mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-15 20:29:48 +00:00
52610d84ad
This pass interchanges loops to provide a more cache-friendly memory access.
For e.g. given a loop like -
for(int i=0;i<N;i++)
for(int j=0;j<N;j++)
A[j][i] = A[j][i]+B[j][i];
is interchanged to -
for(int j=0;j<N;j++)
for(int i=0;i<N;i++)
A[j][i] = A[j][i]+B[j][i];
This pass is currently disabled by default.
To give a brief introduction it consists of 3 stages-
LoopInterchangeLegality : Checks the legality of loop interchange based on Dependency matrix.
LoopInterchangeProfitability: A very basic heuristic has been added to check for profitibility. This will evolve over time.
LoopInterchangeTransform : Which does the actual transform.
LNT Performance tests shows improvement in Polybench/linear-algebra/kernels/mvt and Polybench/linear-algebra/kernels/gemver becnmarks.
TODO:
1) Add support for reductions and lcssa phi.
2) Improve profitability model.
3) Improve loop selection algorithm to select best loop for interchange. Currently the innermost loop is selected for interchange.
4) Improve compile time regression found in llvm lnt due to this pass.
5) Fix issues in Dependency Analysis module.
A special thanks to Hal for reviewing this code.
Review: http://reviews.llvm.org/D7499
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@231458 91177308-0d34-0410-b5e6-96231b3b80d8
55 lines
1.1 KiB
CMake
55 lines
1.1 KiB
CMake
add_llvm_library(LLVMScalarOpts
|
|
ADCE.cpp
|
|
AlignmentFromAssumptions.cpp
|
|
BDCE.cpp
|
|
ConstantHoisting.cpp
|
|
ConstantProp.cpp
|
|
CorrelatedValuePropagation.cpp
|
|
DCE.cpp
|
|
DeadStoreElimination.cpp
|
|
EarlyCSE.cpp
|
|
FlattenCFGPass.cpp
|
|
GVN.cpp
|
|
InductiveRangeCheckElimination.cpp
|
|
IndVarSimplify.cpp
|
|
JumpThreading.cpp
|
|
LICM.cpp
|
|
LoadCombine.cpp
|
|
LoopDeletion.cpp
|
|
LoopIdiomRecognize.cpp
|
|
LoopInstSimplify.cpp
|
|
LoopInterchange.cpp
|
|
LoopRerollPass.cpp
|
|
LoopRotation.cpp
|
|
LoopStrengthReduce.cpp
|
|
LoopUnrollPass.cpp
|
|
LoopUnswitch.cpp
|
|
LowerAtomic.cpp
|
|
LowerExpectIntrinsic.cpp
|
|
MemCpyOptimizer.cpp
|
|
MergedLoadStoreMotion.cpp
|
|
PartiallyInlineLibCalls.cpp
|
|
PlaceSafepoints.cpp
|
|
Reassociate.cpp
|
|
Reg2Mem.cpp
|
|
RewriteStatepointsForGC.cpp
|
|
SCCP.cpp
|
|
SROA.cpp
|
|
SampleProfile.cpp
|
|
Scalar.cpp
|
|
ScalarReplAggregates.cpp
|
|
Scalarizer.cpp
|
|
SeparateConstOffsetFromGEP.cpp
|
|
SimplifyCFGPass.cpp
|
|
Sink.cpp
|
|
StraightLineStrengthReduce.cpp
|
|
StructurizeCFG.cpp
|
|
TailRecursionElimination.cpp
|
|
|
|
ADDITIONAL_HEADER_DIRS
|
|
${LLVM_MAIN_INCLUDE_DIR}/llvm/Transforms
|
|
${LLVM_MAIN_INCLUDE_DIR}/llvm/Transforms/Scalar
|
|
)
|
|
|
|
add_dependencies(LLVMScalarOpts intrinsics_gen)
|