mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-20 19:42:54 +02:00
54fe21d18f
This allows handling of a lot more of the interesting cases in Blender. Most of the large functions unlikely to be inlined have this pattern. This is a special case for what clang emits for OpenCL 3 element vectors. Annoyingly, these are emitted as <3 x elt>* pointers, but accessed as <4 x elt>* operations. This also needs to handle cases where a struct containing a single vector is used. llvm-svn: 309419
38 lines
2.0 KiB
LLVM
38 lines
2.0 KiB
LLVM
; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -amdgpu-any-address-space-out-arguments -amdgpu-rewrite-out-arguments < %s | FileCheck %s
|
|
|
|
; CHECK: %void_one_out_non_private_arg_i32_1_use = type { i32 }
|
|
; CHECK: %bitcast_pointer_as1 = type { <3 x i32> }
|
|
|
|
; CHECK-LABEL: define private %void_one_out_non_private_arg_i32_1_use @void_one_out_non_private_arg_i32_1_use.body(i32 addrspace(1)* %val) #0 {
|
|
; CHECK-NEXT: ret %void_one_out_non_private_arg_i32_1_use zeroinitializer
|
|
|
|
; CHECK-LABEL: define void @void_one_out_non_private_arg_i32_1_use(i32 addrspace(1)*) #1 {
|
|
; CHECK-NEXT: %2 = call %void_one_out_non_private_arg_i32_1_use @void_one_out_non_private_arg_i32_1_use.body(i32 addrspace(1)* undef)
|
|
; CHECK-NEXT: %3 = extractvalue %void_one_out_non_private_arg_i32_1_use %2, 0
|
|
; CHECK-NEXT: store i32 %3, i32 addrspace(1)* %0, align 4
|
|
; CHECK-NEXT: ret void
|
|
define void @void_one_out_non_private_arg_i32_1_use(i32 addrspace(1)* %val) #0 {
|
|
store i32 0, i32 addrspace(1)* %val
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: define private %bitcast_pointer_as1 @bitcast_pointer_as1.body(<3 x i32> addrspace(1)* %out) #0 {
|
|
; CHECK-NEXT: %load = load volatile <4 x i32>, <4 x i32> addrspace(1)* undef
|
|
; CHECK-NEXT: %bitcast = bitcast <3 x i32> addrspace(1)* %out to <4 x i32> addrspace(1)*
|
|
; CHECK-NEXT: %1 = shufflevector <4 x i32> %load, <4 x i32> undef, <3 x i32> <i32 0, i32 1, i32 2>
|
|
; CHECK-NEXT: %2 = insertvalue %bitcast_pointer_as1 undef, <3 x i32> %1, 0
|
|
; CHECK-NEXT: ret %bitcast_pointer_as1 %2
|
|
|
|
; CHECK-LABEL: define void @bitcast_pointer_as1(<3 x i32> addrspace(1)*) #1 {
|
|
; CHECK-NEXT: %2 = call %bitcast_pointer_as1 @bitcast_pointer_as1.body(<3 x i32> addrspace(1)* undef)
|
|
define void @bitcast_pointer_as1(<3 x i32> addrspace(1)* %out) #0 {
|
|
%load = load volatile <4 x i32>, <4 x i32> addrspace(1)* undef
|
|
%bitcast = bitcast <3 x i32> addrspace(1)* %out to <4 x i32> addrspace(1)*
|
|
store <4 x i32> %load, <4 x i32> addrspace(1)* %bitcast
|
|
ret void
|
|
}
|
|
|
|
; CHECK: attributes #0 = { nounwind }
|
|
; CHECK: attributes #1 = { alwaysinline nounwind }
|
|
attributes #0 = { nounwind }
|