RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-19 11:02:59 +02:00
Code Issues Projects Releases Wiki Activity

Fix PR33031: correct the estimate of maximum offset for instructions spilling/filling the stack.

Browse Source 
llvm-svn: 304196
This commit is contained in:
Kristof Beyls 2017-05-30 06:58:41 +00:00
parent 84b18ab08d
commit 1166792bbb
2 changed files with 82 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
lib/Target/AArch64/AArch64FrameLowering.cpp
View File

@ -137,6 +137,34 @@ static cl::opt<bool> EnableRedZone("aarch64-redzone",
STATISTIC(NumRedZoneFunctions, "Number of functions using red zone");
/// Look at each instruction that references stack frames and return the stack
/// size limit beyond which some of these instructions will require a scratch
/// register during their expansion later.
static unsigned estimateRSStackSizeLimit(MachineFunction &MF) {
// FIXME: For now, just conservatively guestimate based on unscaled indexing
// range. We'll end up allocating an unnecessary spill slot a lot, but
// realistically that's not a big deal at this stage of the game.
for (MachineBasicBlock &MBB : MF) {
for (MachineInstr &MI : MBB) {
if (MI.isDebugValue() || MI.isPseudo() ||
MI.getOpcode() == AArch64::ADDXri ||
MI.getOpcode() == AArch64::ADDSXri)
continue;
for (unsigned i = 0, e = MI.getNumOperands(); i != e; ++i) {
if (!MI.getOperand(i).isFI())
continue;
int Offset = 0;
if (isAArch64FrameOffsetLegal(MI, Offset, nullptr, nullptr, nullptr) ==
AArch64FrameOffsetCannotUpdate)
return 0;
}
}
}
return 255;
}
bool AArch64FrameLowering::canUseRedZone(const MachineFunction &MF) const {
if (!EnableRedZone)
return false;
@ -1169,16 +1197,13 @@ void AArch64FrameLowering::determineCalleeSaves(MachineFunction &MF,
unsigned NumRegsSpilled = SavedRegs.count();
bool CanEliminateFrame = NumRegsSpilled == 0;
// FIXME: Set BigStack if any stack slot references may be out of range.
// For now, just conservatively guestimate based on unscaled indexing
// range. We'll end up allocating an unnecessary spill slot a lot, but
// realistically that's not a big deal at this stage of the game.
// The CSR spill slots have not been allocated yet, so estimateStackSize
// won't include them.
MachineFrameInfo &MFI = MF.getFrameInfo();
unsigned CFSize = MFI.estimateStackSize(MF) + 8 * NumRegsSpilled;
DEBUG(dbgs() << "Estimated stack frame size: " << CFSize << " bytes.\n");
bool BigStack = (CFSize >= 256);
unsigned EstimatedStackSizeLimit = estimateRSStackSizeLimit(MF);
bool BigStack = (CFSize > EstimatedStackSizeLimit);
if (BigStack || !CanEliminateFrame || RegInfo->cannotEliminateFrame(MF))
AFI->setHasStackFrame(true);

52
test/CodeGen/AArch64/reg-scavenge-frame.mir Normal file
View File

@ -0,0 +1,52 @@
# RUN: llc -run-pass=prologepilog -verify-machineinstrs %s -o - | 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"
define void @ScavengeForFrameWithoutOffset() { ret void }
...
---
name: ScavengeForFrameWithoutOffset
tracksRegLiveness: true
stack:
- { id: 0, type: spill-slot, offset: 0, size: 32, alignment: 8 }
body: |
bb.0:
liveins: %d16_d17_d18_d19
%x0 = COPY %xzr
%x1 = COPY %xzr
%x2 = COPY %xzr
%x3 = COPY %xzr
%x4 = COPY %xzr
%x5 = COPY %xzr
%x6 = COPY %xzr
%x7 = COPY %xzr
%x8 = COPY %xzr
%x9 = COPY %xzr
%x10 = COPY %xzr
%x11 = COPY %xzr
%x12 = COPY %xzr
%x13 = COPY %xzr
%x14 = COPY %xzr
%x15 = COPY %xzr
%x16 = COPY %xzr
%x17 = COPY %xzr
%x18 = COPY %xzr
%x19 = COPY %xzr
%x20 = COPY %xzr
%x21 = COPY %xzr
%x22 = COPY %xzr
%x23 = COPY %xzr
%x24 = COPY %xzr
%x25 = COPY %xzr
%x26 = COPY %xzr
%x27 = COPY %xzr
%x28 = COPY %xzr
%fp = COPY %xzr
%lr = COPY %xzr
ST1Fourv1d killed %d16_d17_d18_d19, %stack.0 :: (store 32 into %stack.0, align 8)
# CHECK: STRXui killed %[[SCAVREG:x[0-9]+|fp|lr]], %sp, [[SPOFFSET:[0-9]+]] :: (store 8 into %stack.1)
# CHECK-NEXT: %[[SCAVREG]] = ADDXri %sp, {{[0-9]+}}, 0
# CHECK-NEXT: ST1Fourv1d killed %d16_d17_d18_d19, killed %[[SCAVREG]] :: (store 32 into %stack.0, align 8)
# CHECK-NEXT: %[[SCAVREG]] = LDRXui %sp, [[SPOFFSET]] :: (load 8 from %stack.1)
...