forked from OSchip/llvm-project
30 lines
1.5 KiB
LLVM
30 lines
1.5 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -march=amdgcn -mcpu=gfx900 < %s | FileCheck %s -check-prefix=GFX9
|
|
; RUN: llc -global-isel -march=amdgcn -mcpu=gfx900 < %s | FileCheck %s -check-prefix=GFX9
|
|
|
|
; Marking the image loads as invariant should allow both loads to be hoisted
|
|
; above both stores.
|
|
define amdgpu_ps void @test(<8 x i32> inreg %load, <8 x i32> inreg %store) {
|
|
; GFX9-LABEL: test:
|
|
; GFX9: ; %bb.0:
|
|
; GFX9-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX9-NEXT: v_mov_b32_e32 v1, 1
|
|
; GFX9-NEXT: image_load v2, v0, s[0:7] dmask:0x1 unorm
|
|
; GFX9-NEXT: image_load v3, v1, s[0:7] dmask:0x1 unorm
|
|
; GFX9-NEXT: s_waitcnt vmcnt(1)
|
|
; GFX9-NEXT: image_store v2, v0, s[8:15] dmask:0x1 unorm
|
|
; GFX9-NEXT: s_waitcnt vmcnt(1)
|
|
; GFX9-NEXT: image_store v3, v1, s[8:15] dmask:0x1 unorm
|
|
; GFX9-NEXT: s_endpgm
|
|
%data0 = call float @llvm.amdgcn.image.load.1d.f32.i32(i32 1, i32 0, <8 x i32> %load, i32 0, i32 0), !invariant.load !0
|
|
call void @llvm.amdgcn.image.store.1d.f32.i32(float %data0, i32 1, i32 0, <8 x i32> %store, i32 0, i32 0)
|
|
%data1 = call float @llvm.amdgcn.image.load.1d.f32.i32(i32 1, i32 1, <8 x i32> %load, i32 0, i32 0), !invariant.load !0
|
|
call void @llvm.amdgcn.image.store.1d.f32.i32(float %data1, i32 1, i32 1, <8 x i32> %store, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
declare float @llvm.amdgcn.image.load.1d.f32.i32(i32 immarg, i32, <8 x i32>, i32 immarg, i32 immarg)
|
|
declare void @llvm.amdgcn.image.store.1d.f32.i32(float, i32 immarg, i32, <8 x i32>, i32 immarg, i32 immarg)
|
|
|
|
!0 = !{}
|