[v8,27/62] target/riscv: vector widening saturating scaled multiply-add

Message ID	20200521094413.10425-28-zhiwei_liu@c-sky.com
State	New
Headers	show Return-Path: <SRS0=QiA4=7D=nongnu.org=qemu-devel-bounces+qemu-devel=archiver.kernel.org@kernel.org> DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 83E4C204EC From: LIU Zhiwei <zhiwei_liu@c-sky.com> To: qemu-devel@nongnu.org, qemu-riscv@nongnu.org Subject: [PATCH v8 27/62] target/riscv: vector widening saturating scaled multiply-add Date: Thu, 21 May 2020 17:43:38 +0800 Message-Id: <20200521094413.10425-28-zhiwei_liu@c-sky.com> In-Reply-To: <20200521094413.10425-1-zhiwei_liu@c-sky.com> References: <20200521094413.10425-1-zhiwei_liu@c-sky.com> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Received-SPF: none client-ip=121.197.200.217; envelope-from=zhiwei_liu@c-sky.com; helo=smtp2200-217.mail.aliyun.com Precedence: list Cc: richard.henderson@linaro.org, wxy194768@alibaba-inc.com, wenmeng_zhang@c-sky.com, alistair.francis@wdc.com, palmer@dabbelt.com, LIU Zhiwei <zhiwei_liu@c-sky.com> Errors-To: qemu-devel-bounces+qemu-devel=archiver.kernel.org@nongnu.org Sender: "Qemu-devel" <qemu-devel-bounces+qemu-devel=archiver.kernel.org@nongnu.org>
Series	target/riscv: support vector extension v0.7.1 \| expand [v8,00/62] target/riscv: support vector extension v0.7.1 [v8,02/62] target/riscv: implementation-defined constant parameters [v8,03/62] target/riscv: support vector extension csr [v8,04/62] target/riscv: add vector configure instruction [v8,05/62] target/riscv: add an internals.h header [v8,06/62] target/riscv: add vector stride load and store instructions [v8,09/62] target/riscv: add vector amo operations [v8,11/62] target/riscv: vector widening integer add and subtract [v8,12/62] target/riscv: vector integer add-with-carry / subtract-with-borrow instructions [v8,14/62] target/riscv: vector single-width bit shift instructions [v8,17/62] target/riscv: vector integer min/max instructions [v8,18/62] target/riscv: vector single-width integer multiply instructions [v8,19/62] target/riscv: vector integer divide instructions [v8,21/62] target/riscv: vector single-width integer multiply-add instructions [v8,22/62] target/riscv: vector widening integer multiply-add instructions [v8,23/62] target/riscv: vector integer merge and move instructions [v8,25/62] target/riscv: vector single-width averaging add and subtract [v8,26/62] target/riscv: vector single-width fractional multiply with rounding and saturation [v8,27/62] target/riscv: vector widening saturating scaled multiply-add [v8,29/62] target/riscv: vector narrowing fixed-point clip instructions [v8,30/62] target/riscv: Update fp_status when float rounding mode changes [v8,32/62] target/riscv: vector widening floating-point add/subtract instructions [v8,34/62] target/riscv: vector widening floating-point multiply [v8,36/62] target/riscv: vector widening floating-point fused multiply-add instructions [v8,38/62] target/riscv: vector floating-point min/max instructions [v8,40/62] target/riscv: vector floating-point compare instructions [v8,45/62] target/riscv: narrowing floating-point/integer type-convert instructions [v8,46/62] target/riscv: vector single-width integer reduction instructions [v8,49/62] target/riscv: vector widening floating-point reduction instructions [v8,51/62] target/riscv: vector mask population count vmpopc [v8,52/62] target/riscv: vmfirst find-first-set mask bit [v8,55/62] target/riscv: vector element index instruction [v8,57/62] target/riscv: integer scalar move instruction [v8,58/62] target/riscv: floating-point scalar move instructions [v8,60/62] target/riscv: vector register gather instruction [v8,62/62] target/riscv: configure and turn on vector extension from command line

diff --git a/target/riscv/helper.h b/target/riscv/helper.h index e6cae1b59c..eb383787a2 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -745,3 +745,25 @@ 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) + +DEF_HELPER_6(vwsmaccu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsmaccu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsmaccu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsmacc_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsmacc_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsmacc_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsmaccsu_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsmaccsu_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsmaccsu_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vwsmaccu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsmaccu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsmaccu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsmacc_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsmacc_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsmacc_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsmaccsu_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsmaccsu_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsmaccsu_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsmaccus_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsmaccus_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vwsmaccus_vx_w, void, ptr, ptr, tl, ptr, env, i32) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index 633f782fbf..2e0e66bdfa 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -424,6 +424,13 @@ 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 +vwsmaccu_vv 111100 . ..... ..... 000 ..... 1010111 @r_vm +vwsmaccu_vx 111100 . ..... ..... 100 ..... 1010111 @r_vm +vwsmacc_vv 111101 . ..... ..... 000 ..... 1010111 @r_vm +vwsmacc_vx 111101 . ..... ..... 100 ..... 1010111 @r_vm +vwsmaccsu_vv 111110 . ..... ..... 000 ..... 1010111 @r_vm +vwsmaccsu_vx 111110 . ..... ..... 100 ..... 1010111 @r_vm +vwsmaccus_vx 111111 . ..... ..... 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 c17f0a6aae..5615915377 100644 --- a/target/riscv/insn_trans/trans_rvv.inc.c +++ b/target/riscv/insn_trans/trans_rvv.inc.c @@ -1758,3 +1758,12 @@ 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) + +/* Vector Widening Saturating Scaled Multiply-Add */ +GEN_OPIVV_WIDEN_TRANS(vwsmaccu_vv, opivv_widen_check) +GEN_OPIVV_WIDEN_TRANS(vwsmacc_vv, opivv_widen_check) +GEN_OPIVV_WIDEN_TRANS(vwsmaccsu_vv, opivv_widen_check) +GEN_OPIVX_WIDEN_TRANS(vwsmaccu_vx) +GEN_OPIVX_WIDEN_TRANS(vwsmacc_vx) +GEN_OPIVX_WIDEN_TRANS(vwsmaccsu_vx) +GEN_OPIVX_WIDEN_TRANS(vwsmaccus_vx) diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index 23868fb1b2..b9c1cf5237 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -2703,3 +2703,208 @@ GEN_VEXT_VX_RM(vsmul_vx_b, 1, 1, clearb) GEN_VEXT_VX_RM(vsmul_vx_h, 2, 2, clearh) GEN_VEXT_VX_RM(vsmul_vx_w, 4, 4, clearl) GEN_VEXT_VX_RM(vsmul_vx_d, 8, 8, clearq) + +/* Vector Widening Saturating Scaled Multiply-Add */ +static inline uint16_t +vwsmaccu8(CPURISCVState *env, int vxrm, uint8_t a, uint8_t b, + uint16_t c) +{ + uint8_t round; + uint16_t res = (uint16_t)a * b; + + round = get_round(vxrm, res, 4); + res = (res >> 4) + round; + return saddu16(env, vxrm, c, res); +} + +static inline uint32_t +vwsmaccu16(CPURISCVState *env, int vxrm, uint16_t a, uint16_t b, + uint32_t c) +{ + uint8_t round; + uint32_t res = (uint32_t)a * b; + + round = get_round(vxrm, res, 8); + res = (res >> 8) + round; + return saddu32(env, vxrm, c, res); +} + +static inline uint64_t +vwsmaccu32(CPURISCVState *env, int vxrm, uint32_t a, uint32_t b, + uint64_t c) +{ + uint8_t round; + uint64_t res = (uint64_t)a * b; + + round = get_round(vxrm, res, 16); + res = (res >> 16) + round; + return saddu64(env, vxrm, c, res); +} + +#define OPIVV3_RM(NAME, TD, T1, T2, TX1, TX2, HD, HS1, HS2, OP) \ +static inline void \ +do_##NAME(void *vd, void *vs1, void *vs2, int i, \ + CPURISCVState *env, int vxrm) \ +{ \ + TX1 s1 = *((T1 *)vs1 + HS1(i)); \ + TX2 s2 = *((T2 *)vs2 + HS2(i)); \ + TD d = *((TD *)vd + HD(i)); \ + *((TD *)vd + HD(i)) = OP(env, vxrm, s2, s1, d); \ +} + +RVVCALL(OPIVV3_RM, vwsmaccu_vv_b, WOP_UUU_B, H2, H1, H1, vwsmaccu8) +RVVCALL(OPIVV3_RM, vwsmaccu_vv_h, WOP_UUU_H, H4, H2, H2, vwsmaccu16) +RVVCALL(OPIVV3_RM, vwsmaccu_vv_w, WOP_UUU_W, H8, H4, H4, vwsmaccu32) +GEN_VEXT_VV_RM(vwsmaccu_vv_b, 1, 2, clearh) +GEN_VEXT_VV_RM(vwsmaccu_vv_h, 2, 4, clearl) +GEN_VEXT_VV_RM(vwsmaccu_vv_w, 4, 8, clearq) + +#define OPIVX3_RM(NAME, TD, T1, T2, TX1, TX2, HD, HS2, OP) \ +static inline void \ +do_##NAME(void *vd, target_long s1, void *vs2, int i, \ + CPURISCVState *env, int vxrm) \ +{ \ + TX2 s2 = *((T2 *)vs2 + HS2(i)); \ + TD d = *((TD *)vd + HD(i)); \ + *((TD *)vd + HD(i)) = OP(env, vxrm, s2, (TX1)(T1)s1, d); \ +} + +RVVCALL(OPIVX3_RM, vwsmaccu_vx_b, WOP_UUU_B, H2, H1, vwsmaccu8) +RVVCALL(OPIVX3_RM, vwsmaccu_vx_h, WOP_UUU_H, H4, H2, vwsmaccu16) +RVVCALL(OPIVX3_RM, vwsmaccu_vx_w, WOP_UUU_W, H8, H4, vwsmaccu32) +GEN_VEXT_VX_RM(vwsmaccu_vx_b, 1, 2, clearh) +GEN_VEXT_VX_RM(vwsmaccu_vx_h, 2, 4, clearl) +GEN_VEXT_VX_RM(vwsmaccu_vx_w, 4, 8, clearq) + +static inline int16_t +vwsmacc8(CPURISCVState *env, int vxrm, int8_t a, int8_t b, int16_t c) +{ + uint8_t round; + int16_t res = (int16_t)a * b; + + round = get_round(vxrm, res, 4); + res = (res >> 4) + round; + return sadd16(env, vxrm, c, res); +} + +static inline int32_t +vwsmacc16(CPURISCVState *env, int vxrm, int16_t a, int16_t b, int32_t c) +{ + uint8_t round; + int32_t res = (int32_t)a * b; + + round = get_round(vxrm, res, 8); + res = (res >> 8) + round; + return sadd32(env, vxrm, c, res); + +} + +static inline int64_t +vwsmacc32(CPURISCVState *env, int vxrm, int32_t a, int32_t b, int64_t c) +{ + uint8_t round; + int64_t res = (int64_t)a * b; + + round = get_round(vxrm, res, 16); + res = (res >> 16) + round; + return sadd64(env, vxrm, c, res); +} + +RVVCALL(OPIVV3_RM, vwsmacc_vv_b, WOP_SSS_B, H2, H1, H1, vwsmacc8) +RVVCALL(OPIVV3_RM, vwsmacc_vv_h, WOP_SSS_H, H4, H2, H2, vwsmacc16) +RVVCALL(OPIVV3_RM, vwsmacc_vv_w, WOP_SSS_W, H8, H4, H4, vwsmacc32) +GEN_VEXT_VV_RM(vwsmacc_vv_b, 1, 2, clearh) +GEN_VEXT_VV_RM(vwsmacc_vv_h, 2, 4, clearl) +GEN_VEXT_VV_RM(vwsmacc_vv_w, 4, 8, clearq) +RVVCALL(OPIVX3_RM, vwsmacc_vx_b, WOP_SSS_B, H2, H1, vwsmacc8) +RVVCALL(OPIVX3_RM, vwsmacc_vx_h, WOP_SSS_H, H4, H2, vwsmacc16) +RVVCALL(OPIVX3_RM, vwsmacc_vx_w, WOP_SSS_W, H8, H4, vwsmacc32) +GEN_VEXT_VX_RM(vwsmacc_vx_b, 1, 2, clearh) +GEN_VEXT_VX_RM(vwsmacc_vx_h, 2, 4, clearl) +GEN_VEXT_VX_RM(vwsmacc_vx_w, 4, 8, clearq) + +static inline int16_t +vwsmaccsu8(CPURISCVState *env, int vxrm, uint8_t a, int8_t b, int16_t c) +{ + uint8_t round; + int16_t res = a * (int16_t)b; + + round = get_round(vxrm, res, 4); + res = (res >> 4) + round; + return ssub16(env, vxrm, c, res); +} + +static inline int32_t +vwsmaccsu16(CPURISCVState *env, int vxrm, uint16_t a, int16_t b, uint32_t c) +{ + uint8_t round; + int32_t res = a * (int32_t)b; + + round = get_round(vxrm, res, 8); + res = (res >> 8) + round; + return ssub32(env, vxrm, c, res); +} + +static inline int64_t +vwsmaccsu32(CPURISCVState *env, int vxrm, uint32_t a, int32_t b, int64_t c) +{ + uint8_t round; + int64_t res = a * (int64_t)b; + + round = get_round(vxrm, res, 16); + res = (res >> 16) + round; + return ssub64(env, vxrm, c, res); +} + +RVVCALL(OPIVV3_RM, vwsmaccsu_vv_b, WOP_SSU_B, H2, H1, H1, vwsmaccsu8) +RVVCALL(OPIVV3_RM, vwsmaccsu_vv_h, WOP_SSU_H, H4, H2, H2, vwsmaccsu16) +RVVCALL(OPIVV3_RM, vwsmaccsu_vv_w, WOP_SSU_W, H8, H4, H4, vwsmaccsu32) +GEN_VEXT_VV_RM(vwsmaccsu_vv_b, 1, 2, clearh) +GEN_VEXT_VV_RM(vwsmaccsu_vv_h, 2, 4, clearl) +GEN_VEXT_VV_RM(vwsmaccsu_vv_w, 4, 8, clearq) +RVVCALL(OPIVX3_RM, vwsmaccsu_vx_b, WOP_SSU_B, H2, H1, vwsmaccsu8) +RVVCALL(OPIVX3_RM, vwsmaccsu_vx_h, WOP_SSU_H, H4, H2, vwsmaccsu16) +RVVCALL(OPIVX3_RM, vwsmaccsu_vx_w, WOP_SSU_W, H8, H4, vwsmaccsu32) +GEN_VEXT_VX_RM(vwsmaccsu_vx_b, 1, 2, clearh) +GEN_VEXT_VX_RM(vwsmaccsu_vx_h, 2, 4, clearl) +GEN_VEXT_VX_RM(vwsmaccsu_vx_w, 4, 8, clearq) + +static inline int16_t +vwsmaccus8(CPURISCVState *env, int vxrm, int8_t a, uint8_t b, int16_t c) +{ + uint8_t round; + int16_t res = (int16_t)a * b; + + round = get_round(vxrm, res, 4); + res = (res >> 4) + round; + return ssub16(env, vxrm, c, res); +} + +static inline int32_t +vwsmaccus16(CPURISCVState *env, int vxrm, int16_t a, uint16_t b, int32_t c) +{ + uint8_t round; + int32_t res = (int32_t)a * b; + + round = get_round(vxrm, res, 8); + res = (res >> 8) + round; + return ssub32(env, vxrm, c, res); +} + +static inline int64_t +vwsmaccus32(CPURISCVState *env, int vxrm, int32_t a, uint32_t b, int64_t c) +{ + uint8_t round; + int64_t res = (int64_t)a * b; + + round = get_round(vxrm, res, 16); + res = (res >> 16) + round; + return ssub64(env, vxrm, c, res); +} + +RVVCALL(OPIVX3_RM, vwsmaccus_vx_b, WOP_SUS_B, H2, H1, vwsmaccus8) +RVVCALL(OPIVX3_RM, vwsmaccus_vx_h, WOP_SUS_H, H4, H2, vwsmaccus16) +RVVCALL(OPIVX3_RM, vwsmaccus_vx_w, WOP_SUS_W, H8, H4, vwsmaccus32) +GEN_VEXT_VX_RM(vwsmaccus_vx_b, 1, 2, clearh) +GEN_VEXT_VX_RM(vwsmaccus_vx_h, 2, 4, clearl) +GEN_VEXT_VX_RM(vwsmaccus_vx_w, 4, 8, clearq)

[v8,27/62] target/riscv: vector widening saturating scaled multiply-add

Commit Message

Patch