1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-22 18:54:02 +01:00
llvm-mirror/test/CodeGen/AMDGPU/dag-divergence.ll
Matt Arsenault 96fe4a902d AMDGPU: Fix DAG divergence not reporting flat loads
Match behavior in DAG of r340343

llvm-svn: 341393
2018-09-04 18:58:19 +00:00

31 lines
1.1 KiB
LLVM

; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=fiji -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
; GCN-LABEL: {{^}}private_load_maybe_divergent:
; GCN: buffer_load_dword
; GCN-NOT: s_load_dword s
; GCN: flat_load_dword
; GCN-NOT: s_load_dword s
define amdgpu_kernel void @private_load_maybe_divergent(i32 addrspace(4)* %k, i32* %flat) {
%load = load volatile i32, i32 addrspace(5)* undef, align 4
%gep = getelementptr inbounds i32, i32 addrspace(4)* %k, i32 %load
%maybe.not.uniform.load = load i32, i32 addrspace(4)* %gep, align 4
store i32 %maybe.not.uniform.load, i32 addrspace(1)* undef
ret void
}
; GCN-LABEL: {{^}}flat_load_maybe_divergent:
; GCN: s_load_dwordx4
; GCN-NOT: s_load
; GCN: flat_load_dword
; GCN-NOT: s_load
; GCN: flat_load_dword
; GCN-NOT: s_load
; GCN: flat_store_dword
define amdgpu_kernel void @flat_load_maybe_divergent(i32 addrspace(4)* %k, i32* %flat) {
%load = load i32, i32* %flat, align 4
%gep = getelementptr inbounds i32, i32 addrspace(4)* %k, i32 %load
%maybe.not.uniform.load = load i32, i32 addrspace(4)* %gep, align 4
store i32 %maybe.not.uniform.load, i32 addrspace(1)* undef
ret void
}