nicolas/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[AArch64] Consider widening instructions in cost calculations

Browse Source 
The AArch64 instruction set has a few "widening" instructions (e.g., uaddl,
saddl, uaddw, etc.) that take one or more doubleword operands and produce
quadword results. The operands are automatically sign- or zero-extended as
appropriate. However, in LLVM IR, these extends are explicit. This patch
updates TTI to consider these widening instructions as single operations whose
cost is attached to the arithmetic instruction. It marks extends that are part
of a widening operation "free" and applies a sub-target specified overhead
(zero by default) to the arithmetic instructions.

Differential Revision: https://reviews.llvm.org/D32706

llvm-svn: 302582
This commit is contained in:
Matthew Simpson
2017-05-09 20:18:12 +00:00
parent 7caaa79879
commit 78fd46b230
5 changed files with 734 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
View File

@@ -1819,11 +1819,13 @@ int BoUpSLP::getEntryCost(TreeEntry *E) {
CInt->getValue().isPowerOf2())
Op2VP = TargetTransformInfo::OP_PowerOf2;
int ScalarCost = VecTy->getNumElements() *
TTI->getArithmeticInstrCost(Opcode, ScalarTy, Op1VK,
Op2VK, Op1VP, Op2VP);
SmallVector<const Value *, 4> Operands(VL0->operand_values());
int ScalarCost =
VecTy->getNumElements() *
TTI->getArithmeticInstrCost(Opcode, ScalarTy, Op1VK, Op2VK, Op1VP,
Op2VP, Operands);
int VecCost = TTI->getArithmeticInstrCost(Opcode, VecTy, Op1VK, Op2VK,
Op1VP, Op2VP);
Op1VP, Op2VP, Operands);
return VecCost - ScalarCost;
}
case Instruction::GetElementPtr: {