diff options
| author | Matt Arsenault <Matthew.Arsenault@amd.com> | 2016-04-12 14:05:04 +0000 |
|---|---|---|
| committer | Matt Arsenault <Matthew.Arsenault@amd.com> | 2016-04-12 14:05:04 +0000 |
| commit | a9dbdcae04005da93d40b338c5281452cdf43b2a (patch) | |
| tree | d41399d88a16e0864cd964fe096948772a228500 /llvm/test/CodeGen/AMDGPU/local-atomics.ll | |
| parent | 21ecfe43babad065576061714fa92299ed28f35c (diff) | |
| download | bcm5719-llvm-a9dbdcae04005da93d40b338c5281452cdf43b2a.tar.gz bcm5719-llvm-a9dbdcae04005da93d40b338c5281452cdf43b2a.zip | |
AMDGPU: Add atomic_inc + atomic_dec intrinsics
These are different than atomicrmw add 1 because they have
an additional input value to clamp the result.
llvm-svn: 266074
Diffstat (limited to 'llvm/test/CodeGen/AMDGPU/local-atomics.ll')
| -rw-r--r-- | llvm/test/CodeGen/AMDGPU/local-atomics.ll | 1 |
1 files changed, 0 insertions, 1 deletions
diff --git a/llvm/test/CodeGen/AMDGPU/local-atomics.ll b/llvm/test/CodeGen/AMDGPU/local-atomics.ll index 529554cf013..ce82ff5475b 100644 --- a/llvm/test/CodeGen/AMDGPU/local-atomics.ll +++ b/llvm/test/CodeGen/AMDGPU/local-atomics.ll @@ -324,7 +324,6 @@ define void @lds_atomic_xchg_noret_i32_offset(i32 addrspace(3)* %ptr) nounwind { ret void } -; XXX - Is it really necessary to load 4 into VGPR? ; FUNC-LABEL: {{^}}lds_atomic_add_noret_i32: ; GCN: s_load_dword [[SPTR:s[0-9]+]], ; GCN: v_mov_b32_e32 [[DATA:v[0-9]+]], 4 |
