[PATCH] D104677: [OpenMP][AMDGCN] Apply fix for isnan, isinf and isfinite for amdgcn.

estewart08 updated this revision to Diff 353773. estewart08 added a comment. Add test_isnan function to hip-header.hip. Repository: rG LLVM Github Monorepo CHANGES SINCE LAST ACTION https://reviews.llvm.org/D104677/new/ https://reviews.llvm.org/D104677 Files:

[PATCH] D104677: [OpenMP][AMDGCN] Apply fix for isnan, isinf and isfinite for amdgcn.

estewart08 added inline comments. Comment at: clang/test/Headers/hip-header.hip:21 +// RUN: -target-cpu gfx906 -emit-llvm %s -fcuda-is-device -o - \ +// RUN: -D__HIPCC_RTC__ -DUSE_ISNAN_WITH_INT_RETURN | FileCheck %s -check-prefixes=AMD_INT_RETURN +// RUN: %clang_cc1

[PATCH] D104677: [OpenMP] Apply fix for isnan, isinf and isinfinite for amdgcn.

estewart08 updated this revision to Diff 353527. estewart08 added a comment. Attempt to use clang-format. Repository: rG LLVM Github Monorepo CHANGES SINCE LAST ACTION https://reviews.llvm.org/D104677/new/ https://reviews.llvm.org/D104677 Files: clang/lib/Headers/__clang_hip_cmath.h

[PATCH] D104677: [OpenMP] Apply fix for isnan, isinf and isinfinite for amdgcn.

estewart08 created this revision. Herald added subscribers: guansong, yaxunl. estewart08 requested review of this revision. Herald added a reviewer: jdoerfert. Herald added subscribers: cfe-commits, sstefan1. Herald added a project: clang. This fixes issues with various return types(bool/int) and

[PATCH] D101911: [OPENMP]Fix PR48851: the locals are not globalized in SPMD mode.

estewart08 accepted this revision. estewart08 added a comment. This revision is now accepted and ready to land. LGTM as a temporary workaround until SPMD properly assigns team private variables. Repository: rG LLVM Github Monorepo CHANGES SINCE LAST ACTION

[PATCH] D101911: [OPENMP]Fix PR48851: the locals are not globalized in SPMD mode.

estewart08 added a comment. In D101911#2738994 , @ABataev wrote: > Hi Ethan, try this patch if it fixes the issue. Tested this on gfx906 and v100, the main reproducer now passes. Repository: rG LLVM Github Monorepo CHANGES SINCE LAST ACTION

[PATCH] D104904: [OpenMP][AMDGCN] Initial math headers support

estewart08 added inline comments. Comment at: clang/test/Headers/Inputs/include/cstdlib:29 float fabs(float __x) { return __builtin_fabs(__x); } +#endif JonChesterfield wrote: > jdoerfert wrote: > > That seems to be fundamentally broken then, but let's see,

[PATCH] D99432: [OPENMP]Fix PR48851: the locals are not globalized in SPMD mode.

estewart08 added a comment. In D99432#2726025 , @ABataev wrote: > In D99432#2726019 , @estewart08 > wrote: > >> In reference to https://bugs.llvm.org/show_bug.cgi?id=48851, I do not see >> how this helps SPMD

[PATCH] D99432: [OPENMP]Fix PR48851: the locals are not globalized in SPMD mode.

estewart08 added a comment. In D99432#2726391 , @ABataev wrote: > In D99432#2726337 , @estewart08 > wrote: > >> In D99432#2726060 , @ABataev wrote: >> >>> In D99432#2726050

[PATCH] D99432: [OPENMP]Fix PR48851: the locals are not globalized in SPMD mode.

estewart08 added a comment. In reference to https://bugs.llvm.org/show_bug.cgi?id=48851, I do not see how this helps SPMD mode with team privatization of declarations in-between target teams and parallel regions. Repository: rG LLVM Github Monorepo CHANGES SINCE LAST ACTION

[PATCH] D99432: [OPENMP]Fix PR48851: the locals are not globalized in SPMD mode.

estewart08 added a comment. In D99432#2726845 , @ABataev wrote: > In D99432#2726588 , @estewart08 > wrote: > >> In D99432#2726391 , @ABataev wrote: >> >>> In D99432#2726337

[PATCH] D99432: [OPENMP]Fix PR48851: the locals are not globalized in SPMD mode.

estewart08 added a comment. In D99432#2726060 , @ABataev wrote: > In D99432#2726050 , @estewart08 > wrote: > >> In D99432#2726025 , @ABataev wrote: >> >>> In D99432#2726019

[PATCH] D99432: [OPENMP]Fix PR48851: the locals are not globalized in SPMD mode.

estewart08 added a comment. In D99432#2728788 , @ABataev wrote: > In D99432#2726997 , @estewart08 > wrote: > >> In D99432#2726845 , @ABataev wrote: >> >>> In D99432#2726588

[PATCH] D99432: [OPENMP]Fix PR48851: the locals are not globalized in SPMD mode.

estewart08 added a comment. In D99432#2736981 , @ABataev wrote: > In D99432#2736970 , @estewart08 > wrote: > >> In D99432#2728788 , @ABataev wrote: >> >>> In D99432#2726997

[PATCH] D104904: [OpenMP][AMDGCN] Initial math headers support

estewart08 added a comment. In D104904#2913983 , @ye-luo wrote: > how to get this moving? We are working on some additions to this patch. The lit failure noted above has been fixed locally. I would expect an update here very soon. Repository: rG

[PATCH] D109885: [MLIR][[amdgpu-arch]][OpenMP] Remove direct dependency on /opt/rocm

estewart08 added a comment. In D109885#3194819 , @ronlieb wrote: > @estewart08 thoughts on a good CMAKE variable to allow users to define > equivalent of /opt/rocm ? and not use environment variable inside the > cmake file. I would be ok with the

[PATCH] D115661: [clang][amdgpu] - Choose when to promote VarDecl to address space 4.

estewart08 added a comment. In D115661#3190477 , @yaxunl wrote: > This may cause perf regressions for HIP. Do you have a test that would show such a regression? Emitting a store to address space (4) in a constructor seems the wrong thing to do.

[PATCH] D115661: [clang][amdgpu] - Choose when to promote VarDecl to address space 4.

estewart08 added a comment. In D115661#3193157 , @arsenm wrote: > In D115661#3193152 , @yaxunl wrote: > >> In D115661#3192983 , @estewart08 >> wrote: >> >>> In

[PATCH] D115661: [clang][amdgpu] - Choose when to promote VarDecl to address space 4.

This revision was not accepted when it landed; it landed in state "Needs Revision". This revision was landed with ongoing or failed builds. This revision was automatically updated to reflect the committed changes. Closed by commit rGd1327f8a574a: [clang][amdgpu] - Choose when to promote VarDecl

[PATCH] D115661: [clang][amdgpu] - Choose when to promote VarDecl to address space 4.

estewart08 created this revision. estewart08 added a reviewer: JonChesterfield. Herald added subscribers: t-tye, tpr, dstuttard, yaxunl, kzhuravl. estewart08 requested review of this revision. Herald added subscribers: cfe-commits, wdng. Herald added a project: clang. There are instances where

[PATCH] D115661: [clang][amdgpu] - Choose when to promote VarDecl to address space 4.

estewart08 updated this revision to Diff 394002. estewart08 added a comment. Resubmit patch with lint. Repository: rG LLVM Github Monorepo CHANGES SINCE LAST ACTION https://reviews.llvm.org/D115661/new/ https://reviews.llvm.org/D115661 Files: clang/lib/CodeGen/TargetInfo.cpp

[PATCH] D104904: [OpenMP][AMDGCN] Initial math headers support

estewart08 added inline comments. Comment at: clang/test/Headers/Inputs/include/cstdlib:29 float fabs(float __x) { return __builtin_fabs(__x); } +#endif jdoerfert wrote: > JonChesterfield wrote: > > jdoerfert wrote: > > > estewart08 wrote: > > > >

[PATCH] D74970: [OpenMP] Refactor the analysis in checkMapClauseBaseExpression using StmtVisitor class.

estewart08 added inline comments. Herald added subscribers: sstefan1, yaxunl. Herald added a project: All. Comment at: clang/lib/Sema/SemaOpenMP.cpp:15450 } + bool VisitCXXThisExpr(CXXThisExpr *CTE) { return true; } + bool VisitStmt(Stmt *) { cchen wrote: >

[PATCH] D74144: [OPENMP50]Add basic support for array-shaping operation.

estewart08 added a comment. Herald added a subscriber: steakhal. Herald added a reviewer: NoQ. Herald added a project: All. In D74144#2308856 , @ABataev wrote: > In D74144#2308796 , @cchen wrote: > >> In