summaryrefslogtreecommitdiffstats
path: root/llvm/test/CodeGen/AMDGPU/bfe-patterns.ll
diff options
context:
space:
mode:
authorMatt Arsenault <Matthew.Arsenault@amd.com>2017-03-21 21:39:51 +0000
committerMatt Arsenault <Matthew.Arsenault@amd.com>2017-03-21 21:39:51 +0000
commit3dbeefa978fb7e7b231b249f9cd90c67b9e83277 (patch)
treed74bf7fe30e44588d573919f3625edacb2586112 /llvm/test/CodeGen/AMDGPU/bfe-patterns.ll
parentf6021ecddc73d14c94ad70938250d58f330795be (diff)
downloadbcm5719-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/bfe-patterns.ll')
-rw-r--r--llvm/test/CodeGen/AMDGPU/bfe-patterns.ll16
1 files changed, 8 insertions, 8 deletions
diff --git a/llvm/test/CodeGen/AMDGPU/bfe-patterns.ll b/llvm/test/CodeGen/AMDGPU/bfe-patterns.ll
index e48744f40fb..5e39a6c6774 100644
--- a/llvm/test/CodeGen/AMDGPU/bfe-patterns.ll
+++ b/llvm/test/CodeGen/AMDGPU/bfe-patterns.ll
@@ -5,7 +5,7 @@
; GCN: {{buffer|flat}}_load_dword [[SRC:v[0-9]+]]
; GCN: {{buffer|flat}}_load_dword [[WIDTH:v[0-9]+]]
; GCN: v_bfe_u32 v{{[0-9]+}}, [[SRC]], 0, [[WIDTH]]
-define void @v_ubfe_sub_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %in0, i32 addrspace(1)* %in1) #1 {
+define amdgpu_kernel void @v_ubfe_sub_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %in0, i32 addrspace(1)* %in1) #1 {
%id.x = tail call i32 @llvm.amdgcn.workitem.id.x()
%in0.gep = getelementptr i32, i32 addrspace(1)* %in0, i32 %id.x
%in1.gep = getelementptr i32, i32 addrspace(1)* %in1, i32 %id.x
@@ -32,7 +32,7 @@ define void @v_ubfe_sub_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %in0, i32
; GCN: [[BFE]]
; GCN: [[SHL]]
-define void @v_ubfe_sub_multi_use_shl_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %in0, i32 addrspace(1)* %in1) #1 {
+define amdgpu_kernel void @v_ubfe_sub_multi_use_shl_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %in0, i32 addrspace(1)* %in1) #1 {
%id.x = tail call i32 @llvm.amdgcn.workitem.id.x()
%in0.gep = getelementptr i32, i32 addrspace(1)* %in0, i32 %id.x
%in1.gep = getelementptr i32, i32 addrspace(1)* %in1, i32 %id.x
@@ -52,7 +52,7 @@ define void @v_ubfe_sub_multi_use_shl_i32(i32 addrspace(1)* %out, i32 addrspace(
; GCN: s_load_dword [[WIDTH:s[0-9]+]]
; GCN: v_mov_b32_e32 [[VWIDTH:v[0-9]+]]
; GCN: v_bfe_u32 v{{[0-9]+}}, [[SRC]], 0, [[VWIDTH]]
-define void @s_ubfe_sub_i32(i32 addrspace(1)* %out, i32 %src, i32 %width) #1 {
+define amdgpu_kernel void @s_ubfe_sub_i32(i32 addrspace(1)* %out, i32 %src, i32 %width) #1 {
%id.x = tail call i32 @llvm.amdgcn.workitem.id.x()
%out.gep = getelementptr i32, i32 addrspace(1)* %out, i32 %id.x
%sub = sub i32 32, %width
@@ -68,7 +68,7 @@ define void @s_ubfe_sub_i32(i32 addrspace(1)* %out, i32 %src, i32 %width) #1 {
; GCN: s_sub_i32 [[SUB:s[0-9]+]], 32, [[WIDTH]]
; GCN-NEXT: s_lshl_b32 [[SHL:s[0-9]+]], [[SRC]], [[SUB]]
; GCN-NEXT: s_lshr_b32 s{{[0-9]+}}, [[SHL]], [[SUB]]
-define void @s_ubfe_sub_multi_use_shl_i32(i32 addrspace(1)* %out, i32 %src, i32 %width) #1 {
+define amdgpu_kernel void @s_ubfe_sub_multi_use_shl_i32(i32 addrspace(1)* %out, i32 %src, i32 %width) #1 {
%id.x = tail call i32 @llvm.amdgcn.workitem.id.x()
%out.gep = getelementptr i32, i32 addrspace(1)* %out, i32 %id.x
%sub = sub i32 32, %width
@@ -83,7 +83,7 @@ define void @s_ubfe_sub_multi_use_shl_i32(i32 addrspace(1)* %out, i32 %src, i32
; GCN: {{buffer|flat}}_load_dword [[SRC:v[0-9]+]]
; GCN: {{buffer|flat}}_load_dword [[WIDTH:v[0-9]+]]
; GCN: v_bfe_i32 v{{[0-9]+}}, [[SRC]], 0, [[WIDTH]]
-define void @v_sbfe_sub_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %in0, i32 addrspace(1)* %in1) #1 {
+define amdgpu_kernel void @v_sbfe_sub_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %in0, i32 addrspace(1)* %in1) #1 {
%id.x = tail call i32 @llvm.amdgcn.workitem.id.x()
%in0.gep = getelementptr i32, i32 addrspace(1)* %in0, i32 %id.x
%in1.gep = getelementptr i32, i32 addrspace(1)* %in1, i32 %id.x
@@ -110,7 +110,7 @@ define void @v_sbfe_sub_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %in0, i32
; GCN: [[BFE]]
; GCN: [[SHL]]
-define void @v_sbfe_sub_multi_use_shl_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %in0, i32 addrspace(1)* %in1) #1 {
+define amdgpu_kernel void @v_sbfe_sub_multi_use_shl_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %in0, i32 addrspace(1)* %in1) #1 {
%id.x = tail call i32 @llvm.amdgcn.workitem.id.x()
%in0.gep = getelementptr i32, i32 addrspace(1)* %in0, i32 %id.x
%in1.gep = getelementptr i32, i32 addrspace(1)* %in1, i32 %id.x
@@ -130,7 +130,7 @@ define void @v_sbfe_sub_multi_use_shl_i32(i32 addrspace(1)* %out, i32 addrspace(
; GCN: s_load_dword [[WIDTH:s[0-9]+]]
; GCN: v_mov_b32_e32 [[VWIDTH:v[0-9]+]]
; GCN: v_bfe_i32 v{{[0-9]+}}, [[SRC]], 0, [[VWIDTH]]
-define void @s_sbfe_sub_i32(i32 addrspace(1)* %out, i32 %src, i32 %width) #1 {
+define amdgpu_kernel void @s_sbfe_sub_i32(i32 addrspace(1)* %out, i32 %src, i32 %width) #1 {
%id.x = tail call i32 @llvm.amdgcn.workitem.id.x()
%out.gep = getelementptr i32, i32 addrspace(1)* %out, i32 %id.x
%sub = sub i32 32, %width
@@ -146,7 +146,7 @@ define void @s_sbfe_sub_i32(i32 addrspace(1)* %out, i32 %src, i32 %width) #1 {
; GCN: s_sub_i32 [[SUB:s[0-9]+]], 32, [[WIDTH]]
; GCN-NEXT: s_lshl_b32 [[SHL:s[0-9]+]], [[SRC]], [[SUB]]
; GCN-NEXT: s_ashr_i32 s{{[0-9]+}}, [[SHL]], [[SUB]]
-define void @s_sbfe_sub_multi_use_shl_i32(i32 addrspace(1)* %out, i32 %src, i32 %width) #1 {
+define amdgpu_kernel void @s_sbfe_sub_multi_use_shl_i32(i32 addrspace(1)* %out, i32 %src, i32 %width) #1 {
%id.x = tail call i32 @llvm.amdgcn.workitem.id.x()
%out.gep = getelementptr i32, i32 addrspace(1)* %out, i32 %id.x
%sub = sub i32 32, %width
OpenPOWER on IntegriCloud