From patchwork Fri May 5 14:12:39 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "juzhe.zhong@rivai.ai" X-Patchwork-Id: 90455 Return-Path: Delivered-To: ouuuleilei@gmail.com Received: by 2002:a59:b0ea:0:b0:3b6:4342:cba0 with SMTP id b10csp437523vqo; Fri, 5 May 2023 07:13:30 -0700 (PDT) X-Google-Smtp-Source: ACHHUZ7Sii8RL54jbsPnU9Noi10phLcNQ647vRbpfpO6fa8EMxQMmCuaBrcpT/xEjzPZPMWS4zyh X-Received: by 2002:a17:906:dc93:b0:94f:a292:20cc with SMTP id cs19-20020a170906dc9300b0094fa29220ccmr1429939ejc.41.1683296010568; Fri, 05 May 2023 07:13:30 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1683296010; cv=none; d=google.com; s=arc-20160816; b=MtLYjmEYDcs+Tt0rTmZlmf5GcrdHtAAZwhAY0PG+71sVkIbTBeoEg6kp8lKXhNicib aBh/9bPzWD5804uyed/dJ5wt5x1fZZxKlBc3uDnBrRce3eKyelJtqrrqM+BWDP9IFkJ7 yEYhgBBu/mHS66X15PscB1WeP/uzyT8I/cYAdIAoUQimy1+wpmTab/a0AlWU2JKFP8Yo ocBqybdVzDahTRbgY0XKUFRMS29G8eQe71mTEUhrwqfuujG3ZQEv3ZBYrIbqSXE2e7RB L8RqGSlh7mHoWNJZwD4VqOv64P0XrOcAIGTMvEvKV1IDF2j6Bspvv8HpvDib8JD1YFMM +D7g== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:feedback-id :content-transfer-encoding:mime-version:message-id:date:subject:cc :to:from:dmarc-filter:delivered-to; bh=xNlq/N2MHedpyvB8Vc2Stb7Rdzxrto5gZoc9zZfm12U=; b=YMJ10sBhgk7570CKCSYjJF6f66o4NDzeaJQVkzhDyByHZkxbILhU1EzMSR9LS/IMuF U28XLF0zn71bT11XSVmUZrWnDfKe+PCSqPUP5GWjW/+L0sElh/UCdJu1hc8D54HuFjB1 M4+Gac5EWn/mOZ/k74CSVYIMIyGLB7/MGj+l5xOYBd1o+pq3alQsdTvO7P+5oIWvDNQ7 KcsAY1W+vvc7O2IFp333z5tx/lKXDpuDcUMeXbUOUHB+0muvCFP/huzdnaXImLGrFoPH MSXmZuZITS2ZQlEesEsNHrP0V7WmANwVi6MXI5Evl4gRZXwvuN8eeV7HmTX6u+3/Qa+X MwRA== ARC-Authentication-Results: i=1; mx.google.com; spf=pass (google.com: domain of gcc-patches-bounces+ouuuleilei=gmail.com@gcc.gnu.org designates 8.43.85.97 as permitted sender) smtp.mailfrom="gcc-patches-bounces+ouuuleilei=gmail.com@gcc.gnu.org" Received: from sourceware.org (server2.sourceware.org. [8.43.85.97]) by mx.google.com with ESMTPS id ge14-20020a170907908e00b009617ad9d89dsi1326050ejb.38.2023.05.05.07.13.30 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Fri, 05 May 2023 07:13:30 -0700 (PDT) Received-SPF: pass (google.com: domain of gcc-patches-bounces+ouuuleilei=gmail.com@gcc.gnu.org designates 8.43.85.97 as permitted sender) client-ip=8.43.85.97; Authentication-Results: mx.google.com; spf=pass (google.com: domain of gcc-patches-bounces+ouuuleilei=gmail.com@gcc.gnu.org designates 8.43.85.97 as permitted sender) smtp.mailfrom="gcc-patches-bounces+ouuuleilei=gmail.com@gcc.gnu.org" Received: from server2.sourceware.org (localhost [IPv6:::1]) by sourceware.org (Postfix) with ESMTP id A18453856278 for ; Fri, 5 May 2023 14:13:16 +0000 (GMT) X-Original-To: gcc-patches@gcc.gnu.org Delivered-To: gcc-patches@gcc.gnu.org Received: from smtpbgeu2.qq.com (smtpbgeu2.qq.com [18.194.254.142]) by sourceware.org (Postfix) with ESMTPS id 21C3E3858D20 for ; Fri, 5 May 2023 14:12:47 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.2 sourceware.org 21C3E3858D20 Authentication-Results: sourceware.org; dmarc=none (p=none dis=none) header.from=rivai.ai Authentication-Results: sourceware.org; spf=pass smtp.mailfrom=rivai.ai X-QQ-mid: bizesmtp67t1683295963t7u1r1kr Received: from rios-cad5.localdomain ( [58.60.1.11]) by bizesmtp.qq.com (ESMTP) with id ; Fri, 05 May 2023 22:12:42 +0800 (CST) X-QQ-SSF: 01400000000000F0Q000000A0000000 X-QQ-FEAT: eTp2eCgHrZmMfQFpJKKPzJC+wbW0fwFnI7HVE8NgZcTPpCY2Tj3UhYYwMwe1u OzPUI/CW787gLwUhlV/M4Dt+QijbFed+s56Uphu5Zu4X6NGwoh2d70MKhRDiuubz1F0n7ST 6APJorhA6TTD7Xn/47HnW20VGS1yQCzMNu4E9tGi9tF92gZ/Mx7HcpVrF+MvoPKgJT5lZgz 6gY4qf3cwjB8XMJESLb++x3QH4A1XZGN/3Ij2WL8oH2M618x/bRmnKhRYeX9/QhbKZhpVO8 Bba1VhxhnN36B5mxRceEHe40Mk8syhi4/hRAyw6JjInxQxBI/8opqx67FkuvM1DyvME0Vjp 1wQkWZt10hcVbLlnGw3FrLXrFzaRQwE7vJ4R1QUgeUAg/LbAIIwuAnP0JkDm5JuqsD3S9kY +zFKidRl/js= X-QQ-GoodBg: 2 X-BIZMAIL-ID: 948424680844889306 From: juzhe.zhong@rivai.ai To: gcc-patches@gcc.gnu.org Cc: kito.cheng@gmail.com, Juzhe-Zhong Subject: [PATCH V2] RISC-V: Fix incorrect demand info merge in local vsetvli optimization [PR109748] Date: Fri, 5 May 2023 22:12:39 +0800 Message-Id: <20230505141239.1323841-1-juzhe.zhong@rivai.ai> X-Mailer: git-send-email 2.36.3 MIME-Version: 1.0 X-QQ-SENDSIZE: 520 Feedback-ID: bizesmtp:rivai.ai:qybglogicsvrgz:qybglogicsvrgz7a-one-0 X-Spam-Status: No, score=-11.0 required=5.0 tests=BAYES_00, GIT_PATCH_0, KAM_DMARC_STATUS, KAM_SHORT, LIKELY_SPAM_BODY, RCVD_IN_DNSWL_NONE, RCVD_IN_MSPIKE_H2, SCC_5_SHORT_WORD_LINES, SPF_PASS, TXREP, T_SCC_BODY_TEXT_LINE, T_SPF_HELO_TEMPERROR autolearn=ham autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on server2.sourceware.org X-BeenThere: gcc-patches@gcc.gnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Gcc-patches mailing list List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: gcc-patches-bounces+ouuuleilei=gmail.com@gcc.gnu.org Sender: "Gcc-patches" X-getmail-retrieved-from-mailbox: =?utf-8?q?INBOX?= X-GMAIL-THRID: =?utf-8?q?1765063797282467067?= X-GMAIL-MSGID: =?utf-8?q?1765063797282467067?= From: Juzhe-Zhong This patch is fixing my recent optimization patch: https://github.com/gcc-mirror/gcc/commit/d51f2456ee51bd59a79b4725ca0e488c25260bbf In that patch, the new_info = parse_insn (i) is not correct. Since consider the following case: vsetvli a5,a4, e8,m1 .. vsetvli zero,a5, e32, m4 vle8.v vmacc.vv ... Since we have backward demand fusion in Phase 1, so the real demand of "vle8.v" is e32, m4. However, if we use parse_insn (vle8.v) = e8, m1 which is not correct. So this patch we change new_info = new_info.parse_insn (i) into: vector_insn_info new_info = m_vector_manager->vector_insn_infos[i->uid ()]; So that, we can correctly optimize codes into: vsetvli a5,a4, e32, m4 .. .. (vsetvli zero,a5, e32, m4 is removed) vle8.v vmacc.vv Since m_vector_manager->vector_insn_infos is the member variable of pass_vsetvl class. We remove static void function "local_eliminate_vsetvl_insn", and make it as the member function of pass_vsetvl class. PR target/109748 gcc/ChangeLog: * config/riscv/riscv-vsetvl.cc (local_eliminate_vsetvl_insn): Remove it. (pass_vsetvl::local_eliminate_vsetvl_insn): New function. gcc/testsuite/ChangeLog: * gcc.target/riscv/rvv/vsetvl/pr109748.c: New test. --- gcc/config/riscv/riscv-vsetvl.cc | 102 ++++++++++-------- .../gcc.target/riscv/rvv/vsetvl/pr109748.c | 36 +++++++ 2 files changed, 93 insertions(+), 45 deletions(-) create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/pr109748.c diff --git a/gcc/config/riscv/riscv-vsetvl.cc b/gcc/config/riscv/riscv-vsetvl.cc index 39b4d21210b..e1efd7b1c40 100644 --- a/gcc/config/riscv/riscv-vsetvl.cc +++ b/gcc/config/riscv/riscv-vsetvl.cc @@ -1056,51 +1056,6 @@ change_vsetvl_insn (const insn_info *insn, const vector_insn_info &info) change_insn (rinsn, new_pat); } -static void -local_eliminate_vsetvl_insn (const vector_insn_info &dem) -{ - const insn_info *insn = dem.get_insn (); - if (!insn || insn->is_artificial ()) - return; - rtx_insn *rinsn = insn->rtl (); - const bb_info *bb = insn->bb (); - if (vsetvl_insn_p (rinsn)) - { - rtx vl = get_vl (rinsn); - for (insn_info *i = insn->next_nondebug_insn (); - real_insn_and_same_bb_p (i, bb); i = i->next_nondebug_insn ()) - { - if (i->is_call () || i->is_asm () - || find_access (i->defs (), VL_REGNUM) - || find_access (i->defs (), VTYPE_REGNUM)) - return; - - if (has_vtype_op (i->rtl ())) - { - if (!vsetvl_discard_result_insn_p (PREV_INSN (i->rtl ()))) - return; - rtx avl = get_avl (i->rtl ()); - if (avl != vl) - return; - set_info *def = find_access (i->uses (), REGNO (avl))->def (); - if (def->insn () != insn) - return; - - vector_insn_info new_info; - new_info.parse_insn (i); - if (!new_info.skip_avl_compatible_p (dem)) - return; - - new_info.set_avl_info (dem.get_avl_info ()); - new_info = dem.merge (new_info, LOCAL_MERGE); - change_vsetvl_insn (insn, new_info); - eliminate_insn (PREV_INSN (i->rtl ())); - return; - } - } - } -} - static bool source_equal_p (insn_info *insn1, insn_info *insn2) { @@ -2672,6 +2627,7 @@ private: void pre_vsetvl (void); /* Phase 5. */ + void local_eliminate_vsetvl_insn (const vector_insn_info &) const; void cleanup_insns (void) const; /* Phase 6. */ @@ -3993,6 +3949,62 @@ pass_vsetvl::pre_vsetvl (void) commit_edge_insertions (); } +/* Local user vsetvl optimizaiton: + + Case 1: + vsetvl a5,a4,e8,mf8 + ... + vsetvl zero,a5,e8,mf8 --> Eliminate directly. + + Case 2: + vsetvl a5,a4,e8,mf8 --> vsetvl a5,a4,e32,mf2 + ... + vsetvl zero,a5,e32,mf2 --> Eliminate directly. */ +void +pass_vsetvl::local_eliminate_vsetvl_insn (const vector_insn_info &dem) const +{ + const insn_info *insn = dem.get_insn (); + if (!insn || insn->is_artificial ()) + return; + rtx_insn *rinsn = insn->rtl (); + const bb_info *bb = insn->bb (); + if (vsetvl_insn_p (rinsn)) + { + rtx vl = get_vl (rinsn); + for (insn_info *i = insn->next_nondebug_insn (); + real_insn_and_same_bb_p (i, bb); i = i->next_nondebug_insn ()) + { + if (i->is_call () || i->is_asm () + || find_access (i->defs (), VL_REGNUM) + || find_access (i->defs (), VTYPE_REGNUM)) + return; + + if (has_vtype_op (i->rtl ())) + { + if (!vsetvl_discard_result_insn_p (PREV_INSN (i->rtl ()))) + return; + rtx avl = get_avl (i->rtl ()); + if (avl != vl) + return; + set_info *def = find_access (i->uses (), REGNO (avl))->def (); + if (def->insn () != insn) + return; + + vector_insn_info new_info + = m_vector_manager->vector_insn_infos[i->uid ()]; + if (!new_info.skip_avl_compatible_p (dem)) + return; + + new_info.set_avl_info (dem.get_avl_info ()); + new_info = dem.merge (new_info, LOCAL_MERGE); + change_vsetvl_insn (insn, new_info); + eliminate_insn (PREV_INSN (i->rtl ())); + return; + } + } + } +} + /* Before VSETVL PASS, RVV instructions pattern is depending on AVL operand implicitly. Since we will emit VSETVL instruction and make RVV instructions depending on VL/VTYPE global status registers, we remove the such AVL operand diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/pr109748.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/pr109748.c new file mode 100644 index 00000000000..81c42c5a82a --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/pr109748.c @@ -0,0 +1,36 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-tree-vectorize -fno-schedule-insns -fno-schedule-insns2" } */ + +#include "riscv_vector.h" + +int byte_mac_vec(unsigned char *a, unsigned char *b, int len) { + size_t vlmax = __riscv_vsetvlmax_e8m1(); + vint32m4_t vec_s = __riscv_vmv_v_x_i32m4(0, vlmax); + vint32m1_t vec_zero = __riscv_vmv_v_x_i32m1(0, vlmax); + int k = len; + + for (size_t vl; k > 0; k -= vl, a += vl, b += vl) { + vl = __riscv_vsetvl_e8m1(k); + + vuint8m1_t a8s = __riscv_vle8_v_u8m1(a, vl); + vuint8m1_t b8s = __riscv_vle8_v_u8m1(b, vl); + vuint32m4_t a8s_extended = __riscv_vzext_vf4_u32m4(a8s, vl); + vuint32m4_t b8s_extended = __riscv_vzext_vf4_u32m4(a8s, vl); + + vint32m4_t a8s_as_i32 = __riscv_vreinterpret_v_u32m4_i32m4(a8s_extended); + vint32m4_t b8s_as_i32 = __riscv_vreinterpret_v_u32m4_i32m4(b8s_extended); + + vec_s = __riscv_vmacc_vv_i32m4_tu(vec_s, a8s_as_i32, b8s_as_i32, vl); + } + + vint32m1_t vec_sum = __riscv_vredsum_vs_i32m4_i32m1(vec_s, vec_zero, __riscv_vsetvl_e32m4(len)); + int sum = __riscv_vmv_x_s_i32m1_i32(vec_sum); + + return sum; +} + +/* { dg-final { scan-assembler-times {vsetvli\s+zero,\s*[a-x0-9]+,\s*e32,\s*m1,\s*t[au],\s*m[au]} 1 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-Oz" no-opts "-g" no-opts "-funroll-loops" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+[a-x0-9]+,\s*zero,\s*e32,\s*m4,\s*t[au],\s*m[au]} 1 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-Oz" no-opts "-g" no-opts "-funroll-loops" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+zero,\s*[a-x0-9]+,\s*e32,\s*m4,\s*t[au],\s*m[au]} 1 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-Oz" no-opts "-g" no-opts "-funroll-loops" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+[a-x0-9]+,\s*[a-x0-9]+,\s*e32,\s*m4,\s*tu,\s*m[au]} 1 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-Oz" no-opts "-g" no-opts "-funroll-loops" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli} 4 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-Oz" no-opts "-g" no-opts "-funroll-loops" } } } } */