1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-01-31 20:51:52 +01:00

AArch64LoadStoreOptimizer: Update kill flags when merging stores

Kill flags need to be updated correctly when moving stores up/down to
form store pair instructions.
Those invalid flags have been ignored before but as of r290014 they are
recognized when using -mllvm -verify-machineinstrs.

Also simplifies test/CodeGen/AArch64/ldst-opt-dbg-limit.mir, renames it
to ldst-opt.mir test and adds a new tests for this change.

Differential Revision: https://reviews.llvm.org/D28875

llvm-svn: 292625
This commit is contained in:
Matthias Braun 2017-01-20 18:04:27 +00:00
parent 71a39ada7d
commit e7959a23ac
3 changed files with 155 additions and 135 deletions

View File

@ -687,9 +687,30 @@ AArch64LoadStoreOpt::mergePairedInsns(MachineBasicBlock::iterator I,
MachineInstrBuilder MIB;
DebugLoc DL = I->getDebugLoc();
MachineBasicBlock *MBB = I->getParent();
MachineOperand RegOp0 = getLdStRegOp(*RtMI);
MachineOperand RegOp1 = getLdStRegOp(*Rt2MI);
// Kill flags may become invalid when moving stores for pairing.
if (RegOp0.isUse()) {
if (!MergeForward) {
// Clear kill flags on store if moving upwards. Example:
// STRWui %w0, ...
// USE %w1
// STRWui kill %w1 ; need to clear kill flag when moving STRWui upwards
RegOp0.setIsKill(false);
RegOp1.setIsKill(false);
} else {
// Clear kill flags of the first stores register. Example:
// STRWui %w1, ...
// USE kill %w1 ; need to clear kill flag when moving STRWui downwards
// STRW %w0
unsigned Reg = getLdStRegOp(*I).getReg();
for (MachineInstr &MI : make_range(std::next(I), Paired))
MI.clearRegisterKills(Reg, TRI);
}
}
MIB = BuildMI(*MBB, InsertionPoint, DL, TII->get(getMatchingPairOpcode(Opc)))
.add(getLdStRegOp(*RtMI))
.add(getLdStRegOp(*Rt2MI))
.add(RegOp0)
.add(RegOp1)
.add(BaseRegOp)
.addImm(OffsetImm)
.setMemRefs(I->mergeMemRefsWith(*Paired));

View File

@ -1,133 +0,0 @@
# RUN: llc -run-pass=aarch64-ldst-opt %s -o - 2>&1 | FileCheck %s
--- |
target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
target triple = "aarch64--linux-gnu"
; Function Attrs: nounwind
define i16 @promote-load-from-store(i32* %dst, i32 %x) #0 {
store i32 %x, i32* %dst
%dst16 = bitcast i32* %dst to i16*
%dst1 = getelementptr inbounds i16, i16* %dst16, i32 1
%x16 = load i16, i16* %dst1
ret i16 %x16
}
; Function Attrs: nounwind
define void @store-pair(i32* %dst, i32 %x, i32 %y) #0 {
%dst01 = bitcast i32* %dst to i32*
%dst1 = getelementptr inbounds i32, i32* %dst, i32 1
store i32 %x, i32* %dst01
store i32 %x, i32* %dst1
ret void
}
attributes #0 = { nounwind }
...
---
name: promote-load-from-store
alignment: 2
exposesReturnsTwice: false
tracksRegLiveness: true
liveins:
- { reg: '%x0' }
- { reg: '%w1' }
frameInfo:
isFrameAddressTaken: false
isReturnAddressTaken: false
hasStackMap: false
hasPatchPoint: false
stackSize: 0
offsetAdjustment: 0
maxAlignment: 0
adjustsStack: false
hasCalls: false
maxCallFrameSize: 0
hasOpaqueSPAdjustment: false
hasVAStart: false
hasMustTailInVarArgFunc: false
body: |
bb.0 (%ir-block.0):
liveins: %w1, %x0, %lr
STRWui killed %w1, %x0, 0 :: (store 4 into %ir.dst)
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
%w0 = LDRHHui killed %x0, 1 :: (load 2 from %ir.dst1)
RET %lr, implicit %w0
...
# CHECK-LABEL: name: promote-load-from-store
# CHECK: STRWui %w1
# CHECK: UBFMWri %w1
---
name: store-pair
alignment: 2
exposesReturnsTwice: false
tracksRegLiveness: true
liveins:
- { reg: '%x0' }
- { reg: '%w1' }
frameInfo:
isFrameAddressTaken: false
isReturnAddressTaken: false
hasStackMap: false
hasPatchPoint: false
stackSize: 0
offsetAdjustment: 0
maxAlignment: 0
adjustsStack: false
hasCalls: false
maxCallFrameSize: 0
hasOpaqueSPAdjustment: false
hasVAStart: false
hasMustTailInVarArgFunc: false
body: |
bb.0 (%ir-block.0):
liveins: %w1, %x0, %lr
STRWui %w1, %x0, 0 :: (store 4 into %ir.dst01)
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
STRWui killed %w1, killed %x0, 1 :: (store 4 into %ir.dst1)
RET %lr
...
# CHECK-LABEL: name: store-pair
# CHECK: STPWi

View File

@ -0,0 +1,132 @@
# RUN: llc -mtriple=aarch64--linux-gnu -run-pass=aarch64-ldst-opt %s -verify-machineinstrs -o - 2>&1 | FileCheck %s
--- |
define void @promote-load-from-store() { ret void }
define void @store-pair() { ret void }
define void @store-pair-clearkill0() { ret void }
define void @store-pair-clearkill1() { ret void }
...
---
name: promote-load-from-store
tracksRegLiveness: true
body: |
bb.0:
liveins: %w1, %x0, %lr
STRWui killed %w1, %x0, 0 :: (store 4)
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
%w0 = LDRHHui killed %x0, 1 :: (load 2)
RET %lr, implicit %w0
...
# Don't count transient instructions towards search limits.
# CHECK-LABEL: name: promote-load-from-store
# CHECK: STRWui %w1
# CHECK: UBFMWri %w1
---
name: store-pair
tracksRegLiveness: true
body: |
bb.0:
liveins: %w1, %x0, %lr
STRWui %w1, %x0, 0 :: (store 4)
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
CFI_INSTRUCTION 0
STRWui killed %w1, killed %x0, 1 :: (store 4)
RET %lr
...
# CHECK-LABEL: name: store-pair
# CHECK: STPWi
---
name: store-pair-clearkill0
tracksRegLiveness: true
body: |
bb.0:
liveins: %w1, %x0, %lr
STRWui %w1, %x0, 0 :: (store 4)
%w2 = COPY %w1
%x3 = COPY %x0
STRWui killed %w1, killed %x0, 1 :: (store 4)
RET %lr
...
# When merging a lower store with an upper one, we must clear kill flags on
# the lower store.
# CHECK-LABEL: store-pair-clearkill0
# CHECK-NOT: STPWi %w1, killed %w1, %x0, 0 :: (store 4)
# CHECK: STPWi %w1, %w1, %x0, 0 :: (store 4)
# CHECK: %w2 = COPY %w1
# CHECK: RET %lr
---
name: store-pair-clearkill1
tracksRegLiveness: true
body: |
bb.0:
liveins: %x0, %lr
%w1 = MOVi32imm 13
%w2 = MOVi32imm 7
STRWui %w1, %x0, 1 :: (store 4)
%w2 = COPY killed %w1
STRWui killed %w2, %x0, 0 :: (store 4)
%w1 = MOVi32imm 42
%w2 = MOVi32imm 7
STRWui %w1, %x0, 0 :: (store 4)
%w2 = COPY killed %w1
STRWui killed %w2, killed %x0, 1 :: (store 4)
RET %lr
...
# When merging an upper store with a lower one, kill flags along the way need
# to be removed; In this case the kill flag on %w1.
# CHECK-LABEL: store-pair-clearkill1
# CHECK: %w1 = MOVi32imm
# CHECK: %w2 = MOVi32imm
# CHECK-NOT: %w2 = COPY killed %w1
# CHECK: %w2 = COPY %w1
# CHECK: STPWi killed %w2, %w1, %x0, 0
# CHECK: %w1 = MOVi32imm
# CHECK: %w2 = MOVi32imm
# CHECK-NOT: %w2 = COPY killed %w1
# CHECK: %w2 = COPY %w1
# CHECK: STPWi %w1, killed %w2, killed %x0, 0