caio/clang-p2996
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
be1294de9dd93ae02002bd1aa4b4a8d62e562c21
clang-p2996/llvm/test/CodeGen/Thumb2/LowOverheadLoops/safe-retaining.mir
David Green 9cb8f4d1ad [ARM] Add a tail-predication loop predicate register 
The semantics of tail predication loops means that the value of LR as an
instruction is executed determines the predicate. In other words:

mov r3, #3
DLSTP lr, r3        // Start tail predication, lr==3
VADD.s32 q0, q1, q2 // Lanes 0,1 and 2 are updated in q0.
mov lr, #1
VADD.s32 q0, q1, q2 // Only first lane is updated.

This means that the value of lr cannot be spilled and re-used in tail
predication regions without potentially altering the behaviour of the
program. More lanes than required could be stored, for example, and in
the case of a gather those lanes might not have been setup, leading to
alignment exceptions.

This patch adds a new lr predicate operand to MVE instructions in order
to keep a reference to the lr that they use as a tail predicate. It will
usually hold the zeroreg meaning not predicated, being set to the LR phi
value in the MVETPAndVPTOptimisationsPass. This will prevent it from
being spilled anywhere that it needs to be used.

A lot of tests needed updating.

Differential Revision: https://reviews.llvm.org/D107638
2021-09-02 13:42:58 +01:00

290 lines
15 KiB
YAML
Raw Blame History

# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -mtriple=thumbv8.1m.main -mattr=+mve -run-pass=arm-low-overhead-loops %s -o - | FileCheck %s
--- |
define arm_aapcs_vfpcc void @test_vqrshruntq_n_s32(<4 x i32>* %a, <4 x i32>* %b, <4 x i32>* %c, i32 %elts, i32 %iters) {
entry:
%cmp = icmp slt i32 %elts, 1
br i1 %cmp, label %exit, label %loop.ph
loop.ph: ; preds = %entry
%start = call i32 @llvm.start.loop.iterations.i32(i32 %iters)
br label %loop.body
loop.body: ; preds = %loop.body, %loop.ph
%lsr.iv = phi i32 [ %lsr.iv.next, %loop.body ], [ %start, %loop.ph ]
%count = phi i32 [ %elts, %loop.ph ], [ %elts.rem, %loop.body ]
%addr.a = phi <4 x i32>* [ %a, %loop.ph ], [ %addr.a.next, %loop.body ]
%addr.b = phi <4 x i32>* [ %b, %loop.ph ], [ %addr.b.next, %loop.body ]
%addr.c = phi <4 x i32>* [ %c, %loop.ph ], [ %addr.c.next, %loop.body ]
%pred = call <4 x i1> @llvm.arm.mve.vctp32(i32 %count)
%elts.rem = sub i32 %count, 4
%masked.load.a = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %addr.a, i32 4, <4 x i1> %pred, <4 x i32> undef)
%masked.load.b = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %addr.b, i32 4, <4 x i1> %pred, <4 x i32> undef)
%bitcast.a = bitcast <4 x i32> %masked.load.a to <8 x i16>
%shrn = call <8 x i16> @llvm.arm.mve.vshrn.v8i16.v4i32(<8 x i16> %bitcast.a, <4 x i32> %masked.load.b, i32 3, i32 1, i32 0, i32 1, i32 0, i32 1)
%bitcast = bitcast <8 x i16> %shrn to <4 x i32>
call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %bitcast, <4 x i32>* %addr.c, i32 4, <4 x i1> %pred)
%addr.a.next = getelementptr <4 x i32>, <4 x i32>* %addr.a, i32 1
%addr.b.next = getelementptr <4 x i32>, <4 x i32>* %addr.b, i32 1
%addr.c.next = getelementptr <4 x i32>, <4 x i32>* %addr.c, i32 1
%loop.dec = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %lsr.iv, i32 1)
%end = icmp ne i32 %loop.dec, 0
%lsr.iv.next = add i32 %lsr.iv, -1
br i1 %end, label %loop.body, label %exit
exit: ; preds = %loop.body, %entry
ret void
}
define arm_aapcs_vfpcc void @test_vqrshruntq_n_s16(<8 x i16>* %a, <8 x i16>* %b, <8 x i16>* %c, i32 %elts, i32 %iters) {
entry:
%cmp = icmp slt i32 %elts, 1
br i1 %cmp, label %exit, label %loop.ph
loop.ph: ; preds = %entry
%start = call i32 @llvm.start.loop.iterations.i32(i32 %iters)
br label %loop.body
loop.body: ; preds = %loop.body, %loop.ph
%lsr.iv = phi i32 [ %lsr.iv.next, %loop.body ], [ %start, %loop.ph ]
%count = phi i32 [ %elts, %loop.ph ], [ %elts.rem, %loop.body ]
%addr.a = phi <8 x i16>* [ %a, %loop.ph ], [ %addr.a.next, %loop.body ]
%addr.b = phi <8 x i16>* [ %b, %loop.ph ], [ %addr.b.next, %loop.body ]
%addr.c = phi <8 x i16>* [ %c, %loop.ph ], [ %addr.c.next, %loop.body ]
%pred = call <8 x i1> @llvm.arm.mve.vctp16(i32 %count)
%elts.rem = sub i32 %count, 8
%masked.load.a = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>* %addr.a, i32 2, <8 x i1> %pred, <8 x i16> undef)
%masked.load.b = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>* %addr.b, i32 2, <8 x i1> %pred, <8 x i16> undef)
%bitcast.a = bitcast <8 x i16> %masked.load.a to <16 x i8>
%shrn = call <16 x i8> @llvm.arm.mve.vshrn.v16i8.v8i16(<16 x i8> %bitcast.a, <8 x i16> %masked.load.b, i32 1, i32 1, i32 0, i32 1, i32 0, i32 1)
%bitcast = bitcast <16 x i8> %shrn to <8 x i16>
call void @llvm.masked.store.v8i16.p0v8i16(<8 x i16> %bitcast, <8 x i16>* %addr.c, i32 2, <8 x i1> %pred)
%addr.a.next = getelementptr <8 x i16>, <8 x i16>* %addr.b, i32 1
%addr.b.next = getelementptr <8 x i16>, <8 x i16>* %addr.b, i32 1
%addr.c.next = getelementptr <8 x i16>, <8 x i16>* %addr.c, i32 1
%loop.dec = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %lsr.iv, i32 1)
%end = icmp ne i32 %loop.dec, 0
%lsr.iv.next = add i32 %lsr.iv, -1
br i1 %end, label %loop.body, label %exit
exit: ; preds = %loop.body, %entry
ret void
}
declare i32 @llvm.start.loop.iterations.i32(i32)
declare i32 @llvm.loop.decrement.reg.i32.i32.i32(i32, i32)
declare <4 x i1> @llvm.arm.mve.vctp32(i32)
declare <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>*, i32 immarg, <4 x i1>, <4 x i32>)
declare void @llvm.masked.store.v4i32.p0v4i32(<4 x i32>, <4 x i32>*, i32 immarg, <4 x i1>)
declare <8 x i16> @llvm.arm.mve.vshrn.v8i16.v4i32(<8 x i16>, <4 x i32>, i32, i32, i32, i32, i32, i32)
declare <8 x i1> @llvm.arm.mve.vctp16(i32)
declare <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>*, i32 immarg, <8 x i1>, <8 x i16>)
declare void @llvm.masked.store.v8i16.p0v8i16(<8 x i16>, <8 x i16>*, i32 immarg, <8 x i1>)
declare <16 x i8> @llvm.arm.mve.vshrn.v16i8.v8i16(<16 x i8>, <8 x i16>, i32, i32, i32, i32, i32, i32)
...
---
name: test_vqrshruntq_n_s32
alignment: 2
tracksRegLiveness: true
registers: []
liveins:
- { reg: '$r0', virtual-reg: '' }
- { reg: '$r1', virtual-reg: '' }
- { reg: '$r2', virtual-reg: '' }
- { reg: '$r3', virtual-reg: '' }
frameInfo:
stackSize: 8
offsetAdjustment: 0
maxAlignment: 4
restorePoint: ''
fixedStack:
- { id: 0, 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: '$lr', callee-saved-restored: false,
debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
- { id: 1, name: '', type: spill-slot, offset: -8, size: 4, alignment: 4,
stack-id: default, callee-saved-register: '$r4', callee-saved-restored: true,
debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
callSites: []
constants: []
machineFunctionInfo: {}
body: |
; CHECK-LABEL: name: test_vqrshruntq_n_s32
; CHECK: bb.0.entry:
; CHECK: successors: %bb.1(0x80000000)
; CHECK: liveins: $lr, $r0, $r1, $r2, $r3, $r4
; CHECK: frame-setup tPUSH 14 /* CC::al */, $noreg, killed $r4, killed $lr, implicit-def $sp, implicit $sp
; CHECK: frame-setup CFI_INSTRUCTION def_cfa_offset 8
; CHECK: frame-setup CFI_INSTRUCTION offset $lr, -4
; CHECK: frame-setup CFI_INSTRUCTION offset $r4, -8
; CHECK: tCMPi8 renamable $r3, 1, 14 /* CC::al */, $noreg, implicit-def $cpsr
; CHECK: t2IT 11, 8, implicit-def $itstate
; CHECK: tPOP_RET 11 /* CC::lt */, killed $cpsr, def $r4, def $pc, implicit killed $itstate
; CHECK: bb.1.loop.ph:
; CHECK: successors: %bb.2(0x80000000)
; CHECK: liveins: $r0, $r1, $r2, $r3
; CHECK: renamable $r4 = tLDRspi $sp, 2, 14 /* CC::al */, $noreg :: (load (s32) from %fixed-stack.0, align 8)
; CHECK: dead $lr = MVE_DLSTP_32 killed renamable $r3
; CHECK: $r12 = tMOVr killed $r4, 14 /* CC::al */, $noreg
; CHECK: bb.2.loop.body:
; CHECK: successors: %bb.2(0x7c000000), %bb.3(0x04000000)
; CHECK: liveins: $r0, $r1, $r2, $r12
; CHECK: $lr = tMOVr $r12, 14 /* CC::al */, $noreg
; CHECK: renamable $r12 = t2SUBri killed $r12, 1, 14 /* CC::al */, $noreg, $noreg
; CHECK: renamable $r1, renamable $q0 = MVE_VLDRWU32_post killed renamable $r1, 16, 0, $noreg, $noreg :: (load (s128) from %ir.addr.b, align 4)
; CHECK: renamable $r0, renamable $q1 = MVE_VLDRWU32_post killed renamable $r0, 16, 0, $noreg, $noreg :: (load (s128) from %ir.addr.a, align 4)
; CHECK: renamable $q1 = MVE_VQSHRUNs32th killed renamable $q1, killed renamable $q0, 3, 0, $noreg, $noreg
; CHECK: renamable $r2 = MVE_VSTRWU32_post killed renamable $q1, killed renamable $r2, 16, 0, killed $noreg, $noreg :: (store (s128) into %ir.addr.c, align 4)
; CHECK: dead $lr = MVE_LETP killed renamable $lr, %bb.2
; CHECK: bb.3.exit:
; CHECK: tPOP_RET 14 /* CC::al */, $noreg, def $r4, def $pc
bb.0.entry:
successors: %bb.1(0x80000000)
liveins: $r0, $r1, $r2, $r3, $r4, $lr
frame-setup tPUSH 14 /* CC::al */, $noreg, killed $r4, killed $lr, implicit-def $sp, implicit $sp
frame-setup CFI_INSTRUCTION def_cfa_offset 8
frame-setup CFI_INSTRUCTION offset $lr, -4
frame-setup CFI_INSTRUCTION offset $r4, -8
tCMPi8 renamable $r3, 1, 14 /* CC::al */, $noreg, implicit-def $cpsr
t2IT 11, 8, implicit-def $itstate
tPOP_RET 11 /* CC::lt */, killed $cpsr, def $r4, def $pc, implicit killed $itstate
bb.1.loop.ph:
successors: %bb.2(0x80000000)
liveins: $r0, $r1, $r2, $r3, $r4, $lr
renamable $r4 = tLDRspi $sp, 2, 14 /* CC::al */, $noreg :: (load (s32) from %fixed-stack.0, align 8)
$lr = t2DoLoopStart renamable $r4
$r12 = tMOVr killed $r4, 14 /* CC::al */, $noreg
bb.2.loop.body:
successors: %bb.2(0x7c000000), %bb.3(0x04000000)
liveins: $r0, $r1, $r2, $r3, $r12
renamable $vpr = MVE_VCTP32 renamable $r3, 0, $noreg, $noreg
$lr = tMOVr $r12, 14 /* CC::al */, $noreg
renamable $r12 = t2SUBri killed $r12, 1, 14 /* CC::al */, $noreg, $noreg
renamable $r3, dead $cpsr = tSUBi8 killed renamable $r3, 4, 14 /* CC::al */, $noreg
MVE_VPST 4, implicit $vpr
renamable $r1, renamable $q0 = MVE_VLDRWU32_post killed renamable $r1, 16, 1, renamable $vpr, $noreg :: (load (s128) from %ir.addr.b, align 4)
renamable $r0, renamable $q1 = MVE_VLDRWU32_post killed renamable $r0, 16, 1, renamable $vpr, $noreg :: (load (s128) from %ir.addr.a, align 4)
renamable $lr = t2LoopDec killed renamable $lr, 1
renamable $q1 = MVE_VQSHRUNs32th killed renamable $q1, killed renamable $q0, 3, 0, $noreg, $noreg
MVE_VPST 8, implicit $vpr
renamable $r2 = MVE_VSTRWU32_post killed renamable $q1, killed renamable $r2, 16, 1, killed renamable $vpr, $noreg :: (store (s128) into %ir.addr.c, align 4)
t2LoopEnd killed renamable $lr, %bb.2, implicit-def dead $cpsr
tB %bb.3, 14 /* CC::al */, $noreg
bb.3.exit:
tPOP_RET 14 /* CC::al */, $noreg, def $r4, def $pc
...
---
name: test_vqrshruntq_n_s16
alignment: 2
tracksRegLiveness: true
registers: []
liveins:
- { reg: '$r0', virtual-reg: '' }
- { reg: '$r1', virtual-reg: '' }
- { reg: '$r2', virtual-reg: '' }
- { reg: '$r3', virtual-reg: '' }
frameInfo:
stackSize: 8
offsetAdjustment: 0
maxAlignment: 4
fixedStack:
- { id: 0, type: default, offset: 0, size: 4, alignment: 8, stack-id: default,
isImmutable: true, isAliased: false, callee-saved-register: '', callee-saved-restored: true,
debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
stack:
- { id: 0, name: '', type: spill-slot, offset: -4, size: 4, alignment: 4,
stack-id: default, callee-saved-register: '$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: '$r4', callee-saved-restored: true,
debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
callSites: []
constants: []
machineFunctionInfo: {}
body: |
; CHECK-LABEL: name: test_vqrshruntq_n_s16
; CHECK: bb.0.entry:
; CHECK: successors: %bb.1(0x80000000)
; CHECK: liveins: $lr, $r0, $r1, $r2, $r3, $r4
; CHECK: frame-setup tPUSH 14 /* CC::al */, $noreg, killed $r4, killed $lr, implicit-def $sp, implicit $sp
; CHECK: frame-setup CFI_INSTRUCTION def_cfa_offset 8
; CHECK: frame-setup CFI_INSTRUCTION offset $lr, -4
; CHECK: frame-setup CFI_INSTRUCTION offset $r4, -8
; CHECK: tCMPi8 renamable $r3, 1, 14 /* CC::al */, $noreg, implicit-def $cpsr
; CHECK: t2IT 11, 8, implicit-def $itstate
; CHECK: tPOP_RET 11 /* CC::lt */, killed $cpsr, def $r4, def $pc, implicit killed $itstate
; CHECK: bb.1.loop.ph:
; CHECK: successors: %bb.2(0x80000000)
; CHECK: liveins: $r0, $r1, $r2, $r3
; CHECK: renamable $r12 = t2LDRi12 $sp, 8, 14 /* CC::al */, $noreg :: (load (s32) from %fixed-stack.0, align 8)
; CHECK: dead $lr = MVE_DLSTP_16 killed renamable $r3
; CHECK: $r4 = tMOVr killed $r12, 14 /* CC::al */, $noreg
; CHECK: bb.2.loop.body:
; CHECK: successors: %bb.2(0x7c000000), %bb.3(0x04000000)
; CHECK: liveins: $r0, $r1, $r2, $r4
; CHECK: $lr = tMOVr $r4, 14 /* CC::al */, $noreg
; CHECK: renamable $r4, dead $cpsr = tSUBi8 killed $r4, 1, 14 /* CC::al */, $noreg
; CHECK: renamable $r1, renamable $q0 = MVE_VLDRHU16_post killed renamable $r1, 16, 0, $noreg, $noreg :: (load (s128) from %ir.addr.b, align 2)
; CHECK: renamable $q1 = MVE_VLDRHU16 killed renamable $r0, 0, 0, $noreg, $noreg :: (load (s128) from %ir.addr.a, align 2)
; CHECK: $r0 = tMOVr $r1, 14 /* CC::al */, $noreg
; CHECK: renamable $q1 = MVE_VQSHRUNs16th killed renamable $q1, killed renamable $q0, 1, 0, $noreg, $noreg
; CHECK: renamable $r2 = MVE_VSTRHU16_post killed renamable $q1, killed renamable $r2, 16, 0, killed $noreg, $noreg :: (store (s128) into %ir.addr.c, align 2)
; CHECK: dead $lr = MVE_LETP killed renamable $lr, %bb.2
; CHECK: bb.3.exit:
; CHECK: tPOP_RET 14 /* CC::al */, $noreg, def $r4, def $pc
bb.0.entry:
successors: %bb.1(0x80000000)
liveins: $r0, $r1, $r2, $r3, $r4, $lr
frame-setup tPUSH 14 /* CC::al */, $noreg, killed $r4, killed $lr, implicit-def $sp, implicit $sp
frame-setup CFI_INSTRUCTION def_cfa_offset 8
frame-setup CFI_INSTRUCTION offset $lr, -4
frame-setup CFI_INSTRUCTION offset $r4, -8
tCMPi8 renamable $r3, 1, 14 /* CC::al */, $noreg, implicit-def $cpsr
t2IT 11, 8, implicit-def $itstate
tPOP_RET 11 /* CC::lt */, killed $cpsr, def $r4, def $pc, implicit killed $itstate
bb.1.loop.ph:
successors: %bb.2(0x80000000)
liveins: $r0, $r1, $r2, $r3, $r4, $lr
renamable $r12 = t2LDRi12 $sp, 8, 14 /* CC::al */, $noreg :: (load (s32) from %fixed-stack.0, align 8)
$lr = t2DoLoopStart renamable $r12
$r4 = tMOVr killed $r12, 14 /* CC::al */, $noreg
bb.2.loop.body:
successors: %bb.2(0x7c000000), %bb.3(0x04000000)
liveins: $r0, $r1, $r2, $r3, $r4
renamable $vpr = MVE_VCTP16 renamable $r3, 0, $noreg, $noreg
$lr = tMOVr $r4, 14 /* CC::al */, $noreg
renamable $r4, dead $cpsr = tSUBi8 killed $r4, 1, 14 /* CC::al */, $noreg
renamable $r3, dead $cpsr = tSUBi8 killed renamable $r3, 8, 14 /* CC::al */, $noreg
MVE_VPST 4, implicit $vpr
renamable $r1, renamable $q0 = MVE_VLDRHU16_post killed renamable $r1, 16, 1, renamable $vpr, $noreg :: (load (s128) from %ir.addr.b, align 2)
renamable $q1 = MVE_VLDRHU16 killed renamable $r0, 0, 1, renamable $vpr, $noreg :: (load (s128) from %ir.addr.a, align 2)
renamable $lr = t2LoopDec killed renamable $lr, 1
$r0 = tMOVr $r1, 14 /* CC::al */, $noreg
renamable $q1 = MVE_VQSHRUNs16th killed renamable $q1, killed renamable $q0, 1, 0, $noreg, $noreg
MVE_VPST 8, implicit $vpr
renamable $r2 = MVE_VSTRHU16_post killed renamable $q1, killed renamable $r2, 16, 1, killed renamable $vpr, $noreg :: (store (s128) into %ir.addr.c, align 2)
t2LoopEnd killed renamable $lr, %bb.2, implicit-def dead $cpsr
tB %bb.3, 14 /* CC::al */, $noreg
bb.3.exit:
tPOP_RET 14 /* CC::al */, $noreg, def $r4, def $pc
...
Reference in New Issue View Git Blame Copy Permalink