maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[AMDGPU] adjusted test checks because minnum with NaN gets simplified 

This was improved with rL337127, but I missed the failure in this test.
I'm not sure what the expected result will be, so I've generalized it
and added a FIXME comment.

llvm-svn: 337128
This commit is contained in:
Sanjay Patel 2018-07-15 15:14:40 +00:00
parent 92d0c1c129
commit 810f51ec1b
1 changed files with 5 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
llvm/test/CodeGen/AMDGPU/fcanonicalize-elimination.ll
View File

@ -379,11 +379,12 @@ define amdgpu_kernel void @test_fold_canonicalize_minnum_value_f32(float addrspa
ret void
}
; FIXME: Should there be more checks here? minnum with NaN operand is simplified away.
; GCN-LABEL: test_fold_canonicalize_sNaN_value_f32:
; GCN: v_min_f32_e32 [[V0:v[0-9]+]], 0x7f800001, v{{[0-9]+}}
; GCN-FLUSH: v_mul_f32_e32 [[RESULT:v[0-9]+]], 1.0, [[V0]]
; GCN-DENORM: v_max_f32_e32 [[RESULT:v[0-9]+]], [[V0]], [[V0]]
; GCN: {{flat|global}}_store_dword v[{{[0-9:]+}}], [[RESULT]]
; VI: v_add_u32_e32 v{{[0-9]+}}
; GFX9: v_add_co_u32_e32 v{{[0-9]+}}
; GCN: {{flat|global}}_store_dword v[{{[0-9:]+}}]
define amdgpu_kernel void @test_fold_canonicalize_sNaN_value_f32(float addrspace(1)* %arg) {
%id = tail call i32 @llvm.amdgcn.workitem.id.x()
%gep = getelementptr inbounds float, float addrspace(1)* %arg, i32 %id