projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 7529f0e) | patch
[clang] Add clang builtins support for gfx90a
authorAnshil Gandhi <Anshil.Gandhi@amd.com>
Thu, 5 Aug 2021 08:08:06 +0000 (02:08 -0600)
committerAnshil Gandhi <Anshil.Gandhi@amd.com>
Thu, 5 Aug 2021 08:08:06 +0000 (02:08 -0600)
commit39dac1f7f65691487dbdc969e343108db5b0f765
tree59a720563abe27055d43e784d1e87802d1253fdftree | snapshot
parent7529f0e3e1427fea93a6a66a2aed5394710e5fb5commit | diff
[clang] Add clang builtins support for gfx90a

Implement target builtins for gfx90a including fadd64, fadd32, add2h,
max and min on various global, flat and ds address spaces for which
intrinsics are implemented.

Differential Revision: https://reviews.llvm.org/D106909
clang/include/clang/Basic/BuiltinsAMDGPU.def diff | blob | history
clang/lib/CodeGen/CGBuiltin.cpp diff | blob | history
clang/test/CodeGenOpenCL/builtins-amdgcn-fp-atomics-gfx7-err.cl [new file with mode: 0644] blob
clang/test/CodeGenOpenCL/builtins-amdgcn-fp-atomics-gfx908-err.cl [new file with mode: 0644] blob
clang/test/CodeGenOpenCL/builtins-fp-atomics-gfx1030.cl [new file with mode: 0644] blob
clang/test/CodeGenOpenCL/builtins-fp-atomics-gfx8.cl [new file with mode: 0644] blob
clang/test/CodeGenOpenCL/builtins-fp-atomics-gfx90a.cl [new file with mode: 0644] blob
Domain: System / Toolchain;