6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2025-10-25 10:27:04 +00:00
Code Issues Projects Releases Wiki Activity

ARM cost model: Address computation in vector mem ops not free

Browse Source 
Adds a function to target transform info to query for the cost of address
computation. The cost model analysis pass now also queries this interface.
The code in LoopVectorize adds the cost of address computation as part of the
memory instruction cost calculation. Only there, we know whether the instruction
will be scalarized or not.
Increase the penality for inserting in to D registers on swift. This becomes
necessary because we now always assume that address computation has a cost and
three is a closer value to the architecture.

radar://13097204

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@174713 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Arnold Schwaighofer
2013-02-08 14:50:48 +00:00
parent f64edf8d80
commit fb55a8fd7c
9 changed files with 134 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
lib/Transforms/Vectorize/LoopVectorize.cpp
View File

@@ -3056,9 +3056,10 @@ LoopVectorizationCostModel::getInstructionCost(Instruction *I, unsigned VF) {
// TODO: We need to estimate the cost of intrinsic calls.
switch (I->getOpcode()) {
case Instruction::GetElementPtr:
// We mark this instruction as zero-cost because scalar GEPs are usually
// lowered to the intruction addressing mode. At the moment we don't
// generate vector geps.
// We mark this instruction as zero-cost because the cost of GEPs in
// vectorized code depends on whether the corresponding memory instruction
// is scalarized or not. Therefore, we handle GEPs with the memory
// instruction cost.
return 0;
case Instruction::Br: {
return TTI.getCFInstrCost(I->getOpcode());
@@ -3113,9 +3114,12 @@ LoopVectorizationCostModel::getInstructionCost(Instruction *I, unsigned VF) {
unsigned AS = SI ? SI->getPointerAddressSpace() :
LI->getPointerAddressSpace();
Value *Ptr = SI ? SI->getPointerOperand() : LI->getPointerOperand();
// We add the cost of address computation here instead of with the gep
// instruction because only here we know whether the operation is
// scalarized.
if (VF == 1)
return TTI.getMemoryOpCost(I->getOpcode(), VectorTy, Alignment, AS);
return TTI.getAddressComputationCost(VectorTy) +
TTI.getMemoryOpCost(I->getOpcode(), VectorTy, Alignment, AS);
// Scalarized loads/stores.
int Stride = Legal->isConsecutivePtr(Ptr);
@@ -3135,15 +3139,17 @@ LoopVectorizationCostModel::getInstructionCost(Instruction *I, unsigned VF) {
VectorTy, i);
}
// The cost of the scalar stores.
// The cost of the scalar loads/stores.
Cost += VF * TTI.getAddressComputationCost(ValTy->getScalarType());
Cost += VF * TTI.getMemoryOpCost(I->getOpcode(), ValTy->getScalarType(),
Alignment, AS);
return Cost;
}
// Wide load/stores.
unsigned Cost = TTI.getMemoryOpCost(I->getOpcode(), VectorTy,
Alignment, AS);
unsigned Cost = TTI.getAddressComputationCost(VectorTy);
Cost += TTI.getMemoryOpCost(I->getOpcode(), VectorTy, Alignment, AS);
if (Reverse)
Cost += TTI.getShuffleCost(TargetTransformInfo::SK_Reverse,
VectorTy, 0);