diff options
| author | Matt Arsenault <Matthew.Arsenault@amd.com> | 2018-08-15 18:25:25 +0300 |
|---|---|---|
| committer | Matt Arsenault <Matthew.Arsenault@amd.com> | 2020-04-10 13:37:32 -0400 |
| commit | 4593e4131affa84e61d7b6844be409ba46d29f11 (patch) | |
| tree | 37360ae46f24a91aa98c6f83d8840823e232b9f3 /llvm/lib/Support/TargetParser.cpp | |
| parent | f5be71b44500b18d636b1f540422dda4012ac192 (diff) | |
| download | llvm-4593e4131affa84e61d7b6844be409ba46d29f11.zip llvm-4593e4131affa84e61d7b6844be409ba46d29f11.tar.gz llvm-4593e4131affa84e61d7b6844be409ba46d29f11.tar.bz2 | |
AMDGPU: Teach toolchain to link rocm device libs
Currently the library is separately linked, but this isn't correct to
implement fast math flags correctly. Each module should get the
version of the library appropriate for its combination of fast math
and related flags, with the attributes propagated into its functions
and internalized.
HIP already maintains the list of libraries, but this is not used for
OpenCL. Unfortunately, HIP uses a separate --hip-device-lib argument,
despite both languages using the same bitcode library. Eventually
these two searches need to be merged.
An additional problem is there are 3 different locations the libraries
are installed, depending on which build is used. This also needs to be
consolidated (or at least the search logic needs to deal with this
unnecessary complexity).
Diffstat (limited to 'llvm/lib/Support/TargetParser.cpp')
| -rw-r--r-- | llvm/lib/Support/TargetParser.cpp | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/llvm/lib/Support/TargetParser.cpp b/llvm/lib/Support/TargetParser.cpp index 84ead58..14a5d19 100644 --- a/llvm/lib/Support/TargetParser.cpp +++ b/llvm/lib/Support/TargetParser.cpp @@ -99,9 +99,9 @@ constexpr GPUInfo AMDGCNGPUs[37] = { {{"gfx906"}, {"gfx906"}, GK_GFX906, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32}, {{"gfx908"}, {"gfx908"}, GK_GFX908, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32}, {{"gfx909"}, {"gfx909"}, GK_GFX909, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32}, - {{"gfx1010"}, {"gfx1010"}, GK_GFX1010, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32}, - {{"gfx1011"}, {"gfx1011"}, GK_GFX1011, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32}, - {{"gfx1012"}, {"gfx1012"}, GK_GFX1012, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32}, + {{"gfx1010"}, {"gfx1010"}, GK_GFX1010, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_WAVE32}, + {{"gfx1011"}, {"gfx1011"}, GK_GFX1011, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_WAVE32}, + {{"gfx1012"}, {"gfx1012"}, GK_GFX1012, FEATURE_FAST_FMA_F32|FEATURE_FAST_DENORMAL_F32|FEATURE_WAVE32}, }; const GPUInfo *getArchEntry(AMDGPU::GPUKind AK, ArrayRef<GPUInfo> Table) { |