From nobody Tue Feb 10 20:30:04 2026 Delivered-To: importer@patchew.org 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; 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=1585588405; cv=none; d=zohomail.com; s=zohoarc; b=DmP1zsdSTB8RRJW7cHcWeZojGYM/H0lre+xhkKeS8GszT4HP0xu0ANvwyIs0VKbzE9qqQW81O7sPPud0nYWbsUbzydPAIs/vCoIM7bNLV8XJxBoXWDwHQS1zKVgClDUgxRXwIBYLmOm5weFig8t5Xn7ViLbWUQ9YnSQ3P0QIaKo= ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=zohomail.com; s=zohoarc; t=1585588405; 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=yHtbIeJ9ycaUK5dMZjp8a8WKpS5gduh1QFDClJ/Ddj4=; b=LW2HVYJudYgYn+WW+qgVeR3CAIzrlR7eFrBA2VRZfRdqYmLPPTzeLexR9yK++NGeqHRT/PJZwYxvHnW7Q2j3LJZbLPuqEh5gd+g1G7qe1RRm4M1hTxKpTD6Vo8gfwL/uNj+zrgON0IfGQs72uOsT+y/bVFYwL9u23+8QOonKG3I= 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 1585588405264893.1783961078299; Mon, 30 Mar 2020 10:13:25 -0700 (PDT) Received: from localhost ([::1]:53428 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1jIxyV-0002wo-Ii for importer@patchew.org; Mon, 30 Mar 2020 13:13:23 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]:58125) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1jIxwr-0000ut-1U for qemu-devel@nongnu.org; Mon, 30 Mar 2020 13:11:42 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1jIxwp-0006WS-I7 for qemu-devel@nongnu.org; Mon, 30 Mar 2020 13:11:40 -0400 Received: from smtp2200-217.mail.aliyun.com ([121.197.200.217]:39773) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1jIxwp-0006OI-3k; Mon, 30 Mar 2020 13:11:39 -0400 Received: from L-PF1D6DP4-1208.hz.ali.com(mailfrom:zhiwei_liu@c-sky.com fp:SMTPD_---.H7lTFzy_1585588291) by smtp.aliyun-inc.com(10.147.41.231); Tue, 31 Mar 2020 01:11:32 +0800 X-Alimail-AntiSpam: AC=PASS; BC=0.07464302|-1; BR=01201311R151ee; CH=green; DM=|OVERLOAD|false|; DS=SPAM|spam_blackmail|0.892561-9.6942e-05-0.107342; FP=0|0|0|0|0|-1|-1|-1; HT=e02c03297; MF=zhiwei_liu@c-sky.com; NM=1; PH=DS; RN=10; RT=10; SR=0; TI=SMTPD_---.H7lTFzy_1585588291; From: LIU Zhiwei To: richard.henderson@linaro.org, alistair23@gmail.com, chihmin.chao@sifive.com, palmer@dabbelt.com Subject: [PATCH v7 47/61] target/riscv: vector single-width floating-point reduction instructions Date: Mon, 30 Mar 2020 23:36:19 +0800 Message-Id: <20200330153633.15298-48-zhiwei_liu@c-sky.com> X-Mailer: git-send-email 2.23.0 In-Reply-To: <20200330153633.15298-1-zhiwei_liu@c-sky.com> References: <20200330153633.15298-1-zhiwei_liu@c-sky.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-detected-operating-system: by eggs.gnu.org: GNU/Linux 3.x [generic] [fuzzy] X-Received-From: 121.197.200.217 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: guoren@linux.alibaba.com, qemu-riscv@nongnu.org, qemu-devel@nongnu.org, wxy194768@alibaba-inc.com, wenmeng_zhang@c-sky.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 --- target/riscv/helper.h | 10 +++++++ target/riscv/insn32.decode | 4 +++ target/riscv/insn_trans/trans_rvv.inc.c | 5 ++++ target/riscv/vector_helper.c | 39 +++++++++++++++++++++++++ 4 files changed, 58 insertions(+) diff --git a/target/riscv/helper.h b/target/riscv/helper.h index ce31577ea9..17fd02c323 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -1073,3 +1073,13 @@ DEF_HELPER_6(vwredsumu_vs_w, void, ptr, ptr, ptr, pt= r, env, i32) DEF_HELPER_6(vwredsum_vs_b, void, ptr, ptr, ptr, ptr, env, i32) DEF_HELPER_6(vwredsum_vs_h, void, ptr, ptr, ptr, ptr, env, i32) DEF_HELPER_6(vwredsum_vs_w, void, ptr, ptr, ptr, ptr, env, i32) + +DEF_HELPER_6(vfredsum_vs_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfredsum_vs_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfredsum_vs_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfredmax_vs_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfredmax_vs_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfredmax_vs_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfredmin_vs_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfredmin_vs_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfredmin_vs_d, void, ptr, ptr, ptr, ptr, env, i32) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index b69d804fda..0592075167 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -539,6 +539,10 @@ vredmaxu_vs 000110 . ..... ..... 010 ..... 1010111= @r_vm vredmax_vs 000111 . ..... ..... 010 ..... 1010111 @r_vm vwredsumu_vs 110000 . ..... ..... 000 ..... 1010111 @r_vm vwredsum_vs 110001 . ..... ..... 000 ..... 1010111 @r_vm +# Vector ordered and unordered reduction sum +vfredsum_vs 0000-1 . ..... ..... 001 ..... 1010111 @r_vm +vfredmin_vs 000101 . ..... ..... 001 ..... 1010111 @r_vm +vfredmax_vs 000111 . ..... ..... 001 ..... 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 52cb4bc489..069ece985b 100644 --- a/target/riscv/insn_trans/trans_rvv.inc.c +++ b/target/riscv/insn_trans/trans_rvv.inc.c @@ -2361,3 +2361,8 @@ GEN_OPIVV_TRANS(vredxor_vs, reduction_check) /* Vector Widening Integer Reduction Instructions */ GEN_OPIVV_WIDEN_TRANS(vwredsum_vs, reduction_check) GEN_OPIVV_WIDEN_TRANS(vwredsumu_vs, reduction_check) + +/* Vector Single-Width Floating-Point Reduction Instructions */ +GEN_OPFVV_TRANS(vfredsum_vs, reduction_check) +GEN_OPFVV_TRANS(vfredmax_vs, reduction_check) +GEN_OPFVV_TRANS(vfredmin_vs, reduction_check) diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index 5035e0bb0e..f37b65288a 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -4416,3 +4416,42 @@ GEN_VEXT_RED(vwredsum_vs_w, int64_t, int32_t, H8, H4= , DO_ADD, clearq) GEN_VEXT_RED(vwredsumu_vs_b, uint16_t, uint8_t, H2, H1, DO_ADD, clearh) GEN_VEXT_RED(vwredsumu_vs_h, uint32_t, uint16_t, H4, H2, DO_ADD, clearl) GEN_VEXT_RED(vwredsumu_vs_w, uint64_t, uint32_t, H8, H4, DO_ADD, clearq) + +/* Vector Single-Width Floating-Point Reduction Instructions */ +#define GEN_VEXT_FRED(NAME, TD, TS2, HD, HS2, OP, CLEAR_FN)\ +void HELPER(NAME)(void *vd, void *v0, void *vs1, \ + void *vs2, CPURISCVState *env, \ + uint32_t desc) \ +{ \ + uint32_t mlen =3D vext_mlen(desc); \ + uint32_t vm =3D vext_vm(desc); \ + uint32_t vl =3D env->vl; \ + uint32_t i; \ + uint32_t tot =3D env_archcpu(env)->cfg.vlen / 8; \ + TD s1 =3D *((TD *)vs1 + HD(0)); \ + \ + for (i =3D 0; i < vl; i++) { \ + TS2 s2 =3D *((TS2 *)vs2 + HS2(i)); \ + if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + continue; \ + } \ + s1 =3D OP(s1, (TD)s2, &env->fp_status); \ + } \ + *((TD *)vd + HD(0)) =3D s1; \ + CLEAR_FN(vd, 1, sizeof(TD), tot); \ +} + +/* Unordered sum */ +GEN_VEXT_FRED(vfredsum_vs_h, uint16_t, uint16_t, H2, H2, float16_add, clea= rh) +GEN_VEXT_FRED(vfredsum_vs_w, uint32_t, uint32_t, H4, H4, float32_add, clea= rl) +GEN_VEXT_FRED(vfredsum_vs_d, uint64_t, uint64_t, H8, H8, float64_add, clea= rq) + +/* Maximum value */ +GEN_VEXT_FRED(vfredmax_vs_h, uint16_t, uint16_t, H2, H2, float16_maxnum, c= learh) +GEN_VEXT_FRED(vfredmax_vs_w, uint32_t, uint32_t, H4, H4, float32_maxnum, c= learl) +GEN_VEXT_FRED(vfredmax_vs_d, uint64_t, uint64_t, H8, H8, float64_maxnum, c= learq) + +/* Minimum value */ +GEN_VEXT_FRED(vfredmin_vs_h, uint16_t, uint16_t, H2, H2, float16_minnum, c= learh) +GEN_VEXT_FRED(vfredmin_vs_w, uint32_t, uint32_t, H4, H4, float32_minnum, c= learl) +GEN_VEXT_FRED(vfredmin_vs_d, uint64_t, uint64_t, H8, H8, float64_minnum, c= learq) --=20 2.23.0