diff options
Diffstat (limited to 'test/CodeGen/AMDGPU/fabs.ll')
| -rw-r--r-- | test/CodeGen/AMDGPU/fabs.ll | 14 |
1 files changed, 7 insertions, 7 deletions
diff --git a/test/CodeGen/AMDGPU/fabs.ll b/test/CodeGen/AMDGPU/fabs.ll index 98e7f9e3e9ad..ac8fa3e45ef5 100644 --- a/test/CodeGen/AMDGPU/fabs.ll +++ b/test/CodeGen/AMDGPU/fabs.ll @@ -13,7 +13,7 @@ ; GCN: v_and_b32 -define void @fabs_fn_free(float addrspace(1)* %out, i32 %in) { +define amdgpu_kernel void @fabs_fn_free(float addrspace(1)* %out, i32 %in) { %bc= bitcast i32 %in to float %fabs = call float @fabs(float %bc) store float %fabs, float addrspace(1)* %out @@ -26,7 +26,7 @@ define void @fabs_fn_free(float addrspace(1)* %out, i32 %in) { ; GCN: v_and_b32 -define void @fabs_free(float addrspace(1)* %out, i32 %in) { +define amdgpu_kernel void @fabs_free(float addrspace(1)* %out, i32 %in) { %bc= bitcast i32 %in to float %fabs = call float @llvm.fabs.f32(float %bc) store float %fabs, float addrspace(1)* %out @@ -37,7 +37,7 @@ define void @fabs_free(float addrspace(1)* %out, i32 %in) { ; R600: |{{(PV|T[0-9])\.[XYZW]}}| ; GCN: v_and_b32 -define void @fabs_f32(float addrspace(1)* %out, float %in) { +define amdgpu_kernel void @fabs_f32(float addrspace(1)* %out, float %in) { %fabs = call float @llvm.fabs.f32(float %in) store float %fabs, float addrspace(1)* %out ret void @@ -49,7 +49,7 @@ define void @fabs_f32(float addrspace(1)* %out, float %in) { ; GCN: v_and_b32 ; GCN: v_and_b32 -define void @fabs_v2f32(<2 x float> addrspace(1)* %out, <2 x float> %in) { +define amdgpu_kernel void @fabs_v2f32(<2 x float> addrspace(1)* %out, <2 x float> %in) { %fabs = call <2 x float> @llvm.fabs.v2f32(<2 x float> %in) store <2 x float> %fabs, <2 x float> addrspace(1)* %out ret void @@ -65,7 +65,7 @@ define void @fabs_v2f32(<2 x float> addrspace(1)* %out, <2 x float> %in) { ; GCN: v_and_b32 ; GCN: v_and_b32 ; GCN: v_and_b32 -define void @fabs_v4f32(<4 x float> addrspace(1)* %out, <4 x float> %in) { +define amdgpu_kernel void @fabs_v4f32(<4 x float> addrspace(1)* %out, <4 x float> %in) { %fabs = call <4 x float> @llvm.fabs.v4f32(<4 x float> %in) store <4 x float> %fabs, <4 x float> addrspace(1)* %out ret void @@ -76,7 +76,7 @@ define void @fabs_v4f32(<4 x float> addrspace(1)* %out, <4 x float> %in) { ; VI: s_load_dword [[ABS_VALUE:s[0-9]+]], s[{{[0-9]+:[0-9]+}}], 0x2c ; GCN-NOT: and ; GCN: v_mul_f32_e64 v{{[0-9]+}}, v{{[0-9]+}}, |[[ABS_VALUE]]| -define void @fabs_fn_fold(float addrspace(1)* %out, float %in0, float %in1) { +define amdgpu_kernel void @fabs_fn_fold(float addrspace(1)* %out, float %in0, float %in1) { %fabs = call float @fabs(float %in0) %fmul = fmul float %fabs, %in1 store float %fmul, float addrspace(1)* %out @@ -88,7 +88,7 @@ define void @fabs_fn_fold(float addrspace(1)* %out, float %in0, float %in1) { ; VI: s_load_dword [[ABS_VALUE:s[0-9]+]], s[{{[0-9]+:[0-9]+}}], 0x2c ; GCN-NOT: and ; GCN: v_mul_f32_e64 v{{[0-9]+}}, v{{[0-9]+}}, |[[ABS_VALUE]]| -define void @fabs_fold(float addrspace(1)* %out, float %in0, float %in1) { +define amdgpu_kernel void @fabs_fold(float addrspace(1)* %out, float %in0, float %in1) { %fabs = call float @llvm.fabs.f32(float %in0) %fmul = fmul float %fabs, %in1 store float %fmul, float addrspace(1)* %out |