[clang] [HIP][SPIRV] Implicit `new`/`delete` should be `cdecl` on host (PR #152023)

https://github.com/yxsamliu approved this pull request. LGTM for now. If we encounter similar situation in future may consider a more generic approach. https://github.com/llvm/llvm-project/pull/152023 ___ cfe-commits mailing list cfe-commits@lists.llv

[clang] [HIP] compressed bundle format defaults to v3 (PR #152600)

https://github.com/yxsamliu closed https://github.com/llvm/llvm-project/pull/152600 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [HIP] compressed bundle format defaults to v3 (PR #152600)

yxsamliu wrote: > Random question, what would compression look like for the offload binaries? > I'm wondering how difficult it would be to switch HIP to using those instead > of the bundles for its binary format. There has been efforts to compress arbitrary ELF sections (https://maskray.me/bl

[clang] [HIP] compressed bundle format defaults to v3 (PR #152600)

https://github.com/yxsamliu created https://github.com/llvm/llvm-project/pull/152600 HIP runtime support for compressed bundle format v3 is in place, therefore switch the default compressed bundle format to v3 in compiler. This allows both compressed and decompressed fat binary size to exceed

[clang] [llvm] [LLVM] Add GNU make jobserver support (PR #145131)

yxsamliu wrote: ping. any further comments or concerns? thanks https://github.com/llvm/llvm-project/pull/145131 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] AMDGPU: Allow readonly features to be written to IR when there is no target (PR #148141)

https://github.com/yxsamliu approved this pull request. https://github.com/llvm/llvm-project/pull/148141 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] HIPSPV: Unbundle SDL (PR #136412)

yxsamliu wrote: > @svenvh @yxsamliu > > ping sorry for the delay. could you please rebase your branch? It is out of date. thanks https://github.com/llvm/llvm-project/pull/136412 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.l

[clang] [HIP][Clang][Driver] Move BC preference logic into ROCm detection (PR #149294)

https://github.com/yxsamliu approved this pull request. https://github.com/llvm/llvm-project/pull/149294 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [HIP][Clang][Driver] Move BC preference logic into ROCm detection (PR #149294)

@@ -77,6 +79,82 @@ class RocmInstallationDetector { SPACKReleaseStr(SPACKReleaseStr.str()) {} }; + struct CommonBitcodeLibsPreferences { +CommonBitcodeLibsPreferences(const Driver &D, + const llvm::opt::ArgList &DriverArgs, +

[clang] [llvm] [LLVM] Add GNU make jobserver support (PR #145131)

https://github.com/yxsamliu updated https://github.com/llvm/llvm-project/pull/145131 >From 36843916f3bc97b5f7d167222e41a9d4ddd5bf0f Mon Sep 17 00:00:00 2001 From: "Yaxun (Sam) Liu" Date: Tue, 17 Jun 2025 17:01:07 -0400 Subject: [PATCH] [Clang][Driver] Add jobserver support for --offload-jobs T

[clang] [llvm] [LLVM] Add GNU make jobserver support (PR #145131)

@@ -0,0 +1,257 @@ +//===- llvm/Support/Jobserver.cpp - Jobserver Client Implementation ---===// +// +// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions. +// See https://llvm.org/LICENSE.txt for license information. +// SPDX-License-Identifier: Ap

[clang] [llvm] [LLVM] Add GNU make jobserver support (PR #145131)

@@ -0,0 +1,257 @@ +//===- llvm/Support/Jobserver.cpp - Jobserver Client Implementation ---===// +// +// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions. +// See https://llvm.org/LICENSE.txt for license information. +// SPDX-License-Identifier: Ap

[clang] [llvm] [LLVM] Add GNU make jobserver support (PR #145131)

@@ -0,0 +1,257 @@ +//===- llvm/Support/Jobserver.cpp - Jobserver Client Implementation ---===// +// +// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions. +// See https://llvm.org/LICENSE.txt for license information. +// SPDX-License-Identifier: Ap

[clang] [llvm] [LLVM] Add GNU make jobserver support (PR #145131)

@@ -0,0 +1,257 @@ +//===- llvm/Support/Jobserver.cpp - Jobserver Client Implementation ---===// +// +// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions. +// See https://llvm.org/LICENSE.txt for license information. +// SPDX-License-Identifier: Ap

[clang] [llvm] [LLVM] Add GNU make jobserver support (PR #145131)

@@ -0,0 +1,257 @@ +//===- llvm/Support/Jobserver.cpp - Jobserver Client Implementation ---===// +// +// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions. +// See https://llvm.org/LICENSE.txt for license information. +// SPDX-License-Identifier: Ap

[clang] [llvm] [LLVM] Add GNU make jobserver support (PR #145131)

@@ -0,0 +1,141 @@ +//===- llvm/Support/Jobserver.h - Jobserver Client --*- C++ -*-===// +// +// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions. +// See https://llvm.org/LICENSE.txt for license information. +// SPDX-License-Identifier: Ap

[clang] [llvm] [LLVM] Add GNU make jobserver support (PR #145131)

@@ -0,0 +1,141 @@ +//===- llvm/Support/Jobserver.h - Jobserver Client --*- C++ -*-===// +// +// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions. +// See https://llvm.org/LICENSE.txt for license information. +// SPDX-License-Identifier: Ap

[clang] [llvm] [LLVM] Add GNU make jobserver support (PR #145131)

@@ -0,0 +1,141 @@ +//===- llvm/Support/Jobserver.h - Jobserver Client --*- C++ -*-===// +// +// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions. +// See https://llvm.org/LICENSE.txt for license information. +// SPDX-License-Identifier: Ap

[clang] [llvm] [LLVM] Add GNU make jobserver support (PR #145131)

@@ -0,0 +1,141 @@ +//===- llvm/Support/Jobserver.h - Jobserver Client --*- C++ -*-===// +// +// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions. +// See https://llvm.org/LICENSE.txt for license information. +// SPDX-License-Identifier: Ap

[clang] [llvm] [LLVM] Add GNU make jobserver support (PR #145131)

@@ -1420,12 +1420,18 @@ int main(int Argc, char **Argv) { parallel::strategy = hardware_concurrency(1); if (auto *Arg = Args.getLastArg(OPT_wrapper_jobs)) { -unsigned Threads = 0; -if (!llvm::to_integer(Arg->getValue(), Threads) || Threads == 0) - reportError(

[clang] [HIP] Add warning for -mwavefrontsize64 on gfx10+ architectures (PR #140185)

@@ -67,6 +67,12 @@ // DUP-NOT: "-target-feature" "{{.*}}wavefrontsize64" // DUP: {{.*}}lld{{.*}} "-plugin-opt=-mattr=+cumode" +// RUN: %clang -### --target=x86_64-linux-gnu -fgpu-rdc -nogpulib \ +// RUN: -nogpuinc --offload-arch=gfx1010 --no-offload-new-driver %s \ +// RUN:

[clang] AMDGPU: Remove "gws" from the “read-only” target feature list (PR #148141)

@@ -816,12 +816,12 @@ kernel void test_target_features_kernel(global int *i) { // NOCPU: attributes #[[ATTR10]] = { convergent nounwind } //. // GFX900: attributes #[[ATTR0:[0-9]+]] = { "objc_arc_inert" } -// GFX900: attributes #[[ATTR1]] = { convergent norecurse nounwind "den

[clang] [llvm] [LLVM] Add GNU make jobserver support (PR #145131)

yxsamliu wrote: ping https://github.com/llvm/llvm-project/pull/145131 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [HIP] Add warning for -mwavefrontsize64 on gfx10+ architectures (PR #140185)

yxsamliu wrote: ping https://github.com/llvm/llvm-project/pull/140185 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [Clang] Respect MS layout attributes during CUDA/HIP device compilation (PR #146620)

yxsamliu wrote: > > This broke the LLDB CI: > > ``` > > 13:02:41 > > /Users/ec2-user/jenkins/workspace/llvm.org/as-lldb-cmake/llvm-project/lldb/source/Plugins/ExpressionParser/Clang/ClangExpressionParser.cpp:834:59: > > error: too few arguments to function call, expected 3, have 2 > > 13:02:41

[clang] [Clang] Respect MS layout attributes during CUDA/HIP device compilation (PR #146620)

yxsamliu wrote: > This broke the LLDB CI: > > ``` > 13:02:41 > /Users/ec2-user/jenkins/workspace/llvm.org/as-lldb-cmake/llvm-project/lldb/source/Plugins/ExpressionParser/Clang/ClangExpressionParser.cpp:834:59: > error: too few arguments to function call, expected 3, have 2 > 13:02:41

[clang] [Clang] Respect MS layout attributes during CUDA/HIP device compilation (PR #146620)

https://github.com/yxsamliu closed https://github.com/llvm/llvm-project/pull/146620 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [HIP] Add warning for -mwavefrontsize64 on gfx10+ architectures (PR #140185)

yxsamliu wrote: I removed the new option and changed the error into a warning. Clang will only emit a warning about wave64 for gfx10+. I will ask HIP runtime to add an option -Werror=unsupported-wave64 in cmake config files since HIP runtime does not support wave64 on gfx10+. https://github.c

[clang] [HIP] Add warning for -mwavefrontsize64 on gfx10+ architectures (PR #140185)

https://github.com/yxsamliu edited https://github.com/llvm/llvm-project/pull/140185 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [HIP] diagnose -mwavefrontsize64 for gfx10+ (PR #140185)

https://github.com/yxsamliu edited https://github.com/llvm/llvm-project/pull/140185 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [HIP] diagnose -mwavefrontsize64 for gfx10+ (PR #140185)

https://github.com/yxsamliu updated https://github.com/llvm/llvm-project/pull/140185 >From 1d8a6ceb3eb3f9e899efde6bf6e86d23dfdfc430 Mon Sep 17 00:00:00 2001 From: "Yaxun (Sam) Liu" Date: Fri, 16 May 2025 00:04:12 -0400 Subject: [PATCH] [HIP] Add warning for -mwavefrontsize64 on gfx10+ architec

[clang] [llvm] [LLVM] Add GNU make jobserver support (PR #145131)

https://github.com/yxsamliu updated https://github.com/llvm/llvm-project/pull/145131 >From 0492b8d9db17c8a59390938033b6d6c8d12946e1 Mon Sep 17 00:00:00 2001 From: "Yaxun (Sam) Liu" Date: Tue, 17 Jun 2025 17:01:07 -0400 Subject: [PATCH] [Clang][Driver] Add jobserver support for --offload-jobs T

[clang] [llvm] [LLVM] Add GNU make jobserver support (PR #145131)

https://github.com/yxsamliu updated https://github.com/llvm/llvm-project/pull/145131 >From de90c70113945cbbe0f0ea6bd4c9f977ad500262 Mon Sep 17 00:00:00 2001 From: "Yaxun (Sam) Liu" Date: Tue, 17 Jun 2025 17:01:07 -0400 Subject: [PATCH] [Clang][Driver] Add jobserver support for --offload-jobs T

[clang] [llvm] [LLVM] Add GNU make jobserver support (PR #145131)

https://github.com/yxsamliu updated https://github.com/llvm/llvm-project/pull/145131 >From 2e891be4a591acbea3214453a423e98eb70b42ad Mon Sep 17 00:00:00 2001 From: "Yaxun (Sam) Liu" Date: Tue, 17 Jun 2025 17:01:07 -0400 Subject: [PATCH] [Clang][Driver] Add jobserver support for --offload-jobs T

[clang] [llvm] [LLVM] Add GNU make jobserver support (PR #145131)

https://github.com/yxsamliu updated https://github.com/llvm/llvm-project/pull/145131 >From 5b5953d2df2bf2aae652625d2a566bc923a8dbfe Mon Sep 17 00:00:00 2001 From: "Yaxun (Sam) Liu" Date: Tue, 17 Jun 2025 17:01:07 -0400 Subject: [PATCH] [Clang][Driver] Add jobserver support for --offload-jobs T

[clang] [llvm] [LLVM] Add GNU make jobserver support (PR #145131)

@@ -133,6 +140,85 @@ void StdThreadPool::processTasks(ThreadPoolTaskGroup *WaitingForGroup) { } } +/// Main loop for worker threads when using a jobserver. +/// This function uses a two-level queue; it first acquires a job slot from the +/// external jobserver, then retriev

[clang] [llvm] [LLVM] Add GNU make jobserver support (PR #145131)

@@ -79,7 +86,7 @@ void StdThreadPool::processTasks(ThreadPoolTaskGroup *WaitingForGroup) { // Yeah, we have a task, grab it and release the lock on the queue // We first need to signal that we are active before popping the queue - // in order for wait() to pr

[clang] [llvm] [LLVM] Add GNU make jobserver support (PR #145131)

@@ -133,6 +140,85 @@ void StdThreadPool::processTasks(ThreadPoolTaskGroup *WaitingForGroup) { } } +/// Main loop for worker threads when using a jobserver. +/// This function uses a two-level queue; it first acquires a job slot from the +/// external jobserver, then retriev

[clang] [llvm] [LLVM] Add GNU make jobserver support (PR #145131)

@@ -119,7 +130,25 @@ class ThreadPoolExecutor : public Executor { auto Task = std::move(WorkStack.back()); WorkStack.pop_back(); Lock.unlock(); - Task(); + + if (TheJobserver) { +JobSlot Slot = TheJobserver->tryAcquire(); +if (Slot.is

[clang] [Clang][OpenCL] Declare cl_amd_media_ops/cl_amd_media_ops2 builtins with -fdeclare-opencl-builtins (PR #143507)

Juan Manuel Martinez =?utf-8?q?Caama=C3=B1o?= , Juan Manuel Martinez =?utf-8?q?Caama=C3=B1o?= , Juan Manuel Martinez =?utf-8?q?Caama=C3=B1o?= , Juan Manuel Martinez =?utf-8?q?Caama=C3=B1o?= , Juan Manuel Martinez =?utf-8?q?Caama=C3=B1o?= Message-ID: In-Reply-To: https://github.com/yxsamliu appr

[clang] [Clang] Properly use `CommaJoined` for `--offload-arch` (PR #146687)

https://github.com/yxsamliu approved this pull request. https://github.com/llvm/llvm-project/pull/146687 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] HIPSPV: Unbundle SDL (PR #136412)

https://github.com/yxsamliu approved this pull request. https://github.com/llvm/llvm-project/pull/136412 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [WIP][AMDGPU] Support for type inferring image load/store builtins for AMDGPU (PR #140210)

@@ -635,5 +635,66 @@ TARGET_BUILTIN(__builtin_amdgcn_bitop3_b16, "IUi", "nc", "bitop3-insts") TARGET_BUILTIN(__builtin_amdgcn_cvt_sr_bf16_f32, "V2yV2yfUiIb", "nc", "f32-to-f16bf16-cvt-sr-insts") TARGET_BUILTIN(__builtin_amdgcn_cvt_sr_f16_f32, "V2hV2hfUiIb", "nc", "f32-to-

[clang] [llvm] [LLVM] Add GNU make jobserver support (PR #145131)

yxsamliu wrote: opened RFC ant LLVM discourse: https://discourse.llvm.org/t/rfc-adding-gnu-make-jobserver-support-to-llvm-for-coordinated-parallelism/87034 https://github.com/llvm/llvm-project/pull/145131 ___ cfe-commits mailing list cfe-commits@lists

[clang] [CUDA][HIP] add options `--[no-]offload-inc` (PR #140106)

https://github.com/yxsamliu closed https://github.com/llvm/llvm-project/pull/140106 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [llvm] [Clang][Driver] Add jobserver support for --offload-jobs (PR #145131)

https://github.com/yxsamliu created https://github.com/llvm/llvm-project/pull/145131 This patch introduces support for the jobserver protocol to control parallelism for device offloading tasks. When running a parallel build with a modern build system like `make -jN` or `ninja -jN`, each Clang

[clang] [HIP] Remove dots in HIP runtime path (PR #143792)

@@ -743,9 +743,11 @@ void Linux::AddHIPRuntimeLibArgs(const ArgList &Args, Args.MakeArgString(StringRef("-L") + RocmInstallation->getLibPath())); if (Args.hasFlag(options::OPT_frtlib_add_rpath, - options::OPT_fno_rtlib_add_rpath, false)) -CmdArgs.

[clang] [HIP] Remove dots in HIP runtime path (PR #143792)

https://github.com/yxsamliu approved this pull request. https://github.com/llvm/llvm-project/pull/143792 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [HIP] Remove dots in HIP runtime path (PR #143792)

@@ -743,9 +743,12 @@ void Linux::AddHIPRuntimeLibArgs(const ArgList &Args, Args.MakeArgString(StringRef("-L") + RocmInstallation->getLibPath())); if (Args.hasFlag(options::OPT_frtlib_add_rpath, - options::OPT_fno_rtlib_add_rpath, false)) +

[clang] [llvm] [AMDGPU][clang][CodeGen][opt] Add late-resolved feature identifying predicates (PR #134016)

https://github.com/yxsamliu approved this pull request. LGTM. Thanks https://github.com/llvm/llvm-project/pull/134016 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] 7232c07 - Reland [HIP] use offload wrapper for non-device-only non-rdc (#143964)

Author: Yaxun (Sam) Liu Date: 2025-06-12T21:41:41-04:00 New Revision: 7232c07eb97d5c21d47a661c9cca8981c7f91698 URL: https://github.com/llvm/llvm-project/commit/7232c07eb97d5c21d47a661c9cca8981c7f91698 DIFF: https://github.com/llvm/llvm-project/commit/7232c07eb97d5c21d47a661c9cca8981c7f91698.dif

[clang] 8890706 - Revert "Reland [HIP] use offload wrapper for non-device-only non-rdc (#132869) (#143964)"

Author: Yaxun (Sam) Liu Date: 2025-06-12T21:33:05-04:00 New Revision: 8890706db67384a423773cc921302dd63d950ef5 URL: https://github.com/llvm/llvm-project/commit/8890706db67384a423773cc921302dd63d950ef5 DIFF: https://github.com/llvm/llvm-project/commit/8890706db67384a423773cc921302dd63d950ef5.dif

[clang] Reland [HIP] use offload wrapper for non-device-only non-rdc (#132869) (PR #143964)

https://github.com/yxsamliu closed https://github.com/llvm/llvm-project/pull/143964 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] Reland [HIP] use offload wrapper for non-device-only non-rdc (#132869) (PR #143964)

https://github.com/yxsamliu updated https://github.com/llvm/llvm-project/pull/143964 >From ff3a9dd0765e499573d8d0049aca1d4568ac586f Mon Sep 17 00:00:00 2001 From: "Yaxun (Sam) Liu" Date: Wed, 11 Jun 2025 14:02:59 -0400 Subject: [PATCH 1/3] Revert "Revert "[HIP] use offload wrapper for non-devi

[clang] Reland [HIP] use offload wrapper for non-device-only non-rdc (#132869) (PR #143964)

@@ -9249,8 +9249,20 @@ void LinkerWrapper::ConstructJob(Compilation &C, const JobAction &JA, // Add the linker arguments to be forwarded by the wrapper. CmdArgs.push_back(Args.MakeArgString(Twine("--linker-path=") + LinkCommand->getEx

[clang] Reland [HIP] use offload wrapper for non-device-only non-rdc (#132869) (PR #143964)

https://github.com/yxsamliu updated https://github.com/llvm/llvm-project/pull/143964 >From 5f3cc287ff2c3c84ba840ebaa0931773341a02b2 Mon Sep 17 00:00:00 2001 From: "Yaxun (Sam) Liu" Date: Wed, 11 Jun 2025 14:02:59 -0400 Subject: [PATCH 1/3] Revert "Revert "[HIP] use offload wrapper for non-devi

[clang] [llvm] [mlir] [NFC][AMDGPU] Fix stale links to ROCm repositories (PR #143949)

https://github.com/yxsamliu approved this pull request. https://github.com/llvm/llvm-project/pull/143949 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] Reland [HIP] use offload wrapper for non-device-only non-rdc (#132869) (PR #143964)

@@ -310,8 +310,8 @@ Error relocateOffloadSection(const ArgList &Args, StringRef Output) { // Remove the old .llvm.offloading section to prevent further linking. ObjcopyArgs.emplace_back("--remove-section"); ObjcopyArgs.emplace_back(".llvm.offloading"); - for (StringRef

[clang] Reland [HIP] use offload wrapper for non-device-only non-rdc (#132869) (PR #143964)

yxsamliu wrote: I split it into 3 commits for ease of reviewing: the original change and the two fixes. https://github.com/llvm/llvm-project/pull/143964 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/lis

[clang] Reland [HIP] use offload wrapper for non-device-only non-rdc (#132869) (PR #143964)

https://github.com/yxsamliu created https://github.com/llvm/llvm-project/pull/143964 Fixed two issues: 1. assertion with -flto. the linker wrapper action is missing for wrapping the device binary. Added it for -flto. 2. when there are two HIP files, the kernels in the second file were not fo

[clang] Revert "[HIP] use offload wrapper for non-device-only non-rdc (#132869)" (PR #143432)

https://github.com/yxsamliu approved this pull request. thanks. I will take a look https://github.com/llvm/llvm-project/pull/143432 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [CUDA] Disallow use of address_space(N) on CUDA device variables. (PR #142857)

https://github.com/yxsamliu approved this pull request. LGTM. Thanks https://github.com/llvm/llvm-project/pull/142857 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [AMDGPU] fix amdgpu_max_num_work_groups in templates (PR #141633)

https://github.com/yxsamliu closed https://github.com/llvm/llvm-project/pull/141633 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [AMDGPU] fix amdgpu_max_num_work_groups in templates (PR #141633)

https://github.com/yxsamliu updated https://github.com/llvm/llvm-project/pull/141633 >From e8692fee660df71b8a7f277d1c85b925a2d678f1 Mon Sep 17 00:00:00 2001 From: "Yaxun (Sam) Liu" Date: Tue, 27 May 2025 13:03:32 -0400 Subject: [PATCH] [AMDGPU] fix amdgpu_max_num_work_groups in templates Clang

[clang] [HIP] disable sanitizer for `__hip_cuid` (PR #141581)

https://github.com/yxsamliu closed https://github.com/llvm/llvm-project/pull/141581 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [AMDGPU] fix amdgpu_max_num_work_groups in templates (PR #141633)

https://github.com/yxsamliu created https://github.com/llvm/llvm-project/pull/141633 Clang does not instantiate amdgpu_max_num_work_groups attribute with one template argument, causing assertion codegen. Fixes: https://github.com/llvm/llvm-project/issues/139570 >From f4849e095e750195d072484cb

[clang] [HIP] disable sanitizer for `__hip_cuid` (PR #141581)

https://github.com/yxsamliu created https://github.com/llvm/llvm-project/pull/141581 Global variable `__hip_cuid_*` is for identifying purpose and does not need sanitization, therefore disable it for sanitizers. >From 503ee3dd5144b4cc2dd83488b2194900605217fd Mon Sep 17 00:00:00 2001 From: "Yax

[clang] [HIP] diagnose -mwavefrontsize64 for gfx10+ (PR #140185)

yxsamliu wrote: > > > I am not ok with this being an error by default. > > > > > > I think compilation must fail when an unsupported and untested option is > > specified. And that includes when the target is SPIR-V. > > I would call it a supported and used option. The unsupported and untested

[clang] [HIP] diagnose -mwavefrontsize64 for gfx10+ (PR #140185)

yxsamliu wrote: > > > I don't think we should be introducing an additional option that behaves > > > identically to another option just differing by a warning. This also > > > isn't really a problem with the language, but the library support. The > > > actual codegen should work just fine. Is

[clang] [HIP] diagnose -mwavefrontsize64 for gfx10+ (PR #140185)

yxsamliu wrote: > I don't think we should be introducing an additional option that behaves > identically to another option just differing by a warning. This also isn't > really a problem with the language, but the library support. The actual > codegen should work just fine. Is there some other

[clang] [llvm] [AMDGPU][clang][CodeGen][opt] Add late-resolved feature identifying predicates (PR #134016)

@@ -585,6 +597,23 @@ Value *CodeGenFunction::EmitAMDGPUBuiltinExpr(unsigned BuiltinID, llvm::Value *Env = EmitScalarExpr(E->getArg(0)); return Builder.CreateCall(F, {Env}); } + case AMDGPU::BI__builtin_amdgcn_processor_is: { +assert(CGM.getTriple().isSPIRV() &&

[clang] [CUDA][HIP] add option -gpuinc (PR #140106)

yxsamliu wrote: > Being able to override a flag is a good thing to have, IMO. There are builds > where the owner of the leaf targets do not have much control over which > options are set by the "default" compilation, so they need to rely on being > able to override preceding options. > > The

[clang] [CUDA][HIP] add option -gpuinc (PR #140106)

yxsamliu wrote: > I thought we already added a generic -stdinc/nostdinc for this there is only -nostdinc but there is no -stdinc https://github.com/llvm/llvm-project/pull/140106 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llv

[clang] [HIP] diagnose -mwavefrontsize64 for gfx10+ (PR #140185)

https://github.com/yxsamliu created https://github.com/llvm/llvm-project/pull/140185 wavefront size 64 is not fully supported for HIP on gfx10+ and it is not tested. As such, currently HIP header contains an pragma error to diagnose such use case by detecting predefined macro `__AMDGCN_WAVEFRO

[clang] [CUDA][HIP] add option -gpuinc (PR #140106)

yxsamliu wrote: > > but there is other comgr user expecting comgr to have -nogpuinc by default. > > changing that will cause regressions. > > If `comgr` can have custom flags then you could just pass the 'do not pass > `-nogpuinc` by default' flag presumably. As I said, I think this is just o

[clang] [CUDA][HIP] add option -gpuinc (PR #140106)

yxsamliu wrote: > > > Hmm, in what cases is `-nogpuinc` added when we don't actually want it? I > > > think we should avoid adding `-nogpuinc` if it's not needed, if possible. > > > > > > comgr is the JIT compiler for HIP on ROCm. comgr uses -nogpuinc by default. > > However, some users of co

[clang] [CUDA][HIP] add option -gpuinc (PR #140106)

yxsamliu wrote: > > comgr is the JIT compiler for HIP on ROCm. comgr uses -nogpuinc by default. > > However, some users of comgr need to override that so that comgr enables > > the wrapper headers. We cannot simply let comgr stop using -nogpuinc by > > default since it will break existing comg

[clang] [CUDA][HIP] add option -gpuinc (PR #140106)

yxsamliu wrote: > > > > > Hmm, in what cases is `-nogpuinc` added when we don't actually want > > > > > it? I think we should avoid adding `-nogpuinc` if it's not needed, if > > > > > possible. > > > > > > > > > > > > comgr is the JIT compiler for HIP on ROCm. comgr uses -nogpuinc by > > > >

[clang] [CUDA][HIP] add option -gpuinc (PR #140106)

yxsamliu wrote: > Hmm, in what cases is `-nogpuinc` added when we don't actually want it? I > think we should avoid adding `-nogpuinc` if it's not needed, if possible. comgr is the JIT compiler for HIP on ROCm. comgr uses -nogpuinc by default. However, some users of comgr need to override that

[clang] [CUDA][HIP] add option -gpuinc (PR #140106)

https://github.com/yxsamliu created https://github.com/llvm/llvm-project/pull/140106 Currently there is only option -nogpuinc for disabling the default CUDA/HIP wrapper headers. However, there are situations where -nogpuinc needs to be overriden for enabling CUDA/HIP wrapper headers. This patc

[clang] [HIP] Fix return type in __clang_hip_cmath.h (PR #139697)

https://github.com/yxsamliu approved this pull request. LGTM. Thanks https://github.com/llvm/llvm-project/pull/139697 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [NFC] Typo in __clang_hip_cmath.h (PR #139892)

https://github.com/yxsamliu approved this pull request. https://github.com/llvm/llvm-project/pull/139892 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [HIP] change default offload archs (PR #139281)

yxsamliu wrote: > I think that in general we also need to decide on what happens when you pick > an amdgcn— triple. IMHO for that case we should probably error out if no mcpu > is provided, since there’s no reasonable default, except for “all”, but that > would be incredibly disruptive. That

[clang] [HIP] change default offload archs (PR #139281)

yxsamliu wrote: So we will wait until amdgcnspirv uses SPRIV backend by default, then switch HIP default offload arch to amdgcnspirv. That sounds a reasonable solution to me. https://github.com/llvm/llvm-project/pull/139281 ___ cfe-commits mailing li

[clang] [HIP] change default offload archs (PR #139281)

yxsamliu wrote: The main obstacle of letting clang emit error when `--offload-arch` is not specified is HIP apps using hipcc as CMAKE_CXX_COMPILER. hipcc adds -xhip by default for .cpp programs. This is a known and long existing issue. Another option is to have multiple `--offload-arch` option

[clang] clang: Remove dest LangAS argument from performAddrSpaceCast (PR #138866)

yxsamliu wrote: I don't think this PR should be merged. Since John is the code owner of clang codegen. https://github.com/llvm/llvm-project/pull/138866 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/list

[clang] [HIP] fix bundle ID for amdgcnspirv (PR #139112)

https://github.com/yxsamliu closed https://github.com/llvm/llvm-project/pull/139112 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [HIP] fix bundle ID for amdgcnspirv (PR #139112)

https://github.com/yxsamliu updated https://github.com/llvm/llvm-project/pull/139112 >From 7606c3bca9ba1de181d16038218963e822bb90e3 Mon Sep 17 00:00:00 2001 From: "Yaxun (Sam) Liu" Date: Thu, 8 May 2025 12:40:23 -0400 Subject: [PATCH] [HIP] fix bundle ID for amdgcnspirv Currently ROCm 6.4.0 on

[clang] [HIP] fix bundle ID for amdgcnspirv (PR #139112)

https://github.com/yxsamliu created https://github.com/llvm/llvm-project/pull/139112 Currently ROCm 6.4.0 only recognize spirv64-amd-amdhsa- in bundle ID. spirv64-amd-amdhsa-unknown causes all HIP apps compiled for amdgcnspirv to fail. Previously we fixed a similar issue for amdgcn-amd-amdhsa-

[clang] [CUDA][HIP] Fix host/device attribute of builtin (PR #138162)

https://github.com/yxsamliu closed https://github.com/llvm/llvm-project/pull/138162 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [NFC][clang-offload-bundler] Simplify main function (PR #138555)

https://github.com/yxsamliu approved this pull request. https://github.com/llvm/llvm-project/pull/138555 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [CUDA][HIP] Fix host/device attribute of builtin (PR #138162)

https://github.com/yxsamliu edited https://github.com/llvm/llvm-project/pull/138162 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [CUDA][HIP] Fix implicit attribute of builtin (PR #138162)

https://github.com/yxsamliu edited https://github.com/llvm/llvm-project/pull/138162 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [CUDA][HIP] Fix implicit attribute of builtin (PR #138162)

https://github.com/yxsamliu edited https://github.com/llvm/llvm-project/pull/138162 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [CUDA][HIP] Fix implicit attribute of builtin (PR #138162)

https://github.com/yxsamliu updated https://github.com/llvm/llvm-project/pull/138162 Rate limit · GitHub body { background-color: #f6f8fa; color: #24292e; font-family: -apple-system,BlinkMacSystemFont,Segoe UI,Helvetica,Arial,sans-

[clang] [CUDA][HIP] Fix implicit attribute of builtin (PR #138162)

@@ -0,0 +1,23 @@ +// expected-no-diagnostics + +// RUN: %clang_cc1 -triple x86_64-unknown-linux-gnu -aux-triple amdgcn-amd-amdhsa -fsyntax-only -verify -xhip %s +// RUN: %clang_cc1 -triple amdgcn-amd-amdhsa -fsyntax-only -fcuda-is-device -verify -xhip %s + +#include "Inputs/cuda

[clang] [CUDA][HIP] Fix implicit attribute of builtin (PR #138162)

https://github.com/yxsamliu updated https://github.com/llvm/llvm-project/pull/138162 >From 7b139b3a06e45f7429e1e0f15eb16d0c3aed5718 Mon Sep 17 00:00:00 2001 From: "Yaxun (Sam) Liu" Date: Thu, 1 May 2025 12:08:05 -0400 Subject: [PATCH] [CUDA][HIP] Fix implicit attribute of builtin When a builti

[clang] [CUDA][HIP] Fix implicit attribute of builtin (PR #138162)

https://github.com/yxsamliu edited https://github.com/llvm/llvm-project/pull/138162 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [CUDA][HIP] Fix implicit attribute of builtin (PR #138162)

https://github.com/yxsamliu created https://github.com/llvm/llvm-project/pull/138162 When a builtin function with generic pointer parameter is passed a pointer with address space, clang creates an overloaded builtin function but does not make it implicit. This causes error when the builtin is

[clang] [Clang][OpenCL][AMDGPU] OpenCL Kernel stubs should be assigned alwaysinline attribute (PR #137769)

https://github.com/yxsamliu approved this pull request. https://github.com/llvm/llvm-project/pull/137769 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

  1   2   3   4   5   6   7   8   9   10   >