From nobody Tue Feb 10 09:43:06 2026 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org ARC-Seal: i=1; a=rsa-sha256; t=1590057578; cv=none; d=zohomail.com; s=zohoarc; b=Xzpippwd3kNXrGWV4gl84uFx3td3esdVFSRQmMtrddEedFatWkzX4s3VYPWn3uyskG4pctyqdCB9g9ZEH9TUVeeQPJYt3reKuEhbzYXtjZr/35nA1UQxYaE3I/qTzFVgNPqMgf30RMfK6Y29tOxse/oTgtk2V4lhkGO/yzfKZqA= ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=zohomail.com; s=zohoarc; t=1590057578; h=Content-Transfer-Encoding:Cc:Date:From:In-Reply-To:List-Subscribe:List-Post:List-Id:List-Archive:List-Help:List-Unsubscribe:MIME-Version:Message-ID:References:Sender:Subject:To; bh=aJnIummNymi3XkuMmhZXcNLRDFJFEfN0ErfeFRZdZZU=; b=ZVDZ278R4hemZboAEBf/soyv982ex0lIv5YMy+FsPLM2mYMoJe0x0pOeE7jqX8lvfEG9WuWs2WGasGA6eu9CGfeYEr0cL7Lo66/18eQYmThC0vCxSmLNlpTEnuvfavXmHzUbNhpeZS8Ln1GaTs+fwwQjZH05lSRSo93ryhBMKas= ARC-Authentication-Results: i=1; mx.zohomail.com; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1590057578819108.62338959390831; Thu, 21 May 2020 03:39:38 -0700 (PDT) Received: from localhost ([::1]:41216 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1jbibx-00019V-AN for importer@patchew.org; Thu, 21 May 2020 06:39:37 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]:37030) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1jbibB-0008VO-KW; Thu, 21 May 2020 06:38:49 -0400 Received: from smtp2200-217.mail.aliyun.com ([121.197.200.217]:48274) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1jbib9-0005Eh-PZ; Thu, 21 May 2020 06:38:49 -0400 Received: from L-PF1D6DP4-1208.hz.ali.com(mailfrom:zhiwei_liu@c-sky.com fp:SMTPD_---.Hbd7mGS_1590057522) by smtp.aliyun-inc.com(10.147.41.137); Thu, 21 May 2020 18:38:42 +0800 X-Alimail-AntiSpam: AC=CONTINUE; BC=0.06436282|-1; CH=blue; DM=|OVERLOAD|false|; DS=CONTINUE|ham_regular_dialog|0.267802-0.00385584-0.728342; FP=0|0|0|0|0|-1|-1|-1; HT=e02c03309; MF=zhiwei_liu@c-sky.com; NM=1; PH=DS; RN=8; RT=8; SR=0; TI=SMTPD_---.Hbd7mGS_1590057522; From: LIU Zhiwei 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> X-Mailer: git-send-email 2.23.0 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: quoted-printable Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: none client-ip=121.197.200.217; envelope-from=zhiwei_liu@c-sky.com; helo=smtp2200-217.mail.aliyun.com X-detected-operating-system: by eggs.gnu.org: First seen = 2020/05/21 05:19:14 X-ACL-Warn: Detected OS = Linux 3.x [generic] [fuzzy] X-Spam_score_int: -18 X-Spam_score: -1.9 X-Spam_bar: - X-Spam_report: (-1.9 / 5.0 requ) BAYES_00=-1.9, UNPARSEABLE_RELAY=0.001, URIBL_BLOCKED=0.001 autolearn=_AUTOLEARN X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.23 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: richard.henderson@linaro.org, wxy194768@alibaba-inc.com, wenmeng_zhang@c-sky.com, alistair.francis@wdc.com, palmer@dabbelt.com, LIU Zhiwei Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" Content-Type: text/plain; charset="utf-8" Signed-off-by: LIU Zhiwei Reviewed-by: Richard Henderson Reviewed-by: Alistair Francis --- target/riscv/helper.h | 22 +++ target/riscv/insn32.decode | 7 + target/riscv/insn_trans/trans_rvv.inc.c | 9 ++ target/riscv/vector_helper.c | 205 ++++++++++++++++++++++++ 4 files changed, 243 insertions(+) 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 =20 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_tr= ans/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 =3D (uint16_t)a * b; + + round =3D get_round(vxrm, res, 4); + res =3D (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 =3D (uint32_t)a * b; + + round =3D get_round(vxrm, res, 8); + res =3D (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 =3D (uint64_t)a * b; + + round =3D get_round(vxrm, res, 16); + res =3D (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 =3D *((T1 *)vs1 + HS1(i)); \ + TX2 s2 =3D *((T2 *)vs2 + HS2(i)); \ + TD d =3D *((TD *)vd + HD(i)); \ + *((TD *)vd + HD(i)) =3D 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 =3D *((T2 *)vs2 + HS2(i)); \ + TD d =3D *((TD *)vd + HD(i)); \ + *((TD *)vd + HD(i)) =3D 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 =3D (int16_t)a * b; + + round =3D get_round(vxrm, res, 4); + res =3D (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 =3D (int32_t)a * b; + + round =3D get_round(vxrm, res, 8); + res =3D (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 =3D (int64_t)a * b; + + round =3D get_round(vxrm, res, 16); + res =3D (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 =3D a * (int16_t)b; + + round =3D get_round(vxrm, res, 4); + res =3D (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 =3D a * (int32_t)b; + + round =3D get_round(vxrm, res, 8); + res =3D (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 =3D a * (int64_t)b; + + round =3D get_round(vxrm, res, 16); + res =3D (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 =3D (int16_t)a * b; + + round =3D get_round(vxrm, res, 4); + res =3D (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 =3D (int32_t)a * b; + + round =3D get_round(vxrm, res, 8); + res =3D (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 =3D (int64_t)a * b; + + round =3D get_round(vxrm, res, 16); + res =3D (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) --=20 2.23.0