From: Alistair Francis <alistair23@gmail.com>
To: LIU Zhiwei <zhiwei_liu@c-sky.com>
Cc: Richard Henderson <richard.henderson@linaro.org>,
Palmer Dabbelt <palmer@dabbelt.com>,
"open list:RISC-V" <qemu-riscv@nongnu.org>,
"qemu-devel@nongnu.org Developers" <qemu-devel@nongnu.org>
Subject: Re: [PATCH 06/38] target/riscv: SIMD 16-bit Shift Instructions
Date: Mon, 15 Mar 2021 17:25:22 -0400 [thread overview]
Message-ID: <CAKmqyKP+=knMPnOtgQq477_=dwswG3TQ+xBBPULnvLma2HmsdQ@mail.gmail.com> (raw)
In-Reply-To: <20210212150256.885-7-zhiwei_liu@c-sky.com>
On Fri, Feb 12, 2021 at 10:16 AM LIU Zhiwei <zhiwei_liu@c-sky.com> wrote:
>
> Signed-off-by: LIU Zhiwei <zhiwei_liu@c-sky.com>
> ---
> target/riscv/helper.h | 9 ++
> target/riscv/insn32.decode | 17 ++++
> target/riscv/insn_trans/trans_rvp.c.inc | 115 ++++++++++++++++++++++++
> target/riscv/packed_helper.c | 104 +++++++++++++++++++++
> 4 files changed, 245 insertions(+)
>
> diff --git a/target/riscv/helper.h b/target/riscv/helper.h
> index a69a6b4e84..20bf400ac2 100644
> --- a/target/riscv/helper.h
> +++ b/target/riscv/helper.h
> @@ -1184,3 +1184,12 @@ DEF_HELPER_3(rsub8, tl, env, tl, tl)
> DEF_HELPER_3(ursub8, tl, env, tl, tl)
> DEF_HELPER_3(ksub8, tl, env, tl, tl)
> DEF_HELPER_3(uksub8, tl, env, tl, tl)
> +
> +DEF_HELPER_3(sra16, tl, env, tl, tl)
> +DEF_HELPER_3(sra16_u, tl, env, tl, tl)
> +DEF_HELPER_3(srl16, tl, env, tl, tl)
> +DEF_HELPER_3(srl16_u, tl, env, tl, tl)
> +DEF_HELPER_3(sll16, tl, env, tl, tl)
> +DEF_HELPER_3(ksll16, tl, env, tl, tl)
> +DEF_HELPER_3(kslra16, tl, env, tl, tl)
> +DEF_HELPER_3(kslra16_u, tl, env, tl, tl)
> diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
> index 358dd1fa10..6f053bfeb7 100644
> --- a/target/riscv/insn32.decode
> +++ b/target/riscv/insn32.decode
> @@ -23,6 +23,7 @@
> %rd 7:5
>
> %sh10 20:10
> +%sh4 20:4
> %csr 20:12
> %rm 12:3
> %nf 29:3 !function=ex_plus_1
> @@ -59,6 +60,7 @@
> @j .................... ..... ....... &j imm=%imm_j %rd
>
> @sh ...... ...... ..... ... ..... ....... &shift shamt=%sh10 %rs1 %rd
> +@sh4 ...... ...... ..... ... ..... ....... &shift shamt=%sh4 %rs1 %rd
> @csr ............ ..... ... ..... ....... %csr %rs1 %rd
>
> @atom_ld ..... aq:1 rl:1 ..... ........ ..... ....... &atomic rs2=0 %rs1 %rd
> @@ -635,3 +637,18 @@ rsub8 0000101 ..... ..... 000 ..... 1111111 @r
> ursub8 0010101 ..... ..... 000 ..... 1111111 @r
> ksub8 0001101 ..... ..... 000 ..... 1111111 @r
> uksub8 0011101 ..... ..... 000 ..... 1111111 @r
> +
> +sra16 0101000 ..... ..... 000 ..... 1111111 @r
> +sra16_u 0110000 ..... ..... 000 ..... 1111111 @r
> +srai16 0111000 0.... ..... 000 ..... 1111111 @sh4
> +srai16_u 0111000 1.... ..... 000 ..... 1111111 @sh4
> +srl16 0101001 ..... ..... 000 ..... 1111111 @r
> +srl16_u 0110001 ..... ..... 000 ..... 1111111 @r
> +srli16 0111001 0.... ..... 000 ..... 1111111 @sh4
> +srli16_u 0111001 1.... ..... 000 ..... 1111111 @sh4
> +sll16 0101010 ..... ..... 000 ..... 1111111 @r
> +slli16 0111010 0.... ..... 000 ..... 1111111 @sh4
> +ksll16 0110010 ..... ..... 000 ..... 1111111 @r
> +kslli16 0111010 1.... ..... 000 ..... 1111111 @sh4
> +kslra16 0101011 ..... ..... 000 ..... 1111111 @r
> +kslra16_u 0110011 ..... ..... 000 ..... 1111111 @r
> diff --git a/target/riscv/insn_trans/trans_rvp.c.inc b/target/riscv/insn_trans/trans_rvp.c.inc
> index 109f560ec9..848edab7e5 100644
> --- a/target/riscv/insn_trans/trans_rvp.c.inc
> +++ b/target/riscv/insn_trans/trans_rvp.c.inc
> @@ -238,3 +238,118 @@ GEN_RVP_R_OOL(rsub8);
> GEN_RVP_R_OOL(ursub8);
> GEN_RVP_R_OOL(ksub8);
> GEN_RVP_R_OOL(uksub8);
> +
> +/* 16-bit Shift Instructions */
> +static bool rvp_shift_ool(DisasContext *ctx, arg_r *a,
> + gen_helper_rvp_r *fn, target_ulong mask)
> +{
> + TCGv src1, src2, dst;
> +
> + src1 = tcg_temp_new();
> + src2 = tcg_temp_new();
> + dst = tcg_temp_new();
> +
> + gen_get_gpr(src1, a->rs1);
> + gen_get_gpr(src2, a->rs2);
> + tcg_gen_andi_tl(src2, src2, mask);
> +
> + fn(dst, cpu_env, src1, src2);
> + gen_set_gpr(a->rd, dst);
> +
> + tcg_temp_free(src1);
> + tcg_temp_free(src2);
> + tcg_temp_free(dst);
> + return true;
> +}
> +
> +typedef void GenGvecShift(unsigned, uint32_t, uint32_t, TCGv_i32,
> + uint32_t, uint32_t);
> +static inline bool
> +rvp_shift(DisasContext *ctx, arg_r *a, uint8_t vece,
> + GenGvecShift *f64, gen_helper_rvp_r *fn,
> + uint8_t mask)
> +{
> + if (!has_ext(ctx, RVP)) {
> + return false;
> + }
> +
> +#ifdef TARGET_RISCV64
Hmm....
I don't want to add any more #defines on the RISC-V xlen. We are
trying to make the QEMU RISC-V implementation xlen independent.
Can you use `riscv_cpu_is_32bit(env)` instead, here are everywhere
else you add a #define TARGET... ?
Alistair
> + if (a->rd && a->rs1 && a->rs2) {
> + TCGv_i32 shift = tcg_temp_new_i32();
> + tcg_gen_extrl_i64_i32(shift, cpu_gpr[a->rs2]);
> + tcg_gen_andi_i32(shift, shift, mask);
> + f64(vece, offsetof(CPURISCVState, gpr[a->rd]),
> + offsetof(CPURISCVState, gpr[a->rs1]),
> + shift, 8, 8);
> + tcg_temp_free_i32(shift);
> + return true;
> + }
> +#endif
> + return rvp_shift_ool(ctx, a, fn, mask);
> +}
> +
> +#define GEN_RVP_SHIFT(NAME, GVEC, VECE) \
> +static bool trans_##NAME(DisasContext *s, arg_r *a) \
> +{ \
> + return rvp_shift(s, a, VECE, GVEC, gen_helper_##NAME, \
> + (8 << VECE) - 1); \
> +}
> +
> +GEN_RVP_SHIFT(sra16, tcg_gen_gvec_sars, 1);
> +GEN_RVP_SHIFT(srl16, tcg_gen_gvec_shrs, 1);
> +GEN_RVP_SHIFT(sll16, tcg_gen_gvec_shls, 1);
> +GEN_RVP_R_OOL(sra16_u);
> +GEN_RVP_R_OOL(srl16_u);
> +GEN_RVP_R_OOL(ksll16);
> +GEN_RVP_R_OOL(kslra16);
> +GEN_RVP_R_OOL(kslra16_u);
> +
> +static bool rvp_shifti_ool(DisasContext *ctx, arg_shift *a,
> + gen_helper_rvp_r *fn)
> +{
> + TCGv src1, dst, shift;
> +
> + src1 = tcg_temp_new();
> + dst = tcg_temp_new();
> +
> + gen_get_gpr(src1, a->rs1);
> + shift = tcg_const_tl(a->shamt);
> + fn(dst, cpu_env, src1, shift);
> + gen_set_gpr(a->rd, dst);
> +
> + tcg_temp_free(src1);
> + tcg_temp_free(dst);
> + tcg_temp_free(shift);
> + return true;
> +}
> +
> +static inline bool
> +rvp_shifti(DisasContext *ctx, arg_shift *a,
> + void (* f64)(TCGv_i64, TCGv_i64, int64_t),
> + gen_helper_rvp_r *fn)
> +{
> + if (!has_ext(ctx, RVP)) {
> + return false;
> + }
> +
> +#ifdef TARGET_RISCV64
> + if (a->rd && a->rs1 && f64) {
> + f64(cpu_gpr[a->rd], cpu_gpr[a->rs1], a->shamt);
> + return true;
> + }
> +#endif
> + return rvp_shifti_ool(ctx, a, fn);
> +}
> +
> +#define GEN_RVP_SHIFTI(NAME, OP, GVEC) \
> +static bool trans_##NAME(DisasContext *s, arg_shift *a) \
> +{ \
> + return rvp_shifti(s, a, GVEC, gen_helper_##OP); \
> +}
> +
> +GEN_RVP_SHIFTI(srai16, sra16, tcg_gen_vec_sar16i_i64);
> +GEN_RVP_SHIFTI(srli16, srl16, tcg_gen_vec_shr16i_i64);
> +GEN_RVP_SHIFTI(slli16, sll16, tcg_gen_vec_shl16i_i64);
> +GEN_RVP_SHIFTI(srai16_u, sra16_u, NULL);
> +GEN_RVP_SHIFTI(srli16_u, srl16_u, NULL);
> +GEN_RVP_SHIFTI(kslli16, ksll16, NULL);
> diff --git a/target/riscv/packed_helper.c b/target/riscv/packed_helper.c
> index 62db072204..7e31c2fe46 100644
> --- a/target/riscv/packed_helper.c
> +++ b/target/riscv/packed_helper.c
> @@ -425,3 +425,107 @@ static inline void do_uksub8(CPURISCVState *env, void *vd, void *va,
> }
>
> RVPR(uksub8, 1, 1);
> +
> +/* 16-bit Shift Instructions */
> +static inline void do_sra16(CPURISCVState *env, void *vd, void *va,
> + void *vb, uint8_t i)
> +{
> + int16_t *d = vd, *a = va;
> + uint8_t shift = *(uint8_t *)vb & 0xf;
> + d[i] = a[i] >> shift;
> +}
> +
> +RVPR(sra16, 1, 2);
> +
> +static inline void do_srl16(CPURISCVState *env, void *vd, void *va,
> + void *vb, uint8_t i)
> +{
> + uint16_t *d = vd, *a = va;
> + uint8_t shift = *(uint8_t *)vb & 0xf;
> + d[i] = a[i] >> shift;
> +}
> +
> +RVPR(srl16, 1, 2);
> +
> +static inline void do_sll16(CPURISCVState *env, void *vd, void *va,
> + void *vb, uint8_t i)
> +{
> + uint16_t *d = vd, *a = va;
> + uint8_t shift = *(uint8_t *)vb & 0xf;
> + d[i] = a[i] << shift;
> +}
> +
> +RVPR(sll16, 1, 2);
> +
> +static inline void do_sra16_u(CPURISCVState *env, void *vd, void *va,
> + void *vb, uint8_t i)
> +{
> + int16_t *d = vd, *a = va;
> + uint8_t shift = *(uint8_t *)vb & 0xf;
> +
> + d[i] = vssra16(env, 0, a[i], shift);
> +}
> +
> +RVPR(sra16_u, 1, 2);
> +
> +static inline void do_srl16_u(CPURISCVState *env, void *vd, void *va,
> + void *vb, uint8_t i)
> +{
> + uint16_t *d = vd, *a = va;
> + uint8_t shift = *(uint8_t *)vb & 0xf;
> +
> + d[i] = vssrl16(env, 0, a[i], shift);
> +}
> +
> +RVPR(srl16_u, 1, 2);
> +
> +static inline void do_ksll16(CPURISCVState *env, void *vd, void *va,
> + void *vb, uint8_t i)
> +{
> + int16_t *d = vd, *a = va, result;
> + uint8_t shift = *(uint8_t *)vb & 0xf;
> +
> + result = a[i] << shift;
> + if (shift > (clrsb32(a[i]) - 16)) {
> + env->vxsat = 0x1;
> + d[i] = (a[i] & INT16_MIN) ? INT16_MIN : INT16_MAX;
> + } else {
> + d[i] = result;
> + }
> +}
> +
> +RVPR(ksll16, 1, 2);
> +
> +static inline void do_kslra16(CPURISCVState *env, void *vd, void *va,
> + void *vb, uint8_t i)
> +{
> + int16_t *d = vd, *a = va;
> + int32_t shift = sextract32((*(target_ulong *)vb), 0, 5);
> +
> + if (shift >= 0) {
> + do_ksll16(env, vd, va, vb, i);
> + } else {
> + shift = -shift;
> + shift = (shift == 16) ? 15 : shift;
> + d[i] = a[i] >> shift;
> + }
> +}
> +
> +RVPR(kslra16, 1, 2);
> +
> +static inline void do_kslra16_u(CPURISCVState *env, void *vd, void *va,
> + void *vb, uint8_t i)
> +{
> + int16_t *d = vd, *a = va;
> + int32_t shift = sextract32((*(uint32_t *)vb), 0, 5);
> +
> + if (shift >= 0) {
> + do_ksll16(env, vd, va, vb, i);
> + } else {
> + shift = -shift;
> + shift = (shift == 16) ? 15 : shift;
> + d[i] = vssra16(env, 0, a[i], shift);
> + }
> +}
> +
> +RVPR(kslra16_u, 1, 2);
> --
> 2.17.1
>
next prev parent reply other threads:[~2021-03-15 21:28 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 [this message]
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 ` [PATCH 22/38] target/riscv: 64-bit Add/Subtract Instructions LIU Zhiwei
2021-02-12 15:02 ` [PATCH 23/38] target/riscv: 32-bit Multiply " 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='CAKmqyKP+=knMPnOtgQq477_=dwswG3TQ+xBBPULnvLma2HmsdQ@mail.gmail.com' \
--to=alistair23@gmail.com \
--cc=palmer@dabbelt.com \
--cc=qemu-devel@nongnu.org \
--cc=qemu-riscv@nongnu.org \
--cc=richard.henderson@linaro.org \
--cc=zhiwei_liu@c-sky.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
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).