search for: createlooprotatepass

...tly Polly uses "EP_EarlyAsPossible" to run as early as possible. As what you suggested: >Instead of removing canonicalization passes, I believe we may want to >move Polly to a later place in the pass manager. Possibly at the >beginning of the loop optimizer right before PM.add(createLoopRotatePass()); I want to move it to the point immediate after someone Loop optimization pass, e.g. MPM.add(createLoopRotatePass()). However no predefined ExtensionPointTy is available for this purpose. Instead, the "EP_ModuleOptimizerEarly" would move Polly before all loop optimization passes. In...

..., but this reduction may in large part being due to Polly not being able to optimise certain pieces of code. Instead of removing canonicalization passes, I believe we may want to move Polly to a later place in the pass manager. Possibly at the beginning of the loop optimizer right before PM.add(createLoopRotatePass()); We would then only need a very low number of canonicalization passes (possibly zero) and instead would put a couple of cleanup passes right after Polly. What do you think? Cheers, Tobias

...eInstructionCombiningPass()); //this is the most expensive canonicalization pass for flop benchmark PM.add(llvm::createCFGSimplificationPass()); PM.add(llvm::createTailCallEliminationPass()); PM.add(llvm::createCFGSimplificationPass()); PM.add(llvm::createReassociatePass()); PM.add(llvm::createLoopRotatePass()); PM.add(llvm::createInstructionCombiningPass()); PM.add(polly::createCodePreparationPass()); } Results are shown on http://188.40.87.11:8000/db_default/v4/nts/46?baseline=44&compare_to=44. As shown in the results, 13 benchmarks have >5% compile-time performance improvements by simply...

...s "EP_EarlyAsPossible" to run as early as possible. As what you suggested: >> Instead of removing canonicalization passes, I believe we may want to >> move Polly to a later place in the pass manager. Possibly at the >> beginning of the loop optimizer right before PM.add(createLoopRotatePass()); > I want to move it to the point immediate after someone Loop optimization pass, e.g. MPM.add(createLoopRotatePass()). However no predefined ExtensionPointTy is available for this purpose. Instead, the "EP_ModuleOptimizerEarly" would move Polly before all loop optimization passes....

...arlyAsPossible" to run as early as possible. As what you suggested: >>> Instead of removing canonicalization passes, I believe we may want to >>> move Polly to a later place in the pass manager. Possibly at the >>> beginning of the loop optimizer right before PM.add(createLoopRotatePass()); >> I want to move it to the point immediate after someone Loop optimization pass, e.g. MPM.add(createLoopRotatePass()). However no predefined ExtensionPointTy is available for this purpose. Instead, the "EP_ModuleOptimizerEarly" would move Polly before all loop optimization pas...

...:createPromoteMemoryToRegisterPass());     PM.add(llvm::createInstructionCombiningPass());     PM.add(llvm::createCFGSimplificationPass());     PM.add(llvm::createTailCallEliminationPass());     PM.add(llvm::createCFGSimplificationPass());     PM.add(llvm::createReassociatePass());     PM.add(llvm::createLoopRotatePass());     PM.add(llvm::createInstructionCombiningPass()); We can see that some of them are also called in common cases (lib/Transforms/IPO/PassManagerBuilder.cpp:181):   MPM.add(createEarlyCSEPass());   MPM.add(createJumpThreadingPass());   MPM.add(createCorrelatedValuePropagationPass());   MPM.add...

...eInstructionCombiningPass()); //this is the most expensive canonicalization pass for flop benchmark PM.add(llvm::createCFGSimplificationPass()); PM.add(llvm::createTailCallEliminationPass()); PM.add(llvm::createCFGSimplificationPass()); PM.add(llvm::createReassociatePass()); PM.add(llvm::createLoopRotatePass()); PM.add(llvm::createInstructionCombiningPass()); if (!SCEVCodegen) PM.add(polly::createIndVarSimplifyPass()); PM.add(polly::createCodePreparationPass()); } If we remove the first "InstructionCombining" pass, then the compile-time is reduced by more than 10% . The results repo...

Tobias Grosser wrote: > As said before, we could probably add it in between those two passes: > > MPM.add(createReassociatePass()); // Reassociate expressions > + addExtensionsToPM(EP_LoopOptimizerStart, MPM); > MPM.add(createLoopRotatePass()); // Rotate Loop As this is in the middle of other LNO passes, can you please rename s/EP_LoopOptimizerStart/EP_Polly_LNO/ or anything other than LoopOptimizerStart? Thanks, Sebastian -- Qualcomm Innovation Center, Inc. is a member of Code Aurora Forum, hosted by The Linux Foundation

...eInstructionCombiningPass()); //this is the most expensive canonicalization pass for flop benchmark PM.add(llvm::createCFGSimplificationPass()); PM.add(llvm::createTailCallEliminationPass()); PM.add(llvm::createCFGSimplificationPass()); PM.add(llvm::createReassociatePass()); PM.add(llvm::createLoopRotatePass()); PM.add(llvm::createInstructionCombiningPass()); PM.add(polly::createCodePreparationPass()); } Results are shown on http://188.40.87.11:8000/db_default/v4/nts/46?baseline=44&compare_to=44. As shown in the results, 13 benchmarks have >5% compile-time performance improvements by simply...

...); } However, I couldn't figure out how to call the LoopRotate and LoopUnroll passes since I cannot use addRequiredID or addRequired for these two transformations. In Scalar.h, I found: > Pass *createLoopUnrollPass(int Threshold = -1, int Count = -1, int AllowPartial = -1); > Pass *createLoopRotatePass(); Is to call these methods the way to go? How?, can somebody show me an excerpt? P.S. I tried hard on Google but I couldn't find anything related. Thanks! Jorge

...teInstructionCombiningPass()); >>> PM.add(llvm::createCFGSimplificationPass()); >>> PM.add(llvm::createTailCallEliminationPass()); >>> PM.add(llvm::createCFGSimplificationPass()); >>> PM.add(llvm::createReassociatePass()); >>> PM.add(llvm::createLoopRotatePass()); >>> PM.add(llvm::createInstructionCombiningPass()); >>> >>> if (!SCEVCodegen) >>> PM.add(polly::createIndVarSimplifyPass()); >>> >>> PM.add(polly::createCodePreparationPass()); >>> PM.add(polly::createRegionSimplify...

...PM.add(llvm::createInstructionCombiningPass()); > > PM.add(llvm::createCFGSimplificationPass()); > > PM.add(llvm::createTailCallEliminationPass()); > > PM.add(llvm::createCFGSimplificationPass()); > > PM.add(llvm::createReassociatePass()); > > PM.add(llvm::createLoopRotatePass()); > > PM.add(llvm::createInstructionCombiningPass()); > > > > if (!SCEVCodegen) > > PM.add(polly::createIndVarSimplifyPass()); > > > > PM.add(polly::createCodePreparationPass()); > > PM.add(polly::createRegionSimplifyPass()); > > Right....

...e > part being due to Polly not being able to optimise certain pieces of > code. > > Instead of removing canonicalization passes, I believe we may want > to move Polly to a later place in the pass manager. Possibly at the > beginning of the loop optimizer right before > PM.add(createLoopRotatePass()); > > We would then only need a very low number of canonicalization passes > (possibly zero) and instead would put a couple of cleanup passes > right > after Polly. What do you think? We experimented with moving Polly down the pass pipeline: when moving Polly past CSE, PRE and ot...

...e canonicalization routines and redo unrolling again. I have set partial unrolling on + have a huge threshold + allows expensive loop trip counts. Still it didn't unroll by 2. MPM.add(createLoopUnrollPass()); MPM.add(createCFGSimplificationPass()); MPM.add(createLoopSimplifyPass()); MPM.add(createLoopRotatePass(SizeLevel == 2 ? 0 : -1)); MPM.add(createLCSSAPass()); MPM.add(createIndVarSimplifyPass()); // Canonicalize indvars MPM.add(createLoopUnrollPass()); Digging deeper I found, that it fails in UnrollRuntimeLoopRemainder function, where it is unable to calculate the BackEdge taken amount....

...09:04 PM, Sebastian Pop wrote: > Tobias Grosser wrote: >> As said before, we could probably add it in between those two passes: >> >> MPM.add(createReassociatePass()); // Reassociate expressions >> + addExtensionsToPM(EP_LoopOptimizerStart, MPM); >> MPM.add(createLoopRotatePass()); // Rotate Loop > > As this is in the middle of other LNO passes, can you please rename > s/EP_LoopOptimizerStart/EP_Polly_LNO/ or anything other than LoopOptimizerStart? It is in the middle? The passes executed before are: MPM.add(createJumpThreadingPass()); // Thread jumps. MPM.a...

...PM.add(llvm::createPromoteMemoryToRegisterPass()); PM.add(llvm::createInstructionCombiningPass()); PM.add(llvm::createCFGSimplificationPass()); PM.add(llvm::createTailCallEliminationPass()); PM.add(llvm::createCFGSimplificationPass()); PM.add(llvm::createReassociatePass()); PM.add(llvm::createLoopRotatePass()); PM.add(llvm::createInstructionCombiningPass()); if (!SCEVCodegen) PM.add(polly::createIndVarSimplifyPass()); PM.add(polly::createCodePreparationPass()); PM.add(polly::createRegionSimplifyPass()); Sergei was saying that on some benchmarks PromoteMemoryToRegister was causing perfo...

...); > PM.add(llvm::createInstructionCombiningPass()); > PM.add(llvm::createCFGSimplificationPass()); > PM.add(llvm::createTailCallEliminationPass()); > PM.add(llvm::createCFGSimplificationPass()); > PM.add(llvm::createReassociatePass()); > PM.add(llvm::createLoopRotatePass()); > PM.add(llvm::createInstructionCombiningPass()); > > We can see that some of them are also called in common cases (lib/Transforms/IPO/PassManagerBuilder.cpp:181): > > MPM.add(createEarlyCSEPass()); > MPM.add(createJumpThreadingPass()); > MPM.add(createCorrela...

...figure out how to call the LoopRotate and > LoopUnroll passes since I cannot use addRequiredID or addRequired for > these two transformations. > > In Scalar.h, I found: > >> Pass *createLoopUnrollPass(int Threshold = -1, int Count = -1, int AllowPartial = -1); >> Pass *createLoopRotatePass(); > > > Is to call these methods the way to go? How?, can somebody show me an > excerpt? The create*Pass methods give you a Pass instance that you can add to a pass manager. If you're replacing "opt", you should look at the opt driver, opt.cpp to see how to do this. Yo...

...again. I have set > partial unrolling on + have a huge threshold + allows expensive loop trip > counts. Still it didn't unroll by 2. > > MPM.add(createLoopUnrollPass()); > > MPM.add(createCFGSimplificationPass()); > > MPM.add(createLoopSimplifyPass()); > > MPM.add(createLoopRotatePass(SizeLevel == 2 ? 0 : -1)); > > MPM.add(createLCSSAPass()); > > MPM.add(createIndVarSimplifyPass()); // Canonicalize indvars > > MPM.add(createLoopUnrollPass()); > > > Digging deeper I found, that it fails in UnrollRuntimeLoopRemainder > function, where it is una...

...gisterPass()); > PM.add(llvm::createInstructionCombiningPass()); > PM.add(llvm::createCFGSimplificationPass()); > PM.add(llvm::createTailCallEliminationPass()); > PM.add(llvm::createCFGSimplificationPass()); > PM.add(llvm::createReassociatePass()); > PM.add(llvm::createLoopRotatePass()); > PM.add(llvm::createInstructionCombiningPass()); > > if (!SCEVCodegen) > PM.add(polly::createIndVarSimplifyPass()); > > PM.add(polly::createCodePreparationPass()); > PM.add(polly::createRegionSimplifyPass()); Right. > Sergei was saying that on some be...