summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorMatthias Braun <matze@braunis.de>2016-08-18 19:47:59 +0000
committerMatthias Braun <matze@braunis.de>2016-08-18 19:47:59 +0000
commitf65766df39c05b5c7a469e0ae57376a8d132487b (patch)
tree05c9d67d4398ee30599fb7cb2d9648173b4be350
parentb1ee91e27d6e803d15856f1ac80f6e2d3a3a60f6 (diff)
RegScavenging: Add scavengeRegisterBackwards()
Re-apply r276044 with off-by-1 instruction fix for the reload placement. This is a variant of scavengeRegister() that works for enterBasicBlockEnd()/backward(). The benefit of the backward mode is that it is not affected by incomplete kill flags. This patch also changes PrologEpilogInserter::doScavengeFrameVirtualRegs() to use the register scavenger in backwards mode. Differential Revision: http://reviews.llvm.org/D21885 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@279124 91177308-0d34-0410-b5e6-96231b3b80d8
-rw-r--r--include/llvm/CodeGen/RegisterScavenging.h18
-rw-r--r--lib/CodeGen/PrologEpilogInserter.cpp147
-rw-r--r--lib/CodeGen/RegisterScavenging.cpp204
-rw-r--r--test/CodeGen/AMDGPU/captured-frame-index.ll4
-rw-r--r--test/CodeGen/Mips/emergency-spill-slot-near-fp.ll88
-rw-r--r--test/CodeGen/PowerPC/dyn-alloca-aligned.ll4
-rw-r--r--test/CodeGen/Thumb/large-stack.ll4
7 files changed, 325 insertions, 144 deletions
diff --git a/include/llvm/CodeGen/RegisterScavenging.h b/include/llvm/CodeGen/RegisterScavenging.h
index efaba1757b5..5b1a1f08e6f 100644
--- a/include/llvm/CodeGen/RegisterScavenging.h
+++ b/include/llvm/CodeGen/RegisterScavenging.h
@@ -157,12 +157,24 @@ public:
/// available and do the appropriate bookkeeping. SPAdj is the stack
/// adjustment due to call frame, it's passed along to eliminateFrameIndex().
/// Returns the scavenged register.
+ /// This function performs worse if kill flags are incomplete, consider using
+ /// scavengeRegisterBackwards() instead!
unsigned scavengeRegister(const TargetRegisterClass *RegClass,
MachineBasicBlock::iterator I, int SPAdj);
unsigned scavengeRegister(const TargetRegisterClass *RegClass, int SPAdj) {
return scavengeRegister(RegClass, MBBI, SPAdj);
}
+ /// Make a register of the specific register class available from the current
+ /// position backwards to the place before \p To. If \p RestoreAfter is true
+ /// this includes the instruction following the current position.
+ /// SPAdj is the stack adjustment due to call frame, it's passed along to
+ /// eliminateFrameIndex().
+ /// Returns the scavenged register.
+ unsigned scavengeRegisterBackwards(const TargetRegisterClass &RC,
+ MachineBasicBlock::iterator To,
+ bool RestoreAfter, int SPAdj);
+
/// Tell the scavenger a register is used.
void setRegUsed(unsigned Reg, LaneBitmask LaneMask = ~0u);
private:
@@ -202,6 +214,12 @@ private:
/// Mark live-in registers of basic block as used.
void setLiveInsUsed(const MachineBasicBlock &MBB);
+
+ /// Spill a register after position \p After and reload it before position
+ /// \p UseMI.
+ ScavengedInfo &spill(unsigned Reg, const TargetRegisterClass &RC, int SPAdj,
+ MachineBasicBlock::iterator After,
+ MachineBasicBlock::iterator &UseMI);
};
} // End llvm namespace
diff --git a/lib/CodeGen/PrologEpilogInserter.cpp b/lib/CodeGen/PrologEpilogInserter.cpp
index a167b3d1c91..7faf245e20f 100644
--- a/lib/CodeGen/PrologEpilogInserter.cpp
+++ b/lib/CodeGen/PrologEpilogInserter.cpp
@@ -41,6 +41,7 @@
#include "llvm/Target/TargetMachine.h"
#include "llvm/Target/TargetRegisterInfo.h"
#include "llvm/Target/TargetSubtargetInfo.h"
+#include <algorithm>
#include <climits>
using namespace llvm;
@@ -1145,6 +1146,55 @@ void PEI::replaceFrameIndices(MachineBasicBlock *BB, MachineFunction &Fn,
}
}
+/// Allocate a register for the virtual register \p VReg. The last use of
+/// \p VReg is around the current position of the register scavenger \p RS.
+/// \p ReserveAfter controls whether the scavenged register needs to be reserved
+/// after the current instruction, otherwise it will only be reserved before the
+/// current instruction.
+static unsigned scavengeVReg(MachineRegisterInfo &MRI, RegScavenger &RS,
+ unsigned VReg, bool ReserveAfter) {
+#ifndef NDEBUG
+ // Verify that all definitions and uses are in the same basic block.
+ const MachineBasicBlock *CommonMBB = nullptr;
+ bool HadDef = false;
+ for (MachineOperand &MO : MRI.reg_nodbg_operands(VReg)) {
+ MachineBasicBlock *MBB = MO.getParent()->getParent();
+ if (CommonMBB == nullptr)
+ CommonMBB = MBB;
+ assert(MBB == CommonMBB && "All defs+uses must be in the same basic block");
+ if (MO.isDef())
+ HadDef = true;
+ }
+ assert(HadDef && "Must have at least 1 Def");
+#endif
+
+ // We should only have one definition of the register. However to accomodate
+ // the requirements of two address code we also allow definitions in
+ // subsequent instructions provided they also read the register. That way
+ // we get a single contiguous lifetime.
+ //
+ // Definitions in MRI.def_begin() are unordered, search for the first.
+ const TargetRegisterInfo &TRI = *MRI.getTargetRegisterInfo();
+ MachineRegisterInfo::def_iterator FirstDef =
+ std::find_if(MRI.def_begin(VReg), MRI.def_end(),
+ [VReg, &TRI](const MachineOperand &MO) {
+ return !MO.getParent()->readsRegister(VReg, &TRI);
+ });
+ assert(FirstDef != MRI.def_end() &&
+ "Must have one definition that does not redefine vreg");
+ MachineInstr &DefMI = *FirstDef->getParent();
+
+ // The register scavenger will report a free register inserting an emergency
+ // spill/reload if necessary.
+ int SPAdj = 0;
+ const TargetRegisterClass &RC = *MRI.getRegClass(VReg);
+ unsigned SReg = RS.scavengeRegisterBackwards(RC, DefMI.getIterator(),
+ ReserveAfter, SPAdj);
+ MRI.replaceRegWith(VReg, SReg);
+ ++NumScavengedRegs;
+ return SReg;
+}
+
/// doScavengeFrameVirtualRegs - Replace all frame index virtual registers
/// with physical registers. Use the register scavenger to find an
/// appropriate register to use.
@@ -1156,78 +1206,51 @@ static void
doScavengeFrameVirtualRegs(MachineFunction &MF, RegScavenger *RS) {
// Run through the instructions and find any virtual registers.
MachineRegisterInfo &MRI = MF.getRegInfo();
+ const TargetRegisterInfo &TRI = *MRI.getTargetRegisterInfo();
for (MachineBasicBlock &MBB : MF) {
- RS->enterBasicBlock(MBB);
-
- int SPAdj = 0;
-
- // The instruction stream may change in the loop, so check MBB.end()
- // directly.
- for (MachineBasicBlock::iterator I = MBB.begin(); I != MBB.end(); ) {
- // We might end up here again with a NULL iterator if we scavenged a
- // register for which we inserted spill code for definition by what was
- // originally the first instruction in MBB.
- if (I == MachineBasicBlock::iterator(nullptr))
- I = MBB.begin();
+ RS->enterBasicBlockEnd(MBB);
+
+ bool LastIterationHadVRegUses = false;
+ for (MachineBasicBlock::iterator I = MBB.end(); I != MBB.begin(); ) {
+ --I;
+ // Move RegScavenger to the position between *I and *std::next(I).
+ RS->backward(I);
+
+ // Look for unassigned vregs in the uses of *std::next(I).
+ if (LastIterationHadVRegUses) {
+ MachineBasicBlock::iterator N = std::next(I);
+ const MachineInstr &NMI = *N;
+ for (const MachineOperand &MO : NMI.operands()) {
+ if (!MO.isReg() || !MO.readsReg())
+ continue;
+ unsigned Reg = MO.getReg();
+ if (TargetRegisterInfo::isVirtualRegister(Reg)) {
+ unsigned SReg = scavengeVReg(MRI, *RS, Reg, true);
+ N->addRegisterKilled(SReg, &TRI, false);
+ RS->setRegUsed(SReg);
+ }
+ }
+ }
+ // Look for unassigned vregs in the defs of *I.
+ LastIterationHadVRegUses = false;
const MachineInstr &MI = *I;
- MachineBasicBlock::iterator J = std::next(I);
- MachineBasicBlock::iterator P =
- I == MBB.begin() ? MachineBasicBlock::iterator(nullptr)
- : std::prev(I);
-
- // RS should process this instruction before we might scavenge at this
- // location. This is because we might be replacing a virtual register
- // defined by this instruction, and if so, registers killed by this
- // instruction are available, and defined registers are not.
- RS->forward(I);
-
for (const MachineOperand &MO : MI.operands()) {
if (!MO.isReg())
continue;
unsigned Reg = MO.getReg();
if (!TargetRegisterInfo::isVirtualRegister(Reg))
continue;
-
- // When we first encounter a new virtual register, it
- // must be a definition.
- assert(MO.isDef() && "frame index virtual missing def!");
- // Scavenge a new scratch register
- const TargetRegisterClass *RC = MRI.getRegClass(Reg);
- unsigned ScratchReg = RS->scavengeRegister(RC, J, SPAdj);
-
- ++NumScavengedRegs;
-
- // Replace this reference to the virtual register with the
- // scratch register.
- assert(ScratchReg && "Missing scratch register!");
- MRI.replaceRegWith(Reg, ScratchReg);
-
- // Because this instruction was processed by the RS before this
- // register was allocated, make sure that the RS now records the
- // register as being used.
- RS->setRegUsed(ScratchReg);
+ // We have to look at all operands anyway so we can precalculate here
+ // whether there is a reading operand. This allows use to skip the use
+ // step in the next iteration if there was none.
+ if (MO.readsReg())
+ LastIterationHadVRegUses = true;
+ if (MO.isDef()) {
+ unsigned SReg = scavengeVReg(MRI, *RS, Reg, false);
+ I->addRegisterDead(SReg, &TRI, false);
+ }
}
-
- // If the scavenger needed to use one of its spill slots, the
- // spill code will have been inserted in between I and J. This is a
- // problem because we need the spill code before I: Move I to just
- // prior to J.
- if (I != std::prev(J)) {
- MBB.splice(J, &MBB, I);
-
- // Before we move I, we need to prepare the RS to visit I again.
- // Specifically, RS will assert if it sees uses of registers that
- // it believes are undefined. Because we have already processed
- // register kills in I, when it visits I again, it will believe that
- // those registers are undefined. To avoid this situation, unprocess
- // the instruction I.
- assert(RS->getCurrentPosition() == I &&
- "The register scavenger has an unexpected position");
- I = P;
- RS->unprocess(P);
- } else
- ++I;
}
}
}
diff --git a/lib/CodeGen/RegisterScavenging.cpp b/lib/CodeGen/RegisterScavenging.cpp
index 953e5353df1..b3eff8b837a 100644
--- a/lib/CodeGen/RegisterScavenging.cpp
+++ b/lib/CodeGen/RegisterScavenging.cpp
@@ -299,6 +299,14 @@ void RegScavenger::backward() {
}
}
+ // Expire scavenge spill frameindex uses.
+ for (ScavengedInfo &I : Scavenged) {
+ if (I.Restore == &MI) {
+ I.Reg = 0;
+ I.Restore = nullptr;
+ }
+ }
+
if (MBBI == MBB->begin()) {
MBBI = MachineBasicBlock::iterator(nullptr);
Tracking = false;
@@ -398,6 +406,69 @@ unsigned RegScavenger::findSurvivorReg(MachineBasicBlock::iterator StartMI,
return Survivor;
}
+static std::pair<unsigned, MachineBasicBlock::iterator>
+findSurvivorBackwards(const TargetRegisterInfo &TRI,
+ MachineBasicBlock::iterator From, MachineBasicBlock::iterator To,
+ BitVector &Available, BitVector &Candidates) {
+ bool FoundTo = false;
+ unsigned Survivor = 0;
+ MachineBasicBlock::iterator Pos;
+ MachineBasicBlock &MBB = *From->getParent();
+ unsigned InstrLimit = 25;
+ unsigned InstrCountDown = InstrLimit;
+ for (MachineBasicBlock::iterator I = From;; --I) {
+ const MachineInstr &MI = *I;
+
+ // Remove any candidates touched by instruction.
+ bool FoundVReg = false;
+ for (const MachineOperand &MO : MI.operands()) {
+ if (MO.isRegMask()) {
+ Candidates.clearBitsNotInMask(MO.getRegMask());
+ continue;
+ }
+ if (!MO.isReg() || MO.isUndef() || MO.isDebug())
+ continue;
+ unsigned Reg = MO.getReg();
+ if (TargetRegisterInfo::isVirtualRegister(Reg)) {
+ FoundVReg = true;
+ } else if (TargetRegisterInfo::isPhysicalRegister(Reg)) {
+ for (MCRegAliasIterator AI(Reg, &TRI, true); AI.isValid(); ++AI)
+ Candidates.reset(*AI);
+ }
+ }
+
+ if (I == To) {
+ // If one of the available registers survived this long take it.
+ Available &= Candidates;
+ int Reg = Available.find_first();
+ if (Reg != -1)
+ return std::make_pair(Reg, MBB.end());
+ // Otherwise we will continue up to InstrLimit instructions to find
+ // the register which is not defined/used for the longest time.
+ FoundTo = true;
+ Pos = To;
+ }
+ if (FoundTo) {
+ if (Survivor == 0 || !Candidates.test(Survivor)) {
+ int Reg = Candidates.find_first();
+ if (Reg == -1)
+ break;
+ Survivor = Reg;
+ }
+ if (--InstrCountDown == 0 || I == MBB.begin())
+ break;
+ if (FoundVReg) {
+ // Keep searching when we find a vreg since the spilled register will
+ // be usefull for this other vreg as well later.
+ InstrCountDown = InstrLimit;
+ Pos = I;
+ }
+ }
+ }
+
+ return std::make_pair(Survivor, Pos);
+}
+
static unsigned getFrameIndexOperandNum(MachineInstr &MI) {
unsigned i = 0;
while (!MI.getOperand(i).isFI()) {
@@ -407,43 +478,16 @@ static unsigned getFrameIndexOperandNum(MachineInstr &MI) {
return i;
}
-unsigned RegScavenger::scavengeRegister(const TargetRegisterClass *RC,
- MachineBasicBlock::iterator I,
- int SPAdj) {
- MachineInstr &MI = *I;
- const MachineFunction &MF = *MI.getParent()->getParent();
- // Consider all allocatable registers in the register class initially
- BitVector Candidates = TRI->getAllocatableSet(MF, RC);
-
- // Exclude all the registers being used by the instruction.
- for (const MachineOperand &MO : MI.operands()) {
- if (MO.isReg() && MO.getReg() != 0 && !(MO.isUse() && MO.isUndef()) &&
- !TargetRegisterInfo::isVirtualRegister(MO.getReg()))
- Candidates.reset(MO.getReg());
- }
-
- // Try to find a register that's unused if there is one, as then we won't
- // have to spill.
- BitVector Available = getRegsAvailable(RC);
- Available &= Candidates;
- if (Available.any())
- Candidates = Available;
-
- // Find the register whose use is furthest away.
- MachineBasicBlock::iterator UseMI;
- unsigned SReg = findSurvivorReg(I, Candidates, 25, UseMI);
-
- // If we found an unused register there is no reason to spill it.
- if (!isRegUsed(SReg)) {
- DEBUG(dbgs() << "Scavenged register: " << TRI->getName(SReg) << "\n");
- return SReg;
- }
-
+RegScavenger::ScavengedInfo &
+RegScavenger::spill(unsigned Reg, const TargetRegisterClass &RC, int SPAdj,
+ MachineBasicBlock::iterator Before,
+ MachineBasicBlock::iterator &UseMI) {
// Find an available scavenging slot with size and alignment matching
// the requirements of the class RC.
+ const MachineFunction &MF = *Before->getParent()->getParent();
const MachineFrameInfo &MFI = MF.getFrameInfo();
- unsigned NeedSize = RC->getSize();
- unsigned NeedAlign = RC->getAlignment();
+ unsigned NeedSize = RC.getSize();
+ unsigned NeedAlign = RC.getAlignment();
unsigned SI = Scavenged.size(), Diff = UINT_MAX;
int FIB = MFI.getObjectIndexBegin(), FIE = MFI.getObjectIndexEnd();
@@ -478,42 +522,110 @@ unsigned RegScavenger::scavengeRegister(const TargetRegisterClass *RC,
}
// Avoid infinite regress
- Scavenged[SI].Reg = SReg;
+ Scavenged[SI].Reg = Reg;
// If the target knows how to save/restore the register, let it do so;
// otherwise, use the emergency stack spill slot.
- if (!TRI->saveScavengerRegister(*MBB, I, UseMI, RC, SReg)) {
- // Spill the scavenged register before I.
+ if (!TRI->saveScavengerRegister(*MBB, Before, UseMI, &RC, Reg)) {
+ // Spill the scavenged register before \p Before.
int FI = Scavenged[SI].FrameIndex;
if (FI < FIB || FI >= FIE) {
std::string Msg = std::string("Error while trying to spill ") +
- TRI->getName(SReg) + " from class " + TRI->getRegClassName(RC) +
+ TRI->getName(Reg) + " from class " + TRI->getRegClassName(&RC) +
": Cannot scavenge register without an emergency spill slot!";
report_fatal_error(Msg.c_str());
}
- TII->storeRegToStackSlot(*MBB, I, SReg, true, Scavenged[SI].FrameIndex,
- RC, TRI);
- MachineBasicBlock::iterator II = std::prev(I);
+ TII->storeRegToStackSlot(*MBB, Before, Reg, true, Scavenged[SI].FrameIndex,
+ &RC, TRI);
+ MachineBasicBlock::iterator II = std::prev(Before);
unsigned FIOperandNum = getFrameIndexOperandNum(*II);
TRI->eliminateFrameIndex(II, SPAdj, FIOperandNum, this);
// Restore the scavenged register before its use (or first terminator).
- TII->loadRegFromStackSlot(*MBB, UseMI, SReg, Scavenged[SI].FrameIndex,
- RC, TRI);
+ TII->loadRegFromStackSlot(*MBB, UseMI, Reg, Scavenged[SI].FrameIndex,
+ &RC, TRI);
II = std::prev(UseMI);
FIOperandNum = getFrameIndexOperandNum(*II);
TRI->eliminateFrameIndex(II, SPAdj, FIOperandNum, this);
}
+ return Scavenged[SI];
+}
+
+unsigned RegScavenger::scavengeRegister(const TargetRegisterClass *RC,
+ MachineBasicBlock::iterator I,
+ int SPAdj) {
+ MachineInstr &MI = *I;
+ const MachineFunction &MF = *MI.getParent()->getParent();
+ // Consider all allocatable registers in the register class initially
+ BitVector Candidates = TRI->getAllocatableSet(MF, RC);
+
+ // Exclude all the registers being used by the instruction.
+ for (const MachineOperand &MO : MI.operands()) {
+ if (MO.isReg() && MO.getReg() != 0 && !(MO.isUse() && MO.isUndef()) &&
+ !TargetRegisterInfo::isVirtualRegister(MO.getReg()))
+ Candidates.reset(MO.getReg());
+ }
+
+ // Try to find a register that's unused if there is one, as then we won't
+ // have to spill.
+ BitVector Available = getRegsAvailable(RC);
+ Available &= Candidates;
+ if (Available.any())
+ Candidates = Available;
+
+ // Find the register whose use is furthest away.
+ MachineBasicBlock::iterator UseMI;
+ unsigned SReg = findSurvivorReg(I, Candidates, 25, UseMI);
- Scavenged[SI].Restore = &*std::prev(UseMI);
+ // If we found an unused register there is no reason to spill it.
+ if (!isRegUsed(SReg)) {
+ DEBUG(dbgs() << "Scavenged register: " << TRI->getName(SReg) << "\n");
+ return SReg;
+ }
- // Doing this here leads to infinite regress.
- // Scavenged[SI].Reg = SReg;
+ ScavengedInfo &Scavenged = spill(SReg, *RC, SPAdj, I, UseMI);
+ Scavenged.Restore = &*std::prev(UseMI);
DEBUG(dbgs() << "Scavenged register (with spill): " << TRI->getName(SReg) <<
"\n");
return SReg;
}
+
+unsigned RegScavenger::scavengeRegisterBackwards(const TargetRegisterClass &RC,
+ MachineBasicBlock::iterator To,
+ bool RestoreAfter, int SPAdj) {
+ const MachineBasicBlock &MBB = *To->getParent();
+ const MachineFunction &MF = *MBB.getParent();
+ // Consider all allocatable registers in the register class initially
+ BitVector Candidates = TRI->getAllocatableSet(MF, &RC);
+
+ // Try to find a register that's unused if there is one, as then we won't
+ // have to spill.
+ BitVector Available = getRegsAvailable(&RC);
+
+ // Find the register whose use is furthest away.
+ MachineBasicBlock::iterator UseMI;
+ std::pair<unsigned, MachineBasicBlock::iterator> P =
+ findSurvivorBackwards(*TRI, MBBI, To, Available, Candidates);
+ unsigned Reg = P.first;
+ assert(Reg != 0 && "No register left to scavenge!");
+ // Found an available register?
+ if (!Available.test(Reg)) {
+ MachineBasicBlock::iterator ReloadAfter =
+ RestoreAfter ? std::next(MBBI) : MBBI;
+ MachineBasicBlock::iterator ReloadBefore = std::next(ReloadAfter);
+ DEBUG(dbgs() << "Reload before: " << *ReloadBefore << '\n');
+ MachineBasicBlock::iterator SpillBefore = P.second;
+ ScavengedInfo &Scavenged = spill(Reg, RC, SPAdj, SpillBefore, ReloadBefore);
+ Scavenged.Restore = &*std::prev(SpillBefore);
+ addRegUnits(RegUnitsAvailable, Reg);
+ DEBUG(dbgs() << "Scavenged register with spill: " << PrintReg(Reg, TRI)
+ << " until " << *SpillBefore);
+ } else {
+ DEBUG(dbgs() << "Scavenged free register: " << PrintReg(Reg, TRI) << '\n');
+ }
+ return Reg;
+}
diff --git a/test/CodeGen/AMDGPU/captured-frame-index.ll b/test/CodeGen/AMDGPU/captured-frame-index.ll
index 161c46b486e..bf6e48d89ca 100644
--- a/test/CodeGen/AMDGPU/captured-frame-index.ll
+++ b/test/CodeGen/AMDGPU/captured-frame-index.ll
@@ -140,8 +140,8 @@ define void @stored_fi_to_global_2_small_objects(float* addrspace(1)* %ptr) #0 {
}
; GCN-LABEL: {{^}}stored_fi_to_global_huge_frame_offset:
-; GCN: s_add_i32 [[BASE_1_OFF_0:s[0-9]+]], 0, 0x3ffc
-; GCN: v_mov_b32_e32 [[BASE_0:v[0-9]+]], 0{{$}}
+; GCN-DAG: s_add_i32 [[BASE_1_OFF_0:s[0-9]+]], 0, 0x3ffc
+; GCN-DAG: v_mov_b32_e32 [[BASE_0:v[0-9]+]], 0{{$}}
; GCN: buffer_store_dword [[BASE_0]], v{{[0-9]+}}, s{{\[[0-9]+:[0-9]+\]}}, s{{[0-9]+}} offen
; GCN: v_mov_b32_e32 [[V_BASE_1_OFF_0:v[0-9]+]], [[BASE_1_OFF_0]]
diff --git a/test/CodeGen/Mips/emergency-spill-slot-near-fp.ll b/test/CodeGen/Mips/emergency-spill-slot-near-fp.ll
index a08b68149a7..625abc1a7e0 100644
--- a/test/CodeGen/Mips/emergency-spill-slot-near-fp.ll
+++ b/test/CodeGen/Mips/emergency-spill-slot-near-fp.ll
@@ -1,34 +1,62 @@
-; Check that register scavenging spill slot is close to $fp.
; RUN: llc -march=mipsel -O0 -relocation-model=pic < %s | FileCheck %s
+; Check that register scavenging spill slot is close to $fp.
+target triple="mipsel--"
-; CHECK: sw ${{.*}}, 8($sp)
-; CHECK: lw ${{.*}}, 8($sp)
+@var = external global i32
+@ptrvar = external global i8*
-define i32 @main(i32 signext %argc, i8** %argv) #0 {
-entry:
- %retval = alloca i32, align 4
- %argc.addr = alloca i32, align 4
- %argv.addr = alloca i8**, align 4
- %v0 = alloca <16 x i8>, align 16
- %.compoundliteral = alloca <16 x i8>, align 16
- %v1 = alloca <16 x i8>, align 16
- %.compoundliteral1 = alloca <16 x i8>, align 16
- %unused_variable = alloca [16384 x i32], align 4
- %result = alloca <16 x i8>, align 16
- store i32 0, i32* %retval
- store i32 %argc, i32* %argc.addr, align 4
- store i8** %argv, i8*** %argv.addr, align 4
- store <16 x i8> <i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 16>, <16 x i8>* %.compoundliteral
- %0 = load <16 x i8>, <16 x i8>* %.compoundliteral
- store <16 x i8> %0, <16 x i8>* %v0, align 16
- store <16 x i8> zeroinitializer, <16 x i8>* %.compoundliteral1
- %1 = load <16 x i8>, <16 x i8>* %.compoundliteral1
- store <16 x i8> %1, <16 x i8>* %v1, align 16
- %2 = load <16 x i8>, <16 x i8>* %v0, align 16
- %3 = load <16 x i8>, <16 x i8>* %v1, align 16
- %mul = mul <16 x i8> %2, %3
- store <16 x i8> %mul, <16 x i8>* %result, align 16
- ret i32 0
-}
+; CHECK-LABEL: func:
+define void @func() {
+ %space = alloca i32, align 4
+ %stackspace = alloca[16384 x i32], align 4
+
+ ; ensure stackspace is not optimized out
+ %stackspace_casted = bitcast [16384 x i32]* %stackspace to i8*
+ store volatile i8* %stackspace_casted, i8** @ptrvar
-attributes #0 = { noinline "no-frame-pointer-elim"="true" }
+ ; Load values to increase register pressure.
+ %v0 = load volatile i32, i32* @var
+ %v1 = load volatile i32, i32* @var
+ %v2 = load volatile i32, i32* @var
+ %v3 = load volatile i32, i32* @var
+ %v4 = load volatile i32, i32* @var
+ %v5 = load volatile i32, i32* @var
+ %v6 = load volatile i32, i32* @var
+ %v7 = load volatile i32, i32* @var
+ %v8 = load volatile i32, i32* @var
+ %v9 = load volatile i32, i32* @var
+ %v10 = load volatile i32, i32* @var
+ %v11 = load volatile i32, i32* @var
+ %v12 = load volatile i32, i32* @var
+ %v13 = load volatile i32, i32* @var
+ %v14 = load volatile i32, i32* @var
+ %v15 = load volatile i32, i32* @var
+ %v16 = load volatile i32, i32* @var
+
+ ; Computing a stack-relative values needs an additional register.
+ ; We should get an emergency spill/reload for this.
+ ; CHECK: sw ${{.*}}, 0($sp)
+ ; CHECK: lw ${{.*}}, 0($sp)
+ store volatile i32 %v0, i32* %space
+
+ ; store values so they are used.
+ store volatile i32 %v0, i32* @var
+ store volatile i32 %v1, i32* @var
+ store volatile i32 %v2, i32* @var
+ store volatile i32 %v3, i32* @var
+ store volatile i32 %v4, i32* @var
+ store volatile i32 %v5, i32* @var
+ store volatile i32 %v6, i32* @var
+ store volatile i32 %v7, i32* @var
+ store volatile i32 %v8, i32* @var
+ store volatile i32 %v9, i32* @var
+ store volatile i32 %v10, i32* @var
+ store volatile i32 %v11, i32* @var
+ store volatile i32 %v12, i32* @var
+ store volatile i32 %v13, i32* @var
+ store volatile i32 %v14, i32* @var
+ store volatile i32 %v15, i32* @var
+ store volatile i32 %v16, i32* @var
+
+ ret void
+}
diff --git a/test/CodeGen/PowerPC/dyn-alloca-aligned.ll b/test/CodeGen/PowerPC/dyn-alloca-aligned.ll
index 0de2e220c2c..e0f28475d8f 100644
--- a/test/CodeGen/PowerPC/dyn-alloca-aligned.ll
+++ b/test/CodeGen/PowerPC/dyn-alloca-aligned.ll
@@ -25,8 +25,8 @@ entry:
; CHECK-DAG: li [[REG1:[0-9]+]], -128
; CHECK-DAG: neg [[REG2:[0-9]+]],
-; CHECK: and [[REG1]], [[REG2]], [[REG1]]
-; CHECK: stdux {{[0-9]+}}, 1, [[REG1]]
+; CHECK: and [[REG3:[0-9]+]], [[REG2]], [[REG1]]
+; CHECK: stdux {{[0-9]+}}, 1, [[REG3]]
; CHECK: blr
diff --git a/test/CodeGen/Thumb/large-stack.ll b/test/CodeGen/Thumb/large-stack.ll
index c5d1044e9d6..c72a67cd8ea 100644
--- a/test/CodeGen/Thumb/large-stack.ll
+++ b/test/CodeGen/Thumb/large-stack.ll
@@ -46,8 +46,8 @@ define i32 @test3() {
; CHECK-LABEL: test3:
; CHECK: ldr [[TEMP:r[0-7]]],
; CHECK: add sp, [[TEMP]]
-; CHECK: ldr [[TEMP]],
-; CHECK: add [[TEMP]], sp
+; CHECK: ldr [[TEMP2:r[0-7]]],
+; CHECK: add [[TEMP2]], sp
; EABI: ldr [[TEMP:r[0-7]]],
; EABI: add sp, [[TEMP]]
; IOS: subs r4, r7, #4