forked from OSchip/llvm-project
47 lines
1.9 KiB
YAML
47 lines
1.9 KiB
YAML
# RUN: llc -march=amdgcn -mcpu=gfx900 -run-pass=machine-scheduler -o - %s | FileCheck %s
|
|
|
|
---
|
|
# Check that the high latency loads are both scheduled first, before the
|
|
# multiplies, despite the presence of a barrier in the function.
|
|
# CHECK: BUFFER_LOAD_DWORD_OFFSET
|
|
# CHECK: BUFFER_LOAD_DWORD_OFFSET
|
|
# CHECK: V_MUL_LO_U32
|
|
# CHECK: V_MUL_LO_U32
|
|
name: test
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5, $vgpr6, $vgpr7, $vgpr8, $vgpr9
|
|
|
|
undef %43.sub3:vreg_128 = COPY $vgpr9
|
|
undef %42.sub2:vreg_128 = COPY $vgpr8
|
|
undef %41.sub1:vreg_128 = COPY $vgpr7
|
|
undef %26.sub0:vreg_128 = COPY $vgpr6
|
|
undef %46.sub3:vreg_128 = COPY $vgpr5
|
|
undef %45.sub2:vreg_128 = COPY $vgpr4
|
|
undef %44.sub1:vreg_128 = COPY $vgpr3
|
|
undef %32.sub0:vreg_128 = COPY $vgpr2
|
|
undef %38.sub1:vreg_64 = COPY $vgpr1
|
|
%38.sub0:vreg_64 = COPY $vgpr0
|
|
|
|
S_BARRIER
|
|
|
|
undef %33.sub0:sgpr_128 = V_READFIRSTLANE_B32 %32.sub0, implicit $exec
|
|
%33.sub1:sgpr_128 = V_READFIRSTLANE_B32 %44.sub1, implicit $exec
|
|
%33.sub2:sgpr_128 = V_READFIRSTLANE_B32 %45.sub2, implicit $exec
|
|
%33.sub3:sgpr_128 = V_READFIRSTLANE_B32 %46.sub3, implicit $exec
|
|
%15:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %33, 0, 0, 0, 0, 0, 0, 0, implicit $exec
|
|
%39:vgpr_32 = V_MUL_LO_U32 %15, %15, implicit $exec
|
|
|
|
undef %27.sub0:sgpr_128 = V_READFIRSTLANE_B32 %26.sub0, implicit $exec
|
|
%27.sub1:sgpr_128 = V_READFIRSTLANE_B32 %41.sub1, implicit $exec
|
|
%27.sub2:sgpr_128 = V_READFIRSTLANE_B32 %42.sub2, implicit $exec
|
|
%27.sub3:sgpr_128 = V_READFIRSTLANE_B32 %43.sub3, implicit $exec
|
|
%19:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %27, 0, 0, 0, 0, 0, 0, 0, implicit $exec
|
|
%40:vgpr_32 = V_MUL_LO_U32 %19, %19, implicit $exec
|
|
|
|
%23:vgpr_32 = V_ADD_U32_e32 %39, %40, implicit $exec
|
|
GLOBAL_STORE_DWORD %38, %23, 0, 0, 0, 0, implicit $exec
|
|
S_ENDPGM 0
|
|
...
|