Account for scalarization costs in BasicTTI::getMemoryOpCost for extending vector loads

When a vector type legalizes to a larger vector type, and the target does not
support the associated extending load (or truncating store), then legalization
will scalarize the load (or store) resulting in an associated scalarization
cost.  BasicTTI::getMemoryOpCost needs to account for this.

Between this, and r205487, PowerPC on the P7 with VSX enabled shows:

MultiSource/Benchmarks/PAQ8p/paq8p: 43% speedup
SingleSource/Benchmarks/BenchmarkGame/puzzle: 51% speedup
SingleSource/UnitTests/Vectorizer/gcc-loops 28% speedup

(some of these are new; some of these, such as PAQ8p, just reverse regressions
that VSX support would trigger)

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@205495 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Hal Finkel 2014-04-03 00:53:59 +00:00
parent 14ae43449c
commit d68b03bcd2
2 changed files with 29 additions and 2 deletions

View File

@ -416,8 +416,30 @@ unsigned BasicTTI::getMemoryOpCost(unsigned Opcode, Type *Src,
assert(!Src->isVoidTy() && "Invalid type");
std::pair<unsigned, MVT> LT = getTLI()->getTypeLegalizationCost(Src);
// Assume that all loads of legal types cost 1.
return LT.first;
// Assuming that all loads of legal types cost 1.
unsigned Cost = LT.first;
if (Src->isVectorTy() &&
Src->getPrimitiveSizeInBits() < LT.second.getSizeInBits()) {
// This is a vector load that legalizes to a larger type than the vector
// itself. Unless the corresponding extending load or truncating store is
// legal, then this will scalarize.
TargetLowering::LegalizeAction LA;
MVT MemVT = getTLI()->getSimpleValueType(Src, true);
if (Opcode == Instruction::Store)
LA = getTLI()->getTruncStoreAction(LT.second, MemVT);
else
LA = getTLI()->getLoadExtAction(ISD::EXTLOAD, MemVT);
if (LA != TargetLowering::Legal && LA != TargetLowering::Custom) {
// This is a vector load/store for some illegal type that is scalarized.
// We must account for the cost of building or decomposing the vector.
Cost += getScalarizationOverhead(Src, Opcode != Instruction::Store,
Opcode == Instruction::Store);
}
}
return Cost;
}
unsigned BasicTTI::getIntrinsicInstrCost(Intrinsic::ID IID, Type *RetTy,

View File

@ -29,6 +29,11 @@ define i32 @loads(i32 %arg) {
; CHECK: cost of 4 {{.*}} load
load i128* undef, align 4
; FIXME: There actually are sub-vector Altivec loads, and so we could handle
; this with a small expense, but we don't currently.
; CHECK: cost of 60 {{.*}} load
load <4 x i16>* undef, align 2
ret i32 undef
}