diff options
| author | Matt Arsenault <Matthew.Arsenault@amd.com> | 2017-07-06 20:57:05 +0000 |
|---|---|---|
| committer | Matt Arsenault <Matthew.Arsenault@amd.com> | 2017-07-06 20:57:05 +0000 |
| commit | 9aa45f047f303b6484afce6716472b3b1f510c7e (patch) | |
| tree | d25023848a172579a8d26d9860316edaffcee5d0 /llvm/test/CodeGen/AMDGPU/multi-divergent-exit-region.ll | |
| parent | a81198d82de20e14efce44826e302785bfda093a (diff) | |
| download | bcm5719-llvm-9aa45f047f303b6484afce6716472b3b1f510c7e.tar.gz bcm5719-llvm-9aa45f047f303b6484afce6716472b3b1f510c7e.zip | |
AMDGPU: Add macro fusion schedule DAG mutation
Try to increase opportunities to shrink vcc uses.
llvm-svn: 307313
Diffstat (limited to 'llvm/test/CodeGen/AMDGPU/multi-divergent-exit-region.ll')
| -rw-r--r-- | llvm/test/CodeGen/AMDGPU/multi-divergent-exit-region.ll | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/llvm/test/CodeGen/AMDGPU/multi-divergent-exit-region.ll b/llvm/test/CodeGen/AMDGPU/multi-divergent-exit-region.ll index 82c27f204a4..ba3ff0b08bc 100644 --- a/llvm/test/CodeGen/AMDGPU/multi-divergent-exit-region.ll +++ b/llvm/test/CodeGen/AMDGPU/multi-divergent-exit-region.ll @@ -66,9 +66,9 @@ ; FIXME: Why is this compare essentially repeated? ; GCN: v_cmp_eq_u32_e32 vcc, 1, [[REG:v[0-9]+]] -; GCN-NEXT: v_cmp_ne_u32_e64 s{{\[[0-9]+:[0-9]+\]}}, 1, [[REG]] ; GCN: v_cndmask_b32_e64 v{{[0-9]+}}, 0, -1, vcc -; GCN: v_cndmask_b32_e64 v{{[0-9]+}}, 0, -1 +; GCN: v_cmp_ne_u32_e32 vcc, 1, [[REG]] +; GCN: v_cndmask_b32_e64 v{{[0-9]+}}, 0, -1, vcc ; GCN: ; %Flow1 ; GCN-NEXT: s_or_b64 exec, exec |
