[vectorizer] Fix a trivial oversight where we always requested the

number of vector registers rather than toggling between vector and
scalar register number based on VF. I don't have a test case as
I spotted this by inspection and on X86 it only makes a difference if
your target is lacking SSE and thus has *no* vector registers.

If someone wants to add a test case for this for ARM or somewhere else
where this is more significant, that would be awesome.

Also made the variable name a bit more sensible while I'm here.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@200211 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Chandler Carruth 2014-01-27 11:12:14 +00:00
parent 4bfa6fecc1
commit 3fa842d791

View File

@ -4962,9 +4962,9 @@ LoopVectorizationCostModel::selectUnrollFactor(bool OptForSize,
if (TC > 1 && TC < TinyTripCountUnrollThreshold)
return 1;
unsigned TargetVectorRegisters = TTI.getNumberOfRegisters(true);
DEBUG(dbgs() << "LV: The target has " << TargetVectorRegisters <<
" vector registers\n");
unsigned TargetNumRegisters = TTI.getNumberOfRegisters(VF > 1);
DEBUG(dbgs() << "LV: The target has " << TargetNumRegisters <<
" registers\n");
LoopVectorizationCostModel::RegisterUsage R = calculateRegisterUsage();
// We divide by these constants so assume that we have at least one
@ -4978,7 +4978,7 @@ LoopVectorizationCostModel::selectUnrollFactor(bool OptForSize,
// Next, divide the remaining registers by the number of registers that is
// required by the loop, in order to estimate how many parallel instances
// fit without causing spills.
unsigned UF = (TargetVectorRegisters - R.LoopInvariantRegs) / R.MaxLocalUsers;
unsigned UF = (TargetNumRegisters - R.LoopInvariantRegs) / R.MaxLocalUsers;
// Clamp the unroll factor ranges to reasonable factors.
unsigned MaxUnrollSize = TTI.getMaximumUnrollFactor();