From: LIU Zhiwei <zhiwei_liu@c-sky.com>
To: qemu-devel@nongnu.org, qemu-riscv@nongnu.org
Cc: palmer@dabbelt.com, richard.henderson@linaro.org,
bin.meng@windriver.com, Alistair.Francis@wdc.com,
LIU Zhiwei <zhiwei_liu@c-sky.com>
Subject: [PATCH v2 09/37] target/riscv: SIMD 16-bit Multiply Instructions
Date: Thu, 10 Jun 2021 15:58:40 +0800 [thread overview]
Message-ID: <20210610075908.3305506-10-zhiwei_liu@c-sky.com> (raw)
In-Reply-To: <20210610075908.3305506-1-zhiwei_liu@c-sky.com>
There are 6 instructions, including 16-bit signed or unsigned multiply,
16-bit signed or unsigned crossed multiply, Q15 signed or signed crossed
saturating multiply.
Signed-off-by: LIU Zhiwei <zhiwei_liu@c-sky.com>
---
target/riscv/helper.h | 7 ++
target/riscv/insn32.decode | 7 ++
target/riscv/insn_trans/trans_rvp.c.inc | 69 ++++++++++++++++
target/riscv/packed_helper.c | 104 ++++++++++++++++++++++++
4 files changed, 187 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index c424e45fe5..d13b84f165 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -1218,3 +1218,10 @@ DEF_HELPER_3(scmplt8, tl, env, tl, tl)
DEF_HELPER_3(scmple8, tl, env, tl, tl)
DEF_HELPER_3(ucmplt8, tl, env, tl, tl)
DEF_HELPER_3(ucmple8, tl, env, tl, tl)
+
+DEF_HELPER_3(smul16, i64, env, tl, tl)
+DEF_HELPER_3(smulx16, i64, env, tl, tl)
+DEF_HELPER_3(umul16, i64, env, tl, tl)
+DEF_HELPER_3(umulx16, i64, env, tl, tl)
+DEF_HELPER_3(khm16, tl, env, tl, tl)
+DEF_HELPER_3(khmx16, tl, env, tl, tl)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index fdbf3798c7..cbee995229 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -821,3 +821,10 @@ scmplt8 0000111 ..... ..... 000 ..... 1110111 @r
scmple8 0001111 ..... ..... 000 ..... 1110111 @r
ucmplt8 0010111 ..... ..... 000 ..... 1110111 @r
ucmple8 0011111 ..... ..... 000 ..... 1110111 @r
+
+smul16 1010000 ..... ..... 000 ..... 1110111 @r
+smulx16 1010001 ..... ..... 000 ..... 1110111 @r
+umul16 1011000 ..... ..... 000 ..... 1110111 @r
+umulx16 1011001 ..... ..... 000 ..... 1110111 @r
+khm16 1000011 ..... ..... 000 ..... 1110111 @r
+khmx16 1001011 ..... ..... 000 ..... 1110111 @r
diff --git a/target/riscv/insn_trans/trans_rvp.c.inc b/target/riscv/insn_trans/trans_rvp.c.inc
index aa432701c8..b93ba63dd8 100644
--- a/target/riscv/insn_trans/trans_rvp.c.inc
+++ b/target/riscv/insn_trans/trans_rvp.c.inc
@@ -217,3 +217,72 @@ GEN_RVP_R_OOL(scmplt8);
GEN_RVP_R_OOL(scmple8);
GEN_RVP_R_OOL(ucmplt8);
GEN_RVP_R_OOL(ucmple8);
+
+/* SIMD 16-bit Multiply Instructions */
+static void set_pair_regs(DisasContext *ctx, TCGv_i64 dst, int rd)
+{
+ TCGv t1, t2;
+
+ t1 = tcg_temp_new();
+ t2 = tcg_temp_new();
+
+ if (is_32bit(ctx)) {
+ TCGv_i32 lo, hi;
+
+ lo = tcg_temp_new_i32();
+ hi = tcg_temp_new_i32();
+ tcg_gen_extr_i64_i32(lo, hi, dst);
+
+ tcg_gen_ext_i32_tl(t1, lo);
+ tcg_gen_ext_i32_tl(t2, hi);
+
+ gen_set_gpr(rd, t1);
+ gen_set_gpr(rd + 1, t2);
+ tcg_temp_free_i32(lo);
+ tcg_temp_free_i32(hi);
+ } else {
+ tcg_gen_trunc_i64_tl(t1, dst);
+ gen_set_gpr(rd, t1);
+ }
+ tcg_temp_free(t1);
+ tcg_temp_free(t2);
+}
+
+static inline bool
+r_d64_ool(DisasContext *ctx, arg_r *a,
+ void (* fn)(TCGv_i64, TCGv_ptr, TCGv, TCGv))
+{
+ TCGv t1, t2;
+ TCGv_i64 t3;
+
+ if (!has_ext(ctx, RVP) || !ctx->ext_psfoperand) {
+ return false;
+ }
+
+ t1 = tcg_temp_new();
+ t2 = tcg_temp_new();
+ t3 = tcg_temp_new_i64();
+
+ gen_get_gpr(t1, a->rs1);
+ gen_get_gpr(t2, a->rs2);
+ fn(t3, cpu_env, t1, t2);
+ set_pair_regs(ctx, t3, a->rd);
+
+ tcg_temp_free(t1);
+ tcg_temp_free(t2);
+ tcg_temp_free_i64(t3);
+ return true;
+}
+
+#define GEN_RVP_R_D64_OOL(NAME) \
+static bool trans_##NAME(DisasContext *s, arg_r *a) \
+{ \
+ return r_d64_ool(s, a, gen_helper_##NAME); \
+}
+
+GEN_RVP_R_D64_OOL(smul16);
+GEN_RVP_R_D64_OOL(smulx16);
+GEN_RVP_R_D64_OOL(umul16);
+GEN_RVP_R_D64_OOL(umulx16);
+GEN_RVP_R_OOL(khm16);
+GEN_RVP_R_OOL(khmx16);
diff --git a/target/riscv/packed_helper.c b/target/riscv/packed_helper.c
index ff86e015e4..13fed2c4d1 100644
--- a/target/riscv/packed_helper.c
+++ b/target/riscv/packed_helper.c
@@ -723,3 +723,107 @@ static inline void do_ucmple8(CPURISCVState *env, void *vd, void *va,
}
RVPR(ucmple8, 1, 1);
+
+/* SIMD 16-bit Multiply Instructions */
+typedef void PackedFn3(CPURISCVState *, void *, void *, void *);
+static inline uint64_t rvpr64(CPURISCVState *env, target_ulong a,
+ target_ulong b, PackedFn3 *fn)
+{
+ uint64_t result;
+
+ fn(env, &result, &a, &b);
+ return result;
+}
+
+#define RVPR64(NAME) \
+uint64_t HELPER(NAME)(CPURISCVState *env, target_ulong a, \
+ target_ulong b) \
+{ \
+ return rvpr64(env, a, b, (PackedFn3 *)do_##NAME); \
+}
+
+static inline void do_smul16(CPURISCVState *env, void *vd, void *va, void *vb)
+{
+ int32_t *d = vd;
+ int16_t *a = va, *b = vb;
+ d[H4(0)] = (int32_t)a[H2(0)] * b[H2(0)];
+ d[H4(1)] = (int32_t)a[H2(1)] * b[H2(1)];
+}
+
+RVPR64(smul16);
+
+static inline void do_smulx16(CPURISCVState *env, void *vd, void *va, void *vb)
+{
+ int32_t *d = vd;
+ int16_t *a = va, *b = vb;
+ d[H4(0)] = (int32_t)a[H2(0)] * b[H2(1)];
+ d[H4(1)] = (int32_t)a[H2(1)] * b[H2(0)];
+}
+
+RVPR64(smulx16);
+
+static inline void do_umul16(CPURISCVState *env, void *vd, void *va, void *vb,
+ uint8_t i)
+{
+ uint32_t *d = vd;
+ uint16_t *a = va, *b = vb;
+ d[H4(0)] = (uint32_t)a[H2(0)] * b[H2(0)];
+ d[H4(1)] = (uint32_t)a[H2(1)] * b[H2(1)];
+}
+
+RVPR64(umul16);
+
+static inline void do_umulx16(CPURISCVState *env, void *vd, void *va, void *vb,
+ uint8_t i)
+{
+ uint32_t *d = vd;
+ uint16_t *a = va, *b = vb;
+ d[H4(0)] = (uint32_t)a[H2(0)] * b[H2(1)];
+ d[H4(1)] = (uint32_t)a[H2(1)] * b[H2(0)];
+}
+
+RVPR64(umulx16);
+
+static inline void do_khm16(CPURISCVState *env, void *vd, void *va,
+ void *vb, uint8_t i)
+{
+ int16_t *d = vd, *a = va, *b = vb;
+
+ if (a[i] == INT16_MIN && b[i] == INT16_MIN) {
+ env->vxsat = 1;
+ d[i] = INT16_MAX;
+ } else {
+ d[i] = (int32_t)a[i] * b[i] >> 15;
+ }
+}
+
+RVPR(khm16, 1, 2);
+
+static inline void do_khmx16(CPURISCVState *env, void *vd, void *va,
+ void *vb, uint8_t i)
+{
+ int16_t *d = vd, *a = va, *b = vb;
+
+ /*
+ * t[x] = ra.H[x] s* rb.H[y];
+ * rt.H[x] = SAT.Q15(t[x] s>> 15);
+ *
+ * (RV32: (x,y)=(1,0),(0,1),
+ * RV64: (x,y)=(3,2),(2,3),
+ * (1,0),(0,1)
+ */
+ if (a[H2(i)] == INT16_MIN && b[H2(i + 1)] == INT16_MIN) {
+ env->vxsat = 1;
+ d[H2(i)] = INT16_MAX;
+ } else {
+ d[H2(i)] = (int32_t)a[H2(i)] * b[H2(i + 1)] >> 15;
+ }
+ if (a[H2(i + 1)] == INT16_MIN && b[H2(i)] == INT16_MIN) {
+ env->vxsat = 1;
+ d[H2(i + 1)] = INT16_MAX;
+ } else {
+ d[H2(i + 1)] = (int32_t)a[H2(i + 1)] * b[H2(i)] >> 15;
+ }
+}
+
+RVPR(khmx16, 2, 2);
--
2.25.1
next prev parent reply other threads:[~2021-06-10 8:06 UTC|newest]
Thread overview: 44+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-06-10 7:58 [PATCH v2 00/37] target/riscv: support packed extension v0.9.4 LIU Zhiwei
2021-06-10 7:58 ` [PATCH v2 01/37] target/riscv: implementation-defined constant parameters LIU Zhiwei
2021-06-10 7:58 ` [PATCH v2 02/37] target/riscv: Make the vector helper functions public LIU Zhiwei
2021-06-10 7:58 ` [PATCH v2 03/37] target/riscv: 16-bit Addition & Subtraction Instructions LIU Zhiwei
2021-06-10 18:00 ` Richard Henderson
2021-06-10 7:58 ` [PATCH v2 04/37] target/riscv: 8-bit Addition & Subtraction Instruction LIU Zhiwei
2021-06-10 19:39 ` Richard Henderson
2021-06-11 4:36 ` LIU Zhiwei
2021-06-24 6:05 ` LIU Zhiwei
2021-06-10 7:58 ` [PATCH v2 05/37] target/riscv: SIMD 16-bit Shift Instructions LIU Zhiwei
2021-06-10 19:44 ` Richard Henderson
2021-06-10 7:58 ` [PATCH v2 06/37] target/riscv: SIMD 8-bit " LIU Zhiwei
2021-06-10 7:58 ` [PATCH v2 07/37] target/riscv: SIMD 16-bit Compare Instructions LIU Zhiwei
2021-06-10 7:58 ` [PATCH v2 08/37] target/riscv: SIMD 8-bit " LIU Zhiwei
2021-06-10 7:58 ` LIU Zhiwei [this message]
2021-06-10 7:58 ` [PATCH v2 10/37] target/riscv: SIMD 8-bit Multiply Instructions LIU Zhiwei
2021-06-10 7:58 ` [PATCH v2 11/37] target/riscv: SIMD 16-bit Miscellaneous Instructions LIU Zhiwei
2021-06-10 7:58 ` [PATCH v2 12/37] target/riscv: SIMD 8-bit " LIU Zhiwei
2021-06-10 7:58 ` [PATCH v2 13/37] target/riscv: 8-bit Unpacking Instructions LIU Zhiwei
2021-06-10 7:58 ` [PATCH v2 14/37] target/riscv: 16-bit Packing Instructions LIU Zhiwei
2021-06-10 7:58 ` [PATCH v2 15/37] target/riscv: Signed MSW 32x32 Multiply and Add Instructions LIU Zhiwei
2021-06-10 7:58 ` [PATCH v2 16/37] target/riscv: Signed MSW 32x16 " LIU Zhiwei
2021-06-10 7:58 ` [PATCH v2 17/37] target/riscv: Signed 16-bit Multiply 32-bit Add/Subtract Instructions LIU Zhiwei
2021-06-10 7:58 ` [PATCH v2 18/37] target/riscv: Signed 16-bit Multiply 64-bit " LIU Zhiwei
2021-06-10 7:58 ` [PATCH v2 19/37] target/riscv: Partial-SIMD Miscellaneous Instructions LIU Zhiwei
2021-06-10 7:58 ` [PATCH v2 20/37] target/riscv: 8-bit Multiply with 32-bit Add Instructions LIU Zhiwei
2021-06-10 7:58 ` [PATCH v2 21/37] target/riscv: 64-bit Add/Subtract Instructions LIU Zhiwei
2021-06-10 7:58 ` [PATCH v2 22/37] target/riscv: 32-bit Multiply " LIU Zhiwei
2021-06-10 7:58 ` [PATCH v2 23/37] target/riscv: Signed 16-bit Multiply with " LIU Zhiwei
2021-06-10 7:58 ` [PATCH v2 24/37] target/riscv: Non-SIMD Q15 saturation ALU Instructions LIU Zhiwei
2021-06-10 7:58 ` [PATCH v2 25/37] target/riscv: Non-SIMD Q31 " LIU Zhiwei
2021-06-10 7:58 ` [PATCH v2 26/37] target/riscv: 32-bit Computation Instructions LIU Zhiwei
2021-06-10 7:58 ` [PATCH v2 27/37] target/riscv: Non-SIMD Miscellaneous Instructions LIU Zhiwei
2021-06-10 7:58 ` [PATCH v2 28/37] target/riscv: RV64 Only SIMD 32-bit Add/Subtract Instructions LIU Zhiwei
2021-06-10 7:59 ` [PATCH v2 29/37] target/riscv: RV64 Only SIMD 32-bit Shift Instructions LIU Zhiwei
2021-06-10 7:59 ` [PATCH v2 30/37] target/riscv: RV64 Only SIMD 32-bit Miscellaneous Instructions LIU Zhiwei
2021-06-10 7:59 ` [PATCH v2 31/37] target/riscv: RV64 Only SIMD Q15 saturating Multiply Instructions LIU Zhiwei
2021-06-10 7:59 ` [PATCH v2 32/37] target/riscv: RV64 Only 32-bit " LIU Zhiwei
2021-06-10 7:59 ` [PATCH v2 33/37] target/riscv: RV64 Only 32-bit Multiply & Add Instructions LIU Zhiwei
2021-06-10 7:59 ` [PATCH v2 34/37] target/riscv: RV64 Only 32-bit Parallel " LIU Zhiwei
2021-06-10 7:59 ` [PATCH v2 35/37] target/riscv: RV64 Only Non-SIMD 32-bit Shift Instructions LIU Zhiwei
2021-06-10 7:59 ` [PATCH v2 36/37] target/riscv: RV64 Only 32-bit Packing Instructions LIU Zhiwei
2021-06-10 7:59 ` [PATCH v2 37/37] target/riscv: configure and turn on packed extension from command line LIU Zhiwei
2021-06-14 22:55 ` [PATCH v2 00/37] target/riscv: support packed extension v0.9.4 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=20210610075908.3305506-10-zhiwei_liu@c-sky.com \
--to=zhiwei_liu@c-sky.com \
--cc=Alistair.Francis@wdc.com \
--cc=bin.meng@windriver.com \
--cc=palmer@dabbelt.com \
--cc=qemu-devel@nongnu.org \
--cc=qemu-riscv@nongnu.org \
--cc=richard.henderson@linaro.org \
/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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).