6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2024-12-13 20:32:21 +00:00
Code Issues Projects Releases Wiki Activity

[PeepholeOptimizer] Take advantage of the isInsertSubreg property in the

Browse Source 
advanced copy optimization.

This is the final step patch toward transforming:
udiv    r0, r0, r2
udiv    r1, r1, r3
vmov.32 d16[0], r0
vmov.32 d16[1], r1
vmov    r0, r1, d16
bx      lr

into:
udiv    r0, r0, r2
udiv    r1, r1, r3
bx      lr

Indeed, thanks to this patch, this optimization is able to look through
vmov.32 d16[0], r0
vmov.32 d16[1], r1

and is able to rewrite the following sequence:
vmov.32 d16[0], r0
vmov.32 d16[1], r1
vmov    r0, r1, d16

into simple generic GPR copies that the coalescer managed to remove.

<rdar://problem/12702965>


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@216144 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Quentin Colombet 2014-08-21 00:19:16 +00:00
parent 7599acc2af
commit e817bdd304
2 changed files with 17 additions and 37 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

45
lib/CodeGen/PeepholeOptimizer.cpp
View File

@ -161,8 +161,9 @@ namespace {
/// \brief Check whether \p MI is a copy like instruction that is
/// not recognized by the register coalescer.
bool isUncoalescableCopy(const MachineInstr &MI) {
return MI.isBitcast() || (!DisableAdvCopyOpt &&
(MI.isRegSequenceLike() ||
return MI.isBitcast() ||
(!DisableAdvCopyOpt &&
(MI.isRegSequenceLike() || MI.isInsertSubregLike() ||
MI.isExtractSubregLike()));
}
};
@ -1271,44 +1272,26 @@ bool ValueTracker::getNextSourceFromRegSequence(unsigned &SrcReg,
return false;
}
/// Extract the inputs from INSERT_SUBREG.
/// INSERT_SUBREG vreg0:sub0, vreg1:sub1, sub3 would produce:
/// - BaseReg: vreg0:sub0
/// - InsertedReg: vreg1:sub1, sub3
static void
getInsertSubregInputs(const MachineInstr &MI,
TargetInstrInfo::RegSubRegPair &BaseReg,
TargetInstrInfo::RegSubRegPairAndIdx &InsertedReg) {
assert(MI.isInsertSubreg() && "Instruction do not have the proper type");
// We are looking at:
// Def = INSERT_SUBREG v0, v1, sub0.
const MachineOperand &MOBaseReg = MI.getOperand(1);
const MachineOperand &MOInsertedReg = MI.getOperand(2);
const MachineOperand &MOSubIdx = MI.getOperand(3);
assert(MOSubIdx.isImm() &&
"One of the subindex of the reg_sequence is not an immediate");
BaseReg.Reg = MOBaseReg.getReg();
BaseReg.SubReg = MOBaseReg.getSubReg();
InsertedReg.Reg = MOInsertedReg.getReg();
InsertedReg.SubReg = MOInsertedReg.getSubReg();
InsertedReg.SubIdx = (unsigned)MOSubIdx.getImm();
}
bool ValueTracker::getNextSourceFromInsertSubreg(unsigned &SrcReg,
unsigned &SrcSubReg) {
assert(Def->isInsertSubreg() && "Invalid definition");
assert((Def->isInsertSubreg() || Def->isInsertSubregLike()) &&
"Invalid definition");
if (Def->getOperand(DefIdx).getSubReg())
// If we are composing subreg, bails out.
// Same remark as getNextSourceFromRegSequence.
// I.e., this may be turned into an assert.
return false;
if (!TII)
// We could handle the REG_SEQUENCE here, but we do not want to
// duplicate the code from the generic TII.
return false;
TargetInstrInfo::RegSubRegPair BaseReg;
TargetInstrInfo::RegSubRegPairAndIdx InsertedReg;
assert(DefIdx == 0 && "Invalid definition");
getInsertSubregInputs(*Def, BaseReg, InsertedReg);
if (!TII->getInsertSubregInputs(*Def, DefIdx, BaseReg, InsertedReg))
return false;
// We are looking at:
// Def = INSERT_SUBREG v0, v1, sub1
@ -1416,7 +1399,7 @@ bool ValueTracker::getNextSourceImpl(unsigned &SrcReg, unsigned &SrcSubReg) {
return false;
if (Def->isRegSequence() || Def->isRegSequenceLike())
return getNextSourceFromRegSequence(SrcReg, SrcSubReg);
if (Def->isInsertSubreg())
if (Def->isInsertSubreg() || Def->isInsertSubregLike())
return getNextSourceFromInsertSubreg(SrcReg, SrcSubReg);
if (Def->isExtractSubreg() || Def->isExtractSubregLike())
return getNextSourceFromExtractSubreg(SrcReg, SrcSubReg);

7
test/CodeGen/ARM/adv-copy-opt.ll
View File

@ -26,11 +26,8 @@
; NOOPT-NEXT: bx lr
;
; OPT-NOT: vmov
; OPT: udiv [[RES_LOW:r[0-9]+]], r0, r2
; OPT-NEXT: udiv [[RES_HIGH:r[0-9]+]], r1, r3
; OPT-NEXT: vmov.32 [[RES:d[0-9]+]][0], [[RES_LOW]]
; OPT-NEXT: vmov.32 [[RES]][1], [[RES_HIGH]]
; OPT-NEXT: vmov r0, r1, [[RES]]
; OPT: udiv r0, r0, r2
; OPT-NEXT: udiv r1, r1, r3
; OPT-NEXT: bx lr
define <2 x i32> @simpleVectorDiv(<2 x i32> %A, <2 x i32> %B) nounwind {
entry: