[clang] [llvm] [AMDGPU] modify named barrier builtins and intrinsics (PR #114550)

2024-11-06 Thread Matt Arsenault via cfe-commits
arsenm wrote: > It's the same code already reviewed downstream. LGTM. The commit message is still not helpful https://github.com/llvm/llvm-project/pull/114550 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mail

[clang] [llvm] [AMDGPU] modify named barrier builtins and intrinsics (PR #114550)

2024-11-06 Thread Gang Chen via cfe-commits
https://github.com/cmc-rep closed https://github.com/llvm/llvm-project/pull/114550 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [llvm] [AMDGPU] modify named barrier builtins and intrinsics (PR #114550)

2024-11-06 Thread Stanislav Mekhanoshin via cfe-commits
https://github.com/rampitec approved this pull request. It's the same code already reviewed downstream. LGTM. https://github.com/llvm/llvm-project/pull/114550 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailma

[clang] [llvm] [AMDGPU] modify named barrier builtins and intrinsics (PR #114550)

2024-11-04 Thread Gang Chen via cfe-commits
cmc-rep wrote: Also, I added the piece in AMDGPULowerModuleLDS during internal review because other reviewers want to see the functional completeness. https://github.com/llvm/llvm-project/pull/114550 ___ cfe-commits mailing list cfe-commits@lists.llvm

[clang] [llvm] [AMDGPU] modify named barrier builtins and intrinsics (PR #114550)

2024-11-01 Thread Gang Chen via cfe-commits
@@ -920,6 +920,124 @@ class AMDGPULowerModuleLDS { return KernelToCreatedDynamicLDS; } + static GlobalVariable *uniquifyGVPerKernel(Module &M, GlobalVariable *GV, cmc-rep wrote: This goes together with the change in AMDGPUMachineFunction.cpp https://g

[clang] [llvm] [AMDGPU] modify named barrier builtins and intrinsics (PR #114550)

2024-11-01 Thread Gang Chen via cfe-commits
@@ -920,6 +920,124 @@ class AMDGPULowerModuleLDS { return KernelToCreatedDynamicLDS; } + static GlobalVariable *uniquifyGVPerKernel(Module &M, GlobalVariable *GV, cmc-rep wrote: This is where the local pointer address is assigned for a named barrier be

[clang] [llvm] [AMDGPU] modify named barrier builtins and intrinsics (PR #114550)

2024-11-01 Thread Matt Arsenault via cfe-commits
@@ -920,6 +920,124 @@ class AMDGPULowerModuleLDS { return KernelToCreatedDynamicLDS; } + static GlobalVariable *uniquifyGVPerKernel(Module &M, GlobalVariable *GV, arsenm wrote: This still should be a separate PR https://github.com/llvm/llvm-project/p

[clang] [llvm] [AMDGPU] modify named barrier builtins and intrinsics (PR #114550)

2024-11-01 Thread Gang Chen via cfe-commits
@@ -920,6 +920,124 @@ class AMDGPULowerModuleLDS { return KernelToCreatedDynamicLDS; } + static GlobalVariable *uniquifyGVPerKernel(Module &M, GlobalVariable *GV, cmc-rep wrote: I will add you to the internal review link. So you can see the review hist

[clang] [llvm] [AMDGPU] modify named barrier builtins and intrinsics (PR #114550)

2024-11-01 Thread Gang Chen via cfe-commits
https://github.com/cmc-rep edited https://github.com/llvm/llvm-project/pull/114550 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [llvm] [AMDGPU] modify named barrier builtins and intrinsics (PR #114550)

2024-11-01 Thread Matt Arsenault via cfe-commits
https://github.com/arsenm edited https://github.com/llvm/llvm-project/pull/114550 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [llvm] [AMDGPU] modify named barrier builtins and intrinsics (PR #114550)

2024-11-01 Thread Matt Arsenault via cfe-commits
@@ -920,6 +920,124 @@ class AMDGPULowerModuleLDS { return KernelToCreatedDynamicLDS; } + static GlobalVariable *uniquifyGVPerKernel(Module &M, GlobalVariable *GV, arsenm wrote: This looks like an unrelated, separate change https://github.com/llvm/llv

[clang] [llvm] [AMDGPU] modify named barrier builtins and intrinsics (PR #114550)

2024-11-01 Thread Matt Arsenault via cfe-commits
https://github.com/arsenm commented: Modify how? There seem to be too many things going on here. Description should say how https://github.com/llvm/llvm-project/pull/114550 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.or

[clang] [llvm] [AMDGPU] modify named barrier builtins and intrinsics (PR #114550)

2024-11-01 Thread via cfe-commits
llvmbot wrote: @llvm/pr-subscribers-llvm-ir Author: Gang Chen (cmc-rep) Changes --- Patch is 132.19 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/114550.diff 21 Files Affected: - (modified) clang/include/clang/Basic/BuiltinsAMDGPU.def (+6

[clang] [llvm] [AMDGPU] modify named barrier builtins and intrinsics (PR #114550)

2024-11-01 Thread via cfe-commits
llvmbot wrote: @llvm/pr-subscribers-clang Author: Gang Chen (cmc-rep) Changes --- Patch is 132.19 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/114550.diff 21 Files Affected: - (modified) clang/include/clang/Basic/BuiltinsAMDGPU.def (+6-6