[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[PATCH v2 17/37] target/riscv: Signed 16-bit Multiply 32-bit Add/Subtrac
From: |
LIU Zhiwei |
Subject: |
[PATCH v2 17/37] target/riscv: Signed 16-bit Multiply 32-bit Add/Subtract Instructions |
Date: |
Thu, 10 Jun 2021 15:58:48 +0800 |
Always contain a signed 16x16 multiply and the 32-bit result can be
written to the destination register or as an operand for an add/subtract
operation.
Signed-off-by: LIU Zhiwei <zhiwei_liu@c-sky.com>
---
target/riscv/helper.h | 19 ++
target/riscv/insn32.decode | 19 ++
target/riscv/insn_trans/trans_rvp.c.inc | 20 ++
target/riscv/packed_helper.c | 268 ++++++++++++++++++++++++
4 files changed, 326 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 854f48d385..5aac6ba578 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -1297,3 +1297,22 @@ DEF_HELPER_4(kmmawb2, tl, env, tl, tl, tl)
DEF_HELPER_4(kmmawb2_u, tl, env, tl, tl, tl)
DEF_HELPER_4(kmmawt2, tl, env, tl, tl, tl)
DEF_HELPER_4(kmmawt2_u, tl, env, tl, tl, tl)
+
+DEF_HELPER_3(smbb16, tl, env, tl, tl)
+DEF_HELPER_3(smbt16, tl, env, tl, tl)
+DEF_HELPER_3(smtt16, tl, env, tl, tl)
+DEF_HELPER_3(kmda, tl, env, tl, tl)
+DEF_HELPER_3(kmxda, tl, env, tl, tl)
+DEF_HELPER_3(smds, tl, env, tl, tl)
+DEF_HELPER_3(smdrs, tl, env, tl, tl)
+DEF_HELPER_3(smxds, tl, env, tl, tl)
+DEF_HELPER_4(kmabb, tl, env, tl, tl, tl)
+DEF_HELPER_4(kmabt, tl, env, tl, tl, tl)
+DEF_HELPER_4(kmatt, tl, env, tl, tl, tl)
+DEF_HELPER_4(kmada, tl, env, tl, tl, tl)
+DEF_HELPER_4(kmaxda, tl, env, tl, tl, tl)
+DEF_HELPER_4(kmads, tl, env, tl, tl, tl)
+DEF_HELPER_4(kmadrs, tl, env, tl, tl, tl)
+DEF_HELPER_4(kmaxds, tl, env, tl, tl, tl)
+DEF_HELPER_4(kmsda, tl, env, tl, tl, tl)
+DEF_HELPER_4(kmsxda, tl, env, tl, tl, tl)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index e5a8f663dc..f590880750 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -900,3 +900,22 @@ kmmawb2 1100111 ..... ..... 001 ..... 1110111 @r
kmmawb2_u 1101111 ..... ..... 001 ..... 1110111 @r
kmmawt2 1110111 ..... ..... 001 ..... 1110111 @r
kmmawt2_u 1111111 ..... ..... 001 ..... 1110111 @r
+
+smbb16 0000100 ..... ..... 001 ..... 1110111 @r
+smbt16 0001100 ..... ..... 001 ..... 1110111 @r
+smtt16 0010100 ..... ..... 001 ..... 1110111 @r
+kmda 0011100 ..... ..... 001 ..... 1110111 @r
+kmxda 0011101 ..... ..... 001 ..... 1110111 @r
+smds 0101100 ..... ..... 001 ..... 1110111 @r
+smdrs 0110100 ..... ..... 001 ..... 1110111 @r
+smxds 0111100 ..... ..... 001 ..... 1110111 @r
+kmabb 0101101 ..... ..... 001 ..... 1110111 @r
+kmabt 0110101 ..... ..... 001 ..... 1110111 @r
+kmatt 0111101 ..... ..... 001 ..... 1110111 @r
+kmada 0100100 ..... ..... 001 ..... 1110111 @r
+kmaxda 0100101 ..... ..... 001 ..... 1110111 @r
+kmads 0101110 ..... ..... 001 ..... 1110111 @r
+kmadrs 0110110 ..... ..... 001 ..... 1110111 @r
+kmaxds 0111110 ..... ..... 001 ..... 1110111 @r
+kmsda 0100110 ..... ..... 001 ..... 1110111 @r
+kmsxda 0100111 ..... ..... 001 ..... 1110111 @r
diff --git a/target/riscv/insn_trans/trans_rvp.c.inc
b/target/riscv/insn_trans/trans_rvp.c.inc
index af490a5ef0..308fc223db 100644
--- a/target/riscv/insn_trans/trans_rvp.c.inc
+++ b/target/riscv/insn_trans/trans_rvp.c.inc
@@ -431,3 +431,23 @@ GEN_RVP_R_ACC_OOL(kmmawb2);
GEN_RVP_R_ACC_OOL(kmmawb2_u);
GEN_RVP_R_ACC_OOL(kmmawt2);
GEN_RVP_R_ACC_OOL(kmmawt2_u);
+
+/* Signed 16-bit Multiply with 32-bit Add/Subtract Instructions */
+GEN_RVP_R_OOL(smbb16);
+GEN_RVP_R_OOL(smbt16);
+GEN_RVP_R_OOL(smtt16);
+GEN_RVP_R_OOL(kmda);
+GEN_RVP_R_OOL(kmxda);
+GEN_RVP_R_OOL(smds);
+GEN_RVP_R_OOL(smdrs);
+GEN_RVP_R_OOL(smxds);
+GEN_RVP_R_ACC_OOL(kmabb);
+GEN_RVP_R_ACC_OOL(kmabt);
+GEN_RVP_R_ACC_OOL(kmatt);
+GEN_RVP_R_ACC_OOL(kmada);
+GEN_RVP_R_ACC_OOL(kmaxda);
+GEN_RVP_R_ACC_OOL(kmads);
+GEN_RVP_R_ACC_OOL(kmadrs);
+GEN_RVP_R_ACC_OOL(kmaxds);
+GEN_RVP_R_ACC_OOL(kmsda);
+GEN_RVP_R_ACC_OOL(kmsxda);
diff --git a/target/riscv/packed_helper.c b/target/riscv/packed_helper.c
index 868a1a71ba..88509fd118 100644
--- a/target/riscv/packed_helper.c
+++ b/target/riscv/packed_helper.c
@@ -1676,3 +1676,271 @@ static inline void do_kmmawt2_u(CPURISCVState *env,
void *vd, void *va,
}
RVPR_ACC(kmmawt2_u, 1, 4);
+
+/* Signed 16-bit Multiply with 32-bit Add/Subtract Instruction */
+static inline void do_smbb16(CPURISCVState *env, void *vd, void *va,
+ void *vb, uint8_t i)
+{
+ int32_t *d = vd;
+ int16_t *a = va, *b = vb;
+ d[H4(i)] = (int32_t)a[H2(2 * i)] * b[H2(2 * i)];
+}
+
+RVPR(smbb16, 1, 4);
+
+static inline void do_smbt16(CPURISCVState *env, void *vd, void *va,
+ void *vb, uint8_t i)
+{
+ int32_t *d = vd;
+ int16_t *a = va, *b = vb;
+ d[H4(i)] = (int32_t)a[H2(2 * i)] * b[H2(2 * i + 1)];
+}
+
+RVPR(smbt16, 1, 4);
+
+static inline void do_smtt16(CPURISCVState *env, void *vd, void *va,
+ void *vb, uint8_t i)
+{
+ int32_t *d = vd;
+ int16_t *a = va, *b = vb;
+ d[H4(i)] = (int32_t)a[H2(2 * i + 1)] * b[H2(2 * i + 1)];
+}
+
+RVPR(smtt16, 1, 4);
+
+static inline void do_kmda(CPURISCVState *env, void *vd, void *va,
+ void *vb, uint8_t i)
+{
+ int32_t *d = vd;
+ int16_t *a = va, *b = vb;
+ if (a[H2(2 * i)] == INT16_MIN && a[H2(2 * i + 1)] == INT16_MIN &&
+ b[H2(2 * i)] == INT16_MIN && a[H2(2 * i + 1)] == INT16_MIN) {
+ d[H4(i)] = INT32_MAX;
+ env->vxsat = 0x1;
+ } else {
+ d[H4(i)] = (int32_t)a[H2(2 * i)] * b[H2(2 * i)] +
+ (int32_t)a[H2(2 * i + 1)] * b[H2(2 * i + 1)];
+ }
+}
+
+RVPR(kmda, 1, 4);
+
+static inline void do_kmxda(CPURISCVState *env, void *vd, void *va,
+ void *vb, uint8_t i)
+{
+ int32_t *d = vd;
+ int16_t *a = va, *b = vb;
+ if (a[H2(2 * i)] == INT16_MIN && a[H2(2 * i + 1)] == INT16_MIN &&
+ b[H2(2 * i)] == INT16_MIN && a[H2(2 * i + 1)] == INT16_MIN) {
+ d[H4(i)] = INT32_MAX;
+ env->vxsat = 0x1;
+ } else {
+ d[H4(i)] = (int32_t)a[H2(2 * i + 1)] * b[H2(2 * i)] +
+ (int32_t)a[H2(2 * i)] * b[H2(2 * i + 1)];
+ }
+}
+
+RVPR(kmxda, 1, 4);
+
+static inline void do_smds(CPURISCVState *env, void *vd, void *va,
+ void *vb, uint8_t i)
+{
+ int32_t *d = vd;
+ int16_t *a = va, *b = vb;
+ d[H4(i)] = (int32_t)a[H2(2 * i + 1)] * b[H2(2 * i + 1)] -
+ (int32_t)a[H2(2 * i)] * b[H2(2 * i)];
+}
+
+RVPR(smds, 1, 4);
+
+static inline void do_smdrs(CPURISCVState *env, void *vd, void *va,
+ void *vb, uint8_t i)
+{
+ int32_t *d = vd;
+ int16_t *a = va, *b = vb;
+ d[H4(i)] = (int32_t)a[H2(2 * i)] * b[H2(2 * i)] -
+ (int32_t)a[H2(2 * i + 1)] * b[H2(2 * i + 1)];
+}
+
+RVPR(smdrs, 1, 4);
+
+static inline void do_smxds(CPURISCVState *env, void *vd, void *va,
+ void *vb, uint8_t i)
+{
+ int32_t *d = vd;
+ int16_t *a = va, *b = vb;
+ d[H4(i)] = (int32_t)a[H2(2 * i + 1)] * b[H2(2 * i)] -
+ (int32_t)a[H2(2 * i)] * b[H2(2 * i + 1)];
+}
+
+RVPR(smxds, 1, 4);
+
+static inline void do_kmabb(CPURISCVState *env, void *vd, void *va,
+ void *vb, void *vc, uint8_t i)
+{
+ int32_t *d = vd, *c = vc;
+ int16_t *a = va, *b = vb;
+ d[H4(i)] = sadd32(env, 0, (int32_t)a[H2(2 * i)] * b[H2(2 * i)], c[H4(i)]);
+}
+
+RVPR_ACC(kmabb, 1, 4);
+
+static inline void do_kmabt(CPURISCVState *env, void *vd, void *va,
+ void *vb, void *vc, uint8_t i)
+{
+ int32_t *d = vd, *c = vc;
+ int16_t *a = va, *b = vb;
+ d[H4(i)] = sadd32(env, 0, (int32_t)a[H2(2 * i)] * b[H2(2 * i + 1)],
+ c[H4(i)]);
+}
+
+RVPR_ACC(kmabt, 1, 4);
+
+static inline void do_kmatt(CPURISCVState *env, void *vd, void *va,
+ void *vb, void *vc, uint8_t i)
+{
+ int32_t *d = vd, *c = vc;
+ int16_t *a = va, *b = vb;
+ d[H4(i)] = sadd32(env, 0, (int32_t)a[H2(2 * i + 1)] * b[H2(2 * i + 1)],
+ c[H4(i)]);
+}
+
+RVPR_ACC(kmatt, 1, 4);
+
+static inline void do_kmada(CPURISCVState *env, void *vd, void *va,
+ void *vb, void *vc, uint8_t i)
+{
+ int32_t *d = vd, *c = vc;
+ int16_t *a = va, *b = vb;
+ int32_t p1, p2;
+ p1 = (int32_t)a[H2(2 * i)] * b[H2(2 * i)];
+ p2 = (int32_t)a[H2(2 * i + 1)] * b[H2(2 * i + 1)];
+
+ if (a[H2(i)] == INT16_MIN && a[H2(i + 1)] == INT16_MIN &&
+ b[H2(i)] == INT16_MIN && b[H2(i + 1)] == INT16_MIN) {
+ if (c[H4(i)] < 0) {
+ d[H4(i)] = INT32_MAX + c[H4(i)] + 1ll;
+ } else {
+ env->vxsat = 0x1;
+ d[H4(i)] = INT32_MAX;
+ }
+ } else {
+ d[H4(i)] = sadd32(env, 0, p1 + p2, c[H4(i)]);
+ }
+}
+
+RVPR_ACC(kmada, 1, 4);
+
+static inline void do_kmaxda(CPURISCVState *env, void *vd, void *va,
+ void *vb, void *vc, uint8_t i)
+{
+ int32_t *d = vd, *c = vc;
+ int16_t *a = va, *b = vb;
+ int32_t p1, p2;
+ p1 = (int32_t)a[H2(2 * i + 1)] * b[H2(2 * i)];
+ p2 = (int32_t)a[H2(2 * i)] * b[H2(2 * i + 1)];
+
+ if (a[H2(2 * i)] == INT16_MIN && a[H2(2 * i + 1)] == INT16_MIN &&
+ b[H2(2 * i)] == INT16_MIN && b[H2(2 * i + 1)] == INT16_MIN) {
+ if (c[H4(i)] < 0) {
+ d[H4(i)] = INT32_MAX + c[H4(i)] + 1ll;
+ } else {
+ env->vxsat = 0x1;
+ d[H4(i)] = INT32_MAX;
+ }
+ } else {
+ d[H4(i)] = sadd32(env, 0, p1 + p2, c[H4(i)]);
+ }
+}
+
+RVPR_ACC(kmaxda, 1, 4);
+
+static inline void do_kmads(CPURISCVState *env, void *vd, void *va,
+ void *vb, void *vc, uint8_t i)
+{
+ int32_t *d = vd, *c = vc;
+ int16_t *a = va, *b = vb;
+ int32_t p1, p2;
+ p1 = (int32_t)a[H2(2 * i + 1)] * b[H2(2 * i + 1)];
+ p2 = (int32_t)a[H2(2 * i)] * b[H2(2 * i)];
+
+ d[H4(i)] = sadd32(env, 0, p1 - p2, c[H4(i)]);
+}
+
+RVPR_ACC(kmads, 1, 4);
+
+static inline void do_kmadrs(CPURISCVState *env, void *vd, void *va,
+ void *vb, void * vc, uint8_t i)
+{
+ int32_t *d = vd, *c = vc;
+ int16_t *a = va, *b = vb;
+ int32_t p1, p2;
+ p1 = (int32_t)a[H2(2 * i)] * b[H2(2 * i)];
+ p2 = (int32_t)a[H2(2 * i + 1)] * b[H2(2 * i + 1)];
+
+ d[H4(i)] = sadd32(env, 0, p1 - p2, c[H4(i)]);
+}
+
+RVPR_ACC(kmadrs, 1, 4);
+
+static inline void do_kmaxds(CPURISCVState *env, void *vd, void *va,
+ void *vb, void *vc, uint8_t i)
+{
+ int32_t *d = vd, *c = vc;
+ int16_t *a = va, *b = vb;
+ int32_t p1, p2;
+ p1 = (int32_t)a[H2(2 * i + 1)] * b[H2(2 * i)];
+ p2 = (int32_t)a[H2(2 * i)] * b[H2(2 * i + 1)];
+
+ d[H4(i)] = sadd32(env, 0, p1 - p2, c[H4(i)]);
+}
+
+RVPR_ACC(kmaxds, 1, 4);
+
+static inline void do_kmsda(CPURISCVState *env, void *vd, void *va,
+ void *vb, void *vc, uint8_t i)
+{
+ int32_t *d = vd, *c = vc;
+ int16_t *a = va, *b = vb;
+ int32_t p1, p2;
+ p1 = (int32_t)a[H2(2 * i)] * b[H2(2 * i)];
+ p2 = (int32_t)a[H2(2 * i + 1)] * b[H2(2 * i + 1)];
+
+ if (a[H2(i)] == INT16_MIN && a[H2(i + 1)] == INT16_MIN &&
+ b[H2(i)] == INT16_MIN && b[H2(i + 1)] == INT16_MIN) {
+ if (c[H4(i)] < 0) {
+ env->vxsat = 0x1;
+ d[H4(i)] = INT32_MIN;
+ } else {
+ d[H4(i)] = c[H4(i)] - 1ll - INT32_MAX;
+ }
+ } else {
+ d[H4(i)] = ssub32(env, 0, c[H4(i)], p1 + p2);
+ }
+}
+
+RVPR_ACC(kmsda, 1, 4);
+
+static inline void do_kmsxda(CPURISCVState *env, void *vd, void *va,
+ void *vb, void * vc, uint8_t i)
+{
+ int32_t *d = vd, *c = vc;
+ int16_t *a = va, *b = vb;
+ int32_t p1, p2;
+ p1 = (int32_t)a[H2(2 * i)] * b[H2(2 * i + 1)];
+ p2 = (int32_t)a[H2(2 * i + 1)] * b[H2(2 * i)];
+
+ if (a[H2(i)] == INT16_MIN && a[H2(i + 1)] == INT16_MIN &&
+ b[H2(i)] == INT16_MIN && b[H2(i + 1)] == INT16_MIN) {
+ if (d[H4(i)] < 0) {
+ env->vxsat = 0x1;
+ d[H4(i)] = INT32_MIN;
+ } else {
+ d[H4(i)] = c[H4(i)] - 1ll - INT32_MAX;
+ }
+ } else {
+ d[H4(i)] = ssub32(env, 0, c[H4(i)], p1 + p2);
+ }
+}
+
+RVPR_ACC(kmsxda, 1, 4);
--
2.25.1
- [PATCH v2 07/37] target/riscv: SIMD 16-bit Compare Instructions, (continued)
- [PATCH v2 07/37] target/riscv: SIMD 16-bit Compare Instructions, LIU Zhiwei, 2021/06/10
- [PATCH v2 08/37] target/riscv: SIMD 8-bit Compare Instructions, LIU Zhiwei, 2021/06/10
- [PATCH v2 09/37] target/riscv: SIMD 16-bit Multiply Instructions, LIU Zhiwei, 2021/06/10
- [PATCH v2 10/37] target/riscv: SIMD 8-bit Multiply Instructions, LIU Zhiwei, 2021/06/10
- [PATCH v2 11/37] target/riscv: SIMD 16-bit Miscellaneous Instructions, LIU Zhiwei, 2021/06/10
- [PATCH v2 12/37] target/riscv: SIMD 8-bit Miscellaneous Instructions, LIU Zhiwei, 2021/06/10
- [PATCH v2 13/37] target/riscv: 8-bit Unpacking Instructions, LIU Zhiwei, 2021/06/10
- [PATCH v2 14/37] target/riscv: 16-bit Packing Instructions, LIU Zhiwei, 2021/06/10
- [PATCH v2 15/37] target/riscv: Signed MSW 32x32 Multiply and Add Instructions, LIU Zhiwei, 2021/06/10
- [PATCH v2 16/37] target/riscv: Signed MSW 32x16 Multiply and Add Instructions, LIU Zhiwei, 2021/06/10
- [PATCH v2 17/37] target/riscv: Signed 16-bit Multiply 32-bit Add/Subtract Instructions,
LIU Zhiwei <=
- [PATCH v2 18/37] target/riscv: Signed 16-bit Multiply 64-bit Add/Subtract Instructions, LIU Zhiwei, 2021/06/10
- [PATCH v2 19/37] target/riscv: Partial-SIMD Miscellaneous Instructions, LIU Zhiwei, 2021/06/10
- [PATCH v2 20/37] target/riscv: 8-bit Multiply with 32-bit Add Instructions, LIU Zhiwei, 2021/06/10
- [PATCH v2 21/37] target/riscv: 64-bit Add/Subtract Instructions, LIU Zhiwei, 2021/06/10
- [PATCH v2 22/37] target/riscv: 32-bit Multiply 64-bit Add/Subtract Instructions, LIU Zhiwei, 2021/06/10
- [PATCH v2 23/37] target/riscv: Signed 16-bit Multiply with 64-bit Add/Subtract Instructions, LIU Zhiwei, 2021/06/10
- [PATCH v2 24/37] target/riscv: Non-SIMD Q15 saturation ALU Instructions, LIU Zhiwei, 2021/06/10
- [PATCH v2 25/37] target/riscv: Non-SIMD Q31 saturation ALU Instructions, LIU Zhiwei, 2021/06/10
- [PATCH v2 26/37] target/riscv: 32-bit Computation Instructions, LIU Zhiwei, 2021/06/10
- [PATCH v2 27/37] target/riscv: Non-SIMD Miscellaneous Instructions, LIU Zhiwei, 2021/06/10