diff options
| author | Matt Arsenault <Matthew.Arsenault@amd.com> | 2017-03-21 21:39:51 +0000 |
|---|---|---|
| committer | Matt Arsenault <Matthew.Arsenault@amd.com> | 2017-03-21 21:39:51 +0000 |
| commit | 3dbeefa978fb7e7b231b249f9cd90c67b9e83277 (patch) | |
| tree | d74bf7fe30e44588d573919f3625edacb2586112 /llvm/test/CodeGen/AMDGPU/frem.ll | |
| parent | f6021ecddc73d14c94ad70938250d58f330795be (diff) | |
| download | bcm5719-llvm-3dbeefa978fb7e7b231b249f9cd90c67b9e83277.tar.gz bcm5719-llvm-3dbeefa978fb7e7b231b249f9cd90c67b9e83277.zip | |
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel
Currently the default C calling convention functions are treated
the same as compute kernels. Make this explicit so the default
calling convention can be changed to a non-kernel.
Converted with perl -pi -e 's/define void/define amdgpu_kernel void/'
on the relevant test directories (and undoing in one place that actually
wanted a non-kernel).
llvm-svn: 298444
Diffstat (limited to 'llvm/test/CodeGen/AMDGPU/frem.ll')
| -rw-r--r-- | llvm/test/CodeGen/AMDGPU/frem.ll | 14 |
1 files changed, 7 insertions, 7 deletions
diff --git a/llvm/test/CodeGen/AMDGPU/frem.ll b/llvm/test/CodeGen/AMDGPU/frem.ll index 58b8308bc78..9778069d047 100644 --- a/llvm/test/CodeGen/AMDGPU/frem.ll +++ b/llvm/test/CodeGen/AMDGPU/frem.ll @@ -15,7 +15,7 @@ ; GCN: v_trunc_f32_e32 v{{[0-9]+}}, v{{[0-9]+}} ; GCN: v_mad_f32 v{{[0-9]+}}, -v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}} ; GCN: s_endpgm -define void @frem_f32(float addrspace(1)* %out, float addrspace(1)* %in1, +define amdgpu_kernel void @frem_f32(float addrspace(1)* %out, float addrspace(1)* %in1, float addrspace(1)* %in2) #0 { %gep2 = getelementptr float, float addrspace(1)* %in2, i32 4 %r0 = load float, float addrspace(1)* %in1, align 4 @@ -33,7 +33,7 @@ define void @frem_f32(float addrspace(1)* %out, float addrspace(1)* %in1, ; GCN: v_trunc_f32_e32 [[TRUNC:v[0-9]+]], [[DIV]] ; GCN: v_mad_f32 [[RESULT:v[0-9]+]], -[[TRUNC]], [[Y]], [[X]] ; GCN: buffer_store_dword [[RESULT]] -define void @unsafe_frem_f32(float addrspace(1)* %out, float addrspace(1)* %in1, +define amdgpu_kernel void @unsafe_frem_f32(float addrspace(1)* %out, float addrspace(1)* %in1, float addrspace(1)* %in2) #1 { %gep2 = getelementptr float, float addrspace(1)* %in2, i32 4 %r0 = load float, float addrspace(1)* %in1, align 4 @@ -54,7 +54,7 @@ define void @unsafe_frem_f32(float addrspace(1)* %out, float addrspace(1)* %in1, ; GCN: v_add_f64 ; GCN: buffer_store_dwordx2 ; GCN: s_endpgm -define void @frem_f64(double addrspace(1)* %out, double addrspace(1)* %in1, +define amdgpu_kernel void @frem_f64(double addrspace(1)* %out, double addrspace(1)* %in1, double addrspace(1)* %in2) #0 { %r0 = load double, double addrspace(1)* %in1, align 8 %r1 = load double, double addrspace(1)* %in2, align 8 @@ -70,7 +70,7 @@ define void @frem_f64(double addrspace(1)* %out, double addrspace(1)* %in1, ; CI: v_trunc_f64_e32 ; GCN: v_fma_f64 ; GCN: s_endpgm -define void @unsafe_frem_f64(double addrspace(1)* %out, double addrspace(1)* %in1, +define amdgpu_kernel void @unsafe_frem_f64(double addrspace(1)* %out, double addrspace(1)* %in1, double addrspace(1)* %in2) #1 { %r0 = load double, double addrspace(1)* %in1, align 8 %r1 = load double, double addrspace(1)* %in2, align 8 @@ -79,7 +79,7 @@ define void @unsafe_frem_f64(double addrspace(1)* %out, double addrspace(1)* %in ret void } -define void @frem_v2f32(<2 x float> addrspace(1)* %out, <2 x float> addrspace(1)* %in1, +define amdgpu_kernel void @frem_v2f32(<2 x float> addrspace(1)* %out, <2 x float> addrspace(1)* %in1, <2 x float> addrspace(1)* %in2) #0 { %gep2 = getelementptr <2 x float>, <2 x float> addrspace(1)* %in2, i32 4 %r0 = load <2 x float>, <2 x float> addrspace(1)* %in1, align 8 @@ -89,7 +89,7 @@ define void @frem_v2f32(<2 x float> addrspace(1)* %out, <2 x float> addrspace(1) ret void } -define void @frem_v4f32(<4 x float> addrspace(1)* %out, <4 x float> addrspace(1)* %in1, +define amdgpu_kernel void @frem_v4f32(<4 x float> addrspace(1)* %out, <4 x float> addrspace(1)* %in1, <4 x float> addrspace(1)* %in2) #0 { %gep2 = getelementptr <4 x float>, <4 x float> addrspace(1)* %in2, i32 4 %r0 = load <4 x float>, <4 x float> addrspace(1)* %in1, align 16 @@ -99,7 +99,7 @@ define void @frem_v4f32(<4 x float> addrspace(1)* %out, <4 x float> addrspace(1) ret void } -define void @frem_v2f64(<2 x double> addrspace(1)* %out, <2 x double> addrspace(1)* %in1, +define amdgpu_kernel void @frem_v2f64(<2 x double> addrspace(1)* %out, <2 x double> addrspace(1)* %in1, <2 x double> addrspace(1)* %in2) #0 { %gep2 = getelementptr <2 x double>, <2 x double> addrspace(1)* %in2, i32 4 %r0 = load <2 x double>, <2 x double> addrspace(1)* %in1, align 16 |

