[MTE] Handle MTE instructions in AArch64LoadStoreOptimizer.

Summary: Generate pre- and post-indexed forms of ST*G and STGP when possible.

Reviewers: ostannard, vitalybuka

Subscribers: kristof.beyls, hiraditya, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D67741

llvm-svn: 372412
This commit is contained in:
Evgeniy Stepanov 2019-09-20 17:36:27 +00:00
parent 330014843c
commit c2bda3e422
3 changed files with 384 additions and 33 deletions
llvm
lib/Target/AArch64
test/CodeGen/AArch64

View File

@ -201,8 +201,22 @@ static bool isNarrowStore(unsigned Opc) {
}
}
// These instruction set memory tag and either keep memory contents unchanged or
// set it to zero, ignoring the address part of the source register.
static bool isTagStore(const MachineInstr &MI) {
switch (MI.getOpcode()) {
default:
return false;
case AArch64::STGOffset:
case AArch64::STZGOffset:
case AArch64::ST2GOffset:
case AArch64::STZ2GOffset:
return true;
}
}
// Scaling factor for unscaled load or store.
static int getMemScale(MachineInstr &MI) {
static int getMemScale(const MachineInstr &MI) {
switch (MI.getOpcode()) {
default:
llvm_unreachable("Opcode has unknown scale!");
@ -255,6 +269,11 @@ static int getMemScale(MachineInstr &MI) {
case AArch64::STURQi:
case AArch64::LDPQi:
case AArch64::STPQi:
case AArch64::STGOffset:
case AArch64::STZGOffset:
case AArch64::ST2GOffset:
case AArch64::STZ2GOffset:
case AArch64::STGPi:
return 16;
}
}
@ -449,6 +468,16 @@ static unsigned getPreIndexedOpcode(unsigned Opc) {
return AArch64::STPWpre;
case AArch64::STPXi:
return AArch64::STPXpre;
case AArch64::STGOffset:
return AArch64::STGPreIndex;
case AArch64::STZGOffset:
return AArch64::STZGPreIndex;
case AArch64::ST2GOffset:
return AArch64::ST2GPreIndex;
case AArch64::STZ2GOffset:
return AArch64::STZ2GPreIndex;
case AArch64::STGPi:
return AArch64::STGPpre;
}
}
@ -518,6 +547,16 @@ static unsigned getPostIndexedOpcode(unsigned Opc) {
return AArch64::STPWpost;
case AArch64::STPXi:
return AArch64::STPXpost;
case AArch64::STGOffset:
return AArch64::STGPostIndex;
case AArch64::STZGOffset:
return AArch64::STZGPostIndex;
case AArch64::ST2GOffset:
return AArch64::ST2GPostIndex;
case AArch64::STZ2GOffset:
return AArch64::STZ2GPostIndex;
case AArch64::STGPi:
return AArch64::STGPpost;
}
}
@ -536,10 +575,30 @@ static bool isPairedLdSt(const MachineInstr &MI) {
case AArch64::STPQi:
case AArch64::STPWi:
case AArch64::STPXi:
case AArch64::STGPi:
return true;
}
}
// Returns the scale and offset range of pre/post indexed variants of MI.
static void getPrePostIndexedMemOpInfo(const MachineInstr &MI, int &Scale,
int &MinOffset, int &MaxOffset) {
bool IsPaired = isPairedLdSt(MI);
bool IsTagStore = isTagStore(MI);
// ST*G and all paired ldst have the same scale in pre/post-indexed variants
// as in the "unsigned offset" variant.
// All other pre/post indexed ldst instructions are unscaled.
Scale = (IsTagStore || IsPaired) ? getMemScale(MI) : 1;
if (IsPaired) {
MinOffset = -64;
MaxOffset = 63;
} else {
MinOffset = -256;
MaxOffset = 255;
}
}
static const MachineOperand &getLdStRegOp(const MachineInstr &MI,
unsigned PairedRegOp = 0) {
assert(PairedRegOp < 2 && "Unexpected register operand idx.");
@ -618,6 +677,11 @@ static bool isMergeableLdStUpdate(MachineInstr &MI) {
case AArch64::LDRWui:
case AArch64::LDRHHui:
case AArch64::LDRBBui:
case AArch64::STGOffset:
case AArch64::STZGOffset:
case AArch64::ST2GOffset:
case AArch64::STZ2GOffset:
case AArch64::STGPi:
// Unscaled instructions.
case AArch64::STURSi:
case AArch64::STURDi:
@ -1328,18 +1392,19 @@ AArch64LoadStoreOpt::mergeUpdateInsn(MachineBasicBlock::iterator I,
unsigned NewOpc = IsPreIdx ? getPreIndexedOpcode(I->getOpcode())
: getPostIndexedOpcode(I->getOpcode());
MachineInstrBuilder MIB;
int Scale, MinOffset, MaxOffset;
getPrePostIndexedMemOpInfo(*I, Scale, MinOffset, MaxOffset);
if (!isPairedLdSt(*I)) {
// Non-paired instruction.
MIB = BuildMI(*I->getParent(), I, I->getDebugLoc(), TII->get(NewOpc))
.add(getLdStRegOp(*Update))
.add(getLdStRegOp(*I))
.add(getLdStBaseOp(*I))
.addImm(Value)
.addImm(Value / Scale)
.setMemRefs(I->memoperands())
.setMIFlags(I->mergeFlagsWith(*Update));
} else {
// Paired instruction.
int Scale = getMemScale(*I);
MIB = BuildMI(*I->getParent(), I, I->getDebugLoc(), TII->get(NewOpc))
.add(getLdStRegOp(*Update))
.add(getLdStRegOp(*I, 0))
@ -1395,28 +1460,21 @@ bool AArch64LoadStoreOpt::isMatchingUpdateInsn(MachineInstr &MemMI,
MI.getOperand(1).getReg() != BaseReg)
break;
bool IsPairedInsn = isPairedLdSt(MemMI);
int UpdateOffset = MI.getOperand(2).getImm();
if (MI.getOpcode() == AArch64::SUBXri)
UpdateOffset = -UpdateOffset;
// For non-paired load/store instructions, the immediate must fit in a
// signed 9-bit integer.
if (!IsPairedInsn && (UpdateOffset > 255 || UpdateOffset < -256))
// The immediate must be a multiple of the scaling factor of the pre/post
// indexed instruction.
int Scale, MinOffset, MaxOffset;
getPrePostIndexedMemOpInfo(MemMI, Scale, MinOffset, MaxOffset);
if (UpdateOffset % Scale != 0)
break;
// For paired load/store instructions, the immediate must be a multiple of
// the scaling factor. The scaled offset must also fit into a signed 7-bit
// integer.
if (IsPairedInsn) {
int Scale = getMemScale(MemMI);
if (UpdateOffset % Scale != 0)
break;
int ScaledOffset = UpdateOffset / Scale;
if (ScaledOffset > 63 || ScaledOffset < -64)
break;
}
// Scaled offset must fit in the instruction immediate.
int ScaledOffset = UpdateOffset / Scale;
if (ScaledOffset > MaxOffset || ScaledOffset < MinOffset)
break;
// If we have a non-zero Offset, we check that it matches the amount
// we're adding to the register.
@ -1442,13 +1500,19 @@ MachineBasicBlock::iterator AArch64LoadStoreOpt::findMatchingUpdateInsnForward(
if (MIUnscaledOffset != UnscaledOffset)
return E;
// If the base register overlaps a destination register, we can't
// merge the update.
bool IsPairedInsn = isPairedLdSt(MemMI);
for (unsigned i = 0, e = IsPairedInsn ? 2 : 1; i != e; ++i) {
Register DestReg = getLdStRegOp(MemMI, i).getReg();
if (DestReg == BaseReg || TRI->isSubRegister(BaseReg, DestReg))
return E;
// If the base register overlaps a source/destination register, we can't
// merge the update. This does not apply to tag store instructions which
// ignore the address part of the source register.
// This does not apply to STGPi as well, which does not have unpredictable
// behavior in this case unlike normal stores, and always performs writeback
// after reading the source register value.
if (!isTagStore(MemMI) && MemMI.getOpcode() != AArch64::STGPi) {
bool IsPairedInsn = isPairedLdSt(MemMI);
for (unsigned i = 0, e = IsPairedInsn ? 2 : 1; i != e; ++i) {
Register DestReg = getLdStRegOp(MemMI, i).getReg();
if (DestReg == BaseReg || TRI->isSubRegister(BaseReg, DestReg))
return E;
}
}
// Track which register units have been modified and used between the first
@ -1496,11 +1560,13 @@ MachineBasicBlock::iterator AArch64LoadStoreOpt::findMatchingUpdateInsnBackward(
return E;
// If the base register overlaps a destination register, we can't
// merge the update.
bool IsPairedInsn = isPairedLdSt(MemMI);
for (unsigned i = 0, e = IsPairedInsn ? 2 : 1; i != e; ++i) {
Register DestReg = getLdStRegOp(MemMI, i).getReg();
if (DestReg == BaseReg || TRI->isSubRegister(BaseReg, DestReg))
return E;
if (!isTagStore(MemMI)) {
bool IsPairedInsn = isPairedLdSt(MemMI);
for (unsigned i = 0, e = IsPairedInsn ? 2 : 1; i != e; ++i) {
Register DestReg = getLdStRegOp(MemMI, i).getReg();
if (DestReg == BaseReg || TRI->isSubRegister(BaseReg, DestReg))
return E;
}
}
// Track which register units have been modified and used between the first
@ -1659,7 +1725,7 @@ bool AArch64LoadStoreOpt::tryToMergeLdStUpdate
// however, is not, so adjust here.
int UnscaledOffset = getLdStOffsetOp(MI).getImm() * getMemScale(MI);
// Look forward to try to find a post-index instruction. For example,
// Look forward to try to find a pre-index instruction. For example,
// ldr x1, [x0, #64]
// add x0, x0, #64
// merged into:

View File

@ -0,0 +1,285 @@
# RUN: llc -mtriple=aarch64-none-linux-gnu -run-pass aarch64-ldst-opt -verify-machineinstrs -o - %s | FileCheck %s
---
### STG and its offset limits
# CHECK-LABEL: name: test_STG_post
# CHECK: STGPostIndex $x0, $x0, 7
name: test_STG_post
body: |
bb.0.entry:
liveins: $x0
STGOffset $x0, $x0, 0
$x0 = ADDXri $x0, 112, 0
RET_ReallyLR implicit $x0
...
# CHECK-LABEL: name: test_STG_post_same_reg
# CHECK: STGPostIndex $x1, $x0, 7
name: test_STG_post_same_reg
body: |
bb.0.entry:
liveins: $x0, $x1
STGOffset $x1, $x0, 0
$x0 = ADDXri $x0, 112, 0
RET_ReallyLR implicit $x0
...
# CHECK-LABEL: name: test_STG_post_unaligned
# CHECK: STGOffset $x0, $x0, 0
# CHECK-NEXT: ADDXri $x0, 8, 0
name: test_STG_post_unaligned
body: |
bb.0.entry:
liveins: $x0
STGOffset $x0, $x0, 0
$x0 = ADDXri $x0, 8, 0
RET_ReallyLR implicit $x0
...
# CHECK-LABEL: name: test_STG_post2
# CHECK: STGPostIndex $x0, $x0, -256
name: test_STG_post2
body: |
bb.0.entry:
liveins: $x0
STGOffset $x0, $x0, 0
$x0 = SUBXri $x0, 4096, 0
RET_ReallyLR implicit $x0
...
# CHECK-LABEL: name: test_STG_post3
# CHECK: STGOffset $x0, $x0, 0
# CHECK-NEXT: SUBXri $x0, 4112, 0
name: test_STG_post3
body: |
bb.0.entry:
liveins: $x0
STGOffset $x0, $x0, 0
$x0 = SUBXri $x0, 4112, 0
RET_ReallyLR implicit $x0
...
# CHECK-LABEL: name: test_STG_post4
# CHECK: STGPostIndex $x0, $x0, 255
name: test_STG_post4
body: |
bb.0.entry:
liveins: $x0
STGOffset $x0, $x0, 0
$x0 = ADDXri $x0, 4080, 0
RET_ReallyLR implicit $x0
...
# CHECK-LABEL: name: test_STG_post5
# CHECK: STGOffset $x0, $x0, 0
# CHECK-NEXT: ADDXri $x0, 4096, 0
name: test_STG_post5
body: |
bb.0.entry:
liveins: $x0
STGOffset $x0, $x0, 0
$x0 = ADDXri $x0, 4096, 0
RET_ReallyLR implicit $x0
...
### The rest of ST*G variants.
# CHECK-LABEL: name: test_STZG_post
# CHECK: STZGPostIndex $x0, $x0, 7
name: test_STZG_post
body: |
bb.0.entry:
liveins: $x0
STZGOffset $x0, $x0, 0
$x0 = ADDXri $x0, 112, 0
RET_ReallyLR implicit $x0
...
# CHECK-LABEL: name: test_ST2G_post
# CHECK: ST2GPostIndex $x0, $x0, 7
name: test_ST2G_post
body: |
bb.0.entry:
liveins: $x0
ST2GOffset $x0, $x0, 0
$x0 = ADDXri $x0, 112, 0
RET_ReallyLR implicit $x0
...
# CHECK-LABEL: name: test_STZ2G_post
# CHECK: STZ2GPostIndex $x0, $x0, 7
name: test_STZ2G_post
body: |
bb.0.entry:
liveins: $x0
STZ2GOffset $x0, $x0, 0
$x0 = ADDXri $x0, 112, 0
RET_ReallyLR implicit $x0
...
### STGP and its offset limits
# CHECK-LABEL: name: test_STGP_post
# CHECK: STGPpost $x1, $x2, $x0, 7
name: test_STGP_post
body: |
bb.0.entry:
liveins: $x0, $x1, $x2
STGPi $x1, $x2, $x0, 0
$x0 = ADDXri $x0, 112, 0
RET_ReallyLR implicit $x0
...
# CHECK-LABEL: name: test_STGP_post2
# CHECK: STGPpost $x1, $x2, $x0, -64
name: test_STGP_post2
body: |
bb.0.entry:
liveins: $x0, $x1, $x2
STGPi $x1, $x2, $x0, 0
$x0 = SUBXri $x0, 1024, 0
RET_ReallyLR implicit $x0
...
# CHECK-LABEL: name: test_STGP_post3
# CHECK: STGPi $x1, $x2, $x0, 0
# CHECK-NEXT: SUBXri $x0, 1040, 0
name: test_STGP_post3
body: |
bb.0.entry:
liveins: $x0, $x1, $x2
STGPi $x1, $x2, $x0, 0
$x0 = SUBXri $x0, 1040, 0
RET_ReallyLR implicit $x0
...
# CHECK-LABEL: name: test_STGP_post4
# CHECK: STGPpost $x1, $x2, $x0, 63
name: test_STGP_post4
body: |
bb.0.entry:
liveins: $x0, $x1, $x2
STGPi $x1, $x2, $x0, 0
$x0 = ADDXri $x0, 1008, 0
RET_ReallyLR implicit $x0
...
# CHECK-LABEL: name: test_STGP_post5
# CHECK: STGPi $x1, $x2, $x0, 0
# CHECK-NEXT: ADDXri $x0, 1024, 0
name: test_STGP_post5
body: |
bb.0.entry:
liveins: $x0, $x1, $x2
STGPi $x1, $x2, $x0, 0
$x0 = ADDXri $x0, 1024, 0
RET_ReallyLR implicit $x0
...
### Pre-indexed forms
# CHECK-LABEL: name: test_STG_pre
# CHECK: STGPreIndex $x0, $x0, 10
name: test_STG_pre
body: |
bb.0.entry:
liveins: $x0
STGOffset $x0, $x0, 10
$x0 = ADDXri $x0, 160, 0
RET_ReallyLR implicit $x0
...
# CHECK-LABEL: name: test_STGP_pre
# CHECK: STGPpre $x1, $x2, $x0, 10
name: test_STGP_pre
body: |
bb.0.entry:
liveins: $x0, $x1, $x2
STGPi $x1, $x2, $x0, 10
$x0 = ADDXri $x0, 160, 0
RET_ReallyLR implicit $x0
...
### Pre-indexed forms with add/sub coming before the store.
# CHECK-LABEL: name: test_STG_pre_back
# CHECK: STGPreIndex $x0, $x0, 2
name: test_STG_pre_back
body: |
bb.0.entry:
liveins: $x0
$x0 = ADDXri $x0, 32, 0
STGOffset $x0, $x0, 0
RET_ReallyLR implicit $x0
...
# CHECK-LABEL: name: test_STGP_pre_back
# CHECK: STGPpre $x1, $x2, $x0, -3
name: test_STGP_pre_back
body: |
bb.0.entry:
liveins: $x0, $x1, $x2
$x0 = SUBXri $x0, 48, 0
STGPi $x1, $x2, $x0, 0
RET_ReallyLR implicit $x0
...
### STGP with source register == address register
# CHECK-LABEL: name: test_STGP_post_same_reg
# CHECK: STGPpost $x0, $x0, $x0, 7
name: test_STGP_post_same_reg
body: |
bb.0.entry:
liveins: $x0
STGPi $x0, $x0, $x0, 0
$x0 = ADDXri $x0, 112, 0
RET_ReallyLR implicit $x0
...
# CHECK-LABEL: name: test_STGP_pre_same_reg
# CHECK: STGPpre $x0, $x0, $x0, 7
name: test_STGP_pre_same_reg
body: |
bb.0.entry:
liveins: $x0
STGPi $x0, $x0, $x0, 7
$x0 = ADDXri $x0, 112, 0
RET_ReallyLR implicit $x0
...
# This case can not be merged because the source register is always read before writeback.
# CHECK-LABEL: name: test_STGP_pre_back_same_reg
# CHECK: SUBXri $x0, 48, 0
# CHECK-NEXT: STGPi $x0, $x0, $x0, 0
name: test_STGP_pre_back_same_reg
body: |
bb.0.entry:
liveins: $x0
$x0 = SUBXri $x0, 48, 0
STGPi $x0, $x0, $x0, 0
RET_ReallyLR implicit $x0
...

View File

@ -65,7 +65,7 @@ entry:
define void @stgp_alloca(i64 %a, i64 %b) {
entry:
; CHECK-LABEL: stgp_alloca:
; CHECK: stgp x0, x1, [sp]
; CHECK: stgp x0, x1, [sp, #-32]!
; CHECK: stgp x1, x0, [sp, #16]
; CHECK: ret
%x = alloca i8, i32 32, align 16