 1010111 @r_vm
+vsmul_vx 100111 . ..... ..... 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 9988fad2fe..60e1e63b7b 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -1528,3 +1528,7 @@ GEN_OPIVV_TRANS(vasub_vv, opivv_check)
GEN_OPIVX_TRANS(vaadd_vx, opivx_check)
GEN_OPIVX_TRANS(vasub_vx, opivx_check)
GEN_OPIVI_TRANS(vaadd_vi, 0, vaadd_vx, opivx_check)
+
+/* Vector Single-Width Fractional Multiply with Rounding and Saturation */
+GEN_OPIVV_TRANS(vsmul_vv, opivv_check)
+GEN_OPIVX_TRANS(vsmul_vx, opivx_check)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index b0a7a3b6e4..74ad07743c 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -2420,3 +2420,106 @@ GEN_VEXT_VX_ENV(vasub_vx_b, 1, 1, clearb)
GEN_VEXT_VX_ENV(vasub_vx_h, 2, 2, clearh)
GEN_VEXT_VX_ENV(vasub_vx_w, 4, 4, clearl)
GEN_VEXT_VX_ENV(vasub_vx_d, 8, 8, clearq)
+
+/* Vector Single-Width Fractional Multiply with Rounding and Saturation */
+static inline int8_t vsmul8(CPURISCVState *env, int8_t a, int8_t b)
+{
+ uint8_t round;
+ int16_t res;
+
+ res = (int16_t)a * (int16_t)b;
+ round = get_round(env, res, 7);
+ res = (res >> 7) + round;
+
+ if (res > INT8_MAX) {
+ env->vxsat = 0x1;
+ return INT8_MAX;
+ } else if (res < INT8_MIN) {
+ env->vxsat = 0x1;
+ return INT8_MIN;
+ } else {
+ return res;
+ }
+}
+static int16_t vsmul16(CPURISCVState *env, int16_t a, int16_t b)
+{
+ uint8_t round;
+ int32_t res;
+
+ res = (int32_t)a * (int32_t)b;
+ round = get_round(env, res, 15);
+ res = (res >> 15) + round;
+
+ if (res > INT16_MAX) {
+ env->vxsat = 0x1;
+ return INT16_MAX;
+ } else if (res < INT16_MIN) {
+ env->vxsat = 0x1;
+ return INT16_MIN;
+ } else {
+ return res;
+ }
+}
+static int32_t vsmul32(CPURISCVState *env, int32_t a, int32_t b)
+{
+ uint8_t round;
+ int64_t res;
+
+ res = (int64_t)a * (int64_t)b;
+ round = get_round(env, res, 31);
+ res = (res >> 31) + round;
+
+ if (res > INT32_MAX) {
+ env->vxsat = 0x1;
+ return INT32_MAX;
+ } else if (res < INT32_MIN) {
+ env->vxsat = 0x1;
+ return INT32_MIN;
+ } else {
+ return res;
+ }
+}
+static int64_t vsmul64(CPURISCVState *env, int64_t a, int64_t b)
+{
+ uint8_t round;
+ uint64_t hi_64, lo_64, Hi62;
+ uint8_t hi62, hi63, lo63;
+
+ muls64(&lo_64, &hi_64, a, b);
+ hi62 = extract64(hi_64, 62, 1);
+ lo63 = extract64(lo_64, 63, 1);
+ hi63 = extract64(hi_64, 63, 1);
+ Hi62 = extract64(hi_64, 0, 62);
+ if (hi62 != hi63) {
+ env->vxsat = 0x1;
+ return INT64_MAX;
+ }
+ round = get_round(env, lo_64, 63);
+ if (round && (Hi62 == 0x3fffffff) && lo63) {
+ env->vxsat = 0x1;
+ return hi62 ? INT64_MIN : INT64_MAX;
+ } else {
+ if (lo63 && round) {
+ return (hi_64 + 1) << 1;
+ } else {
+ return (hi_64 << 1) | lo63 | round;
+ }
+ }
+}
+RVVCALL(OPIVV2_ENV, vsmul_vv_b, OP_SSS_B, H1, H1, H1, vsmul8)
+RVVCALL(OPIVV2_ENV, vsmul_vv_h, OP_SSS_H, H2, H2, H2, vsmul16)
+RVVCALL(OPIVV2_ENV, vsmul_vv_w, OP_SSS_W, H4, H4, H4, vsmul32)
+RVVCALL(OPIVV2_ENV, vsmul_vv_d, OP_SSS_D, H8, H8, H8, vsmul64)
+GEN_VEXT_VV_ENV(vsmul_vv_b, 1, 1, clearb)
+GEN_VEXT_VV_ENV(vsmul_vv_h, 2, 2, clearh)
+GEN_VEXT_VV_ENV(vsmul_vv_w, 4, 4, clearl)
+GEN_VEXT_VV_ENV(vsmul_vv_d, 8, 8, clearq)
+
+RVVCALL(OPIVX2_ENV, vsmul_vx_b, OP_SSS_B, H1, H1, vsmul8)
+RVVCALL(OPIVX2_ENV, vsmul_vx_h, OP_SSS_H, H2, H2, vsmul16)
+RVVCALL(OPIVX2_ENV, vsmul_vx_w, OP_SSS_W, H4, H4, vsmul32)
+RVVCALL(OPIVX2_ENV, vsmul_vx_d, OP_SSS_D, H8, H8, vsmul64)
+GEN_VEXT_VX_ENV(vsmul_vx_b, 1, 1, clearb)
+GEN_VEXT_VX_ENV(vsmul_vx_h, 2, 2, clearh)
+GEN_VEXT_VX_ENV(vsmul_vx_w, 4, 4, clearl)
+GEN_VEXT_VX_ENV(vsmul_vx_d, 8, 8, clearq)
--
2.23.0
- Re: [PATCH v5 22/60] target/riscv: vector integer merge and move instructions, (continued)
- [PATCH v5 23/60] target/riscv: vector single-width saturating add and subtract, LIU Zhiwei, 2020/03/12
- [PATCH v5 24/60] target/riscv: vector single-width averaging add and subtract, LIU Zhiwei, 2020/03/12
- Re: [PATCH v5 24/60] target/riscv: vector single-width averaging add and subtract, Richard Henderson, 2020/03/14
- Re: [PATCH v5 24/60] target/riscv: vector single-width averaging add and subtract, Richard Henderson, 2020/03/14
- Re: [PATCH v5 24/60] target/riscv: vector single-width averaging add and subtract, LIU Zhiwei, 2020/03/14
- Re: [PATCH v5 24/60] target/riscv: vector single-width averaging add and subtract, Richard Henderson, 2020/03/14
- Re: [PATCH v5 24/60] target/riscv: vector single-width averaging add and subtract, LIU Zhiwei, 2020/03/15
- Re: [PATCH v5 24/60] target/riscv: vector single-width averaging add and subtract, Richard Henderson, 2020/03/15
[PATCH v5 25/60] target/riscv: vector single-width fractional multiply with rounding and saturation,
LIU Zhiwei <=
[PATCH v5 26/60] target/riscv: vector widening saturating scaled multiply-add, LIU Zhiwei, 2020/03/12
[PATCH v5 27/60] target/riscv: vector single-width scaling shift instructions, LIU Zhiwei, 2020/03/12
[PATCH v5 28/60] target/riscv: vector narrowing fixed-point clip instructions, LIU Zhiwei, 2020/03/12
[PATCH v5 29/60] target/riscv: vector single-width floating-point add/subtract instructions, LIU Zhiwei, 2020/03/12
[PATCH v5 30/60] target/riscv: vector widening floating-point add/subtract instructions, LIU Zhiwei, 2020/03/12