llvm-project/llvm/test/CodeGen/AMDGPU/fold-fi-mubuf.mir

294 lines
11 KiB
YAML

# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -mtriple=amdgcn-amd-amdhsa -verify-machineinstrs -run-pass si-fold-operands,dead-mi-elimination %s -o - | FileCheck -check-prefix=GCN %s
# Kernels can have no FP
---
name: kernel_no_fold_fi_non_stack_rsrc_and_soffset
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 4
stack:
- { id: 0, size: 4, alignment: 4, local-offset: 0 }
machineFunctionInfo:
isEntryFunction: true
scratchRSrcReg: '$sgpr96_sgpr97_sgpr98_sgpr99'
stackPtrOffsetReg: '$sgpr32'
body: |
bb.0:
liveins: $sgpr12_sgpr13_sgpr14_sgpr15
; GCN-LABEL: name: kernel_no_fold_fi_non_stack_rsrc_and_soffset
; GCN: liveins: $sgpr12_sgpr13_sgpr14_sgpr15
; GCN: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr12_sgpr13_sgpr14_sgpr15
; GCN: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 %stack.0, implicit $exec
; GCN: [[BUFFER_LOAD_DWORD_IDXEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_IDXEN [[V_MOV_B32_e32_]], [[COPY]], 0, 0, 0, 0, 0, implicit $exec
; GCN: $vgpr0 = COPY [[BUFFER_LOAD_DWORD_IDXEN]]
; GCN: SI_RETURN_TO_EPILOG $vgpr0
%0:sgpr_128 = COPY $sgpr12_sgpr13_sgpr14_sgpr15
%1:sreg_32_xm0 = S_MOV_B32 0
%2:vgpr_32 = V_MOV_B32_e32 %stack.0, implicit $exec
%3:vgpr_32 = BUFFER_LOAD_DWORD_IDXEN %2, %0, %1, 0, 0, 0, 0, implicit $exec
$vgpr0 = COPY %3
SI_RETURN_TO_EPILOG $vgpr0
...
---
name: kernel_no_fold_fi_non_stack_rsrc
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 4
stack:
- { id: 0, size: 4, alignment: 4, local-offset: 0 }
machineFunctionInfo:
isEntryFunction: true
scratchRSrcReg: '$sgpr96_sgpr97_sgpr98_sgpr99'
stackPtrOffsetReg: '$sgpr32'
body: |
bb.0:
liveins: $sgpr12_sgpr13_sgpr14_sgpr15
; GCN-LABEL: name: kernel_no_fold_fi_non_stack_rsrc
; GCN: liveins: $sgpr12_sgpr13_sgpr14_sgpr15
; GCN: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr12_sgpr13_sgpr14_sgpr15
; GCN: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 %stack.0, implicit $exec
; GCN: [[BUFFER_LOAD_DWORD_IDXEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_IDXEN [[V_MOV_B32_e32_]], [[COPY]], 0, 0, 0, 0, 0, implicit $exec
; GCN: $vgpr0 = COPY [[BUFFER_LOAD_DWORD_IDXEN]]
; GCN: SI_RETURN_TO_EPILOG $vgpr0
%0:sgpr_128 = COPY $sgpr12_sgpr13_sgpr14_sgpr15
%2:vgpr_32 = V_MOV_B32_e32 %stack.0, implicit $exec
%3:vgpr_32 = BUFFER_LOAD_DWORD_IDXEN %2, %0, 0, 0, 0, 0, 0, implicit $exec
$vgpr0 = COPY %3
SI_RETURN_TO_EPILOG $vgpr0
...
---
name: kernel_no_fold_fi_non_stack_soffset
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 4
stack:
- { id: 0, size: 4, alignment: 4, local-offset: 0 }
machineFunctionInfo:
isEntryFunction: true
scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
stackPtrOffsetReg: '$sgpr32'
body: |
bb.0:
; GCN-LABEL: name: kernel_no_fold_fi_non_stack_soffset
; GCN: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 %stack.0, implicit $exec
; GCN: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 7, implicit $exec
; GCN: BUFFER_STORE_DWORD_OFFEN [[V_MOV_B32_e32_1]], [[V_MOV_B32_e32_]], $sgpr0_sgpr1_sgpr2_sgpr3, 0, 0, 0, 0, 0, implicit $exec
; GCN: [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN [[V_MOV_B32_e32_]], $sgpr0_sgpr1_sgpr2_sgpr3, 0, 0, 0, 0, 0, implicit $exec
; GCN: $vgpr0 = COPY [[BUFFER_LOAD_DWORD_OFFEN]]
; GCN: S_ENDPGM 0, implicit $vgpr0
%0:vgpr_32 = V_MOV_B32_e32 %stack.0, implicit $exec
%1:vgpr_32 = V_MOV_B32_e32 7, implicit $exec
%2:sreg_32_xm0 = S_MOV_B32 0
BUFFER_STORE_DWORD_OFFEN %1:vgpr_32, %0:vgpr_32, $sgpr0_sgpr1_sgpr2_sgpr3, %2, 0, 0, 0, 0, implicit $exec
%3:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN %0:vgpr_32, $sgpr0_sgpr1_sgpr2_sgpr3, %2, 0, 0, 0, 0, implicit $exec
$vgpr0 = COPY %3
S_ENDPGM 0, implicit $vgpr0
...
---
name: kernel_fold_fi_mubuf
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 4
stack:
- { id: 0, size: 4, alignment: 4, local-offset: 0 }
machineFunctionInfo:
isEntryFunction: true
scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
stackPtrOffsetReg: '$sgpr32'
body: |
bb.0:
; GCN-LABEL: name: kernel_fold_fi_mubuf
; GCN: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 7, implicit $exec
; GCN: BUFFER_STORE_DWORD_OFFEN [[V_MOV_B32_e32_]], %stack.0, $sgpr0_sgpr1_sgpr2_sgpr3, 0, 0, 0, 0, 0, implicit $exec
; GCN: [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN %stack.0, $sgpr0_sgpr1_sgpr2_sgpr3, 0, 0, 0, 0, 0, implicit $exec
; GCN: $vgpr0 = COPY [[BUFFER_LOAD_DWORD_OFFEN]]
; GCN: S_ENDPGM 0, implicit $vgpr0
%0:vgpr_32 = V_MOV_B32_e32 %stack.0, implicit $exec
%1:vgpr_32 = V_MOV_B32_e32 7, implicit $exec
BUFFER_STORE_DWORD_OFFEN %1:vgpr_32, %0:vgpr_32, $sgpr0_sgpr1_sgpr2_sgpr3, 0, 0, 0, 0, 0, implicit $exec
%2:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN %0:vgpr_32, $sgpr0_sgpr1_sgpr2_sgpr3, 0, 0, 0, 0, 0, implicit $exec
$vgpr0 = COPY %2
S_ENDPGM 0, implicit $vgpr0
...
# Functions have an unswizzled SP/FP relative to the wave offset
---
name: function_no_fold_fi_non_stack_rsrc_and_soffset
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 4
stack:
- { id: 0, size: 4, alignment: 4, local-offset: 0 }
machineFunctionInfo:
isEntryFunction: false
scratchRSrcReg: '$sgpr96_sgpr97_sgpr98_sgpr99'
frameOffsetReg: '$sgpr32'
stackPtrOffsetReg: '$sgpr32'
body: |
bb.0:
liveins: $sgpr12_sgpr13_sgpr14_sgpr15
; GCN-LABEL: name: function_no_fold_fi_non_stack_rsrc_and_soffset
; GCN: liveins: $sgpr12_sgpr13_sgpr14_sgpr15
; GCN: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr12_sgpr13_sgpr14_sgpr15
; GCN: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 %stack.0, implicit $exec
; GCN: [[BUFFER_LOAD_DWORD_IDXEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_IDXEN [[V_MOV_B32_e32_]], [[COPY]], 0, 0, 0, 0, 0, implicit $exec
; GCN: $vgpr0 = COPY [[BUFFER_LOAD_DWORD_IDXEN]]
; GCN: SI_RETURN_TO_EPILOG $vgpr0
%0:sgpr_128 = COPY $sgpr12_sgpr13_sgpr14_sgpr15
%1:sreg_32_xm0 = S_MOV_B32 0
%2:vgpr_32 = V_MOV_B32_e32 %stack.0, implicit $exec
%3:vgpr_32 = BUFFER_LOAD_DWORD_IDXEN %2, %0, %1, 0, 0, 0, 0, implicit $exec
$vgpr0 = COPY %3
SI_RETURN_TO_EPILOG $vgpr0
...
---
name: function_no_fold_fi_non_stack_rsrc
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 4
stack:
- { id: 0, size: 4, alignment: 4, local-offset: 0 }
machineFunctionInfo:
isEntryFunction: false
scratchRSrcReg: '$sgpr96_sgpr97_sgpr98_sgpr99'
frameOffsetReg: '$sgpr32'
stackPtrOffsetReg: '$sgpr32'
body: |
bb.0:
liveins: $sgpr12_sgpr13_sgpr14_sgpr15
; GCN-LABEL: name: function_no_fold_fi_non_stack_rsrc
; GCN: liveins: $sgpr12_sgpr13_sgpr14_sgpr15
; GCN: [[COPY:%[0-9]+]]:sgpr_128 = COPY $sgpr12_sgpr13_sgpr14_sgpr15
; GCN: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 %stack.0, implicit $exec
; GCN: [[BUFFER_LOAD_DWORD_IDXEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_IDXEN [[V_MOV_B32_e32_]], [[COPY]], 0, 0, 0, 0, 0, implicit $exec
; GCN: $vgpr0 = COPY [[BUFFER_LOAD_DWORD_IDXEN]]
; GCN: SI_RETURN_TO_EPILOG $vgpr0
%0:sgpr_128 = COPY $sgpr12_sgpr13_sgpr14_sgpr15
%2:vgpr_32 = V_MOV_B32_e32 %stack.0, implicit $exec
%3:vgpr_32 = BUFFER_LOAD_DWORD_IDXEN %2, %0, 0, 0, 0, 0, 0, implicit $exec
$vgpr0 = COPY %3
SI_RETURN_TO_EPILOG $vgpr0
...
---
name: function_no_fold_fi_non_stack_soffset
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 4
stack:
- { id: 0, size: 4, alignment: 4, local-offset: 0 }
machineFunctionInfo:
isEntryFunction: false
scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
frameOffsetReg: '$sgpr32'
stackPtrOffsetReg: '$sgpr32'
body: |
bb.0:
; GCN-LABEL: name: function_no_fold_fi_non_stack_soffset
; GCN: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 7, implicit $exec
; GCN: BUFFER_STORE_DWORD_OFFEN [[V_MOV_B32_e32_]], %stack.0, $sgpr0_sgpr1_sgpr2_sgpr3, 0, 0, 0, 0, 0, implicit $exec
; GCN: [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN %stack.0, $sgpr0_sgpr1_sgpr2_sgpr3, 0, 0, 0, 0, 0, implicit $exec
; GCN: $vgpr0 = COPY [[BUFFER_LOAD_DWORD_OFFEN]]
; GCN: S_ENDPGM 0, implicit $vgpr0
%0:vgpr_32 = V_MOV_B32_e32 %stack.0, implicit $exec
%1:vgpr_32 = V_MOV_B32_e32 7, implicit $exec
BUFFER_STORE_DWORD_OFFEN %1:vgpr_32, %0:vgpr_32, $sgpr0_sgpr1_sgpr2_sgpr3, 0, 0, 0, 0, 0, implicit $exec
%2:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN %0:vgpr_32, $sgpr0_sgpr1_sgpr2_sgpr3, 0, 0, 0, 0, 0, implicit $exec
$vgpr0 = COPY %2
S_ENDPGM 0, implicit $vgpr0
...
---
name: function_fold_fi_mubuf_wave_relative
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 4
stack:
- { id: 0, size: 4, alignment: 4, local-offset: 0 }
machineFunctionInfo:
isEntryFunction: false
scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
frameOffsetReg: '$sgpr32'
stackPtrOffsetReg: '$sgpr32'
body: |
bb.0:
; GCN-LABEL: name: function_fold_fi_mubuf_wave_relative
; GCN: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 7, implicit $exec
; GCN: BUFFER_STORE_DWORD_OFFEN [[V_MOV_B32_e32_]], %stack.0, $sgpr0_sgpr1_sgpr2_sgpr3, 0, 0, 0, 0, 0, implicit $exec
; GCN: [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN %stack.0, $sgpr0_sgpr1_sgpr2_sgpr3, 0, 0, 0, 0, 0, implicit $exec
; GCN: $vgpr0 = COPY [[BUFFER_LOAD_DWORD_OFFEN]]
; GCN: S_ENDPGM 0, implicit $vgpr0
%0:vgpr_32 = V_MOV_B32_e32 %stack.0, implicit $exec
%1:vgpr_32 = V_MOV_B32_e32 7, implicit $exec
BUFFER_STORE_DWORD_OFFEN %1:vgpr_32, %0:vgpr_32, $sgpr0_sgpr1_sgpr2_sgpr3, 0, 0, 0, 0, 0, implicit $exec
%2:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN %0:vgpr_32, $sgpr0_sgpr1_sgpr2_sgpr3, 0, 0, 0, 0, 0, implicit $exec
$vgpr0 = COPY %2
S_ENDPGM 0, implicit $vgpr0
...
---
name: function_fold_fi_mubuf_stack_relative
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 4
stack:
- { id: 0, size: 4, alignment: 4, local-offset: 0 }
machineFunctionInfo:
isEntryFunction: false
scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
frameOffsetReg: '$sgpr32'
stackPtrOffsetReg: '$sgpr32'
body: |
bb.0:
; GCN-LABEL: name: function_fold_fi_mubuf_stack_relative
; GCN: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 7, implicit $exec
; GCN: BUFFER_STORE_DWORD_OFFEN [[V_MOV_B32_e32_]], %stack.0, $sgpr0_sgpr1_sgpr2_sgpr3, 0, 0, 0, 0, 0, implicit $exec
; GCN: [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN %stack.0, $sgpr0_sgpr1_sgpr2_sgpr3, 0, 0, 0, 0, 0, implicit $exec
; GCN: $vgpr0 = COPY [[BUFFER_LOAD_DWORD_OFFEN]]
; GCN: S_ENDPGM 0, implicit $vgpr0
%0:vgpr_32 = V_MOV_B32_e32 %stack.0, implicit $exec
%1:vgpr_32 = V_MOV_B32_e32 7, implicit $exec
BUFFER_STORE_DWORD_OFFEN %1:vgpr_32, %0:vgpr_32, $sgpr0_sgpr1_sgpr2_sgpr3, 0, 0, 0, 0, 0, implicit $exec
%2:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN %0:vgpr_32, $sgpr0_sgpr1_sgpr2_sgpr3, 0, 0, 0, 0, 0, implicit $exec
$vgpr0 = COPY %2
S_ENDPGM 0, implicit $vgpr0
...