Add a target lowering hook to control whether it's worthwhile to compress fp constant.

For x86, if sse2 is available, it's not a good idea since cvtss2sd is slower than a movsd load and it prevents load folding. On x87, it's important to shrink fp constant since fldt is very expensive.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@47931 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Evan Cheng
2008-03-05 01:30:59 +00:00
parent d19189e990
commit 6fd599fa69
4 changed files with 24 additions and 1 deletions

View File

@@ -504,7 +504,8 @@ static SDOperand ExpandConstantFP(ConstantFPSDNode *CFP, bool UseCP,
if (CFP->isValueValidForType(SVT, CFP->getValueAPF()) &&
// Only do this if the target has a native EXTLOAD instruction from
// smaller type.
TLI.isLoadXLegal(ISD::EXTLOAD, SVT)) {
TLI.isLoadXLegal(ISD::EXTLOAD, SVT) &&
TLI.ShouldShrinkFPConstant(VT)) {
const Type *SType = MVT::getTypeForValueType(SVT);
LLVMC = cast<ConstantFP>(ConstantExpr::getFPTrunc(LLVMC, SType));
VT = SVT;