RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-01-31 20:51:52 +01:00
Code Issues Projects Releases Wiki Activity

[Pass Manager] remove EarlyCSE as clean-up for VectorCombine

Browse Source 
EarlyCSE was added with D75145, but the motivating test is
not regressed by removing the extra pass now. That might be
because VectorCombine altered the way it processes instructions,
or it might be from (re)moving VectorCombine in the pipeline.

The extra round of EarlyCSE appears to cost approximately
0.26% in compile-time as discussed in D80236, so we need some
evidence to justify its inclusion here, but we do not have
that (yet).

I suspect that between SLP and VectorCombine, we are creating
patterns that InstCombine and/or codegen are not prepared for,
but we will need to reduce those examples and include them as
PhaseOrdering and/or test-suite benchmarks.
This commit is contained in:
Sanjay Patel 2020-05-24 12:20:22 -04:00
parent 639aa30744
commit b7b5a06ca8
10 changed files with 3 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
lib/Passes/PassBuilder.cpp
View File

@ -1014,7 +1014,6 @@ ModulePassManager PassBuilder::buildModuleOptimizationPipeline(
// Enhance/cleanup vector code.
OptimizePM.addPass(VectorCombinePass());
OptimizePM.addPass(EarlyCSEPass());
OptimizePM.addPass(InstCombinePass());
// Unroll small loops to hide loop backedge latency and saturate any parallel

8
lib/Transforms/IPO/PassManagerBuilder.cpp
View File

@ -783,7 +783,6 @@ void PassManagerBuilder::populateModulePassManager(
// Enhance/cleanup vector code.
MPM.add(createVectorCombinePass());
MPM.add(createEarlyCSEPass());
addExtensionsToPM(EP_Peephole, MPM);
MPM.add(createInstructionCombiningPass());
@ -1019,7 +1018,6 @@ void PassManagerBuilder::addLTOOptimizationPasses(legacy::PassManagerBase &PM) {
// Now that we've optimized loops (in particular loop induction variables),
// we may have exposed more scalar opportunities. Run parts of the scalar
// optimizer again at this point.
PM.add(createVectorCombinePass());
PM.add(createInstructionCombiningPass()); // Initial cleanup
PM.add(createCFGSimplificationPass()); // if-convert
PM.add(createSCCPPass()); // Propagate exposed constants
@ -1027,10 +1025,10 @@ void PassManagerBuilder::addLTOOptimizationPasses(legacy::PassManagerBase &PM) {
PM.add(createBitTrackingDCEPass());
// More scalar chains could be vectorized due to more alias information
if (SLPVectorize) {
if (SLPVectorize)
PM.add(createSLPVectorizerPass()); // Vectorize parallel scalar chains.
PM.add(createVectorCombinePass()); // Clean up partial vectorization.
}
PM.add(createVectorCombinePass()); // Clean up partial vectorization.
// After vectorization, assume intrinsics may tell us more about pointer
// alignments.

3
test/CodeGen/AMDGPU/opt-pipeline.ll
View File

@ -246,7 +246,6 @@
; GCN-O1-NEXT: Simplify the CFG
; GCN-O1-NEXT: Dominator Tree Construction
; GCN-O1-NEXT: Optimize scalar/vector ops
; GCN-O1-NEXT: Early CSE
; GCN-O1-NEXT: Basic Alias Analysis (stateless AA impl)
; GCN-O1-NEXT: Function Alias Analysis Results
; GCN-O1-NEXT: Natural Loop Information
@ -597,7 +596,6 @@
; GCN-O2-NEXT: Inject TLI Mappings
; GCN-O2-NEXT: SLP Vectorizer
; GCN-O2-NEXT: Optimize scalar/vector ops
; GCN-O2-NEXT: Early CSE
; GCN-O2-NEXT: Optimization Remark Emitter
; GCN-O2-NEXT: Combine redundant instructions
; GCN-O2-NEXT: Canonicalize natural loops
@ -950,7 +948,6 @@
; GCN-O3-NEXT: Inject TLI Mappings
; GCN-O3-NEXT: SLP Vectorizer
; GCN-O3-NEXT: Optimize scalar/vector ops
; GCN-O3-NEXT: Early CSE
; GCN-O3-NEXT: Optimization Remark Emitter
; GCN-O3-NEXT: Combine redundant instructions
; GCN-O3-NEXT: Canonicalize natural loops

1
test/Other/new-pm-defaults.ll
View File

@ -261,7 +261,6 @@
; CHECK-O3-NEXT: Running pass: SLPVectorizerPass
; CHECK-Os-NEXT: Running pass: SLPVectorizerPass
; CHECK-O-NEXT: Running pass: VectorCombinePass
; CHECK-O-NEXT: Running pass: EarlyCSEPass
; CHECK-O-NEXT: Running pass: InstCombinePass
; CHECK-O-NEXT: Running pass: LoopUnrollPass
; CHECK-O-NEXT: Running pass: WarnMissedTransformationsPass

1
test/Other/new-pm-thinlto-defaults.ll
View File

@ -231,7 +231,6 @@
; CHECK-POSTLINK-O3-NEXT: Running pass: SLPVectorizerPass
; CHECK-POSTLINK-Os-NEXT: Running pass: SLPVectorizerPass
; CHECK-POSTLINK-O-NEXT: Running pass: VectorCombinePass
; CHECK-POSTLINK-O-NEXT: Running pass: EarlyCSEPass
; CHECK-POSTLINK-O-NEXT: Running pass: InstCombinePass
; CHECK-POSTLINK-O-NEXT: Running pass: LoopUnrollPass
; CHECK-POSTLINK-O-NEXT: Running pass: WarnMissedTransformationsPass

1
test/Other/new-pm-thinlto-postlink-pgo-defaults.ll
View File

@ -199,7 +199,6 @@
; CHECK-O3-NEXT: Running pass: SLPVectorizerPass
; CHECK-Os-NEXT: Running pass: SLPVectorizerPass
; CHECK-O-NEXT: Running pass: VectorCombinePass
; CHECK-O-NEXT: Running pass: EarlyCSEPass
; CHECK-O-NEXT: Running pass: InstCombinePass
; CHECK-O-NEXT: Running pass: LoopUnrollPass
; CHECK-O-NEXT: Running pass: WarnMissedTransformationsPass

1
test/Other/new-pm-thinlto-postlink-samplepgo-defaults.ll
View File

@ -210,7 +210,6 @@
; CHECK-O3-NEXT: Running pass: SLPVectorizerPass
; CHECK-Os-NEXT: Running pass: SLPVectorizerPass
; CHECK-O-NEXT: Running pass: VectorCombinePass
; CHECK-O-NEXT: Running pass: EarlyCSEPass
; CHECK-O-NEXT: Running pass: InstCombinePass
; CHECK-O-NEXT: Running pass: LoopUnrollPass
; CHECK-O-NEXT: Running pass: WarnMissedTransformationsPass

1
test/Other/opt-O2-pipeline.ll
View File

@ -253,7 +253,6 @@
; CHECK-NEXT: Inject TLI Mappings
; CHECK-NEXT: SLP Vectorizer
; CHECK-NEXT: Optimize scalar/vector ops
; CHECK-NEXT: Early CSE
; CHECK-NEXT: Optimization Remark Emitter
; CHECK-NEXT: Combine redundant instructions
; CHECK-NEXT: Canonicalize natural loops

1
test/Other/opt-O3-pipeline.ll
View File

@ -258,7 +258,6 @@
; CHECK-NEXT: Inject TLI Mappings
; CHECK-NEXT: SLP Vectorizer
; CHECK-NEXT: Optimize scalar/vector ops
; CHECK-NEXT: Early CSE
; CHECK-NEXT: Optimization Remark Emitter
; CHECK-NEXT: Combine redundant instructions
; CHECK-NEXT: Canonicalize natural loops

1
test/Other/opt-Os-pipeline.ll
View File

@ -239,7 +239,6 @@
; CHECK-NEXT: Inject TLI Mappings
; CHECK-NEXT: SLP Vectorizer
; CHECK-NEXT: Optimize scalar/vector ops
; CHECK-NEXT: Early CSE
; CHECK-NEXT: Optimization Remark Emitter
; CHECK-NEXT: Combine redundant instructions
; CHECK-NEXT: Canonicalize natural loops