From: LIU Zhiwei <zhiwei_liu@c-sky.com>
To: qemu-devel@nongnu.org
Cc: richard.henderson@linaro.org, LIU Zhiwei <zhiwei_liu@c-sky.com>,
qemu-riscv@nongnu.org, palmer@dabbelt.com, alistair23@gmail.com
Subject: [PATCH 22/38] target/riscv: 64-bit Add/Subtract Instructions
Date: Fri, 12 Feb 2021 23:02:40 +0800 [thread overview]
Message-ID: <20210212150256.885-23-zhiwei_liu@c-sky.com> (raw)
In-Reply-To: <20210212150256.885-1-zhiwei_liu@c-sky.com>
Signed-off-by: LIU Zhiwei <zhiwei_liu@c-sky.com>
---
target/riscv/helper.h | 11 ++
target/riscv/insn32.decode | 11 ++
target/riscv/insn_trans/trans_rvp.c.inc | 72 +++++++++++++
target/riscv/packed_helper.c | 132 ++++++++++++++++++++++++
4 files changed, 226 insertions(+)
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 0ddd07b305..cce4c8cbcc 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -1327,3 +1327,14 @@ DEF_HELPER_4(pbsada, tl, env, tl, tl, tl)
DEF_HELPER_4(smaqa, tl, env, tl, tl, tl)
DEF_HELPER_4(umaqa, tl, env, tl, tl, tl)
DEF_HELPER_4(smaqa_su, tl, env, tl, tl, tl)
+
+DEF_HELPER_3(add64, i64, env, i64, i64)
+DEF_HELPER_3(radd64, i64, env, i64, i64)
+DEF_HELPER_3(uradd64, i64, env, i64, i64)
+DEF_HELPER_3(kadd64, i64, env, i64, i64)
+DEF_HELPER_3(ukadd64, i64, env, i64, i64)
+DEF_HELPER_3(sub64, i64, env, i64, i64)
+DEF_HELPER_3(rsub64, i64, env, i64, i64)
+DEF_HELPER_3(ursub64, i64, env, i64, i64)
+DEF_HELPER_3(ksub64, i64, env, i64, i64)
+DEF_HELPER_3(uksub64, i64, env, i64, i64)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 6a50abca21..b52e1c1142 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -797,3 +797,14 @@ pbsada 1111111 ..... ..... 000 ..... 1111111 @r
smaqa 1100100 ..... ..... 000 ..... 1111111 @r
umaqa 1100110 ..... ..... 000 ..... 1111111 @r
smaqa_su 1100101 ..... ..... 000 ..... 1111111 @r
+
+add64 1100000 ..... ..... 001 ..... 1111111 @r
+radd64 1000000 ..... ..... 001 ..... 1111111 @r
+uradd64 1010000 ..... ..... 001 ..... 1111111 @r
+kadd64 1001000 ..... ..... 001 ..... 1111111 @r
+ukadd64 1011000 ..... ..... 001 ..... 1111111 @r
+sub64 1100001 ..... ..... 001 ..... 1111111 @r
+rsub64 1000001 ..... ..... 001 ..... 1111111 @r
+ursub64 1010001 ..... ..... 001 ..... 1111111 @r
+ksub64 1001001 ..... ..... 001 ..... 1111111 @r
+uksub64 1011001 ..... ..... 001 ..... 1111111 @r
diff --git a/target/riscv/insn_trans/trans_rvp.c.inc b/target/riscv/insn_trans/trans_rvp.c.inc
index 0877cd04b4..94e5e09425 100644
--- a/target/riscv/insn_trans/trans_rvp.c.inc
+++ b/target/riscv/insn_trans/trans_rvp.c.inc
@@ -670,3 +670,75 @@ GEN_RVP_R_ACC_OOL(pbsada);
GEN_RVP_R_ACC_OOL(smaqa);
GEN_RVP_R_ACC_OOL(umaqa);
GEN_RVP_R_ACC_OOL(smaqa_su);
+
+/*
+ *** 64-bit Profile Instructions
+ */
+/* 64-bit Addition & Subtraction Instructions */
+static bool
+r_d64_s64_s64_ool(DisasContext *ctx, arg_r *a,
+ void (* fn)(TCGv_i64, TCGv_ptr, TCGv_i64, TCGv_i64))
+{
+#ifdef TARGET_RISCV64
+ return r_ool(ctx, a, fn);
+#else
+ TCGv a0, a1, b0, b1, d0, d1;
+ TCGv_i64 src1, src2, dst;
+
+ if (!has_ext(ctx, RVP) || !ctx->ext_p64) {
+ return false;
+ }
+
+ src1 = tcg_temp_new_i64();
+ src2 = tcg_temp_new_i64();
+ dst = tcg_temp_new_i64();
+ a0 = tcg_temp_new_i32();
+ a1 = tcg_temp_new_i32();
+ b0 = tcg_temp_new_i32();
+ b1 = tcg_temp_new_i32();
+
+ gen_get_gpr(a0, a->rs1);
+ gen_get_gpr(a1, a->rs1 + 1);
+ tcg_gen_concat_i32_i64(src1, a0, a1);
+ gen_get_gpr(b0, a->rs2);
+ gen_get_gpr(b1, a->rs2 + 1);
+ tcg_gen_concat_i32_i64(src2, b0, b1);
+
+ fn(dst, cpu_env, src1, src2);
+
+ d0 = tcg_temp_new_i32();
+ d1 = tcg_temp_new_i32();
+ tcg_gen_extrl_i64_i32(d0, dst);
+ tcg_gen_extrh_i64_i32(d1, dst);
+ gen_set_gpr(a->rd, d0);
+ gen_set_gpr(a->rd + 1, d1);
+ tcg_temp_free_i32(d0);
+ tcg_temp_free_i32(d1);
+
+ tcg_temp_free_i64(src1);
+ tcg_temp_free_i64(src2);
+ tcg_temp_free_i64(dst);
+ tcg_temp_free_i32(a0);
+ tcg_temp_free_i32(a1);
+ tcg_temp_free_i32(b0);
+ tcg_temp_free_i32(b1);
+ return true;
+#endif
+}
+
+#define GEN_RVP_R_D64_S64_S64_OOL(NAME) \
+static bool trans_##NAME(DisasContext *s, arg_r *a) \
+{ \
+ return r_d64_s64_s64_ool(s, a, gen_helper_##NAME); \
+}
+
+GEN_RVP_R_D64_S64_S64_OOL(add64);
+GEN_RVP_R_D64_S64_S64_OOL(radd64);
+GEN_RVP_R_D64_S64_S64_OOL(uradd64);
+GEN_RVP_R_D64_S64_S64_OOL(kadd64);
+GEN_RVP_R_D64_S64_S64_OOL(ukadd64);
+GEN_RVP_R_D64_S64_S64_OOL(sub64);
+GEN_RVP_R_D64_S64_S64_OOL(rsub64);
+GEN_RVP_R_D64_S64_S64_OOL(ursub64);
+GEN_RVP_R_D64_S64_S64_OOL(ksub64);
+GEN_RVP_R_D64_S64_S64_OOL(uksub64);
diff --git a/target/riscv/packed_helper.c b/target/riscv/packed_helper.c
index 02a0f912e9..0629c5178b 100644
--- a/target/riscv/packed_helper.c
+++ b/target/riscv/packed_helper.c
@@ -2097,3 +2097,135 @@ static inline void do_smaqa_su(CPURISCVState *env, void *vd, void *va,
}
RVPR_ACC(smaqa_su, 1, 4);
+
+/*
+ *** 64-bit Profile Instructions
+ */
+/* 64-bit Addition & Subtraction Instructions */
+
+/* Define a common function to loop elements in packed register */
+static inline uint64_t
+rvpr64_64_64(CPURISCVState *env, uint64_t a, uint64_t b,
+ uint8_t step, uint8_t size, PackedFn3i *fn)
+{
+ int i, passes = sizeof(uint64_t) / size;
+ uint64_t result = 0;
+
+ for (i = 0; i < passes; i += step) {
+ fn(env, &result, &a, &b, i);
+ }
+ return result;
+}
+
+#define RVPR64_64_64(NAME, STEP, SIZE) \
+uint64_t HELPER(NAME)(CPURISCVState *env, uint64_t a, uint64_t b) \
+{ \
+ return rvpr64_64_64(env, a, b, STEP, SIZE, (PackedFn3i *)do_##NAME); \
+}
+
+static inline void do_add64(CPURISCVState *env, void *vd, void *va,
+ void *vb, uint8_t i)
+{
+ int64_t *d = vd, *a = va, *b = vb;
+ *d = *a + *b;
+}
+
+RVPR64_64_64(add64, 1, 8);
+
+static inline int64_t hadd64(int64_t a, int64_t b)
+{
+ int64_t res = a + b;
+ int64_t over = (res ^ a) & (res ^ b) & INT64_MIN;
+
+ /* With signed overflow, bit 64 is inverse of bit 63. */
+ return (res >> 1) ^ over;
+}
+
+static inline void do_radd64(CPURISCVState *env, void *vd, void *va,
+ void *vb, uint8_t i)
+{
+ int64_t *d = vd, *a = va, *b = vb;
+ *d = hadd64(*a, *b);
+}
+
+RVPR64_64_64(radd64, 1, 8);
+
+static inline uint64_t haddu64(uint64_t a, uint64_t b)
+{
+ uint64_t res = a + b;
+ bool over = res < a;
+
+ return over ? ((res >> 1) | INT64_MIN) : (res >> 1);
+}
+
+static inline void do_uradd64(CPURISCVState *env, void *vd, void *va,
+ void *vb, uint8_t i)
+{
+ uint64_t *d = vd, *a = va, *b = vb;
+ *d = haddu64(*a, *b);
+}
+
+RVPR64_64_64(uradd64, 1, 8);
+
+static inline void do_kadd64(CPURISCVState *env, void *vd, void *va,
+ void *vb, uint8_t i)
+{
+ int64_t *d = vd, *a = va, *b = vb;
+ *d = sadd64(env, 0, *a, *b);
+}
+
+RVPR64_64_64(kadd64, 1, 8);
+
+static inline void do_ukadd64(CPURISCVState *env, void *vd, void *va,
+ void *vb, uint8_t i)
+{
+ uint64_t *d = vd, *a = va, *b = vb;
+ *d = saddu64(env, 0, *a, *b);
+}
+
+RVPR64_64_64(ukadd64, 1, 8);
+
+static inline void do_sub64(CPURISCVState *env, void *vd, void *va,
+ void *vb, uint8_t i)
+{
+ int64_t *d = vd, *a = va, *b = vb;
+ *d = *a - *b;
+}
+
+RVPR64_64_64(sub64, 1, 8);
+
+static inline void do_rsub64(CPURISCVState *env, void *vd, void *va,
+ void *vb, uint8_t i)
+{
+ int64_t *d = vd, *a = va, *b = vb;
+ *d = hsub64(*a, *b);
+}
+
+RVPR64_64_64(rsub64, 1, 8);
+
+static inline void do_ursub64(CPURISCVState *env, void *vd, void *va,
+ void *vb, uint8_t i)
+{
+ uint64_t *d = vd, *a = va, *b = vb;
+ *d = hsubu64(*a, *b);
+}
+
+RVPR64_64_64(ursub64, 1, 8);
+
+static inline void do_ksub64(CPURISCVState *env, void *vd, void *va,
+ void *vb, uint8_t i)
+{
+ int64_t *d = vd, *a = va, *b = vb;
+ *d = ssub64(env, 0, *a, *b);
+}
+
+RVPR64_64_64(ksub64, 1, 8);
+
+static inline void do_uksub64(CPURISCVState *env, void *vd, void *va,
+ void *vb, uint8_t i)
+{
+ uint64_t *d = vd, *a = va, *b = vb;
+ *d = ssubu64(env, 0, *a, *b);
+}
+
+RVPR64_64_64(uksub64, 1, 8);
--
2.17.1
next prev parent reply other threads:[~2021-02-12 15:50 UTC|newest]
Thread overview: 75+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-02-12 15:02 [PATCH 00/38] target/riscv: support packed extension v0.9.2 LIU Zhiwei
2021-02-12 15:02 ` [PATCH 01/38] target/riscv: implementation-defined constant parameters LIU Zhiwei
2021-03-09 14:08 ` Alistair Francis
2021-02-12 15:02 ` [PATCH 02/38] target/riscv: Hoist vector functions LIU Zhiwei
2021-03-09 14:10 ` Alistair Francis
2021-02-12 15:02 ` [PATCH 03/38] target/riscv: Fixup saturate subtract function LIU Zhiwei
2021-02-12 18:52 ` Richard Henderson
2021-03-09 14:11 ` Alistair Francis
2021-02-12 15:02 ` [PATCH 04/38] target/riscv: 16-bit Addition & Subtraction Instructions LIU Zhiwei
2021-02-12 18:03 ` Richard Henderson
2021-02-18 8:39 ` LIU Zhiwei
2021-02-18 16:20 ` Richard Henderson
2021-02-12 19:02 ` Richard Henderson
2021-02-18 8:47 ` LIU Zhiwei
2021-02-18 16:21 ` Richard Henderson
2021-02-12 15:02 ` [PATCH 05/38] target/riscv: 8-bit Addition & Subtraction Instruction LIU Zhiwei
2021-03-15 21:22 ` Alistair Francis
2021-05-24 1:00 ` Palmer Dabbelt
2021-05-26 5:43 ` LIU Zhiwei
2021-05-26 6:15 ` Palmer Dabbelt
2021-02-12 15:02 ` [PATCH 06/38] target/riscv: SIMD 16-bit Shift Instructions LIU Zhiwei
2021-03-15 21:25 ` Alistair Francis
2021-03-16 2:40 ` LIU Zhiwei
2021-03-16 19:54 ` Alistair Francis
2021-03-17 2:30 ` LIU Zhiwei
2021-03-17 20:39 ` Alistair Francis
2021-02-12 15:02 ` [PATCH 07/38] target/riscv: SIMD 8-bit " LIU Zhiwei
2021-03-15 21:27 ` Alistair Francis
2021-05-24 4:46 ` Palmer Dabbelt
2021-02-12 15:02 ` [PATCH 08/38] target/riscv: SIMD 16-bit Compare Instructions LIU Zhiwei
2021-03-15 21:28 ` Alistair Francis
2021-05-26 5:30 ` Palmer Dabbelt
2021-05-26 5:31 ` Palmer Dabbelt
2021-02-12 15:02 ` [PATCH 09/38] target/riscv: SIMD 8-bit " LIU Zhiwei
2021-03-15 21:31 ` Alistair Francis
2021-02-12 15:02 ` [PATCH 10/38] target/riscv: SIMD 16-bit Multiply Instructions LIU Zhiwei
2021-02-12 15:02 ` [PATCH 11/38] target/riscv: SIMD 8-bit " LIU Zhiwei
2021-03-15 21:33 ` Alistair Francis
2021-02-12 15:02 ` [PATCH 12/38] target/riscv: SIMD 16-bit Miscellaneous Instructions LIU Zhiwei
2021-03-15 21:35 ` Alistair Francis
2021-02-12 15:02 ` [PATCH 13/38] target/riscv: SIMD 8-bit " LIU Zhiwei
2021-03-16 14:38 ` Alistair Francis
2021-02-12 15:02 ` [PATCH 14/38] target/riscv: 8-bit Unpacking Instructions LIU Zhiwei
2021-03-16 14:40 ` Alistair Francis
2021-02-12 15:02 ` [PATCH 15/38] target/riscv: 16-bit Packing Instructions LIU Zhiwei
2021-03-16 14:42 ` Alistair Francis
2021-02-12 15:02 ` [PATCH 16/38] target/riscv: Signed MSW 32x32 Multiply and Add Instructions LIU Zhiwei
2021-02-12 15:02 ` [PATCH 17/38] target/riscv: Signed MSW 32x16 " LIU Zhiwei
2021-03-16 16:01 ` Alistair Francis
2021-02-12 15:02 ` [PATCH 18/38] target/riscv: Signed 16-bit Multiply 32-bit Add/Subtract Instructions LIU Zhiwei
2021-02-12 15:02 ` [PATCH 19/38] target/riscv: Signed 16-bit Multiply 64-bit " LIU Zhiwei
2021-02-12 15:02 ` [PATCH 20/38] target/riscv: Partial-SIMD Miscellaneous Instructions LIU Zhiwei
2021-03-16 19:44 ` Alistair Francis
2021-02-12 15:02 ` [PATCH 21/38] target/riscv: 8-bit Multiply with 32-bit Add Instructions LIU Zhiwei
2021-02-12 15:02 ` LIU Zhiwei [this message]
2021-02-12 15:02 ` [PATCH 23/38] target/riscv: 32-bit Multiply 64-bit Add/Subtract Instructions LIU Zhiwei
2021-02-12 15:02 ` [PATCH 24/38] target/riscv: Signed 16-bit Multiply with " LIU Zhiwei
2021-02-12 15:02 ` [PATCH 25/38] target/riscv: Non-SIMD Q15 saturation ALU Instructions LIU Zhiwei
2021-02-12 15:02 ` [PATCH 26/38] target/riscv: Non-SIMD Q31 " LIU Zhiwei
2021-02-12 15:02 ` [PATCH 27/38] target/riscv: 32-bit Computation Instructions LIU Zhiwei
2021-02-12 15:02 ` [PATCH 28/38] target/riscv: Non-SIMD Miscellaneous Instructions LIU Zhiwei
2021-02-12 15:02 ` [PATCH 29/38] target/riscv: RV64 Only SIMD 32-bit Add/Subtract Instructions LIU Zhiwei
2021-02-12 15:02 ` [PATCH 30/38] target/riscv: RV64 Only SIMD 32-bit Shift Instructions LIU Zhiwei
2021-02-12 15:02 ` [PATCH 31/38] target/riscv: RV64 Only SIMD 32-bit Miscellaneous Instructions LIU Zhiwei
2021-02-12 15:02 ` [PATCH 32/38] target/riscv: RV64 Only SIMD Q15 saturating Multiply Instructions LIU Zhiwei
2021-02-12 15:02 ` [PATCH 33/38] target/riscv: RV64 Only 32-bit " LIU Zhiwei
2021-02-12 15:02 ` [PATCH 34/38] target/riscv: RV64 Only 32-bit Multiply & Add Instructions LIU Zhiwei
2021-02-12 15:02 ` [PATCH 35/38] target/riscv: RV64 Only 32-bit Parallel " LIU Zhiwei
2021-02-12 15:02 ` [PATCH 36/38] target/riscv: RV64 Only Non-SIMD 32-bit Shift Instructions LIU Zhiwei
2021-02-12 15:02 ` [PATCH 37/38] target/riscv: RV64 Only 32-bit Packing Instructions LIU Zhiwei
2021-02-12 15:02 ` [PATCH 38/38] target/riscv: configure and turn on packed extension from command line LIU Zhiwei
2021-03-05 6:14 ` [PATCH 00/38] target/riscv: support packed extension v0.9.2 LIU Zhiwei
2021-04-13 3:27 ` LIU Zhiwei
2021-04-15 4:46 ` Alistair Francis
2021-04-15 5:50 ` LIU Zhiwei
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=20210212150256.885-23-zhiwei_liu@c-sky.com \
--to=zhiwei_liu@c-sky.com \
--cc=alistair23@gmail.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 NNTP newsgroup(s).