diff options
Diffstat (limited to 'llvm/test/CodeGen/AMDGPU/schedule-barrier.mir')
| -rw-r--r-- | llvm/test/CodeGen/AMDGPU/schedule-barrier.mir | 46 |
1 files changed, 46 insertions, 0 deletions
diff --git a/llvm/test/CodeGen/AMDGPU/schedule-barrier.mir b/llvm/test/CodeGen/AMDGPU/schedule-barrier.mir new file mode 100644 index 00000000000..a72a406ff09 --- /dev/null +++ b/llvm/test/CodeGen/AMDGPU/schedule-barrier.mir @@ -0,0 +1,46 @@ +# 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, 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, 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 +... |
