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
diff --git a/llvm/test/CodeGen/AMDGPU/fabs.ll b/llvm/test/CodeGen/AMDGPU/fabs.ll
index 98e7f9e..ac8fa3e 100644
--- a/llvm/test/CodeGen/AMDGPU/fabs.ll
+++ b/llvm/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 @@
; 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 @@
; 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 @@
; 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 @@
; 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 @@
; 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 @@
; 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