diff options
| author | Stanislav Mekhanoshin <Stanislav.Mekhanoshin@amd.com> | 2017-09-11 17:13:57 +0000 |
|---|---|---|
| committer | Stanislav Mekhanoshin <Stanislav.Mekhanoshin@amd.com> | 2017-09-11 17:13:57 +0000 |
| commit | 710da42b86bb7c1756ad74d3b1fd47b76e981eb6 (patch) | |
| tree | 8f7d509dfb5863591c759eb6c404aeeb711b168b /llvm/test/CodeGen/AMDGPU/v_madak_f16.ll | |
| parent | 894dbbe8eb0e3d8fc7d8746a76d2380f0c2b6c0f (diff) | |
| download | bcm5719-llvm-710da42b86bb7c1756ad74d3b1fd47b76e981eb6.tar.gz bcm5719-llvm-710da42b86bb7c1756ad74d3b1fd47b76e981eb6.zip | |
[AMDGPU] Produce madak and madmk from the two-address pass
These two instructions are normally selected, but when the
two address pass converts mac into mad we end up with the
mad where we could have one of these.
Differential Revision: https://reviews.llvm.org/D37389
llvm-svn: 312928
Diffstat (limited to 'llvm/test/CodeGen/AMDGPU/v_madak_f16.ll')
| -rw-r--r-- | llvm/test/CodeGen/AMDGPU/v_madak_f16.ll | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/llvm/test/CodeGen/AMDGPU/v_madak_f16.ll b/llvm/test/CodeGen/AMDGPU/v_madak_f16.ll index 0148ff470b7..ab47cc99a21 100644 --- a/llvm/test/CodeGen/AMDGPU/v_madak_f16.ll +++ b/llvm/test/CodeGen/AMDGPU/v_madak_f16.ll @@ -23,9 +23,9 @@ entry: } ; GCN-LABEL: {{^}}madak_f16_use_2 -; SI: v_mad_f32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}} +; SI: v_madak_f32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}, 0x41200000 ; SI: v_mac_f32_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}} -; VI: v_mad_f16 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}} +; VI: v_madak_f16 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}, 0x4900 ; VI: v_mac_f16_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}} ; GCN: s_endpgm define amdgpu_kernel void @madak_f16_use_2( |
