[v11,34/61] target/riscv: vector single-width floating-point fused multiply-add instructions

Message ID	20200623215920.2594-35-zhiwei_liu@c-sky.com
State	New
Headers	show Return-Path: <SRS0=Q9tF=AE=nongnu.org=qemu-devel-bounces+qemu-devel=archiver.kernel.org@kernel.org> DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 6EFBF20874 From: LIU Zhiwei <zhiwei_liu@c-sky.com> To: qemu-devel@nongnu.org, qemu-riscv@nongnu.org Subject: [PATCH v11 34/61] target/riscv: vector single-width floating-point fused multiply-add instructions Date: Wed, 24 Jun 2020 05:58:53 +0800 Message-Id: <20200623215920.2594-35-zhiwei_liu@c-sky.com> In-Reply-To: <20200623215920.2594-1-zhiwei_liu@c-sky.com> References: <20200623215920.2594-1-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 <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 [v11,00/61] target/riscv: support vector extension v0.7.1 [v11,01/61] target/riscv: add vector extension field in CPURISCVState [v11,03/61] target/riscv: support vector extension csr [v11,05/61] target/riscv: add an internals.h header [v11,06/61] target/riscv: add vector stride load and store instructions [v11,08/61] target/riscv: add fault-only-first unit stride load [v11,10/61] target/riscv: vector single-width integer add and subtract [v11,12/61] target/riscv: vector integer add-with-carry / subtract-with-borrow instructions [v11,14/61] target/riscv: vector single-width bit shift instructions [v11,16/61] target/riscv: vector integer comparison instructions [v11,18/61] target/riscv: vector single-width integer multiply instructions [v11,19/61] target/riscv: vector integer divide instructions [v11,21/61] target/riscv: vector single-width integer multiply-add instructions [v11,23/61] target/riscv: vector integer merge and move instructions [v11,25/61] target/riscv: vector single-width averaging add and subtract [v11,27/61] target/riscv: vector widening saturating scaled multiply-add [v11,29/61] target/riscv: vector narrowing fixed-point clip instructions [v11,32/61] target/riscv: vector single-width floating-point multiply/divide instructions [v11,34/61] target/riscv: vector single-width floating-point fused multiply-add instructions [v11,36/61] target/riscv: vector floating-point square-root instruction [v11,38/61] target/riscv: vector floating-point sign-injection instructions [v11,40/61] target/riscv: vector floating-point classify instructions [v11,42/61] target/riscv: vector floating-point/integer type-convert instructions [v11,45/61] target/riscv: vector single-width integer reduction instructions [v11,47/61] target/riscv: vector single-width floating-point reduction instructions [v11,48/61] target/riscv: vector widening floating-point reduction instructions [v11,49/61] target/riscv: vector mask-register logical instructions [v11,52/61] target/riscv: set-X-first mask bit [v11,54/61] target/riscv: vector element index instruction [v11,56/61] target/riscv: integer scalar move instruction [v11,58/61] target/riscv: vector slide instructions [v11,60/61] target/riscv: vector compress instruction [v11,61/61] target/riscv: configure and turn on vector extension from command line

diff --git a/target/riscv/helper.h b/target/riscv/helper.h index 9d7dcfeef9..108a177f25 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -857,3 +857,52 @@ DEF_HELPER_6(vfwmul_vv_h, void, ptr, ptr, ptr, ptr, env, i32) DEF_HELPER_6(vfwmul_vv_w, void, ptr, ptr, ptr, ptr, env, i32) DEF_HELPER_6(vfwmul_vf_h, void, ptr, ptr, i64, ptr, env, i32) DEF_HELPER_6(vfwmul_vf_w, void, ptr, ptr, i64, ptr, env, i32) + +DEF_HELPER_6(vfmacc_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmacc_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmacc_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmacc_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmacc_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmacc_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmsac_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmsac_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmsac_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmsac_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmsac_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmsac_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmadd_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmadd_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmadd_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmadd_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmadd_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmadd_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmsub_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmsub_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmsub_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmsub_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmsub_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfnmsub_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfmacc_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmacc_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmacc_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmacc_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmacc_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmacc_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmsac_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmsac_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmsac_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmsac_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmsac_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmsac_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmadd_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmadd_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmadd_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmadd_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmadd_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmadd_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmsub_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmsub_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfmsub_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmsub_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmsub_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfnmsub_vf_d, void, ptr, ptr, i64, ptr, env, i32) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index dd9bca7eeb..9ca765d37f 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -465,6 +465,22 @@ vfdiv_vf 100000 . ..... ..... 101 ..... 1010111 @r_vm vfrdiv_vf 100001 . ..... ..... 101 ..... 1010111 @r_vm vfwmul_vv 111000 . ..... ..... 001 ..... 1010111 @r_vm vfwmul_vf 111000 . ..... ..... 101 ..... 1010111 @r_vm +vfmacc_vv 101100 . ..... ..... 001 ..... 1010111 @r_vm +vfnmacc_vv 101101 . ..... ..... 001 ..... 1010111 @r_vm +vfnmacc_vf 101101 . ..... ..... 101 ..... 1010111 @r_vm +vfmacc_vf 101100 . ..... ..... 101 ..... 1010111 @r_vm +vfmsac_vv 101110 . ..... ..... 001 ..... 1010111 @r_vm +vfmsac_vf 101110 . ..... ..... 101 ..... 1010111 @r_vm +vfnmsac_vv 101111 . ..... ..... 001 ..... 1010111 @r_vm +vfnmsac_vf 101111 . ..... ..... 101 ..... 1010111 @r_vm +vfmadd_vv 101000 . ..... ..... 001 ..... 1010111 @r_vm +vfmadd_vf 101000 . ..... ..... 101 ..... 1010111 @r_vm +vfnmadd_vv 101001 . ..... ..... 001 ..... 1010111 @r_vm +vfnmadd_vf 101001 . ..... ..... 101 ..... 1010111 @r_vm +vfmsub_vv 101010 . ..... ..... 001 ..... 1010111 @r_vm +vfmsub_vf 101010 . ..... ..... 101 ..... 1010111 @r_vm +vfnmsub_vv 101011 . ..... ..... 001 ..... 1010111 @r_vm +vfnmsub_vf 101011 . ..... ..... 101 ..... 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 3ce7815f5d..ee601fd790 100644 --- a/target/riscv/insn_trans/trans_rvv.inc.c +++ b/target/riscv/insn_trans/trans_rvv.inc.c @@ -2061,3 +2061,21 @@ GEN_OPFVF_TRANS(vfrdiv_vf, opfvf_check) /* Vector Widening Floating-Point Multiply */ GEN_OPFVV_WIDEN_TRANS(vfwmul_vv, opfvv_widen_check) GEN_OPFVF_WIDEN_TRANS(vfwmul_vf) + +/* Vector Single-Width Floating-Point Fused Multiply-Add Instructions */ +GEN_OPFVV_TRANS(vfmacc_vv, opfvv_check) +GEN_OPFVV_TRANS(vfnmacc_vv, opfvv_check) +GEN_OPFVV_TRANS(vfmsac_vv, opfvv_check) +GEN_OPFVV_TRANS(vfnmsac_vv, opfvv_check) +GEN_OPFVV_TRANS(vfmadd_vv, opfvv_check) +GEN_OPFVV_TRANS(vfnmadd_vv, opfvv_check) +GEN_OPFVV_TRANS(vfmsub_vv, opfvv_check) +GEN_OPFVV_TRANS(vfnmsub_vv, opfvv_check) +GEN_OPFVF_TRANS(vfmacc_vf, opfvf_check) +GEN_OPFVF_TRANS(vfnmacc_vf, opfvf_check) +GEN_OPFVF_TRANS(vfmsac_vf, opfvf_check) +GEN_OPFVF_TRANS(vfnmsac_vf, opfvf_check) +GEN_OPFVF_TRANS(vfmadd_vf, opfvf_check) +GEN_OPFVF_TRANS(vfnmadd_vf, opfvf_check) +GEN_OPFVF_TRANS(vfmsub_vf, opfvf_check) +GEN_OPFVF_TRANS(vfnmsub_vf, opfvf_check) diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index 6441d0ee08..1173964efd 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -3432,3 +3432,254 @@ RVVCALL(OPFVF2, vfwmul_vf_h, WOP_UUU_H, H4, H2, vfwmul16) RVVCALL(OPFVF2, vfwmul_vf_w, WOP_UUU_W, H8, H4, vfwmul32) GEN_VEXT_VF(vfwmul_vf_h, 2, 4, clearl) GEN_VEXT_VF(vfwmul_vf_w, 4, 8, clearq) + +/* Vector Single-Width Floating-Point Fused Multiply-Add Instructions */ +#define OPFVV3(NAME, TD, T1, T2, TX1, TX2, HD, HS1, HS2, OP) \ +static void do_##NAME(void *vd, void *vs1, void *vs2, int i, \ + CPURISCVState *env) \ +{ \ + TX1 s1 = *((T1 *)vs1 + HS1(i)); \ + TX2 s2 = *((T2 *)vs2 + HS2(i)); \ + TD d = *((TD *)vd + HD(i)); \ + *((TD *)vd + HD(i)) = OP(s2, s1, d, &env->fp_status); \ +} + +static uint16_t fmacc16(uint16_t a, uint16_t b, uint16_t d, float_status *s) +{ + return float16_muladd(a, b, d, 0, s); +} + +static uint32_t fmacc32(uint32_t a, uint32_t b, uint32_t d, float_status *s) +{ + return float32_muladd(a, b, d, 0, s); +} + +static uint64_t fmacc64(uint64_t a, uint64_t b, uint64_t d, float_status *s) +{ + return float64_muladd(a, b, d, 0, s); +} + +RVVCALL(OPFVV3, vfmacc_vv_h, OP_UUU_H, H2, H2, H2, fmacc16) +RVVCALL(OPFVV3, vfmacc_vv_w, OP_UUU_W, H4, H4, H4, fmacc32) +RVVCALL(OPFVV3, vfmacc_vv_d, OP_UUU_D, H8, H8, H8, fmacc64) +GEN_VEXT_VV_ENV(vfmacc_vv_h, 2, 2, clearh) +GEN_VEXT_VV_ENV(vfmacc_vv_w, 4, 4, clearl) +GEN_VEXT_VV_ENV(vfmacc_vv_d, 8, 8, clearq) + +#define OPFVF3(NAME, TD, T1, T2, TX1, TX2, HD, HS2, OP) \ +static void do_##NAME(void *vd, uint64_t s1, void *vs2, int i, \ + CPURISCVState *env) \ +{ \ + TX2 s2 = *((T2 *)vs2 + HS2(i)); \ + TD d = *((TD *)vd + HD(i)); \ + *((TD *)vd + HD(i)) = OP(s2, (TX1)(T1)s1, d, &env->fp_status);\ +} + +RVVCALL(OPFVF3, vfmacc_vf_h, OP_UUU_H, H2, H2, fmacc16) +RVVCALL(OPFVF3, vfmacc_vf_w, OP_UUU_W, H4, H4, fmacc32) +RVVCALL(OPFVF3, vfmacc_vf_d, OP_UUU_D, H8, H8, fmacc64) +GEN_VEXT_VF(vfmacc_vf_h, 2, 2, clearh) +GEN_VEXT_VF(vfmacc_vf_w, 4, 4, clearl) +GEN_VEXT_VF(vfmacc_vf_d, 8, 8, clearq) + +static uint16_t fnmacc16(uint16_t a, uint16_t b, uint16_t d, float_status *s) +{ + return float16_muladd(a, b, d, + float_muladd_negate_c | float_muladd_negate_product, s); +} + +static uint32_t fnmacc32(uint32_t a, uint32_t b, uint32_t d, float_status *s) +{ + return float32_muladd(a, b, d, + float_muladd_negate_c | float_muladd_negate_product, s); +} + +static uint64_t fnmacc64(uint64_t a, uint64_t b, uint64_t d, float_status *s) +{ + return float64_muladd(a, b, d, + float_muladd_negate_c | float_muladd_negate_product, s); +} + +RVVCALL(OPFVV3, vfnmacc_vv_h, OP_UUU_H, H2, H2, H2, fnmacc16) +RVVCALL(OPFVV3, vfnmacc_vv_w, OP_UUU_W, H4, H4, H4, fnmacc32) +RVVCALL(OPFVV3, vfnmacc_vv_d, OP_UUU_D, H8, H8, H8, fnmacc64) +GEN_VEXT_VV_ENV(vfnmacc_vv_h, 2, 2, clearh) +GEN_VEXT_VV_ENV(vfnmacc_vv_w, 4, 4, clearl) +GEN_VEXT_VV_ENV(vfnmacc_vv_d, 8, 8, clearq) +RVVCALL(OPFVF3, vfnmacc_vf_h, OP_UUU_H, H2, H2, fnmacc16) +RVVCALL(OPFVF3, vfnmacc_vf_w, OP_UUU_W, H4, H4, fnmacc32) +RVVCALL(OPFVF3, vfnmacc_vf_d, OP_UUU_D, H8, H8, fnmacc64) +GEN_VEXT_VF(vfnmacc_vf_h, 2, 2, clearh) +GEN_VEXT_VF(vfnmacc_vf_w, 4, 4, clearl) +GEN_VEXT_VF(vfnmacc_vf_d, 8, 8, clearq) + +static uint16_t fmsac16(uint16_t a, uint16_t b, uint16_t d, float_status *s) +{ + return float16_muladd(a, b, d, float_muladd_negate_c, s); +} + +static uint32_t fmsac32(uint32_t a, uint32_t b, uint32_t d, float_status *s) +{ + return float32_muladd(a, b, d, float_muladd_negate_c, s); +} + +static uint64_t fmsac64(uint64_t a, uint64_t b, uint64_t d, float_status *s) +{ + return float64_muladd(a, b, d, float_muladd_negate_c, s); +} + +RVVCALL(OPFVV3, vfmsac_vv_h, OP_UUU_H, H2, H2, H2, fmsac16) +RVVCALL(OPFVV3, vfmsac_vv_w, OP_UUU_W, H4, H4, H4, fmsac32) +RVVCALL(OPFVV3, vfmsac_vv_d, OP_UUU_D, H8, H8, H8, fmsac64) +GEN_VEXT_VV_ENV(vfmsac_vv_h, 2, 2, clearh) +GEN_VEXT_VV_ENV(vfmsac_vv_w, 4, 4, clearl) +GEN_VEXT_VV_ENV(vfmsac_vv_d, 8, 8, clearq) +RVVCALL(OPFVF3, vfmsac_vf_h, OP_UUU_H, H2, H2, fmsac16) +RVVCALL(OPFVF3, vfmsac_vf_w, OP_UUU_W, H4, H4, fmsac32) +RVVCALL(OPFVF3, vfmsac_vf_d, OP_UUU_D, H8, H8, fmsac64) +GEN_VEXT_VF(vfmsac_vf_h, 2, 2, clearh) +GEN_VEXT_VF(vfmsac_vf_w, 4, 4, clearl) +GEN_VEXT_VF(vfmsac_vf_d, 8, 8, clearq) + +static uint16_t fnmsac16(uint16_t a, uint16_t b, uint16_t d, float_status *s) +{ + return float16_muladd(a, b, d, float_muladd_negate_product, s); +} + +static uint32_t fnmsac32(uint32_t a, uint32_t b, uint32_t d, float_status *s) +{ + return float32_muladd(a, b, d, float_muladd_negate_product, s); +} + +static uint64_t fnmsac64(uint64_t a, uint64_t b, uint64_t d, float_status *s) +{ + return float64_muladd(a, b, d, float_muladd_negate_product, s); +} + +RVVCALL(OPFVV3, vfnmsac_vv_h, OP_UUU_H, H2, H2, H2, fnmsac16) +RVVCALL(OPFVV3, vfnmsac_vv_w, OP_UUU_W, H4, H4, H4, fnmsac32) +RVVCALL(OPFVV3, vfnmsac_vv_d, OP_UUU_D, H8, H8, H8, fnmsac64) +GEN_VEXT_VV_ENV(vfnmsac_vv_h, 2, 2, clearh) +GEN_VEXT_VV_ENV(vfnmsac_vv_w, 4, 4, clearl) +GEN_VEXT_VV_ENV(vfnmsac_vv_d, 8, 8, clearq) +RVVCALL(OPFVF3, vfnmsac_vf_h, OP_UUU_H, H2, H2, fnmsac16) +RVVCALL(OPFVF3, vfnmsac_vf_w, OP_UUU_W, H4, H4, fnmsac32) +RVVCALL(OPFVF3, vfnmsac_vf_d, OP_UUU_D, H8, H8, fnmsac64) +GEN_VEXT_VF(vfnmsac_vf_h, 2, 2, clearh) +GEN_VEXT_VF(vfnmsac_vf_w, 4, 4, clearl) +GEN_VEXT_VF(vfnmsac_vf_d, 8, 8, clearq) + +static uint16_t fmadd16(uint16_t a, uint16_t b, uint16_t d, float_status *s) +{ + return float16_muladd(d, b, a, 0, s); +} + +static uint32_t fmadd32(uint32_t a, uint32_t b, uint32_t d, float_status *s) +{ + return float32_muladd(d, b, a, 0, s); +} + +static uint64_t fmadd64(uint64_t a, uint64_t b, uint64_t d, float_status *s) +{ + return float64_muladd(d, b, a, 0, s); +} + +RVVCALL(OPFVV3, vfmadd_vv_h, OP_UUU_H, H2, H2, H2, fmadd16) +RVVCALL(OPFVV3, vfmadd_vv_w, OP_UUU_W, H4, H4, H4, fmadd32) +RVVCALL(OPFVV3, vfmadd_vv_d, OP_UUU_D, H8, H8, H8, fmadd64) +GEN_VEXT_VV_ENV(vfmadd_vv_h, 2, 2, clearh) +GEN_VEXT_VV_ENV(vfmadd_vv_w, 4, 4, clearl) +GEN_VEXT_VV_ENV(vfmadd_vv_d, 8, 8, clearq) +RVVCALL(OPFVF3, vfmadd_vf_h, OP_UUU_H, H2, H2, fmadd16) +RVVCALL(OPFVF3, vfmadd_vf_w, OP_UUU_W, H4, H4, fmadd32) +RVVCALL(OPFVF3, vfmadd_vf_d, OP_UUU_D, H8, H8, fmadd64) +GEN_VEXT_VF(vfmadd_vf_h, 2, 2, clearh) +GEN_VEXT_VF(vfmadd_vf_w, 4, 4, clearl) +GEN_VEXT_VF(vfmadd_vf_d, 8, 8, clearq) + +static uint16_t fnmadd16(uint16_t a, uint16_t b, uint16_t d, float_status *s) +{ + return float16_muladd(d, b, a, + float_muladd_negate_c | float_muladd_negate_product, s); +} + +static uint32_t fnmadd32(uint32_t a, uint32_t b, uint32_t d, float_status *s) +{ + return float32_muladd(d, b, a, + float_muladd_negate_c | float_muladd_negate_product, s); +} + +static uint64_t fnmadd64(uint64_t a, uint64_t b, uint64_t d, float_status *s) +{ + return float64_muladd(d, b, a, + float_muladd_negate_c | float_muladd_negate_product, s); +} + +RVVCALL(OPFVV3, vfnmadd_vv_h, OP_UUU_H, H2, H2, H2, fnmadd16) +RVVCALL(OPFVV3, vfnmadd_vv_w, OP_UUU_W, H4, H4, H4, fnmadd32) +RVVCALL(OPFVV3, vfnmadd_vv_d, OP_UUU_D, H8, H8, H8, fnmadd64) +GEN_VEXT_VV_ENV(vfnmadd_vv_h, 2, 2, clearh) +GEN_VEXT_VV_ENV(vfnmadd_vv_w, 4, 4, clearl) +GEN_VEXT_VV_ENV(vfnmadd_vv_d, 8, 8, clearq) +RVVCALL(OPFVF3, vfnmadd_vf_h, OP_UUU_H, H2, H2, fnmadd16) +RVVCALL(OPFVF3, vfnmadd_vf_w, OP_UUU_W, H4, H4, fnmadd32) +RVVCALL(OPFVF3, vfnmadd_vf_d, OP_UUU_D, H8, H8, fnmadd64) +GEN_VEXT_VF(vfnmadd_vf_h, 2, 2, clearh) +GEN_VEXT_VF(vfnmadd_vf_w, 4, 4, clearl) +GEN_VEXT_VF(vfnmadd_vf_d, 8, 8, clearq) + +static uint16_t fmsub16(uint16_t a, uint16_t b, uint16_t d, float_status *s) +{ + return float16_muladd(d, b, a, float_muladd_negate_c, s); +} + +static uint32_t fmsub32(uint32_t a, uint32_t b, uint32_t d, float_status *s) +{ + return float32_muladd(d, b, a, float_muladd_negate_c, s); +} + +static uint64_t fmsub64(uint64_t a, uint64_t b, uint64_t d, float_status *s) +{ + return float64_muladd(d, b, a, float_muladd_negate_c, s); +} + +RVVCALL(OPFVV3, vfmsub_vv_h, OP_UUU_H, H2, H2, H2, fmsub16) +RVVCALL(OPFVV3, vfmsub_vv_w, OP_UUU_W, H4, H4, H4, fmsub32) +RVVCALL(OPFVV3, vfmsub_vv_d, OP_UUU_D, H8, H8, H8, fmsub64) +GEN_VEXT_VV_ENV(vfmsub_vv_h, 2, 2, clearh) +GEN_VEXT_VV_ENV(vfmsub_vv_w, 4, 4, clearl) +GEN_VEXT_VV_ENV(vfmsub_vv_d, 8, 8, clearq) +RVVCALL(OPFVF3, vfmsub_vf_h, OP_UUU_H, H2, H2, fmsub16) +RVVCALL(OPFVF3, vfmsub_vf_w, OP_UUU_W, H4, H4, fmsub32) +RVVCALL(OPFVF3, vfmsub_vf_d, OP_UUU_D, H8, H8, fmsub64) +GEN_VEXT_VF(vfmsub_vf_h, 2, 2, clearh) +GEN_VEXT_VF(vfmsub_vf_w, 4, 4, clearl) +GEN_VEXT_VF(vfmsub_vf_d, 8, 8, clearq) + +static uint16_t fnmsub16(uint16_t a, uint16_t b, uint16_t d, float_status *s) +{ + return float16_muladd(d, b, a, float_muladd_negate_product, s); +} + +static uint32_t fnmsub32(uint32_t a, uint32_t b, uint32_t d, float_status *s) +{ + return float32_muladd(d, b, a, float_muladd_negate_product, s); +} + +static uint64_t fnmsub64(uint64_t a, uint64_t b, uint64_t d, float_status *s) +{ + return float64_muladd(d, b, a, float_muladd_negate_product, s); +} + +RVVCALL(OPFVV3, vfnmsub_vv_h, OP_UUU_H, H2, H2, H2, fnmsub16) +RVVCALL(OPFVV3, vfnmsub_vv_w, OP_UUU_W, H4, H4, H4, fnmsub32) +RVVCALL(OPFVV3, vfnmsub_vv_d, OP_UUU_D, H8, H8, H8, fnmsub64) +GEN_VEXT_VV_ENV(vfnmsub_vv_h, 2, 2, clearh) +GEN_VEXT_VV_ENV(vfnmsub_vv_w, 4, 4, clearl) +GEN_VEXT_VV_ENV(vfnmsub_vv_d, 8, 8, clearq) +RVVCALL(OPFVF3, vfnmsub_vf_h, OP_UUU_H, H2, H2, fnmsub16) +RVVCALL(OPFVF3, vfnmsub_vf_w, OP_UUU_W, H4, H4, fnmsub32) +RVVCALL(OPFVF3, vfnmsub_vf_d, OP_UUU_D, H8, H8, fnmsub64) +GEN_VEXT_VF(vfnmsub_vf_h, 2, 2, clearh) +GEN_VEXT_VF(vfnmsub_vf_w, 4, 4, clearl) +GEN_VEXT_VF(vfnmsub_vf_d, 8, 8, clearq)

[v11,34/61] target/riscv: vector single-width floating-point fused multiply-add instructions

Commit Message

Patch