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/ds_write2st64.ll b/llvm/test/CodeGen/AMDGPU/ds_write2st64.ll
index 872e773..a395af3 100644
--- a/llvm/test/CodeGen/AMDGPU/ds_write2st64.ll
+++ b/llvm/test/CodeGen/AMDGPU/ds_write2st64.ll
@@ -7,7 +7,7 @@
 ; SI-DAG: v_lshlrev_b32_e32 [[VPTR:v[0-9]+]], 2, v{{[0-9]+}}
 ; SI: ds_write2st64_b32 [[VPTR]], [[VAL]], [[VAL]] offset1:1
 ; SI: s_endpgm
-define void @simple_write2st64_one_val_f32_0_1(float addrspace(1)* %C, float addrspace(1)* %in) #0 {
+define amdgpu_kernel void @simple_write2st64_one_val_f32_0_1(float addrspace(1)* %C, float addrspace(1)* %in) #0 {
   %x.i = tail call i32 @llvm.amdgcn.workitem.id.x() #1
   %in.gep = getelementptr float, float addrspace(1)* %in, i32 %x.i
   %val = load float, float addrspace(1)* %in.gep, align 4
@@ -25,7 +25,7 @@
 ; SI-DAG: v_lshlrev_b32_e32 [[VPTR:v[0-9]+]], 2, v{{[0-9]+}}
 ; SI: ds_write2st64_b32 [[VPTR]], [[VAL0]], [[VAL1]] offset0:2 offset1:5
 ; SI: s_endpgm
-define void @simple_write2st64_two_val_f32_2_5(float addrspace(1)* %C, float addrspace(1)* %in) #0 {
+define amdgpu_kernel void @simple_write2st64_two_val_f32_2_5(float addrspace(1)* %C, float addrspace(1)* %in) #0 {
   %x.i = tail call i32 @llvm.amdgcn.workitem.id.x() #1
   %in.gep.0 = getelementptr float, float addrspace(1)* %in, i32 %x.i
   %in.gep.1 = getelementptr float, float addrspace(1)* %in.gep.0, i32 1
@@ -46,7 +46,7 @@
 ; SI-DAG: v_lshlrev_b32_e32 [[VPTR:v[0-9]+]], 2, v{{[0-9]+}}
 ; SI: ds_write2st64_b32 [[VPTR]], [[VAL0]], [[VAL1]] offset1:255
 ; SI: s_endpgm
-define void @simple_write2st64_two_val_max_offset_f32(float addrspace(1)* %C, float addrspace(1)* %in, float addrspace(3)* %lds) #0 {
+define amdgpu_kernel void @simple_write2st64_two_val_max_offset_f32(float addrspace(1)* %C, float addrspace(1)* %in, float addrspace(3)* %lds) #0 {
   %x.i = tail call i32 @llvm.amdgcn.workitem.id.x() #1
   %in.gep.0 = getelementptr float, float addrspace(1)* %in, i32 %x.i
   %in.gep.1 = getelementptr float, float addrspace(1)* %in.gep.0, i32 1
@@ -66,7 +66,7 @@
 ; SI-DAG: v_add_i32_e32 [[VPTR:v[0-9]+]],
 ; SI: ds_write2st64_b64 [[VPTR]], [[VAL0]], [[VAL1]] offset0:4 offset1:127
 ; SI: s_endpgm
-define void @simple_write2st64_two_val_max_offset_f64(double addrspace(1)* %C, double addrspace(1)* %in, double addrspace(3)* %lds) #0 {
+define amdgpu_kernel void @simple_write2st64_two_val_max_offset_f64(double addrspace(1)* %C, double addrspace(1)* %in, double addrspace(3)* %lds) #0 {
   %x.i = tail call i32 @llvm.amdgcn.workitem.id.x() #1
   %in.gep.0 = getelementptr double, double addrspace(1)* %in, i32 %x.i
   %in.gep.1 = getelementptr double, double addrspace(1)* %in.gep.0, i32 1
@@ -85,7 +85,7 @@
 ; SI-NOT: ds_write2st64_b64
 ; SI: ds_write2_b64 {{v[0-9]+}}, {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}} offset1:8
 ; SI: s_endpgm
-define void @byte_size_only_divisible_64_write2st64_f64(double addrspace(1)* %C, double addrspace(1)* %in, double addrspace(3)* %lds) #0 {
+define amdgpu_kernel void @byte_size_only_divisible_64_write2st64_f64(double addrspace(1)* %C, double addrspace(1)* %in, double addrspace(3)* %lds) #0 {
   %x.i = tail call i32 @llvm.amdgcn.workitem.id.x() #1
   %in.gep = getelementptr double, double addrspace(1)* %in, i32 %x.i
   %val = load double, double addrspace(1)* %in.gep, align 8