From nobody Wed Nov 19 00:14:28 2025 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=1613144452; cv=none; d=zohomail.com; s=zohoarc; b=fvi/k1OUm0NXHbBrBrEHEaUyQJjMQ1iGiCvVNghyEu7ufi+GdEen8s/OpJMKEUdqTtwvRb+ttoOAnaPxrJGpgId5BhTyef/dqsbYehLbJIgbYU30zJ7KD4NJnncUgJHfadJ21YFzLF5LVEApELhun5vXGCAhNEb4YRizQfq/HFQ= ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=zohomail.com; s=zohoarc; t=1613144452; h=Cc:Date:From:In-Reply-To:List-Subscribe:List-Post:List-Id:List-Archive:List-Help:List-Unsubscribe:Message-ID:References:Sender:Subject:To; bh=nmJOlO0elZFQnzTDMmYLkHvBjzTl0tJ77gGsmbLaWYw=; b=g43aZq3HSMuddBVkQJ+Hqt1MZS5h35+wd8op79RFPfVRktpgAy9qbNRehVftZtq8iEFIMFrCatmcDv9oFGy+RTDVe3jvVDtcOkSieJzSO/29XzgCTPg+2lWpO1TmzWkZ3UTimauHBTmuPeZSmYgld8EmEOVvkToArHjVNCLb2dc= 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 1613144451943593.7025646400714; Fri, 12 Feb 2021 07:40:51 -0800 (PST) Received: from localhost ([::1]:45908 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1lAaYs-0006Jp-QT for importer@patchew.org; Fri, 12 Feb 2021 10:40:50 -0500 Received: from eggs.gnu.org ([2001:470:142:3::10]:49646) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1lAaVB-0003iC-Rd; Fri, 12 Feb 2021 10:37:07 -0500 Received: from smtp2200-217.mail.aliyun.com ([121.197.200.217]:45396) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1lAaV8-0001lX-UK; Fri, 12 Feb 2021 10:37:01 -0500 Received: from localhost.localdomain(mailfrom:zhiwei_liu@c-sky.com fp:SMTPD_---.JYH6X8G_1613144211) by smtp.aliyun-inc.com(10.147.42.253); Fri, 12 Feb 2021 23:36:51 +0800 X-Alimail-AntiSpam: AC=CONTINUE; BC=0.07436322|-1; CH=green; DM=|CONTINUE|false|; DS=CONTINUE|ham_system_inform|0.620553-0.00353106-0.375916; FP=0|0|0|0|0|-1|-1|-1; HT=ay29a033018047190; MF=zhiwei_liu@c-sky.com; NM=1; PH=DS; RN=6; RT=6; SR=0; TI=SMTPD_---.JYH6X8G_1613144211; From: LIU Zhiwei To: qemu-devel@nongnu.org Subject: [PATCH 16/38] target/riscv: Signed MSW 32x32 Multiply and Add Instructions Date: Fri, 12 Feb 2021 23:02:34 +0800 Message-Id: <20210212150256.885-17-zhiwei_liu@c-sky.com> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20210212150256.885-1-zhiwei_liu@c-sky.com> References: <20210212150256.885-1-zhiwei_liu@c-sky.com> 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-Spam_score_int: -18 X-Spam_score: -1.9 X-Spam_bar: - X-Spam_report: (-1.9 / 5.0 requ) BAYES_00=-1.9, SPF_HELO_NONE=0.001, SPF_NONE=0.001, UNPARSEABLE_RELAY=0.001 autolearn=ham autolearn_force=no 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, LIU Zhiwei , qemu-riscv@nongnu.org, palmer@dabbelt.com, alistair23@gmail.com Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Signed-off-by: LIU Zhiwei --- target/riscv/helper.h | 9 ++ target/riscv/insn32.decode | 9 ++ target/riscv/insn_trans/trans_rvp.c.inc | 44 ++++++++++ target/riscv/packed_helper.c | 109 ++++++++++++++++++++++++ 4 files changed, 171 insertions(+) diff --git a/target/riscv/helper.h b/target/riscv/helper.h index 4dc66cf4cc..0bd21c8514 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -1268,3 +1268,12 @@ DEF_HELPER_3(pkbb16, tl, env, tl, tl) DEF_HELPER_3(pkbt16, tl, env, tl, tl) DEF_HELPER_3(pktt16, tl, env, tl, tl) DEF_HELPER_3(pktb16, tl, env, tl, tl) + +DEF_HELPER_3(smmul, tl, env, tl, tl) +DEF_HELPER_3(smmul_u, tl, env, tl, tl) +DEF_HELPER_4(kmmac, tl, env, tl, tl, tl) +DEF_HELPER_4(kmmac_u, tl, env, tl, tl, tl) +DEF_HELPER_4(kmmsb, tl, env, tl, tl, tl) +DEF_HELPER_4(kmmsb_u, tl, env, tl, tl, tl) +DEF_HELPER_3(kwmmul, tl, env, tl, tl) +DEF_HELPER_3(kwmmul_u, tl, env, tl, tl) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index a4d9ff2282..e0be2790dc 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -736,3 +736,12 @@ pkbb16 0000111 ..... ..... 001 ..... 1111111 @r pkbt16 0001111 ..... ..... 001 ..... 1111111 @r pktt16 0010111 ..... ..... 001 ..... 1111111 @r pktb16 0011111 ..... ..... 001 ..... 1111111 @r + +smmul 0100000 ..... ..... 001 ..... 1111111 @r +smmul_u 0101000 ..... ..... 001 ..... 1111111 @r +kmmac 0110000 ..... ..... 001 ..... 1111111 @r +kmmac_u 0111000 ..... ..... 001 ..... 1111111 @r +kmmsb 0100001 ..... ..... 001 ..... 1111111 @r +kmmsb_u 0101001 ..... ..... 001 ..... 1111111 @r +kwmmul 0110001 ..... ..... 001 ..... 1111111 @r +kwmmul_u 0111001 ..... ..... 001 ..... 1111111 @r diff --git a/target/riscv/insn_trans/trans_rvp.c.inc b/target/riscv/insn_tr= ans/trans_rvp.c.inc index 99a19019eb..fbc9c0b57b 100644 --- a/target/riscv/insn_trans/trans_rvp.c.inc +++ b/target/riscv/insn_trans/trans_rvp.c.inc @@ -520,3 +520,47 @@ GEN_RVP_R_OOL(pkbb16); GEN_RVP_R_OOL(pkbt16); GEN_RVP_R_OOL(pktt16); GEN_RVP_R_OOL(pktb16); + +/* Most Significant Word "32x32" Multiply & Add Instructions */ +GEN_RVP_R_OOL(smmul); +GEN_RVP_R_OOL(smmul_u); + +/* Function to accumulate destination register */ +static inline bool r_acc_ool(DisasContext *ctx, arg_r *a, + void (* fn)(TCGv, TCGv_ptr, TCGv, TCGv, TCGv)) +{ + TCGv src1, src2, src3, dst; + if (!has_ext(ctx, RVP)) { + return false; + } + + src1 =3D tcg_temp_new(); + src2 =3D tcg_temp_new(); + src3 =3D tcg_temp_new(); + dst =3D tcg_temp_new(); + + gen_get_gpr(src1, a->rs1); + gen_get_gpr(src2, a->rs2); + gen_get_gpr(src3, a->rd); + fn(dst, cpu_env, src1, src2, src3); + gen_set_gpr(a->rd, dst); + + tcg_temp_free(src1); + tcg_temp_free(src2); + tcg_temp_free(src3); + tcg_temp_free(dst); + return true; +} + +#define GEN_RVP_R_ACC_OOL(NAME) \ +static bool trans_##NAME(DisasContext *s, arg_r *a) \ +{ \ + return r_acc_ool(s, a, gen_helper_##NAME); \ +} + +GEN_RVP_R_ACC_OOL(kmmac); +GEN_RVP_R_ACC_OOL(kmmac_u); +GEN_RVP_R_ACC_OOL(kmmsb); +GEN_RVP_R_ACC_OOL(kmmsb_u); +GEN_RVP_R_OOL(kwmmul); +GEN_RVP_R_OOL(kwmmul_u); diff --git a/target/riscv/packed_helper.c b/target/riscv/packed_helper.c index fe1b48c86d..c1322d2fac 100644 --- a/target/riscv/packed_helper.c +++ b/target/riscv/packed_helper.c @@ -1368,3 +1368,112 @@ static inline void do_pktb16(CPURISCVState *env, vo= id *vd, void *va, } =20 RVPR(pktb16, 2, 2); + +/* Most Significant Word "32x32" Multiply & Add Instructions */ +static inline void do_smmul(CPURISCVState *env, void *vd, void *va, + void *vb, uint8_t i) +{ + int32_t *d =3D vd, *a =3D va, *b =3D vb; + d[i] =3D (int64_t)a[i] * b[i] >> 32; +} + +RVPR(smmul, 1, 4); + +static inline void do_smmul_u(CPURISCVState *env, void *vd, void *va, + void *vb, uint8_t i) +{ + int32_t *d =3D vd, *a =3D va, *b =3D vb; + d[i] =3D ((int64_t)a[i] * b[i] + (uint32_t)INT32_MIN) >> 32; +} + +RVPR(smmul_u, 1, 4); + +typedef void PackedFn4i(CPURISCVState *, void *, void *, + void *, void *, uint8_t); + +static inline target_ulong +rvpr_acc(CPURISCVState *env, target_ulong a, + target_ulong b, target_ulong c, + uint8_t step, uint8_t size, PackedFn4i *fn) +{ + int i, passes =3D sizeof(target_ulong) / size; + target_ulong result =3D 0; + + for (i =3D 0; i < passes; i +=3D step) { + fn(env, &result, &a, &b, &c, i); + } + return result; +} + +#define RVPR_ACC(NAME, STEP, SIZE) \ +target_ulong HELPER(NAME)(CPURISCVState *env, target_ulong a, \ + target_ulong b, target_ulong c) \ +{ \ + return rvpr_acc(env, a, b, c, STEP, SIZE, (PackedFn4i *)do_##NAME);\ +} + +static inline void do_kmmac(CPURISCVState *env, void *vd, void *va, + void *vb, void *vc, uint8_t i) +{ + int32_t *d =3D vd, *a =3D va, *b =3D vb, *c =3D vc; + d[i] =3D sadd32(env, 0, ((int64_t)a[i] * b[i]) >> 32, c[i]); +} + +RVPR_ACC(kmmac, 1, 4); + +static inline void do_kmmac_u(CPURISCVState *env, void *vd, void *va, + void *vb, void *vc, uint8_t i) +{ + int32_t *d =3D vd, *a =3D va, *b =3D vb, *c =3D vc; + d[i] =3D sadd32(env, 0, ((int64_t)a[i] * b[i] + + (uint32_t)INT32_MIN) >> 32, c[i]); +} + +RVPR_ACC(kmmac_u, 1, 4); + +static inline void do_kmmsb(CPURISCVState *env, void *vd, void *va, + void *vb, void *vc, uint8_t i) +{ + int32_t *d =3D vd, *a =3D va, *b =3D vb, *c =3D vc; + d[i] =3D ssub32(env, 0, c[i], (int64_t)a[i] * b[i] >> 32); +} + +RVPR_ACC(kmmsb, 1, 4); + +static inline void do_kmmsb_u(CPURISCVState *env, void *vd, void *va, + void *vb, void *vc, uint8_t i) +{ + int32_t *d =3D vd, *a =3D va, *b =3D vb, *c =3D vc; + d[i] =3D ssub32(env, 0, c[i], ((int64_t)a[i] * b[i] + + (uint32_t)INT32_MIN) >> 32); +} + +RVPR_ACC(kmmsb_u, 1, 4); + +static inline void do_kwmmul(CPURISCVState *env, void *vd, void *va, + void *vb, uint8_t i) +{ + int32_t *d =3D vd, *a =3D va, *b =3D vb; + if (a[i] =3D=3D INT32_MIN && b[i] =3D=3D INT32_MIN) { + env->vxsat =3D 0x1; + d[i] =3D INT32_MAX; + } else { + d[i] =3D (int64_t)a[i] * b[i] >> 31; + } +} + +RVPR(kwmmul, 1, 4); + +static inline void do_kwmmul_u(CPURISCVState *env, void *vd, void *va, + void *vb, uint8_t i) +{ + int32_t *d =3D vd, *a =3D va, *b =3D vb; + if (a[i] =3D=3D INT32_MIN && b[i] =3D=3D INT32_MIN) { + env->vxsat =3D 0x1; + d[i] =3D INT32_MAX; + } else { + d[i] =3D ((int64_t)a[i] * b[i] + (1ull << 30)) >> 31; + } +} + +RVPR(kwmmul_u, 1, 4); --=20 2.17.1