[PATCH] D148796: [AMDGPU][GFX908] Add builtin support for global add atomic f16/f32

mariusz-sikora-at-amd added inline comments. Comment at: clang/lib/Sema/SemaChecking.cpp:4491 +// the builtin. +TheCall->setType(Context.VoidTy); +return false; arsenm wrote: > I'm assuming mutating the AST is very not OK I based my changes on how

[PATCH] D148796: [AMDGPU][GFX908] Add builtin support for global add atomic f16/f32

mariusz-sikora-at-amd added reviewers: arsenm, rampitec, gandhi21299, foad. mariusz-sikora-at-amd added a comment. Herald added a subscriber: StephenFan. This is a proposal how we could extend global fadd atomic builtins support for gfx908 Repository: rG LLVM Github Monorepo CHANGES SINCE

[PATCH] D148796: [AMDGPU][GFX908] Add builtin support for global add atomic f16/f32

mariusz-sikora-at-amd created this revision. Herald added subscribers: kosarev, kerbowa, hiraditya, tpr, dstuttard, yaxunl, jvesely, kzhuravl. Herald added a project: All. mariusz-sikora-at-amd requested review of this revision. Herald added subscribers: llvm-commits, cfe-commits, wdng. Herald

[PATCH] D146808: [AMDGPU] Add clang builtin for __builtin_amdgcn_ds_atomic_fadd_v2f16

This revision was landed with ongoing or failed builds. This revision was automatically updated to reflect the committed changes. Closed by commit rG69061f96275c: [AMDGPU] Add clang builtin for __builtin_amdgcn_ds_atomic_fadd_v2f16 (authored by mariusz-sikora-at-amd). Repository: rG LLVM

[PATCH] D146808: [AMDGPU] Add clang builtin for __builtin_amdgcn_ds_atomic_fadd_v2f16

mariusz-sikora-at-amd created this revision. Herald added subscribers: kosarev, kerbowa, tpr, dstuttard, yaxunl, jvesely, kzhuravl. Herald added a project: All. mariusz-sikora-at-amd requested review of this revision. Herald added subscribers: cfe-commits, wdng. Herald added a project: clang.

[PATCH] D146701: [AMDGPU] Create Subtarget Features for some of 16 bits atomic fadd instructions

This revision was landed with ongoing or failed builds. This revision was automatically updated to reflect the committed changes. Closed by commit rGea064ee2a3bd: [AMDGPU] Create Subtarget Features for some of 16 bits atomic fadd instructions (authored by mariusz-sikora-at-amd). Repository: rG

[PATCH] D146701: [AMDGPU] Create Subtarget Features for some of 16 bits atomic fadd instructions

mariusz-sikora-at-amd updated this revision to Diff 507871. mariusz-sikora-at-amd added a comment. Put back Real Instructions under SubtargetPredicate associated with gfx generation. Repository: rG LLVM Github Monorepo CHANGES SINCE LAST ACTION https://reviews.llvm.org/D146701/new/

[PATCH] D146701: [AMDGPU] Create Subtarget Features for some of 16 bits atomic fadd instructions

mariusz-sikora-at-amd added inline comments. Comment at: llvm/lib/Target/AMDGPU/FLATInstructions.td:1915 +defm GLOBAL_ATOMIC_PK_ADD_F16 : FLAT_Global_Real_Atomics_vi <0x04e, 0>; +defm GLOBAL_ATOMIC_PK_ADD_BF16 : FLAT_Global_Real_Atomics_vi<0x52>; foad wrote: >

[PATCH] D146701: [AMDGPU] Create Subtarget Features for some of 16 bits atomic fadd instructions

mariusz-sikora-at-amd added inline comments. Comment at: llvm/lib/Target/AMDGPU/BUFInstructions.td:2891 +let SubtargetPredicate = HasAtomicFaddNoRtnInsts in { +defm BUFFER_ATOMIC_ADD_F32: MUBUF_Real_Atomic_vi <0x4d>; foad wrote: > Is this still required?

[PATCH] D146701: [AMDGPU] Create Subtarget Features for some of 16 bits atomic fadd instructions

mariusz-sikora-at-amd added inline comments. Comment at: llvm/lib/Target/AMDGPU/FLATInstructions.td:1915 +defm GLOBAL_ATOMIC_PK_ADD_F16 : FLAT_Global_Real_Atomics_vi <0x04e, 0>; +defm GLOBAL_ATOMIC_PK_ADD_BF16 : FLAT_Global_Real_Atomics_vi<0x52>; foad wrote: >

[PATCH] D146701: [AMDGPU] Create Subtarget Features for some of 16 bits atomic fadd instructions

mariusz-sikora-at-amd updated this revision to Diff 507722. mariusz-sikora-at-amd added a comment. Changes after review. Repository: rG LLVM Github Monorepo CHANGES SINCE LAST ACTION https://reviews.llvm.org/D146701/new/ https://reviews.llvm.org/D146701 Files:

[PATCH] D146701: [AMDGPU] Create Subtarget Features for some of 16 bits atomic fadd instructions

mariusz-sikora-at-amd added inline comments. Comment at: clang/include/clang/Basic/BuiltinsAMDGPU.def:233 +TARGET_BUILTIN(__builtin_amdgcn_global_atomic_fadd_v2bf16, "V2sV2s*1V2s", "t", "atomic-global-pk-add-bf16-inst") +TARGET_BUILTIN(__builtin_amdgcn_ds_atomic_fadd_v2bf16,

[PATCH] D146701: [AMDGPU] Create Subtarget Features for some of 16 bits atomic fadd instructions

mariusz-sikora-at-amd created this revision. Herald added subscribers: kosarev, foad, kerbowa, hiraditya, tpr, dstuttard, yaxunl, jvesely, kzhuravl, arsenm. Herald added a project: All. mariusz-sikora-at-amd requested review of this revision. Herald added subscribers: llvm-commits, cfe-commits,

[PATCH] D135110: [NFC] [HLSL] Move common metadata to LLVMFrontend

mariusz-sikora-at-amd added a comment. In D135110#3859844 , @mstorsjo wrote: > I don't quite know why, but it seems like this new library breaks tests of > llvm-config; if I start out with an empty build directory and run `ninja > check-llvm` (or