summaryrefslogtreecommitdiffstats
path: root/llvm/lib
diff options
context:
space:
mode:
authorRobert Lougher <rob.lougher@gmail.com>2015-01-29 16:18:29 +0000
committerRobert Lougher <rob.lougher@gmail.com>2015-01-29 16:18:29 +0000
commitc69cfeeafa166435be3e5d6bace9a4c392d09fd4 (patch)
tree4543d264acdee8db5e4daa6cba817f920a65eed2 /llvm/lib
parenta749b3ee6a1598e1d0050524227f59348098fd30 (diff)
downloadbcm5719-llvm-c69cfeeafa166435be3e5d6bace9a4c392d09fd4.tar.gz
bcm5719-llvm-c69cfeeafa166435be3e5d6bace9a4c392d09fd4.zip
[X86] Use single add/sub for large stack offsets
For large stack offsets the compiler generates multiple immediate mode sub/add instructions in the prologue/epilogue. This patch makes the compiler place the final amount to be added/subtracted into a register, which is then added/substracted with a single operation. Differential Revision: http://reviews.llvm.org/D7226 llvm-svn: 227458
Diffstat (limited to 'llvm/lib')
-rw-r--r--llvm/lib/Target/X86/X86FrameLowering.cpp59
1 files changed, 46 insertions, 13 deletions
diff --git a/llvm/lib/Target/X86/X86FrameLowering.cpp b/llvm/lib/Target/X86/X86FrameLowering.cpp
index 16aab16d63e..bb2007dd682 100644
--- a/llvm/lib/Target/X86/X86FrameLowering.cpp
+++ b/llvm/lib/Target/X86/X86FrameLowering.cpp
@@ -82,6 +82,14 @@ static unsigned getADDriOpcode(unsigned IsLP64, int64_t Imm) {
}
}
+static unsigned getSUBrrOpcode(unsigned isLP64) {
+ return isLP64 ? X86::SUB64rr : X86::SUB32rr;
+}
+
+static unsigned getADDrrOpcode(unsigned isLP64) {
+ return isLP64 ? X86::ADD64rr : X86::ADD32rr;
+}
+
static unsigned getANDriOpcode(bool IsLP64, int64_t Imm) {
if (IsLP64) {
if (isInt<8>(Imm))
@@ -165,6 +173,18 @@ static unsigned findDeadCallerSavedReg(MachineBasicBlock &MBB,
return 0;
}
+static bool isEAXLiveIn(MachineFunction &MF) {
+ for (MachineRegisterInfo::livein_iterator II = MF.getRegInfo().livein_begin(),
+ EE = MF.getRegInfo().livein_end(); II != EE; ++II) {
+ unsigned Reg = II->first;
+
+ if (Reg == X86::RAX || Reg == X86::EAX || Reg == X86::AX ||
+ Reg == X86::AH || Reg == X86::AL)
+ return true;
+ }
+
+ return false;
+}
/// emitSPUpdate - Emit a series of instructions to increment / decrement the
/// stack pointer by a constant value.
@@ -187,6 +207,32 @@ void emitSPUpdate(MachineBasicBlock &MBB, MachineBasicBlock::iterator &MBBI,
DebugLoc DL = MBB.findDebugLoc(MBBI);
while (Offset) {
+ if (Offset > Chunk) {
+ // Rather than emit a long series of instructions for large offsets,
+ // load the offset into a register and do one sub/add
+ unsigned Reg = 0;
+
+ if (isSub && !isEAXLiveIn(*MBB.getParent()))
+ Reg = (unsigned)(Is64BitTarget ? X86::RAX : X86::EAX);
+ else
+ Reg = findDeadCallerSavedReg(MBB, MBBI, TRI, Is64BitTarget);
+
+ if (Reg) {
+ Opc = Is64BitTarget ? X86::MOV64ri : X86::MOV32ri;
+ BuildMI(MBB, MBBI, DL, TII.get(Opc), Reg)
+ .addImm(Offset);
+ Opc = isSub
+ ? getSUBrrOpcode(Is64BitTarget)
+ : getADDrrOpcode(Is64BitTarget);
+ MachineInstr *MI = BuildMI(MBB, MBBI, DL, TII.get(Opc), StackPtr)
+ .addReg(StackPtr)
+ .addReg(Reg);
+ MI->getOperand(3).setIsDead(); // The EFLAGS implicit def is dead.
+ Offset = 0;
+ continue;
+ }
+ }
+
uint64_t ThisVal = (Offset > Chunk) ? Chunk : Offset;
if (ThisVal == (Is64BitTarget ? 8 : 4)) {
// Use push / pop instead.
@@ -316,19 +362,6 @@ static int mergeSPUpdates(MachineBasicBlock &MBB,
return Offset;
}
-static bool isEAXLiveIn(MachineFunction &MF) {
- for (MachineRegisterInfo::livein_iterator II = MF.getRegInfo().livein_begin(),
- EE = MF.getRegInfo().livein_end(); II != EE; ++II) {
- unsigned Reg = II->first;
-
- if (Reg == X86::EAX || Reg == X86::AX ||
- Reg == X86::AH || Reg == X86::AL)
- return true;
- }
-
- return false;
-}
-
void
X86FrameLowering::emitCalleeSavedFrameMoves(MachineBasicBlock &MBB,
MachineBasicBlock::iterator MBBI,
OpenPOWER on IntegriCloud