6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2026-04-20 00:20:11 +00:00
Code Issues Projects Releases Wiki Activity

Allow vectorization of division by uniform power of 2.

Browse Source 
This patch adds support to recognize division by uniform power of 2 and modifies the cost table to vectorize division by uniform power of 2 whenever possible.
Updates Cost model for Loop and SLP Vectorizer.The cost table is currently only updated for X86 backend.
Thanks to Hal, Andrea, Sanjay for the review. (http://reviews.llvm.org/D4971)



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@216371 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Karthik Bhat
2014-08-25 04:56:54 +00:00
parent 9fdcfdd601
commit e637d65af3
11 changed files with 187 additions and 50 deletions
Download Patch File Download Diff File Expand all files Collapse all files
lib/Transforms/Vectorize/SLPVectorizer.cpp
+14 -4
View File
@@ -1425,6 +1425,10 @@ int BoUpSLP::getEntryCost(TreeEntry *E) {
TargetTransformInfo::OK_AnyValue;
TargetTransformInfo::OperandValueKind Op2VK =
TargetTransformInfo::OK_UniformConstantValue;
TargetTransformInfo::OperandValueProperties Op1VP =
TargetTransformInfo::OP_None;
TargetTransformInfo::OperandValueProperties Op2VP =
TargetTransformInfo::OP_None;
// If all operands are exactly the same ConstantInt then set the
// operand kind to OK_UniformConstantValue.
@@ -1446,11 +1450,17 @@ int BoUpSLP::getEntryCost(TreeEntry *E) {
CInt != cast<ConstantInt>(I->getOperand(1)))
Op2VK = TargetTransformInfo::OK_NonUniformConstantValue;
}
// FIXME: Currently cost of model modification for division by
// power of 2 is handled only for X86. Add support for other targets.
if (Op2VK == TargetTransformInfo::OK_UniformConstantValue && CInt &&
CInt->getValue().isPowerOf2())
Op2VP = TargetTransformInfo::OP_PowerOf2;
ScalarCost =
VecTy->getNumElements() *
TTI->getArithmeticInstrCost(Opcode, ScalarTy, Op1VK, Op2VK);
VecCost = TTI->getArithmeticInstrCost(Opcode, VecTy, Op1VK, Op2VK);
ScalarCost = VecTy->getNumElements() *
TTI->getArithmeticInstrCost(Opcode, ScalarTy, Op1VK, Op2VK,
Op1VP, Op2VP);
VecCost = TTI->getArithmeticInstrCost(Opcode, VecTy, Op1VK, Op2VK,
Op1VP, Op2VP);
}
return VecCost - ScalarCost;
}