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/Thumb2/mve-vpt-block-fold-vcmp.mir

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

142 lines
8.6 KiB
Plaintext
Raw Normal View History

[ARM] Reegenerate MVE tests. NFC The mve-phireg.ll test no longer really tests what it was added for, but the original case was fairly complex. I've left the test in as a general codegen test.
2020-01-15 15:50:14 +08:00
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
[ARM][MVE] VPT Blocks: findVCMPToFoldIntoVPS This is a recommit of D71330, but with a few things fixed and changed: 1) ReachingDefAnalysis: this was not running with optnone as it was checking skipFunction(), which other analysis passes don't do. I guess this is a copy-paste from a codegen pass. 2) VPTBlockPass: here I've added skipFunction(), because like most/all optimisations, we don't want to run this with optnone. This fixes the issues with the initial/previous commit: the VPTBlockPass was running with optnone, but ReachingDefAnalysis wasn't, and so VPTBlockPass was crashing querying ReachingDefAnalysis. I've added test case mve-vpt-block-optnone.mir to check that we don't run VPTBlock with optnone. Differential Revision: https://reviews.llvm.org/D71470
2020-01-07 21:54:47 +08:00
# RUN: llc -run-pass arm-mve-vpt %s -o - | FileCheck %s
--- |
target datalayout = "e-m:e-p:32:32-Fi8-i64:64-v128:64:128-a:0:32-n32-S64"
target triple = "thumbv8.1m.main-arm-unknown-eabihf"
define dso_local <4 x i32> @foo(<4 x i32>* %src, <4 x i32>* %src2, <4 x i32>* %src3, <4 x i32>* %dest, <4 x i32>* %dest2, <4 x i32>* %dest3, <4 x float> %a1) local_unnamed_addr #0 {
entry:
%c = fcmp one <4 x float> %a1, zeroinitializer
%w = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %src, i32 4, <4 x i1> %c, <4 x i32> undef)
tail call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %w, <4 x i32>* %dest, i32 4, <4 x i1> %c)
%w2 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %src2, i32 4, <4 x i1> %c, <4 x i32> undef)
tail call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %w2, <4 x i32>* %dest2, i32 4, <4 x i1> %c)
%w3 = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %src3, i32 4, <4 x i1> %c, <4 x i32> undef)
tail call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %w3, <4 x i32>* %dest3, i32 4, <4 x i1> %c)
ret <4 x i32> %w3
}
declare <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>*, i32 immarg, <4 x i1>, <4 x i32>) #2
declare void @llvm.masked.store.v4i32.p0v4i32(<4 x i32>, <4 x i32>*, i32 immarg, <4 x i1>) #3
attributes #0 = { nounwind readnone "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "frame-pointer"="all" "less-precise-fpmad"="false" "min-legal-vector-width"="128" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="generic" "target-features"="+armv8.1-m.main,+fp-armv8d16sp,+fp16,+fpregs,+fullfp16,+hwdiv,+lob,+mve.fp,+ras,+strict-align,+thumb-mode,+vfp2sp,+vfp3d16sp,+vfp4d16sp" "unsafe-fp-math"="false" "use-soft-float"="false" }
attributes #1 = { nounwind readnone }
attributes #2 = { argmemonly nounwind readonly willreturn }
attributes #3 = { argmemonly nounwind willreturn }
attributes #4 = { noduplicate nounwind }
attributes #5 = { nounwind }
!llvm.module.flags = !{!0, !1}
!llvm.ident = !{!2}
!0 = !{i32 1, !"wchar_size", i32 4}
!1 = !{i32 1, !"min_enum_size", i32 4}
!2 = !{!"clang version 10.0.0 (http://github.com/llvm/llvm-project 90450197deaf91160a22825e6746d998aad05704)"}
...
---
name: foo
alignment: 2
exposesReturnsTwice: false
legalized: false
regBankSelected: false
selected: false
failedISel: false
tracksRegLiveness: true
hasWinCFI: false
registers: []
liveins:
- { reg: '$r0', virtual-reg: '' }
- { reg: '$r1', virtual-reg: '' }
- { reg: '$r2', virtual-reg: '' }
- { reg: '$q0', virtual-reg: '' }
frameInfo:
isFrameAddressTaken: false
isReturnAddressTaken: false
hasStackMap: false
hasPatchPoint: false
stackSize: 8
offsetAdjustment: 0
maxAlignment: 4
adjustsStack: false
hasCalls: false
stackProtector: ''
maxCallFrameSize: 0
cvBytesOfCalleeSavedRegisters: 0
hasOpaqueSPAdjustment: false
hasVAStart: false
hasMustTailInVarArgFunc: false
localFrameSize: 0
savePoint: ''
restorePoint: ''
fixedStack:
- { id: 0, type: default, offset: 12, size: 4, alignment: 4, stack-id: default,
isImmutable: true, isAliased: false, callee-saved-register: '', callee-saved-restored: true,
debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
- { id: 1, type: default, offset: 8, size: 4, alignment: 8, stack-id: default,
isImmutable: true, isAliased: false, callee-saved-register: '', callee-saved-restored: true,
debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
- { id: 2, type: default, offset: 4, size: 4, alignment: 4, stack-id: default,
isImmutable: true, isAliased: false, callee-saved-register: '', callee-saved-restored: true,
debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
- { id: 3, type: default, offset: 0, size: 4, alignment: 8, stack-id: default,
isImmutable: true, isAliased: false, callee-saved-register: '', callee-saved-restored: true,
debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
stack:
- { id: 0, name: '', type: spill-slot, offset: -4, size: 4, alignment: 4,
stack-id: default, callee-saved-register: '$lr', callee-saved-restored: false,
debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
- { id: 1, name: '', type: spill-slot, offset: -8, size: 4, alignment: 4,
stack-id: default, callee-saved-register: '$r7', callee-saved-restored: true,
debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
callSites: []
constants: []
machineFunctionInfo: {}
body: |
bb.0.entry:
liveins: $q0, $r0, $r1, $r2, $lr
[ARM] Reegenerate MVE tests. NFC The mve-phireg.ll test no longer really tests what it was added for, but the original case was fairly complex. I've left the test in as a general codegen test.
2020-01-15 15:50:14 +08:00
; CHECK-LABEL: name: foo
; CHECK: liveins: $q0, $r0, $r1, $r2, $lr
[MIR][ARM] MachineOperand comments This adds infrastructure to print and parse MIR MachineOperand comments. The motivation for the ARM backend is to print condition code names instead of magic constants that are difficult to read (for human beings). For example, instead of this: dead renamable $r2, $cpsr = tEOR killed renamable $r2, renamable $r1, 14, $noreg t2Bcc %bb.4, 0, killed $cpsr we now print this: dead renamable $r2, $cpsr = tEOR killed renamable $r2, renamable $r1, 14 /* CC::always */, $noreg t2Bcc %bb.4, 0 /* CC:eq */, killed $cpsr This shows that MachineOperand comments are enclosed between /* and */. In this example, the EOR instruction is not conditionally executed (i.e. it is "always executed"), which is encoded by the 14 immediate machine operand. Thus, now this machine operand has /* CC::always */ as a comment. The 0 on the next conditional branch instruction represents the equal condition code, thus now this operand has /* CC:eq */ as a comment. As it is a comment, the MI lexer/parser completely ignores it. The benefit is that this keeps the change in the lexer extremely minimal and no target specific parsing needs to be done. The changes on the MIPrinter side are also minimal, as there is only one target hooks that is used to create the machine operand comments. Differential Revision: https://reviews.llvm.org/D74306
2020-02-24 22:19:21 +08:00
; CHECK: $sp = frame-setup t2STMDB_UPD $sp, 14 /* CC::al */, $noreg, killed $r7, killed $lr
[ARM] Reegenerate MVE tests. NFC The mve-phireg.ll test no longer really tests what it was added for, but the original case was fairly complex. I've left the test in as a general codegen test.
2020-01-15 15:50:14 +08:00
; CHECK: frame-setup CFI_INSTRUCTION def_cfa_offset 8
; CHECK: frame-setup CFI_INSTRUCTION offset $lr, -4
; CHECK: frame-setup CFI_INSTRUCTION offset $r7, -8
[MIR][ARM] MachineOperand comments This adds infrastructure to print and parse MIR MachineOperand comments. The motivation for the ARM backend is to print condition code names instead of magic constants that are difficult to read (for human beings). For example, instead of this: dead renamable $r2, $cpsr = tEOR killed renamable $r2, renamable $r1, 14, $noreg t2Bcc %bb.4, 0, killed $cpsr we now print this: dead renamable $r2, $cpsr = tEOR killed renamable $r2, renamable $r1, 14 /* CC::always */, $noreg t2Bcc %bb.4, 0 /* CC:eq */, killed $cpsr This shows that MachineOperand comments are enclosed between /* and */. In this example, the EOR instruction is not conditionally executed (i.e. it is "always executed"), which is encoded by the 14 immediate machine operand. Thus, now this machine operand has /* CC::always */ as a comment. The 0 on the next conditional branch instruction represents the equal condition code, thus now this operand has /* CC:eq */ as a comment. As it is a comment, the MI lexer/parser completely ignores it. The benefit is that this keeps the change in the lexer extremely minimal and no target specific parsing needs to be done. The changes on the MIPrinter side are also minimal, as there is only one target hooks that is used to create the machine operand comments. Differential Revision: https://reviews.llvm.org/D74306
2020-02-24 22:19:21 +08:00
; CHECK: $r7 = frame-setup tMOVr killed $sp, 14 /* CC::al */, $noreg
[ARM] Reegenerate MVE tests. NFC The mve-phireg.ll test no longer really tests what it was added for, but the original case was fairly complex. I've left the test in as a general codegen test.
2020-01-15 15:50:14 +08:00
; CHECK: frame-setup CFI_INSTRUCTION def_cfa_register $r7
[MIR][ARM] MachineOperand comments This adds infrastructure to print and parse MIR MachineOperand comments. The motivation for the ARM backend is to print condition code names instead of magic constants that are difficult to read (for human beings). For example, instead of this: dead renamable $r2, $cpsr = tEOR killed renamable $r2, renamable $r1, 14, $noreg t2Bcc %bb.4, 0, killed $cpsr we now print this: dead renamable $r2, $cpsr = tEOR killed renamable $r2, renamable $r1, 14 /* CC::always */, $noreg t2Bcc %bb.4, 0 /* CC:eq */, killed $cpsr This shows that MachineOperand comments are enclosed between /* and */. In this example, the EOR instruction is not conditionally executed (i.e. it is "always executed"), which is encoded by the 14 immediate machine operand. Thus, now this machine operand has /* CC::always */ as a comment. The 0 on the next conditional branch instruction represents the equal condition code, thus now this operand has /* CC:eq */ as a comment. As it is a comment, the MI lexer/parser completely ignores it. The benefit is that this keeps the change in the lexer extremely minimal and no target specific parsing needs to be done. The changes on the MIPrinter side are also minimal, as there is only one target hooks that is used to create the machine operand comments. Differential Revision: https://reviews.llvm.org/D74306
2020-02-24 22:19:21 +08:00
; CHECK: renamable $r12 = t2LDRi12 $r7, 16, 14 /* CC::al */, $noreg :: (load 4 from %fixed-stack.2)
; CHECK: renamable $lr = t2LDRi12 $r7, 12, 14 /* CC::al */, $noreg :: (load 4 from %fixed-stack.1)
; CHECK: renamable $r3 = t2LDRi12 $r7, 8, 14 /* CC::al */, $noreg :: (load 4 from %fixed-stack.0)
[ARM] Reegenerate MVE tests. NFC The mve-phireg.ll test no longer really tests what it was added for, but the original case was fairly complex. I've left the test in as a general codegen test.
2020-01-15 15:50:14 +08:00
; CHECK: BUNDLE implicit-def $vpr, implicit-def dead $q0, implicit-def $d0, implicit-def $s0, implicit-def $s1, implicit-def $d1, implicit-def $s2, implicit-def $s3, implicit $q0, implicit $zr, implicit killed $r0, implicit killed $r3, implicit killed $r1, implicit killed $lr {
; CHECK: MVE_VPTv4f32r 1, renamable $q0, $zr, 10, implicit-def $vpr
; CHECK: renamable $q0 = MVE_VLDRWU32 killed renamable $r0, 0, 1, internal renamable $vpr :: (load 16 from %ir.src, align 4)
; CHECK: MVE_VSTRWU32 internal killed renamable $q0, killed renamable $r3, 0, 1, internal renamable $vpr :: (store 16 into %ir.dest, align 4)
; CHECK: renamable $q0 = MVE_VLDRWU32 killed renamable $r1, 0, 1, internal renamable $vpr :: (load 16 from %ir.src2, align 4)
; CHECK: MVE_VSTRWU32 internal killed renamable $q0, killed renamable $lr, 0, 1, internal renamable $vpr :: (store 16 into %ir.dest2, align 4)
; CHECK: }
; CHECK: BUNDLE implicit-def $q0, implicit-def $d0, implicit-def $s0, implicit-def $s1, implicit-def $d1, implicit-def $s2, implicit-def $s3, implicit killed $vpr, implicit killed $r2, implicit killed $r12 {
; CHECK: MVE_VPST 4, implicit $vpr
; CHECK: renamable $q0 = MVE_VLDRWU32 killed renamable $r2, 0, 1, renamable $vpr :: (load 16 from %ir.src3, align 4)
; CHECK: MVE_VSTRWU32 internal renamable $q0, killed renamable $r12, 0, 1, killed renamable $vpr :: (store 16 into %ir.dest3, align 4)
; CHECK: }
[MIR][ARM] MachineOperand comments This adds infrastructure to print and parse MIR MachineOperand comments. The motivation for the ARM backend is to print condition code names instead of magic constants that are difficult to read (for human beings). For example, instead of this: dead renamable $r2, $cpsr = tEOR killed renamable $r2, renamable $r1, 14, $noreg t2Bcc %bb.4, 0, killed $cpsr we now print this: dead renamable $r2, $cpsr = tEOR killed renamable $r2, renamable $r1, 14 /* CC::always */, $noreg t2Bcc %bb.4, 0 /* CC:eq */, killed $cpsr This shows that MachineOperand comments are enclosed between /* and */. In this example, the EOR instruction is not conditionally executed (i.e. it is "always executed"), which is encoded by the 14 immediate machine operand. Thus, now this machine operand has /* CC::always */ as a comment. The 0 on the next conditional branch instruction represents the equal condition code, thus now this operand has /* CC:eq */ as a comment. As it is a comment, the MI lexer/parser completely ignores it. The benefit is that this keeps the change in the lexer extremely minimal and no target specific parsing needs to be done. The changes on the MIPrinter side are also minimal, as there is only one target hooks that is used to create the machine operand comments. Differential Revision: https://reviews.llvm.org/D74306
2020-02-24 22:19:21 +08:00
; CHECK: $sp = t2LDMIA_RET $sp, 14 /* CC::al */, $noreg, def $r7, def $pc, implicit $q0
[ARM][MVE] VPT Blocks: findVCMPToFoldIntoVPS This is a recommit of D71330, but with a few things fixed and changed: 1) ReachingDefAnalysis: this was not running with optnone as it was checking skipFunction(), which other analysis passes don't do. I guess this is a copy-paste from a codegen pass. 2) VPTBlockPass: here I've added skipFunction(), because like most/all optimisations, we don't want to run this with optnone. This fixes the issues with the initial/previous commit: the VPTBlockPass was running with optnone, but ReachingDefAnalysis wasn't, and so VPTBlockPass was crashing querying ReachingDefAnalysis. I've added test case mve-vpt-block-optnone.mir to check that we don't run VPTBlock with optnone. Differential Revision: https://reviews.llvm.org/D71470
2020-01-07 21:54:47 +08:00
$sp = frame-setup t2STMDB_UPD $sp, 14, $noreg, killed $r7, killed $lr
frame-setup CFI_INSTRUCTION def_cfa_offset 8
frame-setup CFI_INSTRUCTION offset $lr, -4
frame-setup CFI_INSTRUCTION offset $r7, -8
$r7 = frame-setup tMOVr killed $sp, 14, $noreg
frame-setup CFI_INSTRUCTION def_cfa_register $r7
renamable $r12 = t2LDRi12 $r7, 16, 14, $noreg :: (load 4 from %fixed-stack.1)
renamable $lr = t2LDRi12 $r7, 12, 14, $noreg :: (load 4 from %fixed-stack.2)
renamable $r3 = t2LDRi12 $r7, 8, 14, $noreg :: (load 4 from %fixed-stack.3)
renamable $vpr = MVE_VCMPf32r renamable $q0, $zr, 10, 0, $noreg
renamable $q0 = MVE_VLDRWU32 killed renamable $r0, 0, 1, renamable $vpr :: (load 16 from %ir.src, align 4)
MVE_VSTRWU32 killed renamable $q0, killed renamable $r3, 0, 1, renamable $vpr :: (store 16 into %ir.dest, align 4)
renamable $q0 = MVE_VLDRWU32 killed renamable $r1, 0, 1, renamable $vpr :: (load 16 from %ir.src2, align 4)
MVE_VSTRWU32 killed renamable $q0, killed renamable $lr, 0, 1, renamable $vpr :: (store 16 into %ir.dest2, align 4)
renamable $q0 = MVE_VLDRWU32 killed renamable $r2, 0, 1, renamable $vpr :: (load 16 from %ir.src3, align 4)
MVE_VSTRWU32 renamable $q0, killed renamable $r12, 0, 1, killed renamable $vpr :: (store 16 into %ir.dest3, align 4)
$sp = t2LDMIA_RET $sp, 14, $noreg, def $r7, def $pc, implicit $q0
...