[llvm-branch-commits] [openmp] 48c54f0 - [OpenMP][NVPTX] Added forward declaration for atomic operations

Author: Shilei Tian Date: 2021-01-21T10:37:16-05:00 New Revision: 48c54f0f623407192e93dc884724a12826eeab4f URL: https://github.com/llvm/llvm-project/commit/48c54f0f623407192e93dc884724a12826eeab4f DIFF: https://github.com/llvm/llvm-project/commit/48c54f0f623407192e93dc884724a12826eeab4f.diff L

[llvm-branch-commits] [openmp] e2a6230 - [OpenMP] Fixed the test environment when building along with LLVM

Author: Shilei Tian Date: 2021-01-06T17:06:16-05:00 New Revision: e2a623094f6bc1b01f9661043b3df908ca1bd037 URL: https://github.com/llvm/llvm-project/commit/e2a623094f6bc1b01f9661043b3df908ca1bd037 DIFF: https://github.com/llvm/llvm-project/commit/e2a623094f6bc1b01f9661043b3df908ca1bd037.diff L

[llvm-branch-commits] [openmp] 5acdae1 - [OpenMP] Fixed an issue that wrong LLVM headers might be included when building libomptarget

Author: Shilei Tian Date: 2021-01-06T17:07:36-05:00 New Revision: 5acdae1f9a772e16850b0ee9648d79a7c3becf23 URL: https://github.com/llvm/llvm-project/commit/5acdae1f9a772e16850b0ee9648d79a7c3becf23 DIFF: https://github.com/llvm/llvm-project/commit/5acdae1f9a772e16850b0ee9648d79a7c3becf23.diff L

[llvm-branch-commits] [clang] 63b42a0 - [NFC] clang/test/openMP/target_codegen.cpp should not depend on ssa name

Author: Jeroen Dobbelaere Date: 2021-01-07T16:39:17-05:00 New Revision: 63b42a0514567d24df617e4587e80e4564ebf120 URL: https://github.com/llvm/llvm-project/commit/63b42a0514567d24df617e4587e80e4564ebf120 DIFF: https://github.com/llvm/llvm-project/commit/63b42a0514567d24df617e4587e80e4564ebf120.d

[llvm-branch-commits] [openmp] 676c7cb - [OpenMP] Added the support for cache line size 256 for A64FX

Author: Shilei Tian Date: 2021-01-09T11:58:47-05:00 New Revision: 676c7cb0c0d4b66affde3ff7fc566c7a5aaa7246 URL: https://github.com/llvm/llvm-project/commit/676c7cb0c0d4b66affde3ff7fc566c7a5aaa7246 DIFF: https://github.com/llvm/llvm-project/commit/676c7cb0c0d4b66affde3ff7fc566c7a5aaa7246.diff L

[llvm-branch-commits] [openmp] 175c336 - [OpenMP] Remove copy constructor of `RTLInfoTy`

Author: Shilei Tian Date: 2021-01-09T13:01:01-05:00 New Revision: 175c336a1c5a7d4cf2e24ec5188c370cd6093ddb URL: https://github.com/llvm/llvm-project/commit/175c336a1c5a7d4cf2e24ec5188c370cd6093ddb DIFF: https://github.com/llvm/llvm-project/commit/175c336a1c5a7d4cf2e24ec5188c370cd6093ddb.diff L

[llvm-branch-commits] [llvm] 894d2db - [LLVM] Added OpenMP to `LLVM_ALL_RUNTIMES`

Author: Shilei Tian Date: 2021-01-10T16:45:51-05:00 New Revision: 894d2dbf502026a2b063340f8214b8ffd7cf7e21 URL: https://github.com/llvm/llvm-project/commit/894d2dbf502026a2b063340f8214b8ffd7cf7e21 DIFF: https://github.com/llvm/llvm-project/commit/894d2dbf502026a2b063340f8214b8ffd7cf7e21.diff L

[llvm-branch-commits] [openmp] 7be3285 - [OpenMP] Not set OPENMP_STANDALONE_BUILD=ON when building OpenMP along with LLVM

Author: Shilei Tian Date: 2021-01-10T16:46:19-05:00 New Revision: 7be3285248bf54d0784a76174cf44cf7c1e780a5 URL: https://github.com/llvm/llvm-project/commit/7be3285248bf54d0784a76174cf44cf7c1e780a5 DIFF: https://github.com/llvm/llvm-project/commit/7be3285248bf54d0784a76174cf44cf7c1e780a5.diff L

[llvm-branch-commits] [openmp] a81c68a - [OpenMP] Take elf_common.c as a interface library

Author: Shilei Tian Date: 2021-01-11T17:34:26-05:00 New Revision: a81c68ae6be58efa24e2573e155d5ef20260399b URL: https://github.com/llvm/llvm-project/commit/a81c68ae6be58efa24e2573e155d5ef20260399b DIFF: https://github.com/llvm/llvm-project/commit/a81c68ae6be58efa24e2573e155d5ef20260399b.diff L

[llvm-branch-commits] [openmp] 0871d6d - [OpenMP] Move memory manager to plugin and make it a common interface

Author: Shilei Tian Date: 2021-01-11T21:33:42-05:00 New Revision: 0871d6d51648dd2a8009ddff59936ea9e3fe871b URL: https://github.com/llvm/llvm-project/commit/0871d6d51648dd2a8009ddff59936ea9e3fe871b DIFF: https://github.com/llvm/llvm-project/commit/0871d6d51648dd2a8009ddff59936ea9e3fe871b.diff L

[llvm-branch-commits] [llvm] 36b0dd8 - [OpenMP] Fixed the issue that CMake variables for OpenMP were not passed through when building OpenMP with LLVM_ENABLE_RUNTIMES

Author: Shilei Tian Date: 2020-12-20T18:40:12-05:00 New Revision: 36b0dd8f678fc446f8088963a70d701507ced8fc URL: https://github.com/llvm/llvm-project/commit/36b0dd8f678fc446f8088963a70d701507ced8fc DIFF: https://github.com/llvm/llvm-project/commit/36b0dd8f678fc446f8088963a70d701507ced8fc.diff L

[llvm-branch-commits] [openmp] 612ddc3 - [OpenMP][Docs] Updated the faq about building an OpenMP offloading capable compiler

Author: Shilei Tian Date: 2020-12-22T13:14:53-05:00 New Revision: 612ddc3117ce7715a3634fa0e0c5c6cdd3619d6b URL: https://github.com/llvm/llvm-project/commit/612ddc3117ce7715a3634fa0e0c5c6cdd3619d6b DIFF: https://github.com/llvm/llvm-project/commit/612ddc3117ce7715a3634fa0e0c5c6cdd3619d6b.diff L

[llvm-branch-commits] [openmp] 1eb082c - [OpenMP][Docs] Fixed a typo in the doc that can mislead users to a CMake error

Author: Shilei Tian Date: 2020-12-22T14:05:58-05:00 New Revision: 1eb082c2ea426f1dab4d1b3541b37c883b3a6b4f URL: https://github.com/llvm/llvm-project/commit/1eb082c2ea426f1dab4d1b3541b37c883b3a6b4f DIFF: https://github.com/llvm/llvm-project/commit/1eb082c2ea426f1dab4d1b3541b37c883b3a6b4f.diff L

[llvm-branch-commits] [llvm] [AMDGPU] Skip non-first termintors when forcing emit zero flag (PR #112116)

https://github.com/shiltian created https://github.com/llvm/llvm-project/pull/112116 None >From 59007297616ea2e11a06401b79833953318d42e0 Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Sat, 12 Oct 2024 23:58:25 -0400 Subject: [PATCH] [AMDGPU] Skip non-first termintors when forcing emit zero

[llvm-branch-commits] [llvm] [AMDGPU] Skip non-first termintors when forcing emit zero flag (PR #112116)

shiltian wrote: > [!WARNING] > This pull request is not mergeable via GitHub because a downstack PR is > open. Once all requirements are satisfied, merge this PR as a stack href="https://app.graphite.dev/github/pr/llvm/llvm-project/112116?utm_source=stack-comment-downstack-mergeability-warning"

[llvm-branch-commits] [llvm] [AMDGPU] Skip non-first termintors when forcing emit zero flag (PR #112116)

https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/112116 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] [TargetTransformInfo] Remove `getFlatAddressSpace` (PR #108787)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/108787 >From 180bf1360412c25c94407dcfe0bbde1b1097b804 Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Sun, 15 Sep 2024 23:06:14 -0400 Subject: [PATCH] [TargetTransformInfo] Remove `getFlatAddressSpace` This has been

[llvm-branch-commits] [clang] clang/AMDGPU: Emit grid size builtins with range metadata (PR #113038)

https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/113038 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [clang] clang/AMDGPU: Emit grid size builtins with range metadata (PR #113038)

@@ -896,5 +896,6 @@ void test_set_fpenv(unsigned long env) { __builtin_amdgcn_set_fpenv(env); } +// CHECK-DAG: [[$GRID_RANGE]] = !{i32 1, i32 0} shiltian wrote: oh I c. range does allow wrap. https://github.com/llvm/llvm-project/pull/113038 ___

[llvm-branch-commits] [clang] clang/AMDGPU: Emit grid size builtins with range metadata (PR #113038)

@@ -896,5 +896,6 @@ void test_set_fpenv(unsigned long env) { __builtin_amdgcn_set_fpenv(env); } +// CHECK-DAG: [[$GRID_RANGE]] = !{i32 1, i32 0} shiltian wrote: the upper bound is smaller than the lower bound? https://github.com/llvm/llvm-project/pull/1130

[llvm-branch-commits] [llvm] AMDGPU: Mark grid size loads with range metadata (PR #113019)

https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/113019 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] [AMDGPU] Still set up the two SGPRs for queue ptr even it is COV5 (PR #112403)

https://github.com/shiltian ready_for_review https://github.com/llvm/llvm-project/pull/112403 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] [AMDGPU] Still set up the two SGPRs for queue ptr even it is COV5 (PR #112403)

shiltian wrote: The only test failure is `CodeGen/AMDGPU/call-args-inreg.ll`. It crashes when lowering function `test_call_external_void_func_a15i32_inreg`. https://github.com/llvm/llvm-project/blob/8d13e7b8c382499c1cf0c2a3184b483e760f266b/llvm/lib/Target/AMDGPU/SIFrameLowering.cpp#L905 https:

[llvm-branch-commits] [llvm] [AMDGPU] Still set up the two SGPRs for queue ptr even it is COV5 (PR #112403)

@@ -4,12 +4,12 @@ define amdgpu_kernel void @s_clear_msb(ptr addrspace(1) %out, i32 %in) { ; SI-LABEL: s_clear_msb: ; SI: ; %bb.0: -; SI-NEXT:s_load_dword s4, s[2:3], 0xb -; SI-NEXT:s_load_dwordx2 s[0:1], s[2:3], 0x9 +; SI-NEXT:s_load_dword s6, s[4:5], 0xb +;

[llvm-branch-commits] [llvm] [AMDGPU][Attributor] Make `AAAMDWavesPerEU` honor existing attribute (PR #114438)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/114438 >From fe1979082eea45d70ac6b6112f2eb4c4fdb2fa72 Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Thu, 31 Oct 2024 12:49:07 -0400 Subject: [PATCH] [WIP][AMDGPU][Attributor] Make `AAAMDWavesPerEU` honor existing

[llvm-branch-commits] [clang] [llvm] [PassBuilder] Add `ThinOrFullLTOPhase` to optimizer pipeline (PR #114577)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/114577 >From 488643ca48229d9c48d9b28916fd887b8be15205 Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Fri, 1 Nov 2024 12:39:52 -0400 Subject: [PATCH] [PassBuilder] Add `ThinOrFullLTOPhase` to optimizer pipeline ---

[llvm-branch-commits] [llvm] [AMDGPU][Attributor] Skip update if an AA is at its initial state (PR #114726)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/114726 >From 4e380599d038e8269c100f7a252331d5db9dffb7 Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Sun, 3 Nov 2024 19:35:26 -0500 Subject: [PATCH] [AMDGPU][Attributor] Skip update if an AA is at its initial state

[llvm-branch-commits] [llvm] [AMDGPU][Attributor] Skip update if an AA is at its initial state (PR #114726)

shiltian wrote: > [!WARNING] > This pull request is not mergeable via GitHub because a downstack PR is > open. Once all requirements are satisfied, merge this PR as a stack href="https://app.graphite.dev/github/pr/llvm/llvm-project/114726?utm_source=stack-comment-downstack-mergeability-warning"

[llvm-branch-commits] [clang] [llvm] [PassBuilder] Add `ThinOrFullLTOPhase` to optimizer pipeline (PR #114577)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/114577 >From a931d1ad84429798fe01ec76dc77cd221f03d2d4 Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Fri, 1 Nov 2024 12:39:52 -0400 Subject: [PATCH] [PassBuilder] Add `ThinOrFullLTOPhase` to optimizer pipeline ---

[llvm-branch-commits] [llvm] [AMDGPU][Attributor] Make `AAAMDWavesPerEU` honor existing attribute (PR #114438)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/114438 >From 79f88836a79e63069eb6b7b58fa376bcd2b32303 Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Thu, 31 Oct 2024 12:49:07 -0400 Subject: [PATCH] [WIP][AMDGPU][Attributor] Make `AAAMDWavesPerEU` honor existing

[llvm-branch-commits] [llvm] [AMDGPU][Attributor] Skip update if an AA is at its initial state (PR #114726)

https://github.com/shiltian created https://github.com/llvm/llvm-project/pull/114726 None >From b7612eddae0b0808f82bb8bc2e6fd6e34361ae5c Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Sun, 3 Nov 2024 19:35:26 -0500 Subject: [PATCH] [AMDGPU][Attributor] Skip update if an AA is at its initial

[llvm-branch-commits] [llvm] [AMDGPU][Attributor] Skip update if an AA is at its initial state (PR #114726)

@@ -740,6 +740,16 @@ struct AAAMDSizeRangeAttribute if (!CallerInfo || !CallerInfo->isValidState()) return false; + /// When the caller AA is in its initial state, the state remains valid + /// but awaits propagation. We skip processing in this case. No

[llvm-branch-commits] [llvm] [AMDGPU][Attributor] Make `AAAMDWavesPerEU` honor existing attribute (PR #114438)

shiltian wrote: bump https://github.com/llvm/llvm-project/pull/114438 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] [AMDGPU][Attributor] Skip update if an AA is at its initial state (PR #114726)

shiltian wrote: bump https://github.com/llvm/llvm-project/pull/114726 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: Treat uint32_max as the default value for amdgpu-max-num-workgroups (PR #113751)

https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/113751 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] [AMDGPU][Attributor] Make `AAAMDWavesPerEU` honor existing attribute (PR #114438)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/114438 >From 66264a1254c322fc0d3aa464125370886ad7da7c Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Thu, 31 Oct 2024 12:49:07 -0400 Subject: [PATCH] [WIP][AMDGPU][Attributor] Make `AAAMDWavesPerEU` honor existing

[llvm-branch-commits] [llvm] [WIP][AMDGPU][Attributor] Make `AAAMDWavesPerEU` honor existing attribute (PR #114438)

@@ -404,21 +404,20 @@ attributes #19 = { "amdgpu-waves-per-eu"="8,9" } ; CHECK: attributes #[[ATTR2]] = { "amdgpu-flat-work-group-size"="1,64" "amdgpu-no-agpr" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-he

[llvm-branch-commits] [llvm] [WIP][AMDGPU][Attributor] Make `AAAMDWavesPerEU` honor existing attribute (PR #114438)

@@ -404,21 +404,20 @@ attributes #19 = { "amdgpu-waves-per-eu"="8,9" } ; CHECK: attributes #[[ATTR2]] = { "amdgpu-flat-work-group-size"="1,64" "amdgpu-no-agpr" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-he

[llvm-branch-commits] [llvm] [AMDGPU][Attributor] Make `AAAMDWavesPerEU` honor existing attribute (PR #114438)

https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/114438 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] [WIP][AMDGPU][Attributor] Make `AAAMDWavesPerEU` honor existing attribute (PR #114438)

https://github.com/shiltian created https://github.com/llvm/llvm-project/pull/114438 None >From 687d29af2f79b07cdc8b8b0044a8c1f828745cfd Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Thu, 31 Oct 2024 12:49:07 -0400 Subject: [PATCH] [WIP][AMDGPU][Attributor] Make `AAAMDWavesPerEU` honor exi

[llvm-branch-commits] [llvm] [WIP][AMDGPU][Attributor] Make `AAAMDWavesPerEU` honor existing attribute (PR #114438)

shiltian wrote: > [!WARNING] > This pull request is not mergeable via GitHub because a downstack PR is > open. Once all requirements are satisfied, merge this PR as a stack href="https://app.graphite.dev/github/pr/llvm/llvm-project/114438?utm_source=stack-comment-downstack-mergeability-warning"

[llvm-branch-commits] [llvm] [AMDGPU][Attributor] Make `AAAMDWavesPerEU` honor existing attribute (PR #114438)

@@ -215,6 +215,19 @@ class AMDGPUInformationCache : public InformationCache { return ST.getWavesPerEU(F, FlatWorkGroupSize); } + std::optional> + getWavesPerEUAttr(const Function &F) { +Attribute Attr = F.getFnAttribute("amdgpu-waves-per-eu"); +if (!Attr.isStri

[llvm-branch-commits] [clang] [llvm] [PassBuilder] Add `ThinOrFullLTOPhase` to early simplication EP call backs (PR #114547)

@@ -821,8 +825,15 @@ void AMDGPUTargetMachine::registerPassBuilderCallbacks(PassBuilder &PB) { PM.addPass(AMDGPUSwLowerLDSPass(*this)); if (EnableLowerModuleLDS) PM.addPass(AMDGPULowerModuleLDSPass(*this)); -if (EnableAMDGPUAttributor && Lev

[llvm-branch-commits] [clang] [llvm] [PassBuilder] Add `ThinOrFullLTOPhase` to early simplication EP call backs (PR #114547)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/114547 >From 912283a403e1a3a95ebead98467cc743024b5455 Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Fri, 1 Nov 2024 10:51:20 -0400 Subject: [PATCH] [PassBuilder] Add `LTOPreLink` to early simplication EP call back

[llvm-branch-commits] [clang] [llvm] [PassBuilder] Add `ThinOrFullLTOPhase` to optimizer pipeline (PR #114577)

https://github.com/shiltian created https://github.com/llvm/llvm-project/pull/114577 None >From dc94afc308989a4dbaee911f93f1cc1855bd7c55 Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Fri, 1 Nov 2024 12:39:52 -0400 Subject: [PATCH] [PassBuilder] Add `ThinOrFullLTOPhase` to optimizer pipeline

[llvm-branch-commits] [clang] [llvm] [PassBuilder] Add `ThinOrFullLTOPhase` to optimizer pipeline (PR #114577)

shiltian wrote: > [!WARNING] > This pull request is not mergeable via GitHub because a downstack PR is > open. Once all requirements are satisfied, merge this PR as a stack href="https://app.graphite.dev/github/pr/llvm/llvm-project/114577?utm_source=stack-comment-downstack-mergeability-warning"

[llvm-branch-commits] [clang] [llvm] [PassBuilder] Add `ThinOrFullLTOPhase` to early simplication EP call backs (PR #114547)

https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/114547 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [clang] [llvm] [PassBuilder] Add `ThinOrFullLTOPhase` to early simplication EP call backs (PR #114547)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/114547 >From e753c4fadf85f1730a458804bec41d32df5a692b Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Fri, 1 Nov 2024 10:51:20 -0400 Subject: [PATCH] [PassBuilder] Add `LTOPreLink` to early simplication EP call back

[llvm-branch-commits] [clang] [llvm] [PassBuilder] Add `ThinOrFullLTOPhase` to early simplication EP call backs (PR #114547)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/114547 >From 8ae74a4c6a96eb0c44668d571aa61116eaa48cbe Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Fri, 1 Nov 2024 10:51:20 -0400 Subject: [PATCH] [PassBuilder] Add `LTOPreLink` to early simplication EP call back

[llvm-branch-commits] [clang] [llvm] [PassBuilder] Add `ThinOrFullLTOPhase` to early simplication EP call backs (PR #114547)

@@ -821,8 +825,15 @@ void AMDGPUTargetMachine::registerPassBuilderCallbacks(PassBuilder &PB) { PM.addPass(AMDGPUSwLowerLDSPass(*this)); if (EnableLowerModuleLDS) PM.addPass(AMDGPULowerModuleLDSPass(*this)); -if (EnableAMDGPUAttributor && Lev

[llvm-branch-commits] [llvm] [AMDGPU][Attributor] Make `AAAMDWavesPerEU` honor existing attribute (PR #114438)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/114438 >From 1aaf29fc290cca84843f0ed1d4b9b9258b8daa36 Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Thu, 31 Oct 2024 12:49:07 -0400 Subject: [PATCH] [WIP][AMDGPU][Attributor] Make `AAAMDWavesPerEU` honor existing

[llvm-branch-commits] [llvm] [AMDGPU][Attributor] Make `AAAMDWavesPerEU` honor existing attribute (PR #114438)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/114438 >From 013d7aeb4698b74af0b48ce74512d770d46cd81e Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Thu, 31 Oct 2024 12:49:07 -0400 Subject: [PATCH] [WIP][AMDGPU][Attributor] Make `AAAMDWavesPerEU` honor existing

[llvm-branch-commits] [llvm] [AMDGPU][Attributor] Make `AAAMDWavesPerEU` honor existing attribute (PR #114438)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/114438 >From 7181479ee055c0c8d15a674d577a9cd694e21621 Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Thu, 31 Oct 2024 12:49:07 -0400 Subject: [PATCH] [WIP][AMDGPU][Attributor] Make `AAAMDWavesPerEU` honor existing

[llvm-branch-commits] [clang] [llvm] [PassBuilder] Add `ThinOrFullLTOPhase` to early simplication EP call backs (PR #114547)

@@ -821,8 +825,15 @@ void AMDGPUTargetMachine::registerPassBuilderCallbacks(PassBuilder &PB) { PM.addPass(AMDGPUSwLowerLDSPass(*this)); if (EnableLowerModuleLDS) PM.addPass(AMDGPULowerModuleLDSPass(*this)); -if (EnableAMDGPUAttributor && Lev

[llvm-branch-commits] [llvm] AMDGPU: Propagate amdgpu-max-num-workgroups attribute (PR #113018)

@@ -821,6 +826,152 @@ AAAMDFlatWorkGroupSize::createForPosition(const IRPosition &IRP, "AAAMDFlatWorkGroupSize is only valid for function position"); } +struct TupleDecIntegerRangeState : public AbstractState { + DecIntegerState X, Y, Z; + + bool isValidState() const

[llvm-branch-commits] [llvm] [TargetTransformInfo] Remove `getFlatAddressSpace` (PR #108787)

https://github.com/shiltian closed https://github.com/llvm/llvm-project/pull/108787 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] [TargetTransformInfo] Remove `getFlatAddressSpace` (PR #108787)

shiltian wrote: The dependent PR has been closed. https://github.com/llvm/llvm-project/pull/108787 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [openmp] release/19.x: [OpenMP] Create versioned libgomp softlinks (#112973) (PR #115944)

shiltian wrote: Are we still releasing 19? https://github.com/llvm/llvm-project/pull/115944 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [openmp] release/19.x: [OpenMP] Create versioned libgomp softlinks (#112973) (PR #115944)

https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/115944 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] [AMDGPU][Attributor] Make `AAAMDWavesPerEU` honor existing attribute (PR #114438)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/114438 >From d0ec41bcb8f0594b86336e45028d490dd4ebf6c4 Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Thu, 31 Oct 2024 12:49:07 -0400 Subject: [PATCH] [WIP][AMDGPU][Attributor] Make `AAAMDWavesPerEU` honor existing

[llvm-branch-commits] [llvm] [AMDGPU][Attributor] Make `AAAMDWavesPerEU` honor existing attribute (PR #114438)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/114438 >From b7f1c2bd5d33a060ab2a8ee942874d208d42cac9 Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Thu, 31 Oct 2024 12:49:07 -0400 Subject: [PATCH] [WIP][AMDGPU][Attributor] Make `AAAMDWavesPerEU` honor existing

[llvm-branch-commits] [llvm] [AMDGPU][Attributor] Make `AAAMDWavesPerEU` honor existing attribute (PR #114438)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/114438 >From 25b1ec0e80072c70628da9d72be8969fd6bb3d87 Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Thu, 31 Oct 2024 12:49:07 -0400 Subject: [PATCH] [WIP][AMDGPU][Attributor] Make `AAAMDWavesPerEU` honor existing

[llvm-branch-commits] [llvm] [AMDGPU][Attributor] Make `AAAMDWavesPerEU` honor existing attribute (PR #114438)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/114438 >From b48566210212165429e6a29665a4fefdf2695e61 Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Thu, 31 Oct 2024 12:49:07 -0400 Subject: [PATCH] [WIP][AMDGPU][Attributor] Make `AAAMDWavesPerEU` honor existing

[llvm-branch-commits] [llvm] [AMDGPU] Still set up the two SGPRs for queue ptr even it is COV5 (PR #112403)

https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/112403 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] [AMDGPU] Fix (PR #115505)

shiltian wrote: > [!WARNING] > This pull request is not mergeable via GitHub because a downstack PR is > open. Once all requirements are satisfied, merge this PR as a stack href="https://app.graphite.dev/github/pr/llvm/llvm-project/115505?utm_source=stack-comment-downstack-mergeability-warning"

[llvm-branch-commits] [llvm] [AMDGPU] Fix (PR #115505)

https://github.com/shiltian created https://github.com/llvm/llvm-project/pull/115505 None >From 8162e61b66ee56e476cf4987a9faff89dfdfc3d0 Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Tue, 29 Oct 2024 01:29:40 -0400 Subject: [PATCH] [AMDGPU] Fix --- llvm/lib/Target/AMDGPU/SIFrameLowering.c

[llvm-branch-commits] [llvm] [AMDGPU] Fix (PR #115505)

https://github.com/shiltian closed https://github.com/llvm/llvm-project/pull/115505 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] [Attributor] Use more appropriate approach to check flat address space (PR #108713)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/108713 >From fb2ed73b44facf865312d7efe32053718fcd6458 Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Thu, 12 Sep 2024 15:25:43 -0400 Subject: [PATCH] [Attributor] Use more appropriate approach to check flat address

[llvm-branch-commits] [llvm] [TargetTransformInfo] Remove `getFlatAddressSpace` (PR #108787)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/108787 >From e6fb6d58ce5cd8d02d769e1a4eb9664449fb785b Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Sun, 15 Sep 2024 23:06:14 -0400 Subject: [PATCH] [TargetTransformInfo] Remove `getFlatAddressSpace` This has been

[llvm-branch-commits] [llvm] [Attributor] Take the address space from addrspacecast directly (PR #108258)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/108258 >From 4f56200b16374ae69b717847872d53a80f505869 Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Wed, 11 Sep 2024 12:23:32 -0400 Subject: [PATCH] [Attributor] Take the address space from addrspacecast directly

[llvm-branch-commits] [llvm] [Attributor] Take the address space from addrspacecast directly (PR #108258)

@@ -12571,17 +12571,59 @@ struct AAAddressSpaceImpl : public AAAddressSpace { void initialize(Attributor &A) override { assert(getAssociatedType()->isPtrOrPtrVectorTy() && "Associated value is not a pointer"); -if (getAssociatedType()->getPointerAddressSpac

[llvm-branch-commits] [llvm] [Attributor] Take the address space from addrspacecast directly (PR #108258)

@@ -12571,17 +12571,59 @@ struct AAAddressSpaceImpl : public AAAddressSpace { void initialize(Attributor &A) override { assert(getAssociatedType()->isPtrOrPtrVectorTy() && "Associated value is not a pointer"); -if (getAssociatedType()->getPointerAddressSpac

[llvm-branch-commits] [llvm] [AMDGPU] Adopt new lowering sequence for `fdiv16` (PR #109295)

https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/109295 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] [TargetTransformInfo] Remove `getFlatAddressSpace` (PR #108787)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/108787 >From ad6ff10e0612cce572b0d950b76b9d3c80c6dee3 Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Sun, 15 Sep 2024 23:06:14 -0400 Subject: [PATCH] [TargetTransformInfo] Remove `getFlatAddressSpace` This has been

[llvm-branch-commits] [llvm] [Attributor] Use more appropriate approach to check flat address space (PR #108713)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/108713 >From 02b52beaefab0b63c3c09fd1f84b907b89c0cf7b Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Thu, 12 Sep 2024 15:25:43 -0400 Subject: [PATCH] [Attributor] Use more appropriate approach to check flat address

[llvm-branch-commits] [llvm] [Attributor] Take the address space from addrspacecast directly (PR #108258)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/108258 >From f85ea4140cb95e46e0c2341cb93090f755e44cef Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Wed, 11 Sep 2024 12:23:32 -0400 Subject: [PATCH] [Attributor] Take the address space from addrspacecast directly

[llvm-branch-commits] [llvm] [TargetTransformInfo] Remove `getFlatAddressSpace` (PR #108787)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/108787 >From 3541dca143c46f0c775bb0c51c8d562dda322cb2 Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Sun, 15 Sep 2024 23:06:14 -0400 Subject: [PATCH] [TargetTransformInfo] Remove `getFlatAddressSpace` This has been

[llvm-branch-commits] [llvm] [Attributor] Use more appropriate approach to check flat address space (PR #108713)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/108713 >From cfce39f2434a0a9b2cab278c909380edef9ce896 Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Thu, 12 Sep 2024 15:25:43 -0400 Subject: [PATCH] [Attributor] Use more appropriate approach to check flat address

[llvm-branch-commits] [llvm] [Attributor] Take the address space from addrspacecast directly (PR #108258)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/108258 >From 081015ee9e9988d7340eff720af47e9292fb3d1c Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Wed, 11 Sep 2024 12:23:32 -0400 Subject: [PATCH] [Attributor] Take the address space from addrspacecast directly

[llvm-branch-commits] [llvm] [Attributor] Take the address space from addrspacecast directly (PR #108258)

https://github.com/shiltian deleted https://github.com/llvm/llvm-project/pull/108258 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] [Attributor] Take the address space from addrspacecast directly (PR #108258)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/108258 >From f79d612a7335e7a150c2347638ea6a9e36bbc1ea Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Wed, 25 Sep 2024 14:42:09 -0400 Subject: [PATCH] [Attributor] Take the address space from addrspacecast directly

[llvm-branch-commits] [llvm] [Attributor] Take the address space from addrspacecast directly (PR #108258)

shiltian wrote: I unstacked from https://github.com/llvm/llvm-project/pull/108786 to unblock this since the ticket needs to be fixed promptly. https://github.com/llvm/llvm-project/pull/108258 ___ llvm-branch-commits mailing list llvm-branch-commits@li

[llvm-branch-commits] [llvm] [TargetTransformInfo] Remove `getFlatAddressSpace` (PR #108787)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/108787 >From f2331fc099d59726b891bb7bdbf6e61ea9e4 Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Sun, 15 Sep 2024 23:06:14 -0400 Subject: [PATCH] [TargetTransformInfo] Remove `getFlatAddressSpace` This has been

[llvm-branch-commits] [llvm] [Attributor] Use more appropriate approach to check flat address space (PR #108713)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/108713 >From 7da66b7196f14567ac3bfc59faeb61a6b80bd6a6 Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Thu, 12 Sep 2024 15:25:43 -0400 Subject: [PATCH] [Attributor] Use more appropriate approach to check flat address

[llvm-branch-commits] [llvm] [Attributor] Take the address space from addrspacecast directly (PR #108258)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/108258 >From dd7eeb45bd239f9910421afef3143d1ae621538c Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Wed, 11 Sep 2024 12:23:32 -0400 Subject: [PATCH] [Attributor] Take the address space from addrspacecast directly

[llvm-branch-commits] [llvm] [Attributor] Use more appropriate approach to check flat address space (PR #108713)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/108713 >From 6356a1548c7c91b44d48159c666abb07df307e9a Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Thu, 12 Sep 2024 15:25:43 -0400 Subject: [PATCH] [Attributor] Use more appropriate approach to check flat address

[llvm-branch-commits] [llvm] [Attributor] Use more appropriate approach to check flat address space (PR #108713)

https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/108713 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] [Attributor] Take the address space from addrspacecast directly (PR #108258)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/108258 >From 1b060670b1e364879f6039a243b67adfc03731d1 Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Wed, 11 Sep 2024 12:23:32 -0400 Subject: [PATCH] [Attributor] Take the address space from addrspacecast directly

[llvm-branch-commits] [llvm] [Attributor] Take the address space from addrspacecast directly (PR #108258)

https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/108258 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] [Attributor] Take the address space from addrspacecast directly (PR #108258)

https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/108258 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] [AMDGPU] Introduce a "new" target feature `xf32-insts` (PR #115214)

https://github.com/shiltian updated https://github.com/llvm/llvm-project/pull/115214 >From 1bf7b52751fd5f09b9e9fb4850f5ca6a022cda81 Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Wed, 6 Nov 2024 16:15:50 -0500 Subject: [PATCH] [AMDGPU] Introduce a "new" target feature `xf32-insts` The featur

[llvm-branch-commits] [clang] [llvm] [AMDGPU] Introduce a new generic target `gfx9-4-generic` (PR #115190)

@@ -576,6 +576,12 @@ Generic processor code objects are versioned. See :ref:`amdgpu-generic-processor - ``v_dot2_f32_f16`` + ``gfx9-4-generic`` ``amdgcn`` - ``gfx940`

[llvm-branch-commits] [llvm] [AMDGPU] Still set up the two SGPRs for queue ptr even it is COV5 (PR #112403)

https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/112403 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] [AMDGPU] Still set up the two SGPRs for queue ptr even it is COV5 (PR #112403)

@@ -4,12 +4,12 @@ define amdgpu_kernel void @s_clear_msb(ptr addrspace(1) %out, i32 %in) { ; SI-LABEL: s_clear_msb: ; SI: ; %bb.0: -; SI-NEXT:s_load_dword s4, s[2:3], 0xb -; SI-NEXT:s_load_dwordx2 s[0:1], s[2:3], 0x9 +; SI-NEXT:s_load_dword s6, s[4:5], 0xb +;

[llvm-branch-commits] [llvm] [AMDGPU] Introduce a "new" target feature `xf32-insts` (PR #115214)

@@ -1110,6 +1110,13 @@ def FeatureRequiresCOV6 : SubtargetFeature<"requires-cov6", "Target Requires Code Object V6" >; +def FeatureXF32Insts : SubtargetFeature<"xf32-insts", + "HasXF32Insts", + "true", + "Has instructions that support xf32 format, such as " + "v_mfm

[llvm-branch-commits] [llvm] [AMDGPU] Introduce a "new" target feature `xf32-insts` (PR #115214)

https://github.com/shiltian created https://github.com/llvm/llvm-project/pull/115214 The feature itself is not new. Just to use it to guard corresponding instructions. >From 4077a199a263252ef45895e2c9b4e6375988fa88 Mon Sep 17 00:00:00 2001 From: Shilei Tian Date: Wed, 6 Nov 2024 16:15:50 -0500

[llvm-branch-commits] [llvm] [AMDGPU] Introduce a "new" target feature `xf32-insts` (PR #115214)

shiltian wrote: > [!WARNING] > This pull request is not mergeable via GitHub because a downstack PR is > open. Once all requirements are satisfied, merge this PR as a stack href="https://app.graphite.dev/github/pr/llvm/llvm-project/115214?utm_source=stack-comment-downstack-mergeability-warning"

[llvm-branch-commits] [llvm] [AMDGPU] Introduce a "new" target feature `xf32-insts` (PR #115214)

https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/115214 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [clang] [llvm] [AMDGPU] Introduce a new generic target `gfx9-4-generic` (PR #115190)

https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/115190 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [clang] [llvm] [AMDGPU] Introduce a new generic target `gfx9-4-generic` (PR #115190)

https://github.com/shiltian deleted https://github.com/llvm/llvm-project/pull/115190 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

<    1   2   3   4   5   6   >