[clang] [Clang][Unittest] Support for `target` update directive and `from` clause in clang unittests (PR #150580)

@@ -4734,6 +4734,65 @@ void x() { EXPECT_TRUE(matchesWithOpenMP(Source8, Matcher)); } +TEST_P(ASTMatchersTest, OMPTargetUpdateDirective_IsStandaloneDirective) { + auto Matcher = ompTargetUpdateDirective(isStandaloneDirective()); + + StringRef Source0 = R"( +void foo()

[clang] [Clang][OpenMP]Default clause variable category (PR #157063)

@@ -20,6 +20,27 @@ using namespace clang; using namespace llvm::omp; +unsigned clang::getOpenMPDefaultVariableCategory(StringRef Str, + const LangOptions &LangOpts) { + unsigned VC = llvm::StringSwitch(Str) +#define OPENMP_DEFAU

[clang] [Clang][OpenMP]Default clause variable category (PR #157063)

@@ -257,6 +264,10 @@ struct OMPInteropInfo final { llvm::SmallVector PreferTypes; }; +unsigned getOpenMPDefaultVariableCategory(StringRef Str, + const LangOptions &LangOpts); +const char *getOpenMPDefaultVariableCategoryName(unsigned

[clang] [Clang][HIP][CUDA] Add `__cluster_dims__` and `__no_cluster__` attribute (PR #156686)

@@ -7532,6 +7532,25 @@ A managed variable can be accessed in both device and host code. }]; } +def CUDAClusterDimsAttrDoc : Documentation { + let Category = DocCatDecl; + let Content = [{ +In CUDA/HIP programming, the ``__cluster_dims__`` attribute can be applied to a ke

[clang] [Clang][HIP][CUDA] Add `__cluster_dims__` and `__no_cluster__` attribute (PR #156686)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/156686 >From 2a30ef5a778fd4aee5ef5f10066ed3bda317e9d1 Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Wed, 3 Sep 2025 10:47:52 -0400 Subject: [PATCH 1/2] [Clang][HIP][CUDA] Add `__cluster_dims__` and `__no_cluster__

[clang] [Clang][Unittest] Support for `target` update directive and `from` clause in clang unittests (PR #150580)

@@ -2742,6 +2742,32 @@ void x() { EXPECT_TRUE(notMatchesWithOpenMP(Source2, Matcher)); } +TEST(ASTMatchersTestOpenMP, OMPTargetUpdateDirective) { + auto Matcher = stmt(ompTargetUpdateDirective()); + + StringRef Source0 = R"( +void foo() { + int arr[8]; + #pra

[clang] [Clang][HIP][CUDA] Add `__cluster_dims__` and `__no_cluster__` attribute (PR #156686)

@@ -7532,6 +7532,25 @@ A managed variable can be accessed in both device and host code. }]; } +def CUDAClusterDimsAttrDoc : Documentation { + let Category = DocCatDecl; + let Content = [{ +In CUDA/HIP programming, the ``__cluster_dims__`` attribute can be applied to a ke

[clang] [Clang][HIP][CUDA] Add `__cluster_dims__` and `__no_cluster__` attribute (PR #156686)

shiltian wrote: > It isn't clear what these are, why/whether we want them, what their signature > is, etc. It is the support for [`__cluster_dims__` attribute](https://docs.nvidia.com/cuda/cuda-c-programming-guide/#thread-block-clusters). > Additionally, we do not allow adding undocumented at

[clang] [Clang][HIP][CUDA] Add `__cluster_dims__` and `__no_cluster__` attribute (PR #156686)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/156686 >From 190dd7af733563bdb99ec5d4812226b86448f273 Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Wed, 3 Sep 2025 10:47:52 -0400 Subject: [PATCH] [Clang][HIP][CUDA] Add `__cluster_dims__` and `__no_cluster__` at

[clang] d25d830 - [NFC] Remove trailing whitespaces from two files

Author: Shilei Tian Date: 2025-09-03T10:51:08-04:00 New Revision: d25d8309d173f81bc26babf9964d4d021b76a4af URL: https://github.com/llvm/llvm-project/commit/d25d8309d173f81bc26babf9964d4d021b76a4af DIFF: https://github.com/llvm/llvm-project/commit/d25d8309d173f81bc26babf9964d4d021b76a4af.diff L

[clang] [Clang][HIP][CUDA] Add `__cluster_dims__` and `__no_cluster__` attribute (PR #156686)

shiltian wrote: * **#156686** https://app.graphite.dev/github/pr/llvm/llvm-project/156686?utm_source=stack-comment-icon"; target="_blank">https://static.graphite.dev/graphite-32x32-black.png"; alt="Graphite" width="10px" height="10px"/> 👈 https://app.graphite.dev/github/pr/llvm/llvm-project/156

[clang] [Clang][HIP][CUDA] Add `__cluster_dims__` and `__no_cluster__` attribute (PR #156686)

https://github.com/shiltian created https://github.com/llvm/llvm-project/pull/156686 This PR adds basic frontend support for `__cluster_dims__` and `__no_cluster__` attribute. Co-authored-by: Yaxun (Sam) Liu Co-authored-by: Jay Foad >From 4d6e3098540bc655b12374d7ac7d0fa13cccbec3 Mon Sep 17

[clang] [llvm] [AMDGPU][gfx1250] Add 128B cooperative atomics (PR #156418)

https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/156418 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [llvm] [AMDGPU][gfx1250] Add 128B cooperative atomics (PR #156418)

@@ -145,6 +154,50 @@ bool SemaAMDGPU::CheckAMDGCNBuiltinFunctionCall(unsigned BuiltinID, return false; } +bool SemaAMDGPU::checkCoopAtomicFunctionCall(CallExpr *TheCall, bool IsStore) { + bool Fail = false; + + // First argument is a global or generic pointer. + Expr *Pt

[clang] [llvm] Openmp 6.0 allow default clause on the target directive (PR #154942)

@@ -0,0 +1,51 @@ + +// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=60 -DOMP60 %s -Wuninitialized + +// RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-version=60 -DOMP60 %s -Wuninitialized + +// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=52 -DOMP52 %s -Wuninitialize

[clang] [llvm] [AMDGPU][Clang] Allow amdgpu-waves-per-eu attribute to lower target occupancy range (PR #138284)

shiltian wrote: Looking at this now, it doesn't seem the same as it was at the start. For the latest changes, I think @arsenm made it clear that waves-per-eu values should always give way to the values calculated from flat-workgroup-size if they differ, since flat-workgroup-size is ABI and wav

[clang] [AMDGCN] Add missing gfx1250 clang tests. NFC. (PR #155478)

https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/155478 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] cleanup 20250823 ret clang (PR #155138)

https://github.com/shiltian approved this pull request. The title needs to be more specific. https://github.com/llvm/llvm-project/pull/155138 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-co

[clang] [flang] [llvm] [OpenMP] Add parser/semantic support for dyn_groupprivate clause (PR #152651)

https://github.com/shiltian commented: Has `dyn_groupprivate` already been approved to be in 6.1 or is this just a PoC implementation? https://github.com/llvm/llvm-project/pull/152651 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lis

[clang] [flang] [llvm] [OpenMP] Add parser/semantic support for dyn_groupprivate clause (PR #152651)

https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/152651 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [llvm] [AMDGPU] Don't allow wgp mode on gfx1250 (PR #153680)

https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/153680 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [llvm] [AMDGPU] Extend __builtin_amdgcn_ds_bpermute argument types (PR #153501)

@@ -159,6 +159,119 @@ Value *EmitAMDGPUGridSize(CodeGenFunction &CGF, unsigned Index) { llvm::MDNode::get(CGF.getLLVMContext(), {})); return LD; } +// Lowers __builtin_amdgcn_ds_bpermute to the corresponding LLVM intrinsic with +// careful bit-level coercio

[clang] [llvm] [AMDGPU] Extend __builtin_amdgcn_ds_bpermute argument types (PR #153501)

@@ -159,6 +159,119 @@ Value *EmitAMDGPUGridSize(CodeGenFunction &CGF, unsigned Index) { llvm::MDNode::get(CGF.getLLVMContext(), {})); return LD; } +// Lowers __builtin_amdgcn_ds_bpermute to the corresponding LLVM intrinsic with +// careful bit-level coercio

[clang] [llvm] [AMDGPU] Extend __builtin_amdgcn_ds_bpermute argument types (PR #153501)

@@ -18,6 +18,132 @@ #include "llvm/Support/AtomicOrdering.h" #include +namespace { + +using llvm::StringRef; +using namespace clang; + +/// Attempts to apply a user-defined conversion on Arg at ArgIndex to a +/// 32-bit-compatible type. If successful, updates TheCall's argume

[clang] [llvm] [AMDGPU] Extend __builtin_amdgcn_ds_bpermute argument types (PR #153501)

https://github.com/shiltian deleted https://github.com/llvm/llvm-project/pull/153501 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [llvm] [AMDGPU] Extend __builtin_amdgcn_ds_bpermute argument types (PR #153501)

@@ -159,6 +159,119 @@ Value *EmitAMDGPUGridSize(CodeGenFunction &CGF, unsigned Index) { llvm::MDNode::get(CGF.getLLVMContext(), {})); return LD; } +// Lowers __builtin_amdgcn_ds_bpermute to the corresponding LLVM intrinsic with +// careful bit-level coercio

[clang] [Clang] Hide `offload-arch` initialization erros behind verbose flag (PR #151964)

https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/151964 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [llvm] [SimplifyCFG] Extend jump-threading to allow live local defs (PR #135079)

https://github.com/shiltian closed https://github.com/llvm/llvm-project/pull/135079 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [llvm] [AMDGPU] Support builtin/intrinsics for async loads/stores on gfx1250 (PR #151058)

https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/151058 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [llvm] [OpenMP] Adds omp_target_is_accessible routine (PR #138294)

shiltian wrote: FWIW, https://github.com/llvm/llvm-project/pull/143058 seems like doing the same thing. https://github.com/llvm/llvm-project/pull/138294 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/lis

[clang] [Clang] Search for 'offload-arch' only next to the clang driver (PR #150965)

https://github.com/shiltian approved this pull request. Is clang tools always installed? https://github.com/llvm/llvm-project/pull/150965 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commit

[clang] [Clang][Unittest] Support for `target` update directive and `from` clause in clang unittests (PR #150580)

https://github.com/shiltian commented: it doesn't seem to be tested? https://github.com/llvm/llvm-project/pull/150580 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [llvm] [AMDGPU] Select VMEM prefetch for llvm.prefetch on gfx1250 (PR #150493)

https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/150493 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [llvm] [NFC][AMDGPU] Rename "amdgpu-as" to "amdgpu-synchronize-as" (PR #148627)

https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/148627 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [Clang] Rework creating offloading toolchains (PR #125556)

shiltian wrote: I don't know which one. My PRs yesterday afternoon have a lot of crash in ADT but after rebase a couple of hours later they were gone. I suppose that would be the one. https://github.com/llvm/llvm-project/pull/125556 ___ cfe-commits m

[clang] [Clang] Rework creating offloading toolchains (PR #125556)

shiltian wrote: Someone else messed up it. The commit has been reverted. https://github.com/llvm/llvm-project/pull/125556 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [llvm] AMDGPU: Support v_wmma_f32_16x16x128_f8f6f4 on gfx1250 (PR #149684)

https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/149684 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [llvm] [AMDGPU] Add support for `v_sat_pk4_i4_[i8,u8]` on gfx1250 (PR #149528)

https://github.com/shiltian closed https://github.com/llvm/llvm-project/pull/149528 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [llvm] [AMDGPU] Add support for `v_sat_pk4_i4_[i8,u8]` on gfx1250 (PR #149528)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/149528 >From 3fb65bcda47f66a47c8295e04102a3a1d675dbd7 Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Fri, 18 Jul 2025 10:36:56 -0400 Subject: [PATCH] [AMDGPU] Add support for `v_sat_pk4_i4_[i8,u8]` on gfx1250 Co-au

[clang] [llvm] [AMDGPU] Add support for `v_sat_pk4_i4_[i8,u8]` on gfx1250 (PR #149528)

https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/149528 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [llvm] [AMDGPU] Add support for `v_permlane16_swap_b32` on gfx1250 (PR #149518)

https://github.com/shiltian closed https://github.com/llvm/llvm-project/pull/149518 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [llvm] [AMDGPU] Add support for `v_permlane16_swap_b32` on gfx1250 (PR #149518)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/149518 >From d58f9605434bfc4de1820f7c6beabd82586a Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Fri, 18 Jul 2025 10:02:30 -0400 Subject: [PATCH] [AMDGPU] Add support for `v_permlane16_swap_b32` on gfx1250 Co-a

[clang] [llvm] [AMDGPU] Add support for `v_permlane16_swap_b32` on gfx1250 (PR #149518)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/149518 >From f7c11e672cebd2488582ee89e66d9777182db1e1 Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Fri, 18 Jul 2025 10:02:30 -0400 Subject: [PATCH] [AMDGPU] Add support for `v_permlane16_swap_b32` on gfx1250 Co-a

[clang] [llvm] [AMDGPU] Add support for `v_permlane16_swap_b32` on gfx1250 (PR #149518)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/149518 >From e6d5fd17af108d454e43a6489eb7580bf007a170 Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Fri, 18 Jul 2025 10:02:30 -0400 Subject: [PATCH] [AMDGPU] Add support for `v_permlane16_swap_b32` on gfx1250 Co-a

[clang] [llvm] [AMDGPU] Add support for `v_permlane16_swap_b32` on gfx1250 (PR #149518)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/149518 >From 8f89191a1714b2e891eda67d844d32be2ccfc27a Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Fri, 18 Jul 2025 10:02:30 -0400 Subject: [PATCH] [AMDGPU] Add support for `v_permlane16_swap_b32` on gfx1250 Co-a

[clang] [llvm] [AMDGPU] Add support for `v_permlane16_swap_b32` on gfx1250 (PR #149518)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/149518 >From 1d045407b88bc8efae91410223e8ba980cdec6d1 Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Fri, 18 Jul 2025 10:02:30 -0400 Subject: [PATCH] [AMDGPU] Add support for `v_permlane16_swap_b32` on gfx1250 Co-a

[clang] [llvm] [AMDGPU] Add support for `v_permlane16_swap_b32` on gfx1250 (PR #149518)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/149518 >From 4d850d602b45130ae958776cd353512116bd5862 Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Fri, 18 Jul 2025 10:02:30 -0400 Subject: [PATCH] [AMDGPU] Add support for `v_permlane16_swap_b32` on gfx1250 Co-a

[clang] [llvm] [AMDGPU] Add support for `v_permlane16_swap_b32` on gfx1250 (PR #149518)

shiltian wrote: ### Merge activity * **Jul 18, 4:46 PM UTC**: A user started a stack merge that includes this pull request via [Graphite](https://app.graphite.dev/github/pr/llvm/llvm-project/149518). https://github.com/llvm/llvm-project/pull/149518 ___

[clang] [llvm] [AMDGPU] Add support for `v_permlane16_swap_b32` on gfx1250 (PR #149518)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/149518 >From 33991acfd14b041071d112de032afe94c6bedf35 Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Fri, 18 Jul 2025 10:02:30 -0400 Subject: [PATCH] [AMDGPU] Add support for `v_permlane16_swap_b32` on gfx1250 Co-a

[clang] [llvm] [AMDGPU] Add support for `v_permlane16_swap_b32` on gfx1250 (PR #149518)

https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/149518 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [llvm] [AMDGPU] Add support for `v_prng_b32` on gfx1250 (PR #149450)

https://github.com/shiltian closed https://github.com/llvm/llvm-project/pull/149450 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [llvm] [AMDGPU] Add support for `v_permlane16_swap_b32` on gfx1250 (PR #149518)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/149518 >From 345d4d9de11d21c1b087cdf88de22f0d90a7ba9f Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Fri, 18 Jul 2025 10:02:30 -0400 Subject: [PATCH] [AMDGPU] Add support for `v_permlane16_swap_b32` on gfx1250 Co-a

[clang] [llvm] [AMDGPU] Add support for `v_prng_b32` on gfx1250 (PR #149450)

shiltian wrote: ### Merge activity * **Jul 18, 2:58 PM UTC**: A user started a stack merge that includes this pull request via [Graphite](https://app.graphite.dev/github/pr/llvm/llvm-project/149450). https://github.com/llvm/llvm-project/pull/149450 ___

[clang] [llvm] [AMDGPU] Add support for `v_prng_b32` on gfx1250 (PR #149450)

@@ -4007,7 +4007,8 @@ SDValue AMDGPUTargetLowering::performIntrinsicWOChainCombine( case Intrinsic::amdgcn_rcp_legacy: case Intrinsic::amdgcn_rsq_legacy: case Intrinsic::amdgcn_rsq_clamp: - case Intrinsic::amdgcn_tanh: { + case Intrinsic::amdgcn_tanh: + case Intrinsic

[clang] [llvm] [AMDGPU] Add support for `v_prng_b32` on gfx1250 (PR #149450)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/149450 >From e35cd5506ed733fcb62eab4c28ab4e9f5966216f Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Fri, 18 Jul 2025 00:26:15 -0400 Subject: [PATCH 1/2] [AMDGPU] Add support for `v_prng_b32` on gfx1250 Co-authored

[clang] [llvm] [AMDGPU] Add support for `v_prng_b32` on gfx1250 (PR #149450)

@@ -4007,7 +4007,8 @@ SDValue AMDGPUTargetLowering::performIntrinsicWOChainCombine( case Intrinsic::amdgcn_rcp_legacy: case Intrinsic::amdgcn_rsq_legacy: case Intrinsic::amdgcn_rsq_clamp: - case Intrinsic::amdgcn_tanh: { + case Intrinsic::amdgcn_tanh: + case Intrinsic

[clang] [llvm] [AMDGPU] Add support for `v_prng_b32` on gfx1250 (PR #149450)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/149450 >From e35cd5506ed733fcb62eab4c28ab4e9f5966216f Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Fri, 18 Jul 2025 00:26:15 -0400 Subject: [PATCH] [AMDGPU] Add support for `v_prng_b32` on gfx1250 Co-authored-by:

[clang] [llvm] [AMDGPU] Add support for `v_prng_b32` on gfx1250 (PR #149450)

https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/149450 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [Clang][AMDGPU] Add the missing builtin `__builtin_amdgcn_sqrt_bf16` (PR #149447)

https://github.com/shiltian closed https://github.com/llvm/llvm-project/pull/149447 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [Clang][AMDGPU] Add the missing builtin `__builtin_amdgcn_sqrt_bf16` (PR #149447)

shiltian wrote: ### Merge activity * **Jul 18, 12:42 PM UTC**: A user started a stack merge that includes this pull request via [Graphite](https://app.graphite.dev/github/pr/llvm/llvm-project/149447). https://github.com/llvm/llvm-project/pull/149447 __

[clang] [llvm] [AMDGPU] Add support for `v_tanh_f32` on gfx1250 (PR #149360)

https://github.com/shiltian closed https://github.com/llvm/llvm-project/pull/149360 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [llvm] [AMDGPU] Add support for `v_tanh_f32` on gfx1250 (PR #149360)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/149360 >From 10b9379f759506e4e1e3c1cab1191ed386609ebe Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Thu, 17 Jul 2025 13:03:14 -0400 Subject: [PATCH] [AMDGPU] Add support for `v_tanh_f32` on gfx1250 Co-authored-by:

[clang] [llvm] [AMDGPU] Add support for `v_tanh_f32` on gfx1250 (PR #149360)

https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/149360 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [llvm] [AMDGPU] Add support for `v_cos_bf16` on gfx1250 (PR #149355)

https://github.com/shiltian closed https://github.com/llvm/llvm-project/pull/149355 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [llvm] [AMDGPU] Add support for `v_cos_bf16` on gfx1250 (PR #149355)

shiltian wrote: ### Merge activity * **Jul 17, 6:41 PM UTC**: A user started a stack merge that includes this pull request via [Graphite](https://app.graphite.dev/github/pr/llvm/llvm-project/149355). https://github.com/llvm/llvm-project/pull/149355 ___

[clang] [llvm] [AMDGPU] Add support for `v_cos_bf16` on gfx1250 (PR #149355)

https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/149355 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [llvm] [AMDGPU] Add support for `v_cos_bf16_e64` on gfx1250 (PR #149355)

shiltian wrote: Oh nice catch. Thanks. https://github.com/llvm/llvm-project/pull/149355 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [llvm] [AMDGPU] Add support for `v_cos_bf16_e64` on gfx1250 (PR #149355)

shiltian wrote: but we do have `v_cos_bf16` in `llvm/test/MC/AMDGPU/gfx1250_asm_vop1.s`? https://github.com/llvm/llvm-project/pull/149355 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commit

[clang] [llvm] [AMDGPU] Add support for `v_sin_bf16_e64` on gfx1250 (PR #149355)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/149355 >From 29b54575b3e64372750466dfafab971697f402f1 Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Thu, 17 Jul 2025 12:45:33 -0400 Subject: [PATCH] [AMDGPU] Add support for `v_sin_bf16_e64` on gfx1250 Co-authored

[clang] [llvm] [AMDGPU] Add support for `v_sin_bf16_e64` on gfx1250 (PR #149355)

shiltian wrote: * **#149355** https://app.graphite.dev/github/pr/llvm/llvm-project/149355?utm_source=stack-comment-icon"; target="_blank">https://static.graphite.dev/graphite-32x32-black.png"; alt="Graphite" width="10px" height="10px"/> 👈 https://app.graphite.dev/github/pr/llvm/llvm-project/149

[clang] [llvm] [AMDGPU] Add support for `v_sin_bf16_e64` on gfx1250 (PR #149355)

https://github.com/shiltian created https://github.com/llvm/llvm-project/pull/149355 Co-authored-by: Mekhanoshin, Stanislav >From a6b7ccf491c4d88b18bfdba0dbf839030df189ec Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Thu, 17 Jul 2025 12:45:33 -0400 Subject: [PATCH] [AMDGPU] Add support for

[clang] [AST] Remove an unnecessary cast (NFC) (PR #149338)

@@ -610,7 +610,7 @@ void StmtPrinter::VisitObjCAtTryStmt(ObjCAtTryStmt *Node) { } } - if (auto *FS = static_cast(Node->getFinallyStmt())) { + if (auto *FS = Node->getFinallyStmt()) { shiltian wrote: If there is no cast, then we'd want to use the type

[clang] [AST] Remove an unnecessary cast (NFC) (PR #149338)

https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/149338 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [Sema] Remove unnecessary casts (NFC) (PR #149340)

https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/149340 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [CodeGen] Remove an unnecessary cast (NFC) (PR #149339)

https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/149339 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [llvm] [AMDGPU] Add support for `v_sin_bf16` on gfx1250 (PR #149241)

https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/149241 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [llvm] [AMDGPU] Add support for `v_sin_bf16` on gfx1250 (PR #149241)

https://github.com/shiltian closed https://github.com/llvm/llvm-project/pull/149241 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [llvm] [AMDGPU] Add support for `v_sin_bf16` on gfx1250 (PR #149241)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/149241 >From 8012a2d62f910c81a38c1c8d1de1a5bbd797d22f Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Wed, 16 Jul 2025 23:48:48 -0400 Subject: [PATCH] [AMDGPU] Add support for `v_sin_bf16` on gfx1250 Co-authored-by:

[clang] [llvm] [AMDGPU] Add support for `v_exp_bf16` on gfx1250 (PR #149229)

https://github.com/shiltian closed https://github.com/llvm/llvm-project/pull/149229 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [llvm] [AMDGPU] Add support for `v_exp_bf16` on gfx1250 (PR #149229)

shiltian wrote: ### Merge activity * **Jul 17, 12:41 PM UTC**: A user started a stack merge that includes this pull request via [Graphite](https://app.graphite.dev/github/pr/llvm/llvm-project/149229). https://github.com/llvm/llvm-project/pull/149229 __

[clang] [Clang][AMDGPU] Add builtins for some buffer resource atomics (PR #149216)

@@ -252,6 +252,15 @@ TARGET_BUILTIN(__builtin_amdgcn_flat_atomic_fmax_f64, "dd*0d", "t", "gfx90a-inst TARGET_BUILTIN(__builtin_amdgcn_ds_atomic_fadd_f64, "dd*3d", "t", "gfx90a-insts") TARGET_BUILTIN(__builtin_amdgcn_ds_atomic_fadd_f32, "ff*3f", "t", "gfx8-insts") +TARGET_BUI

[clang] [llvm] [AMDGPU] Add support for `v_exp_bf16` on gfx1250 (PR #149229)

@@ -25,4 +25,27 @@ define amdgpu_ps void @llvm_log2_bf16_s(ptr addrspace(1) %out, bfloat inreg %src ret void } +define amdgpu_ps void @llvm_exp2_bf16_v(ptr addrspace(1) %out, bfloat %src) { +; GCN-LABEL: llvm_exp2_bf16_v: +; GCN: ; %bb.0: +; GCN-NEXT:v_exp_bf16_e3

[clang] [llvm] [AMDGPU] Add support for `v_rsq_bf16` on gfx1250 (PR #149194)

shiltian wrote: * **#149194** https://app.graphite.dev/github/pr/llvm/llvm-project/149194?utm_source=stack-comment-icon"; target="_blank">https://static.graphite.dev/graphite-32x32-black.png"; alt="Graphite" width="10px" height="10px"/> 👈 https://app.graphite.dev/github/pr/llvm/llvm-project/149

[clang] [llvm] [AMDGPU] Add support for `v_rsq_bf16` on gfx1250 (PR #149194)

https://github.com/shiltian created https://github.com/llvm/llvm-project/pull/149194 Co-authored-by: Mekhanoshin, Stanislav >From 296077854b4bcad36f9b924da1dbfe4376d8b4d5 Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Wed, 16 Jul 2025 17:31:42 -0400 Subject: [PATCH] [AMDGPU] Add support for

[clang] [llvm] [AMDGPU] Add support for `v_rcp_bf16` on gfx1250 (PR #148916)

shiltian wrote: * **#148916** https://app.graphite.dev/github/pr/llvm/llvm-project/148916?utm_source=stack-comment-icon"; target="_blank">https://static.graphite.dev/graphite-32x32-black.png"; alt="Graphite" width="10px" height="10px"/> 👈 https://app.graphite.dev/github/pr/llvm/llvm-project/148

[clang] [llvm] [AMDGPU] Add support for `v_rcp_bf16` on gfx1250 (PR #148916)

https://github.com/shiltian created https://github.com/llvm/llvm-project/pull/148916 Co-authored-by: Mekhanoshin, Stanislav >From b0c51e4f67e0740d916d1596ced8f93228d93b1c Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Tue, 15 Jul 2025 14:10:18 -0400 Subject: [PATCH] [AMDGPU] Add support for

[clang] [Sema] Remove unnecessary casts (NFC) (PR #148871)

https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/148871 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [llvm] [AMDGPU] Add support for `v_tanh_bf16` on gfx1250 (PR #147425)

shiltian wrote: FWIW, the crash still exists. https://github.com/llvm/llvm-project/pull/147425 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [llvm] [AMDGPU] Add support for `v_tanh_bf16` on gfx1250 (PR #147425)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/147425 >From f75f85e997f95bd29e244e199d16c89dffca1232 Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Mon, 14 Jul 2025 12:56:54 -0400 Subject: [PATCH] [AMDGPU] Add support for `v_tanh_bf16` on gfx1250 Co-authored-by

[clang] [llvm] [AMDGPU] Add support for `v_tanh_bf16` on gfx1250 (PR #147425)

@@ -2,169 +2,69 @@ # RUN: llvm-mc -triple=amdgcn -mcpu=gfx1250 -mattr=+real-true16 -disassemble -show-encoding < %s | FileCheck -check-prefixes=GFX1250,GFX1250-REAL16 %s # RUN: llvm-mc -triple=amdgcn -mcpu=gfx1250 -mattr=-real-true16 -disassemble -show-encoding < %s | FileChec

[clang] [llvm] [AMDGPU] Add support for `v_tanh_bf16` on gfx1250 (PR #147425)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/147425 >From 2c36f0664993d54841245fe62d062af3b7332c97 Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Mon, 14 Jul 2025 12:56:54 -0400 Subject: [PATCH] [AMDGPU] Add support for `v_tanh_bf16` on gfx1250 Co-authored-by

[clang] [llvm] [NFC][AMDGPU] Rename "amdgpu-as" to "amdgpu-synchronize-as" (PR #148627)

@@ -704,12 +704,12 @@ void diagnoseUnknownMMRAASName(const MachineInstr &MI, StringRef AS) { DiagnosticInfoUnsupported(Fn, Str.str(), MI.getDebugLoc(), DS_Warning)); } -/// Reads \p MI's MMRAs to parse the "amdgpu-as" MMRA. +/// Reads \p MI's MMRAs to parse the "amdgpu-

[clang] [llvm] [AMDGPU] Add support for `v_tanh_bf16` on gfx1250 (PR #147425)

shiltian wrote: This PR is messed up at this moment. https://github.com/llvm/llvm-project/pull/147425 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

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

@@ -266,7 +266,7 @@ AMDGPUTargetInfo::AMDGPUTargetInfo(const llvm::Triple &Triple, MaxAtomicPromoteWidth = MaxAtomicInlineWidth = 64; CUMode = !(GPUFeatures & llvm::AMDGPU::FEATURE_WGP); - for (auto F : {"image-insts", "gws", "vmem-to-lds-load-insts"}) + for (auto F : {

[clang] [Clang][NFC] Add alias target for amdgpu-arch-tool and nvptx-arch-tool (PR #147558)

https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/147558 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [llvm] [AMDGPU] Add support for `v_cvt_f16_bf8` on gfx1250 (PR #146305)

@@ -2,51 +2,41 @@ # RUN: llvm-mc -triple=amdgcn -mcpu=gfx1250 -mattr=+real-true16 -disassemble -show-encoding < %s | FileCheck -check-prefixes=GFX1250,GFX1250-REAL16 %s # RUN: llvm-mc -triple=amdgcn -mcpu=gfx1250 -mattr=-real-true16 -disassemble -show-encoding < %s | FileCheck

[clang] [llvm] [AMDGPU] Add support for `v_cvt_f16_bf8` on gfx1250 (PR #146305)

@@ -2,51 +2,41 @@ # RUN: llvm-mc -triple=amdgcn -mcpu=gfx1250 -mattr=+real-true16 -disassemble -show-encoding < %s | FileCheck -check-prefixes=GFX1250,GFX1250-REAL16 %s # RUN: llvm-mc -triple=amdgcn -mcpu=gfx1250 -mattr=-real-true16 -disassemble -show-encoding < %s | FileCheck

[clang] [llvm] [AMDGPU] Add support for `v_tanh_bf16` on gfx1250 (PR #147425)

shiltian wrote: For some reason there is a crash in `llvm/test/CodeGen/AMDGPU/llvm.amdgcn.tanh.ll`. ``` LLVM ERROR: Cannot select: t28: ch = store<(store (s16) into %ir.out.load, addrspace 1)> t0, t27, t30, undef:i64 t27: i16 = bitcast t21 t21: bf16 = llvm.amdgcn.tanh TargetConstant:i64<

[clang] [llvm] [AMDGPU] Add support for `v_tanh_bf16` on gfx1250 (PR #147425)

@@ -13658,6 +13658,7 @@ bool SITargetLowering::isCanonicalized(Register Reg, const MachineFunction &MF, case Intrinsic::amdgcn_frexp_mant: case Intrinsic::amdgcn_fdot2: case Intrinsic::amdgcn_trig_preop: +case Intrinsic::amdgcn_tanh: shiltian w

[clang] [llvm] [AMDGPU] Add support for `v_tanh_bf16` on gfx1250 (PR #147425)

@@ -13658,6 +13658,7 @@ bool SITargetLowering::isCanonicalized(Register Reg, const MachineFunction &MF, case Intrinsic::amdgcn_frexp_mant: case Intrinsic::amdgcn_fdot2: case Intrinsic::amdgcn_trig_preop: +case Intrinsic::amdgcn_tanh: shiltian w

  1   2   3   4   5   6   7   8   9   10   >