From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from esa1.mentor.iphmx.com (esa1.mentor.iphmx.com [68.232.129.153]) by sourceware.org (Postfix) with ESMTPS id 851EF3850417 for ; Wed, 14 Sep 2022 09:41:39 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.1 sourceware.org 851EF3850417 Authentication-Results: sourceware.org; dmarc=none (p=none dis=none) header.from=codesourcery.com Authentication-Results: sourceware.org; spf=pass smtp.mailfrom=mentor.com X-IronPort-AV: E=Sophos;i="5.93,315,1654588800"; d="scan'208,223";a="85736516" Received: from orw-gwy-02-in.mentorg.com ([192.94.38.167]) by esa1.mentor.iphmx.com with ESMTP; 14 Sep 2022 01:41:38 -0800 IronPort-SDR: +nXGJ6fp8mJy9OdsY/nHk8lU+UJVHuHKQe1TGOfB1qqHIrBz0DO1HUwnUKv3XJAT/YLrwXTWUs 75GzaxXyf6XecS+DZXv5rEqxjVo22bYb90LPGedDOEHjmOKMqod0Mc2P0ouYzB/uhyYL+gPpXx rB/sh8Qg1OitTWPxyA1IR83gkgDuGmg+QottpLYIesqe7zwDV4yKgF2Uc9vmioMgvAaeS0o8kp QRJtS5bfAjhoFOQ6onq4jCBQQ27pf6iZSc95jUIyAhxO7hKeHZNNFPjMzP67oFynuKI/GqTpCu yg0= From: Thomas Schwinge To: Tom de Vries CC: Subject: Re: [committed][nvptx] Add uniform_warp_check insn In-Reply-To: <20220201183125.GA4286@delia.home> References: <20220201183125.GA4286@delia.home> User-Agent: Notmuch/0.29.3+94~g74c3f1b (https://notmuchmail.org) Emacs/27.1 (x86_64-pc-linux-gnu) Date: Wed, 14 Sep 2022 11:41:30 +0200 Message-ID: <87fsgumgxh.fsf@euler.schwinge.homeip.net> MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="=-=-=" X-Originating-IP: [137.202.0.90] X-ClientProxiedBy: svr-ies-mbx-09.mgc.mentorg.com (139.181.222.9) To svr-ies-mbx-10.mgc.mentorg.com (139.181.222.10) X-Spam-Status: No, score=-11.9 required=5.0 tests=BAYES_00,GIT_PATCH_0,HEADER_FROM_DIFFERENT_DOMAINS,KAM_DMARC_STATUS,SPF_HELO_PASS,SPF_PASS,TXREP,T_SCC_BODY_TEXT_LINE autolearn=ham autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on server2.sourceware.org List-Id: --=-=-= Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Hi Tom! On 2022-02-01T19:31:27+0100, Tom de Vries via Gcc-patches wrote: > Hi, > > On a GT 1030, with driver version 470.94 and -mptx=3D3.1 I run into: > ... > FAIL: libgomp.oacc-c/../libgomp.oacc-c-c++-common/parallel-dims.c \ > -DACC_DEVICE_TYPE_nvidia=3D1 -DACC_MEM_SHARED=3D0 -foffload=3Dnvptx-non= e \ > -O2 execution test > ... This relates to PR99932 "OpenACC/nvptx offloading execution regressions starting with CUDA 11.2-era Nvidia Driver 460.27.04". You've fixed that for GCC 12+, but testing nvptx offloading for GCC 11, GCC 10 branches on a system with current Nvidia Driver, we're still running into the several FAILs and annoying 'WARNING: program timed out' reported in PR99932. GCC 11, GCC 10 only build '.version 3.1' target libraries, and with "[nvptx] Add bar.warp.sync" in place (which this patch here thus only textually depends on), we've got good test results again. OK to push to GCC 11, GCC 10 branches the attached "[nvptx] Add uniform_warp_check insn"? Gr=C3=BC=C3=9Fe Thomas > which minimizes to the same test-case as listed in commit "[nvptx] > Update default ptx isa to 6.3". > > The problem is again that the first diverging branch is not handled as su= ch in > SASS, which causes problems with a subsequent shfl insn, but given that w= e > have -mptx=3D3.1 we can't use the bar.warp.sync insn. > > Given that the default is now -mptx=3D6.3, and consequently -mptx=3D3.1 i= s of a > lesser importance, implement the next best thing: abort when detecting > non-convergence using this insn: > ... > { .reg.b32 act; > vote.ballot.b32 act,1; > .reg.pred uni; > setp.eq.b32 uni,act,0xffffffff; > @ !uni trap; > @ !uni exit; > } > ... > > Interestingly, the effect of this is that rather than aborting, the test-= case > now passes. > > Tested on x86_64 with nvptx accelerator. > > Committed to trunk. > > Thanks, > - Tom > > [nvptx] Add uniform_warp_check insn > > gcc/ChangeLog: > > 2022-01-31 Tom de Vries > > * config/nvptx/nvptx.cc (nvptx_single): Use nvptx_uniform_warp_chec= k. > * config/nvptx/nvptx.md (define_c_enum "unspecv"): Add > UNSPECV_UNIFORM_WARP_CHECK. > (define_insn "nvptx_uniform_warp_check"): New define_insn. > > --- > gcc/config/nvptx/nvptx.cc | 22 ++++++++++++++++++---- > gcc/config/nvptx/nvptx.md | 18 ++++++++++++++++++ > 2 files changed, 36 insertions(+), 4 deletions(-) > > diff --git a/gcc/config/nvptx/nvptx.cc b/gcc/config/nvptx/nvptx.cc > index 1b91990ca1f..b3bb97c3c14 100644 > --- a/gcc/config/nvptx/nvptx.cc > +++ b/gcc/config/nvptx/nvptx.cc > @@ -4631,15 +4631,29 @@ nvptx_single (unsigned mask, basic_block from, ba= sic_block to) > if (tail_branch) > { > label_insn =3D emit_label_before (label, before); > - if (TARGET_PTX_6_0 && mode =3D=3D GOMP_DIM_VECTOR) > - warp_sync =3D emit_insn_after (gen_nvptx_warpsync (), label_i= nsn); > + if (mode =3D=3D GOMP_DIM_VECTOR) > + { > + if (TARGET_PTX_6_0) > + warp_sync =3D emit_insn_after (gen_nvptx_warpsync (), > + label_insn); > + else > + warp_sync =3D emit_insn_after (gen_nvptx_uniform_warp_che= ck (), > + label_insn); > + } > before =3D label_insn; > } > else > { > label_insn =3D emit_label_after (label, tail); > - if (TARGET_PTX_6_0 && mode =3D=3D GOMP_DIM_VECTOR) > - warp_sync =3D emit_insn_after (gen_nvptx_warpsync (), label_i= nsn); > + if (mode =3D=3D GOMP_DIM_VECTOR) > + { > + if (TARGET_PTX_6_0) > + warp_sync =3D emit_insn_after (gen_nvptx_warpsync (), > + label_insn); > + else > + warp_sync =3D emit_insn_after (gen_nvptx_uniform_warp_che= ck (), > + label_insn); > + } > if ((mode =3D=3D GOMP_DIM_VECTOR || mode =3D=3D GOMP_DIM_WORKER= ) > && CALL_P (tail) && find_reg_note (tail, REG_NORETURN, NULL= )) > emit_insn_after (gen_exit (), label_insn); > diff --git a/gcc/config/nvptx/nvptx.md b/gcc/config/nvptx/nvptx.md > index b4c7cd6e56d..92768dd9e95 100644 > --- a/gcc/config/nvptx/nvptx.md > +++ b/gcc/config/nvptx/nvptx.md > @@ -57,6 +57,7 @@ (define_c_enum "unspecv" [ > UNSPECV_XCHG > UNSPECV_BARSYNC > UNSPECV_WARPSYNC > + UNSPECV_UNIFORM_WARP_CHECK > UNSPECV_MEMBAR > UNSPECV_MEMBAR_CTA > UNSPECV_MEMBAR_GL > @@ -1985,6 +1986,23 @@ (define_insn "nvptx_warpsync" > "\\tbar.warp.sync\\t0xffffffff;" > [(set_attr "predicable" "false")]) > > +(define_insn "nvptx_uniform_warp_check" > + [(unspec_volatile [(const_int 0)] UNSPECV_UNIFORM_WARP_CHECK)] > + "" > + { > + output_asm_insn ("{", NULL); > + output_asm_insn ("\\t" ".reg.b32" "\\t" "act;", NULL); > + output_asm_insn ("\\t" "vote.ballot.b32" "\\t" "act,1;", NULL); > + output_asm_insn ("\\t" ".reg.pred" "\\t" "uni;", NULL); > + output_asm_insn ("\\t" "setp.eq.b32" "\\t" "uni,act,0xfffffff= f;", > + NULL); > + output_asm_insn ("@ !uni\\t" "trap;", NULL); > + output_asm_insn ("@ !uni\\t" "exit;", NULL); > + output_asm_insn ("}", NULL); > + return ""; > + } > + [(set_attr "predicable" "false")]) > + > (define_expand "memory_barrier" > [(set (match_dup 0) > (unspec_volatile:BLK [(match_dup 0)] UNSPECV_MEMBAR))] ----------------- Siemens Electronic Design Automation GmbH; Anschrift: Arnulfstra=C3=9Fe 201= , 80634 M=C3=BCnchen; Gesellschaft mit beschr=C3=A4nkter Haftung; Gesch=C3= =A4ftsf=C3=BChrer: Thomas Heurung, Frank Th=C3=BCrauf; Sitz der Gesellschaf= t: M=C3=BCnchen; Registergericht M=C3=BCnchen, HRB 106955 --=-=-= Content-Type: text/x-diff Content-Disposition: inline; filename="0001-nvptx-Add-uniform_warp_check-insn.patch" >From 8128d1ef7f7c1d6a65122845f7ba8ce87e867851 Mon Sep 17 00:00:00 2001 From: Tom de Vries Date: Fri, 28 Jan 2022 10:28:59 +0100 Subject: [PATCH] [nvptx] Add uniform_warp_check insn On a GT 1030, with driver version 470.94 and -mptx=3.1 I run into: ... FAIL: libgomp.oacc-c/../libgomp.oacc-c-c++-common/parallel-dims.c \ -DACC_DEVICE_TYPE_nvidia=1 -DACC_MEM_SHARED=0 -foffload=nvptx-none \ -O2 execution test ... which minimizes to the same test-case as listed in commit "[nvptx] Update default ptx isa to 6.3". The problem is again that the first diverging branch is not handled as such in SASS, which causes problems with a subsequent shfl insn, but given that we have -mptx=3.1 we can't use the bar.warp.sync insn. Given that the default is now -mptx=6.3, and consequently -mptx=3.1 is of a lesser importance, implement the next best thing: abort when detecting non-convergence using this insn: ... { .reg.b32 act; vote.ballot.b32 act,1; .reg.pred uni; setp.eq.b32 uni,act,0xffffffff; @ !uni trap; @ !uni exit; } ... Interestingly, the effect of this is that rather than aborting, the test-case now passes. Tested on x86_64 with nvptx accelerator. gcc/ChangeLog: 2022-01-31 Tom de Vries * config/nvptx/nvptx.c (nvptx_single): Use nvptx_uniform_warp_check. * config/nvptx/nvptx.md (define_c_enum "unspecv"): Add UNSPECV_UNIFORM_WARP_CHECK. (define_insn "nvptx_uniform_warp_check"): New define_insn. (cherry picked from commit f32f74c2e8cef5fe37af6d4e8d7e8f6b4c8ae9a8) --- gcc/config/nvptx/nvptx.c | 22 ++++++++++++++++++---- gcc/config/nvptx/nvptx.md | 18 ++++++++++++++++++ 2 files changed, 36 insertions(+), 4 deletions(-) diff --git a/gcc/config/nvptx/nvptx.c b/gcc/config/nvptx/nvptx.c index 6782f13f787..6618b6fdc39 100644 --- a/gcc/config/nvptx/nvptx.c +++ b/gcc/config/nvptx/nvptx.c @@ -4425,15 +4425,29 @@ nvptx_single (unsigned mask, basic_block from, basic_block to) if (tail_branch) { label_insn = emit_label_before (label, before); - if (TARGET_PTX_6_0 && mode == GOMP_DIM_VECTOR) - warp_sync = emit_insn_after (gen_nvptx_warpsync (), label_insn); + if (mode == GOMP_DIM_VECTOR) + { + if (TARGET_PTX_6_0) + warp_sync = emit_insn_after (gen_nvptx_warpsync (), + label_insn); + else + warp_sync = emit_insn_after (gen_nvptx_uniform_warp_check (), + label_insn); + } before = label_insn; } else { label_insn = emit_label_after (label, tail); - if (TARGET_PTX_6_0 && mode == GOMP_DIM_VECTOR) - warp_sync = emit_insn_after (gen_nvptx_warpsync (), label_insn); + if (mode == GOMP_DIM_VECTOR) + { + if (TARGET_PTX_6_0) + warp_sync = emit_insn_after (gen_nvptx_warpsync (), + label_insn); + else + warp_sync = emit_insn_after (gen_nvptx_uniform_warp_check (), + label_insn); + } if ((mode == GOMP_DIM_VECTOR || mode == GOMP_DIM_WORKER) && CALL_P (tail) && find_reg_note (tail, REG_NORETURN, NULL)) emit_insn_after (gen_exit (), label_insn); diff --git a/gcc/config/nvptx/nvptx.md b/gcc/config/nvptx/nvptx.md index b2350ab0d2d..34062027312 100644 --- a/gcc/config/nvptx/nvptx.md +++ b/gcc/config/nvptx/nvptx.md @@ -56,6 +56,7 @@ UNSPECV_XCHG UNSPECV_BARSYNC UNSPECV_WARPSYNC + UNSPECV_UNIFORM_WARP_CHECK UNSPECV_MEMBAR UNSPECV_MEMBAR_CTA UNSPECV_DIM_POS @@ -1483,6 +1484,23 @@ "\\tbar.warp.sync\\t0xffffffff;" [(set_attr "predicable" "false")]) +(define_insn "nvptx_uniform_warp_check" + [(unspec_volatile [(const_int 0)] UNSPECV_UNIFORM_WARP_CHECK)] + "" + { + output_asm_insn ("{", NULL); + output_asm_insn ("\\t" ".reg.b32" "\\t" "act;", NULL); + output_asm_insn ("\\t" "vote.ballot.b32" "\\t" "act,1;", NULL); + output_asm_insn ("\\t" ".reg.pred" "\\t" "uni;", NULL); + output_asm_insn ("\\t" "setp.eq.b32" "\\t" "uni,act,0xffffffff;", + NULL); + output_asm_insn ("@ !uni\\t" "trap;", NULL); + output_asm_insn ("@ !uni\\t" "exit;", NULL); + output_asm_insn ("}", NULL); + return ""; + } + [(set_attr "predicable" "false")]) + (define_expand "memory_barrier" [(set (match_dup 0) (unspec_volatile:BLK [(match_dup 0)] UNSPECV_MEMBAR))] -- 2.35.1 --=-=-=--