maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/AMDGPU/pei-scavenge-sgpr-carry-out...

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

168 lines
14 KiB
Plaintext
Raw Normal View History

AMDGPU: Handle frame index expansion with no free SGPRs pre gfx9 Since an add instruction must produce an unused carry out, this requires additional SGPRs. This can be avoided by keeping the entire offset computation in SGPRs. If one SGPR is still available, this only costs one extra mov. If none are available, the entire computation can be done in place and reversed. This does assume the use is a VGPR operand. This was already assumed, and we currently only select frame indexes to VALU instructions. This should probably be fixed at some point to handle more possible MIR. llvm-svn: 370929
2019-09-05 01:12:57 +08:00
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=fiji -verify-machineinstrs -run-pass=prologepilog %s -o - | FileCheck %s
# Test what happens when an SGPR is unavailable for the unused add
# carry out when materializing the frame index.
# There are truly no free SGPRs, so the entire frame index expansion
# needs to be inverted to restore the original frame register.
---
name: scavenge_sgpr_pei_no_sgprs
tracksRegLiveness: true
stack:
- { id: 0, type: default, offset: 0, size: 4, alignment: 8192 }
- { id: 1, type: default, offset: 0, size: 4, alignment: 8192 }
machineFunctionInfo:
isEntryFunction: false
scratchRSrcReg: $sgpr0_sgpr1_sgpr2_sgpr3
[AMDGPU] Move frame pointer from s34 to s33 Remove the gap left between the stack pointer (s32) and frame pointer (s34) now that the scratch wave offset is no longer a part of the calling convention ABI. Update llvm/docs/AMDGPUUsage.rst to reflect the change. Tags: #llvm Differential Revision: https://reviews.llvm.org/D75657
2020-03-04 09:39:47 +08:00
frameOffsetReg: $sgpr33
AMDGPU: Handle frame index expansion with no free SGPRs pre gfx9 Since an add instruction must produce an unused carry out, this requires additional SGPRs. This can be avoided by keeping the entire offset computation in SGPRs. If one SGPR is still available, this only costs one extra mov. If none are available, the entire computation can be done in place and reversed. This does assume the use is a VGPR operand. This was already assumed, and we currently only select frame indexes to VALU instructions. This should probably be fixed at some point to handle more possible MIR. llvm-svn: 370929
2019-09-05 01:12:57 +08:00
stackPtrOffsetReg: $sgpr32
body: |
bb.0:
liveins: $vgpr1
; CHECK-LABEL: name: scavenge_sgpr_pei_no_sgprs
[AMDGPU] Enable base pointer. When the callee requires a dynamic stack realignment, it is not possible to correcty access the incoming stack arguments using the stack pointer. We reserve a base pointer in such cases to access the function arguments inside the callee. The base pointer will hold the incoming stack pointer value before any kind of delta added to it. Reviewed By: arsenm, scott.linder Differential Revision: https://reviews.llvm.org/D78811
2020-04-21 17:34:33 +08:00
; CHECK: liveins: $sgpr27, $vgpr1
[AMDGPU] Move frame pointer from s34 to s33 Remove the gap left between the stack pointer (s32) and frame pointer (s34) now that the scratch wave offset is no longer a part of the calling convention ABI. Update llvm/docs/AMDGPUUsage.rst to reflect the change. Tags: #llvm Differential Revision: https://reviews.llvm.org/D75657
2020-03-04 09:39:47 +08:00
; CHECK: $sgpr27 = frame-setup COPY $sgpr33
AMDGPU: Handle frame index expansion with no free SGPRs pre gfx9 Since an add instruction must produce an unused carry out, this requires additional SGPRs. This can be avoided by keeping the entire offset computation in SGPRs. If one SGPR is still available, this only costs one extra mov. If none are available, the entire computation can be done in place and reversed. This does assume the use is a VGPR operand. This was already assumed, and we currently only select frame indexes to VALU instructions. This should probably be fixed at some point to handle more possible MIR. llvm-svn: 370929
2019-09-05 01:12:57 +08:00
; CHECK: $sgpr4 = frame-setup S_ADD_U32 $sgpr32, 524224, implicit-def $scc
[AMDGPU] Move frame pointer from s34 to s33 Remove the gap left between the stack pointer (s32) and frame pointer (s34) now that the scratch wave offset is no longer a part of the calling convention ABI. Update llvm/docs/AMDGPUUsage.rst to reflect the change. Tags: #llvm Differential Revision: https://reviews.llvm.org/D75657
2020-03-04 09:39:47 +08:00
; CHECK: $sgpr33 = frame-setup S_AND_B32 killed $sgpr4, 4294443008, implicit-def $scc
AMDGPU: Handle frame index expansion with no free SGPRs pre gfx9 Since an add instruction must produce an unused carry out, this requires additional SGPRs. This can be avoided by keeping the entire offset computation in SGPRs. If one SGPR is still available, this only costs one extra mov. If none are available, the entire computation can be done in place and reversed. This does assume the use is a VGPR operand. This was already assumed, and we currently only select frame indexes to VALU instructions. This should probably be fixed at some point to handle more possible MIR. llvm-svn: 370929
2019-09-05 01:12:57 +08:00
; CHECK: $sgpr32 = frame-setup S_ADD_U32 $sgpr32, 1572864, implicit-def $scc
; CHECK: S_NOP 0, implicit-def $sgpr4, implicit-def $sgpr5, implicit-def $sgpr6, implicit-def $sgpr7, implicit-def $sgpr8, implicit-def $sgpr9, implicit-def $sgpr10, implicit-def $sgpr11, implicit-def $sgpr12, implicit-def $sgpr13, implicit-def $sgpr14, implicit-def $sgpr15, implicit-def $sgpr16, implicit-def $sgpr17, implicit-def $sgpr18, implicit-def $sgpr19, implicit-def $sgpr20, implicit-def $sgpr21, implicit-def $sgpr22, implicit-def $sgpr23, implicit-def $sgpr24, implicit-def $sgpr25, implicit-def $sgpr26, implicit-def $sgpr17, implicit-def $sgpr28, implicit-def $sgpr29, implicit-def $sgpr30, implicit-def $sgpr31, implicit-def $vcc
[AMDGPU] Move frame pointer from s34 to s33 Remove the gap left between the stack pointer (s32) and frame pointer (s34) now that the scratch wave offset is no longer a part of the calling convention ABI. Update llvm/docs/AMDGPUUsage.rst to reflect the change. Tags: #llvm Differential Revision: https://reviews.llvm.org/D75657
2020-03-04 09:39:47 +08:00
; CHECK: $sgpr33 = S_LSHR_B32 $sgpr33, 6, implicit-def $scc
; CHECK: $sgpr33 = S_ADD_U32 killed $sgpr33, 8192, implicit-def $scc
; CHECK: $vgpr2 = COPY killed $sgpr33
; CHECK: $sgpr33 = S_SUB_U32 killed $sgpr33, 8192, implicit-def $scc
; CHECK: $sgpr33 = S_LSHL_B32 $sgpr33, 6, implicit-def $scc
AMDGPU: Handle frame index expansion with no free SGPRs pre gfx9 Since an add instruction must produce an unused carry out, this requires additional SGPRs. This can be avoided by keeping the entire offset computation in SGPRs. If one SGPR is still available, this only costs one extra mov. If none are available, the entire computation can be done in place and reversed. This does assume the use is a VGPR operand. This was already assumed, and we currently only select frame indexes to VALU instructions. This should probably be fixed at some point to handle more possible MIR. llvm-svn: 370929
2019-09-05 01:12:57 +08:00
; CHECK: $vgpr0 = V_OR_B32_e32 killed $vgpr2, $vgpr1, implicit $exec, implicit $sgpr4, implicit $sgpr5, implicit $sgpr6, implicit $sgpr7, implicit $sgpr8, implicit $sgpr9, implicit $sgpr10, implicit $sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $sgpr16, implicit $sgpr17, implicit $sgpr18, implicit $sgpr19, implicit $sgpr20, implicit $sgpr21, implicit $sgpr22, implicit $sgpr23, implicit $sgpr24, implicit $sgpr25, implicit $sgpr26, implicit $sgpr17, implicit $sgpr28, implicit $sgpr29, implicit $sgpr30, implicit $sgpr31
; CHECK: $sgpr32 = frame-destroy S_SUB_U32 $sgpr32, 1572864, implicit-def $scc
[AMDGPU] Move frame pointer from s34 to s33 Remove the gap left between the stack pointer (s32) and frame pointer (s34) now that the scratch wave offset is no longer a part of the calling convention ABI. Update llvm/docs/AMDGPUUsage.rst to reflect the change. Tags: #llvm Differential Revision: https://reviews.llvm.org/D75657
2020-03-04 09:39:47 +08:00
; CHECK: $sgpr33 = frame-setup COPY $sgpr27
AMDGPU: Handle frame index expansion with no free SGPRs pre gfx9 Since an add instruction must produce an unused carry out, this requires additional SGPRs. This can be avoided by keeping the entire offset computation in SGPRs. If one SGPR is still available, this only costs one extra mov. If none are available, the entire computation can be done in place and reversed. This does assume the use is a VGPR operand. This was already assumed, and we currently only select frame indexes to VALU instructions. This should probably be fixed at some point to handle more possible MIR. llvm-svn: 370929
2019-09-05 01:12:57 +08:00
; CHECK: S_ENDPGM 0, implicit $vcc
S_NOP 0, implicit-def $sgpr4, implicit-def $sgpr5, implicit-def $sgpr6, implicit-def $sgpr7, implicit-def $sgpr8, implicit-def $sgpr9, implicit-def $sgpr10, implicit-def $sgpr11, implicit-def $sgpr12, implicit-def $sgpr13, implicit-def $sgpr14, implicit-def $sgpr15, implicit-def $sgpr16, implicit-def $sgpr17, implicit-def $sgpr18, implicit-def $sgpr19, implicit-def $sgpr20, implicit-def $sgpr21, implicit-def $sgpr22, implicit-def $sgpr23, implicit-def $sgpr24, implicit-def $sgpr25, implicit-def $sgpr26, implicit-def $sgpr17, implicit-def $sgpr28, implicit-def $sgpr29, implicit-def $sgpr30, implicit-def $sgpr31, implicit-def $vcc
$vgpr0 = V_OR_B32_e32 %stack.1, $vgpr1, implicit $exec, implicit $sgpr4, implicit $sgpr5, implicit $sgpr6, implicit $sgpr7, implicit $sgpr8, implicit $sgpr9, implicit $sgpr10, implicit $sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $sgpr16, implicit $sgpr17, implicit $sgpr18, implicit $sgpr19, implicit $sgpr20, implicit $sgpr21, implicit $sgpr22, implicit $sgpr23, implicit $sgpr24, implicit $sgpr25, implicit $sgpr26, implicit $sgpr17, implicit $sgpr28, implicit $sgpr29, implicit $sgpr30, implicit $sgpr31
S_ENDPGM 0, implicit $vcc
...
# One 32-bit SGPR is available for the intermediate scale computation,
# so only an extra copy to VALU is necessary.
---
name: scavenge_sgpr_pei_one_sgpr
tracksRegLiveness: true
stack:
- { id: 0, type: default, offset: 0, size: 4, alignment: 8192 }
- { id: 1, type: default, offset: 0, size: 4, alignment: 8192 }
machineFunctionInfo:
isEntryFunction: false
scratchRSrcReg: $sgpr0_sgpr1_sgpr2_sgpr3
[AMDGPU] Move frame pointer from s34 to s33 Remove the gap left between the stack pointer (s32) and frame pointer (s34) now that the scratch wave offset is no longer a part of the calling convention ABI. Update llvm/docs/AMDGPUUsage.rst to reflect the change. Tags: #llvm Differential Revision: https://reviews.llvm.org/D75657
2020-03-04 09:39:47 +08:00
frameOffsetReg: $sgpr33
AMDGPU: Handle frame index expansion with no free SGPRs pre gfx9 Since an add instruction must produce an unused carry out, this requires additional SGPRs. This can be avoided by keeping the entire offset computation in SGPRs. If one SGPR is still available, this only costs one extra mov. If none are available, the entire computation can be done in place and reversed. This does assume the use is a VGPR operand. This was already assumed, and we currently only select frame indexes to VALU instructions. This should probably be fixed at some point to handle more possible MIR. llvm-svn: 370929
2019-09-05 01:12:57 +08:00
stackPtrOffsetReg: $sgpr32
body: |
bb.0:
liveins: $vgpr1
; CHECK-LABEL: name: scavenge_sgpr_pei_one_sgpr
[AMDGPU] Enable base pointer. When the callee requires a dynamic stack realignment, it is not possible to correcty access the incoming stack arguments using the stack pointer. We reserve a base pointer in such cases to access the function arguments inside the callee. The base pointer will hold the incoming stack pointer value before any kind of delta added to it. Reviewed By: arsenm, scott.linder Differential Revision: https://reviews.llvm.org/D78811
2020-04-21 17:34:33 +08:00
; CHECK: liveins: $sgpr27, $vgpr1
[AMDGPU] Move frame pointer from s34 to s33 Remove the gap left between the stack pointer (s32) and frame pointer (s34) now that the scratch wave offset is no longer a part of the calling convention ABI. Update llvm/docs/AMDGPUUsage.rst to reflect the change. Tags: #llvm Differential Revision: https://reviews.llvm.org/D75657
2020-03-04 09:39:47 +08:00
; CHECK: $sgpr27 = frame-setup COPY $sgpr33
AMDGPU: Handle frame index expansion with no free SGPRs pre gfx9 Since an add instruction must produce an unused carry out, this requires additional SGPRs. This can be avoided by keeping the entire offset computation in SGPRs. If one SGPR is still available, this only costs one extra mov. If none are available, the entire computation can be done in place and reversed. This does assume the use is a VGPR operand. This was already assumed, and we currently only select frame indexes to VALU instructions. This should probably be fixed at some point to handle more possible MIR. llvm-svn: 370929
2019-09-05 01:12:57 +08:00
; CHECK: $sgpr4 = frame-setup S_ADD_U32 $sgpr32, 524224, implicit-def $scc
[AMDGPU] Move frame pointer from s34 to s33 Remove the gap left between the stack pointer (s32) and frame pointer (s34) now that the scratch wave offset is no longer a part of the calling convention ABI. Update llvm/docs/AMDGPUUsage.rst to reflect the change. Tags: #llvm Differential Revision: https://reviews.llvm.org/D75657
2020-03-04 09:39:47 +08:00
; CHECK: $sgpr33 = frame-setup S_AND_B32 killed $sgpr4, 4294443008, implicit-def $scc
AMDGPU: Handle frame index expansion with no free SGPRs pre gfx9 Since an add instruction must produce an unused carry out, this requires additional SGPRs. This can be avoided by keeping the entire offset computation in SGPRs. If one SGPR is still available, this only costs one extra mov. If none are available, the entire computation can be done in place and reversed. This does assume the use is a VGPR operand. This was already assumed, and we currently only select frame indexes to VALU instructions. This should probably be fixed at some point to handle more possible MIR. llvm-svn: 370929
2019-09-05 01:12:57 +08:00
; CHECK: $sgpr32 = frame-setup S_ADD_U32 $sgpr32, 1572864, implicit-def $scc
; CHECK: S_NOP 0, implicit-def $sgpr4, implicit-def $sgpr5, implicit-def $sgpr6, implicit-def $sgpr7, implicit-def $sgpr8, implicit-def $sgpr9, implicit-def $sgpr10, implicit-def $sgpr11, implicit-def $sgpr12, implicit-def $sgpr13, implicit-def $sgpr14, implicit-def $sgpr15, implicit-def $sgpr16, implicit-def $sgpr17, implicit-def $sgpr18, implicit-def $sgpr19, implicit-def $sgpr20, implicit-def $sgpr21, implicit-def $sgpr22, implicit-def $sgpr23, implicit-def $sgpr24, implicit-def $sgpr25, implicit-def $sgpr26, implicit-def $sgpr17, implicit-def $sgpr28, implicit-def $sgpr30, implicit-def $sgpr31, implicit-def $vcc
[AMDGPU] Move frame pointer from s34 to s33 Remove the gap left between the stack pointer (s32) and frame pointer (s34) now that the scratch wave offset is no longer a part of the calling convention ABI. Update llvm/docs/AMDGPUUsage.rst to reflect the change. Tags: #llvm Differential Revision: https://reviews.llvm.org/D75657
2020-03-04 09:39:47 +08:00
; CHECK: $sgpr29 = S_LSHR_B32 $sgpr33, 6, implicit-def $scc
AMDGPU: Handle frame index expansion with no free SGPRs pre gfx9 Since an add instruction must produce an unused carry out, this requires additional SGPRs. This can be avoided by keeping the entire offset computation in SGPRs. If one SGPR is still available, this only costs one extra mov. If none are available, the entire computation can be done in place and reversed. This does assume the use is a VGPR operand. This was already assumed, and we currently only select frame indexes to VALU instructions. This should probably be fixed at some point to handle more possible MIR. llvm-svn: 370929
2019-09-05 01:12:57 +08:00
; CHECK: $sgpr29 = S_ADD_U32 killed $sgpr29, 8192, implicit-def $scc
; CHECK: $vgpr2 = COPY killed $sgpr29
; CHECK: $vgpr0 = V_OR_B32_e32 killed $vgpr2, $vgpr1, implicit $exec, implicit $sgpr4, implicit $sgpr5, implicit $sgpr6, implicit $sgpr7, implicit $sgpr8, implicit $sgpr9, implicit $sgpr10, implicit $sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $sgpr16, implicit $sgpr17, implicit $sgpr18, implicit $sgpr19, implicit $sgpr20, implicit $sgpr21, implicit $sgpr22, implicit $sgpr23, implicit $sgpr24, implicit $sgpr25, implicit $sgpr26, implicit $sgpr17, implicit $sgpr28, implicit $sgpr31
; CHECK: $sgpr32 = frame-destroy S_SUB_U32 $sgpr32, 1572864, implicit-def $scc
[AMDGPU] Move frame pointer from s34 to s33 Remove the gap left between the stack pointer (s32) and frame pointer (s34) now that the scratch wave offset is no longer a part of the calling convention ABI. Update llvm/docs/AMDGPUUsage.rst to reflect the change. Tags: #llvm Differential Revision: https://reviews.llvm.org/D75657
2020-03-04 09:39:47 +08:00
; CHECK: $sgpr33 = frame-setup COPY $sgpr27
AMDGPU: Handle frame index expansion with no free SGPRs pre gfx9 Since an add instruction must produce an unused carry out, this requires additional SGPRs. This can be avoided by keeping the entire offset computation in SGPRs. If one SGPR is still available, this only costs one extra mov. If none are available, the entire computation can be done in place and reversed. This does assume the use is a VGPR operand. This was already assumed, and we currently only select frame indexes to VALU instructions. This should probably be fixed at some point to handle more possible MIR. llvm-svn: 370929
2019-09-05 01:12:57 +08:00
; CHECK: S_ENDPGM 0, implicit $vcc
S_NOP 0, implicit-def $sgpr4, implicit-def $sgpr5, implicit-def $sgpr6, implicit-def $sgpr7, implicit-def $sgpr8, implicit-def $sgpr9, implicit-def $sgpr10, implicit-def $sgpr11, implicit-def $sgpr12, implicit-def $sgpr13, implicit-def $sgpr14, implicit-def $sgpr15, implicit-def $sgpr16, implicit-def $sgpr17, implicit-def $sgpr18, implicit-def $sgpr19, implicit-def $sgpr20, implicit-def $sgpr21, implicit-def $sgpr22, implicit-def $sgpr23, implicit-def $sgpr24, implicit-def $sgpr25, implicit-def $sgpr26, implicit-def $sgpr17, implicit-def $sgpr28, implicit-def $sgpr30, implicit-def $sgpr31, implicit-def $vcc
$vgpr0 = V_OR_B32_e32 %stack.1, $vgpr1, implicit $exec, implicit $sgpr4, implicit $sgpr5, implicit $sgpr6, implicit $sgpr7, implicit $sgpr8, implicit $sgpr9, implicit $sgpr10, implicit $sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $sgpr16, implicit $sgpr17, implicit $sgpr18, implicit $sgpr19, implicit $sgpr20, implicit $sgpr21, implicit $sgpr22, implicit $sgpr23, implicit $sgpr24, implicit $sgpr25, implicit $sgpr26, implicit $sgpr17, implicit $sgpr28, implicit $sgpr31
S_ENDPGM 0, implicit $vcc
...
AMDGPU: Reuse carry out register during FI elimination Summary: Pre gfx9 we need to scavenge a 64-bit SGPR to use as the carry out for an Add. If only one SGPR was available this crashed when trying to scavenge another 32bit SGPR to materialize the offset. Instead, reuse a 32-bit SGPR from the carry out as the offset register. Also prefer to use vcc for the unused carry out when it is available. Reviewers: arsenm, rampitec Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D70614
2019-11-23 04:25:13 +08:00
# When only one 64-bit SGPR is available for the unused carry out pre gfx9,
# we must reuse one of the 32-bit SGPR sub-regs to materialize the offset.
---
name: scavenge_sgpr_pei_one_sgpr_64
tracksRegLiveness: true
stack:
- { id: 0, type: default, offset: 0, size: 4, alignment: 8192 }
- { id: 1, type: default, offset: 0, size: 4, alignment: 8192 }
machineFunctionInfo:
isEntryFunction: false
scratchRSrcReg: $sgpr0_sgpr1_sgpr2_sgpr3
[AMDGPU] Move frame pointer from s34 to s33 Remove the gap left between the stack pointer (s32) and frame pointer (s34) now that the scratch wave offset is no longer a part of the calling convention ABI. Update llvm/docs/AMDGPUUsage.rst to reflect the change. Tags: #llvm Differential Revision: https://reviews.llvm.org/D75657
2020-03-04 09:39:47 +08:00
frameOffsetReg: $sgpr33
AMDGPU: Reuse carry out register during FI elimination Summary: Pre gfx9 we need to scavenge a 64-bit SGPR to use as the carry out for an Add. If only one SGPR was available this crashed when trying to scavenge another 32bit SGPR to materialize the offset. Instead, reuse a 32-bit SGPR from the carry out as the offset register. Also prefer to use vcc for the unused carry out when it is available. Reviewers: arsenm, rampitec Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D70614
2019-11-23 04:25:13 +08:00
stackPtrOffsetReg: $sgpr32
body: |
bb.0:
liveins: $vgpr1
; CHECK-LABEL: name: scavenge_sgpr_pei_one_sgpr_64
[AMDGPU] Enable base pointer. When the callee requires a dynamic stack realignment, it is not possible to correcty access the incoming stack arguments using the stack pointer. We reserve a base pointer in such cases to access the function arguments inside the callee. The base pointer will hold the incoming stack pointer value before any kind of delta added to it. Reviewed By: arsenm, scott.linder Differential Revision: https://reviews.llvm.org/D78811
2020-04-21 17:34:33 +08:00
; CHECK: liveins: $sgpr27, $vgpr1
[AMDGPU] Move frame pointer from s34 to s33 Remove the gap left between the stack pointer (s32) and frame pointer (s34) now that the scratch wave offset is no longer a part of the calling convention ABI. Update llvm/docs/AMDGPUUsage.rst to reflect the change. Tags: #llvm Differential Revision: https://reviews.llvm.org/D75657
2020-03-04 09:39:47 +08:00
; CHECK: $sgpr27 = frame-setup COPY $sgpr33
AMDGPU: Reuse carry out register during FI elimination Summary: Pre gfx9 we need to scavenge a 64-bit SGPR to use as the carry out for an Add. If only one SGPR was available this crashed when trying to scavenge another 32bit SGPR to materialize the offset. Instead, reuse a 32-bit SGPR from the carry out as the offset register. Also prefer to use vcc for the unused carry out when it is available. Reviewers: arsenm, rampitec Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D70614
2019-11-23 04:25:13 +08:00
; CHECK: $sgpr4 = frame-setup S_ADD_U32 $sgpr32, 524224, implicit-def $scc
[AMDGPU] Move frame pointer from s34 to s33 Remove the gap left between the stack pointer (s32) and frame pointer (s34) now that the scratch wave offset is no longer a part of the calling convention ABI. Update llvm/docs/AMDGPUUsage.rst to reflect the change. Tags: #llvm Differential Revision: https://reviews.llvm.org/D75657
2020-03-04 09:39:47 +08:00
; CHECK: $sgpr33 = frame-setup S_AND_B32 killed $sgpr4, 4294443008, implicit-def $scc
AMDGPU: Reuse carry out register during FI elimination Summary: Pre gfx9 we need to scavenge a 64-bit SGPR to use as the carry out for an Add. If only one SGPR was available this crashed when trying to scavenge another 32bit SGPR to materialize the offset. Instead, reuse a 32-bit SGPR from the carry out as the offset register. Also prefer to use vcc for the unused carry out when it is available. Reviewers: arsenm, rampitec Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D70614
2019-11-23 04:25:13 +08:00
; CHECK: $sgpr32 = frame-setup S_ADD_U32 $sgpr32, 1572864, implicit-def $scc
; CHECK: S_NOP 0, implicit-def $sgpr4, implicit-def $sgpr5, implicit-def $sgpr6, implicit-def $sgpr7, implicit-def $sgpr8, implicit-def $sgpr9, implicit-def $sgpr10, implicit-def $sgpr11, implicit-def $sgpr12, implicit-def $sgpr13, implicit-def $sgpr14, implicit-def $sgpr15, implicit-def $sgpr16, implicit-def $sgpr17, implicit-def $sgpr18, implicit-def $sgpr19, implicit-def $sgpr20, implicit-def $sgpr21, implicit-def $sgpr22, implicit-def $sgpr23, implicit-def $sgpr24, implicit-def $sgpr25, implicit-def $sgpr26, implicit-def $sgpr17, implicit-def $sgpr30, implicit-def $sgpr31, implicit-def $vcc
[AMDGPU] Reuse register during frame index elimination If there were no free VGPRs we would need two emergency spill slots for register scavenging during PEI/frame index elimination. Reuse 'ResultReg' for scale calculation so that only one spill is needed. Differential Revision: https://reviews.llvm.org/D76387
2020-03-19 04:47:39 +08:00
; CHECK: $vgpr2 = V_LSHRREV_B32_e64 6, $sgpr33, implicit $exec
AMDGPU: Reuse carry out register during FI elimination Summary: Pre gfx9 we need to scavenge a 64-bit SGPR to use as the carry out for an Add. If only one SGPR was available this crashed when trying to scavenge another 32bit SGPR to materialize the offset. Instead, reuse a 32-bit SGPR from the carry out as the offset register. Also prefer to use vcc for the unused carry out when it is available. Reviewers: arsenm, rampitec Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D70614
2019-11-23 04:25:13 +08:00
; CHECK: $sgpr28 = S_MOV_B32 8192
AMDGPU: Rename add/sub with carry out instructions The hardware has created a real mess in the naming for add/sub, which have been renamed basically every generation. Switch the carry out pseudos to have the gfx9/gfx10 names. We were using the original SI/CI v_add_i32/v_sub_i32 names. Later targets reintroduced these names as carryless instructions with a saturating clamp bit, which we do not define. Do this rename so we can unambiguously add these missing instructions. The carry-in versions should also be renamed, but at least those had a consistent _u32 name to begin with. The 16-bit instructions were also renamed, but aren't ambiguous. This does regress assembler error message quality in some cases. In mismatched wave32/wave64 situations, this will switch from "unsupported instruction" to "invalid operand", with the error pointing at the wrong position. I couldn't quite follow how the assembler selects these, but the previous behavior seemed accidental to me. It looked like there was a partial attempt to handle this which was never completed (i.e. there is an AMDGPUOperand::isBoolReg but it isn't used for anything).
2020-07-14 21:18:36 +08:00
; CHECK: $vgpr2, dead $sgpr28_sgpr29 = V_ADD_CO_U32_e64 killed $sgpr28, killed $vgpr2, 0, implicit $exec
AMDGPU: Reuse carry out register during FI elimination Summary: Pre gfx9 we need to scavenge a 64-bit SGPR to use as the carry out for an Add. If only one SGPR was available this crashed when trying to scavenge another 32bit SGPR to materialize the offset. Instead, reuse a 32-bit SGPR from the carry out as the offset register. Also prefer to use vcc for the unused carry out when it is available. Reviewers: arsenm, rampitec Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D70614
2019-11-23 04:25:13 +08:00
; CHECK: $vgpr0 = V_OR_B32_e32 killed $vgpr2, $vgpr1, implicit $exec, implicit $sgpr4, implicit $sgpr5, implicit $sgpr6, implicit $sgpr7, implicit $sgpr8, implicit $sgpr9, implicit $sgpr10, implicit $sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $sgpr16, implicit $sgpr17, implicit $sgpr18, implicit $sgpr19, implicit $sgpr20, implicit $sgpr21, implicit $sgpr22, implicit $sgpr23, implicit $sgpr24, implicit $sgpr25, implicit $sgpr26, implicit $sgpr17, implicit $sgpr31
; CHECK: $sgpr32 = frame-destroy S_SUB_U32 $sgpr32, 1572864, implicit-def $scc
[AMDGPU] Move frame pointer from s34 to s33 Remove the gap left between the stack pointer (s32) and frame pointer (s34) now that the scratch wave offset is no longer a part of the calling convention ABI. Update llvm/docs/AMDGPUUsage.rst to reflect the change. Tags: #llvm Differential Revision: https://reviews.llvm.org/D75657
2020-03-04 09:39:47 +08:00
; CHECK: $sgpr33 = frame-setup COPY $sgpr27
AMDGPU: Reuse carry out register during FI elimination Summary: Pre gfx9 we need to scavenge a 64-bit SGPR to use as the carry out for an Add. If only one SGPR was available this crashed when trying to scavenge another 32bit SGPR to materialize the offset. Instead, reuse a 32-bit SGPR from the carry out as the offset register. Also prefer to use vcc for the unused carry out when it is available. Reviewers: arsenm, rampitec Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D70614
2019-11-23 04:25:13 +08:00
; CHECK: S_ENDPGM 0, implicit $vcc
S_NOP 0, implicit-def $sgpr4, implicit-def $sgpr5, implicit-def $sgpr6, implicit-def $sgpr7, implicit-def $sgpr8, implicit-def $sgpr9, implicit-def $sgpr10, implicit-def $sgpr11, implicit-def $sgpr12, implicit-def $sgpr13, implicit-def $sgpr14, implicit-def $sgpr15, implicit-def $sgpr16, implicit-def $sgpr17, implicit-def $sgpr18, implicit-def $sgpr19, implicit-def $sgpr20, implicit-def $sgpr21, implicit-def $sgpr22, implicit-def $sgpr23, implicit-def $sgpr24, implicit-def $sgpr25, implicit-def $sgpr26, implicit-def $sgpr17, implicit-def $sgpr30, implicit-def $sgpr31, implicit-def $vcc
$vgpr0 = V_OR_B32_e32 %stack.1, $vgpr1, implicit $exec, implicit $sgpr4, implicit $sgpr5, implicit $sgpr6, implicit $sgpr7, implicit $sgpr8, implicit $sgpr9, implicit $sgpr10, implicit $sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $sgpr16, implicit $sgpr17, implicit $sgpr18, implicit $sgpr19, implicit $sgpr20, implicit $sgpr21, implicit $sgpr22, implicit $sgpr23, implicit $sgpr24, implicit $sgpr25, implicit $sgpr26, implicit $sgpr17, implicit $sgpr31
S_ENDPGM 0, implicit $vcc
...
# Prefer to use vcc as unused carry out.
---
name: scavenge_sgpr_pei_prefer_vcc
tracksRegLiveness: true
stack:
- { id: 0, type: default, offset: 0, size: 4, alignment: 8192 }
- { id: 1, type: default, offset: 0, size: 4, alignment: 8192 }
machineFunctionInfo:
isEntryFunction: false
scratchRSrcReg: $sgpr0_sgpr1_sgpr2_sgpr3
[AMDGPU] Move frame pointer from s34 to s33 Remove the gap left between the stack pointer (s32) and frame pointer (s34) now that the scratch wave offset is no longer a part of the calling convention ABI. Update llvm/docs/AMDGPUUsage.rst to reflect the change. Tags: #llvm Differential Revision: https://reviews.llvm.org/D75657
2020-03-04 09:39:47 +08:00
frameOffsetReg: $sgpr33
AMDGPU: Reuse carry out register during FI elimination Summary: Pre gfx9 we need to scavenge a 64-bit SGPR to use as the carry out for an Add. If only one SGPR was available this crashed when trying to scavenge another 32bit SGPR to materialize the offset. Instead, reuse a 32-bit SGPR from the carry out as the offset register. Also prefer to use vcc for the unused carry out when it is available. Reviewers: arsenm, rampitec Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D70614
2019-11-23 04:25:13 +08:00
stackPtrOffsetReg: $sgpr32
body: |
bb.0:
liveins: $vgpr1
; CHECK-LABEL: name: scavenge_sgpr_pei_prefer_vcc
[AMDGPU] Enable base pointer. When the callee requires a dynamic stack realignment, it is not possible to correcty access the incoming stack arguments using the stack pointer. We reserve a base pointer in such cases to access the function arguments inside the callee. The base pointer will hold the incoming stack pointer value before any kind of delta added to it. Reviewed By: arsenm, scott.linder Differential Revision: https://reviews.llvm.org/D78811
2020-04-21 17:34:33 +08:00
; CHECK: liveins: $sgpr27, $vgpr1
[AMDGPU] Move frame pointer from s34 to s33 Remove the gap left between the stack pointer (s32) and frame pointer (s34) now that the scratch wave offset is no longer a part of the calling convention ABI. Update llvm/docs/AMDGPUUsage.rst to reflect the change. Tags: #llvm Differential Revision: https://reviews.llvm.org/D75657
2020-03-04 09:39:47 +08:00
; CHECK: $sgpr27 = frame-setup COPY $sgpr33
AMDGPU: Reuse carry out register during FI elimination Summary: Pre gfx9 we need to scavenge a 64-bit SGPR to use as the carry out for an Add. If only one SGPR was available this crashed when trying to scavenge another 32bit SGPR to materialize the offset. Instead, reuse a 32-bit SGPR from the carry out as the offset register. Also prefer to use vcc for the unused carry out when it is available. Reviewers: arsenm, rampitec Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D70614
2019-11-23 04:25:13 +08:00
; CHECK: $sgpr4 = frame-setup S_ADD_U32 $sgpr32, 524224, implicit-def $scc
[AMDGPU] Move frame pointer from s34 to s33 Remove the gap left between the stack pointer (s32) and frame pointer (s34) now that the scratch wave offset is no longer a part of the calling convention ABI. Update llvm/docs/AMDGPUUsage.rst to reflect the change. Tags: #llvm Differential Revision: https://reviews.llvm.org/D75657
2020-03-04 09:39:47 +08:00
; CHECK: $sgpr33 = frame-setup S_AND_B32 killed $sgpr4, 4294443008, implicit-def $scc
AMDGPU: Reuse carry out register during FI elimination Summary: Pre gfx9 we need to scavenge a 64-bit SGPR to use as the carry out for an Add. If only one SGPR was available this crashed when trying to scavenge another 32bit SGPR to materialize the offset. Instead, reuse a 32-bit SGPR from the carry out as the offset register. Also prefer to use vcc for the unused carry out when it is available. Reviewers: arsenm, rampitec Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D70614
2019-11-23 04:25:13 +08:00
; CHECK: $sgpr32 = frame-setup S_ADD_U32 $sgpr32, 1572864, implicit-def $scc
; CHECK: S_NOP 0, implicit-def $sgpr4, implicit-def $sgpr5, implicit-def $sgpr6, implicit-def $sgpr7, implicit-def $sgpr8, implicit-def $sgpr9, implicit-def $sgpr10, implicit-def $sgpr11, implicit-def $sgpr12, implicit-def $sgpr13, implicit-def $sgpr14, implicit-def $sgpr15, implicit-def $sgpr16, implicit-def $sgpr17, implicit-def $sgpr18, implicit-def $sgpr19, implicit-def $sgpr20, implicit-def $sgpr21, implicit-def $sgpr22, implicit-def $sgpr23, implicit-def $sgpr24, implicit-def $sgpr25, implicit-def $sgpr26, implicit-def $sgpr17, implicit-def $sgpr30, implicit-def $sgpr31
[AMDGPU] Reuse register during frame index elimination If there were no free VGPRs we would need two emergency spill slots for register scavenging during PEI/frame index elimination. Reuse 'ResultReg' for scale calculation so that only one spill is needed. Differential Revision: https://reviews.llvm.org/D76387
2020-03-19 04:47:39 +08:00
; CHECK: $vgpr2 = V_LSHRREV_B32_e64 6, $sgpr33, implicit $exec
AMDGPU: Reuse carry out register during FI elimination Summary: Pre gfx9 we need to scavenge a 64-bit SGPR to use as the carry out for an Add. If only one SGPR was available this crashed when trying to scavenge another 32bit SGPR to materialize the offset. Instead, reuse a 32-bit SGPR from the carry out as the offset register. Also prefer to use vcc for the unused carry out when it is available. Reviewers: arsenm, rampitec Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D70614
2019-11-23 04:25:13 +08:00
; CHECK: $vcc_lo = S_MOV_B32 8192
AMDGPU: Rename add/sub with carry out instructions The hardware has created a real mess in the naming for add/sub, which have been renamed basically every generation. Switch the carry out pseudos to have the gfx9/gfx10 names. We were using the original SI/CI v_add_i32/v_sub_i32 names. Later targets reintroduced these names as carryless instructions with a saturating clamp bit, which we do not define. Do this rename so we can unambiguously add these missing instructions. The carry-in versions should also be renamed, but at least those had a consistent _u32 name to begin with. The 16-bit instructions were also renamed, but aren't ambiguous. This does regress assembler error message quality in some cases. In mismatched wave32/wave64 situations, this will switch from "unsupported instruction" to "invalid operand", with the error pointing at the wrong position. I couldn't quite follow how the assembler selects these, but the previous behavior seemed accidental to me. It looked like there was a partial attempt to handle this which was never completed (i.e. there is an AMDGPUOperand::isBoolReg but it isn't used for anything).
2020-07-14 21:18:36 +08:00
; CHECK: $vgpr2, dead $vcc = V_ADD_CO_U32_e64 killed $vcc_lo, killed $vgpr2, 0, implicit $exec
AMDGPU: Reuse carry out register during FI elimination Summary: Pre gfx9 we need to scavenge a 64-bit SGPR to use as the carry out for an Add. If only one SGPR was available this crashed when trying to scavenge another 32bit SGPR to materialize the offset. Instead, reuse a 32-bit SGPR from the carry out as the offset register. Also prefer to use vcc for the unused carry out when it is available. Reviewers: arsenm, rampitec Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D70614
2019-11-23 04:25:13 +08:00
; CHECK: $vgpr0 = V_OR_B32_e32 killed $vgpr2, $vgpr1, implicit $exec, implicit $sgpr4, implicit $sgpr5, implicit $sgpr6, implicit $sgpr7, implicit $sgpr8, implicit $sgpr9, implicit $sgpr10, implicit $sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $sgpr16, implicit $sgpr17, implicit $sgpr18, implicit $sgpr19, implicit $sgpr20, implicit $sgpr21, implicit $sgpr22, implicit $sgpr23, implicit $sgpr24, implicit $sgpr25, implicit $sgpr26, implicit $sgpr17, implicit $sgpr31
; CHECK: $sgpr32 = frame-destroy S_SUB_U32 $sgpr32, 1572864, implicit-def $scc
[AMDGPU] Move frame pointer from s34 to s33 Remove the gap left between the stack pointer (s32) and frame pointer (s34) now that the scratch wave offset is no longer a part of the calling convention ABI. Update llvm/docs/AMDGPUUsage.rst to reflect the change. Tags: #llvm Differential Revision: https://reviews.llvm.org/D75657
2020-03-04 09:39:47 +08:00
; CHECK: $sgpr33 = frame-setup COPY $sgpr27
AMDGPU: Reuse carry out register during FI elimination Summary: Pre gfx9 we need to scavenge a 64-bit SGPR to use as the carry out for an Add. If only one SGPR was available this crashed when trying to scavenge another 32bit SGPR to materialize the offset. Instead, reuse a 32-bit SGPR from the carry out as the offset register. Also prefer to use vcc for the unused carry out when it is available. Reviewers: arsenm, rampitec Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D70614
2019-11-23 04:25:13 +08:00
; CHECK: S_ENDPGM 0
S_NOP 0, implicit-def $sgpr4, implicit-def $sgpr5, implicit-def $sgpr6, implicit-def $sgpr7, implicit-def $sgpr8, implicit-def $sgpr9, implicit-def $sgpr10, implicit-def $sgpr11, implicit-def $sgpr12, implicit-def $sgpr13, implicit-def $sgpr14, implicit-def $sgpr15, implicit-def $sgpr16, implicit-def $sgpr17, implicit-def $sgpr18, implicit-def $sgpr19, implicit-def $sgpr20, implicit-def $sgpr21, implicit-def $sgpr22, implicit-def $sgpr23, implicit-def $sgpr24, implicit-def $sgpr25, implicit-def $sgpr26, implicit-def $sgpr17, implicit-def $sgpr30, implicit-def $sgpr31
$vgpr0 = V_OR_B32_e32 %stack.1, $vgpr1, implicit $exec, implicit $sgpr4, implicit $sgpr5, implicit $sgpr6, implicit $sgpr7, implicit $sgpr8, implicit $sgpr9, implicit $sgpr10, implicit $sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $sgpr16, implicit $sgpr17, implicit $sgpr18, implicit $sgpr19, implicit $sgpr20, implicit $sgpr21, implicit $sgpr22, implicit $sgpr23, implicit $sgpr24, implicit $sgpr25, implicit $sgpr26, implicit $sgpr17, implicit $sgpr31
S_ENDPGM 0
...