[PATCH] D88471: [Passes] Run peeling as part of simple/full loop unrolling.

[Florian Hahn via Phabricator via llvm-commits]

fhahn updated this revision to Diff 295788.
fhahn added a comment.



In D88471#2308260 <https://reviews.llvm.org/D88471#2308260>, @lebedev.ri wrote:

> The patch doesn't seem to apply for me:

Rebased, should apply now.

In terms of runtime impact, I measured the following impact on SPEC2006 on ARM64 with -O3 -flto, outside the noise:

  test-suite...006/450.soplex/450.soplex.test   -2.4%
  test-suite...6/464.h264ref/464.h264ref.test    1.3%
  test-suite...T2006/473.astar/473.astar.test   -0.9%

Presumably the h264ref regression is related to wrong decisions in the cost modeling and probably warrants some further analysis.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D88471/new/

https://reviews.llvm.org/D88471

Files:
  llvm/include/llvm/Transforms/Scalar.h
  llvm/include/llvm/Transforms/Scalar/LoopUnrollPass.h
  llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
  llvm/lib/Transforms/Scalar/LoopUnrollPass.cpp
  llvm/test/Transforms/PhaseOrdering/X86/peel-before-lv-to-enable-vectorization.ll


Index: llvm/test/Transforms/PhaseOrdering/X86/peel-before-lv-to-enable-vectorization.ll
===================================================================
--- llvm/test/Transforms/PhaseOrdering/X86/peel-before-lv-to-enable-vectorization.ll
+++ llvm/test/Transforms/PhaseOrdering/X86/peel-before-lv-to-enable-vectorization.ll
@@ -11,7 +11,9 @@
 
 define i32 @test(i32* readonly %p, i32* readnone %q) {
 ; CHECK-LABEL: define i32 @test(
-; CHECK-NOT: vector.body
+; CHECK: vector.body:
+; CHECK:   %index.next = add i64 %index, 8
+; CHECK: middle.block:
 ;
 entry:
   %cmp.not7 = icmp eq i32* %p, %q
Index: llvm/lib/Transforms/Scalar/LoopUnrollPass.cpp
===================================================================
--- llvm/lib/Transforms/Scalar/LoopUnrollPass.cpp
+++ llvm/lib/Transforms/Scalar/LoopUnrollPass.cpp
@@ -1299,7 +1299,7 @@
 Pass *llvm::createSimpleLoopUnrollPass(int OptLevel, bool OnlyWhenForced,
                                        bool ForgetAllSCEV) {
   return createLoopUnrollPass(OptLevel, OnlyWhenForced, ForgetAllSCEV, -1, -1,
-                              0, 0, 0, 0);
+                              0, 0, 0, 1);
 }
 
 PreservedAnalyses LoopFullUnrollPass::run(Loop &L, LoopAnalysisManager &AM,
@@ -1327,7 +1327,7 @@
                                  OnlyWhenForced, ForgetSCEV, /*Count*/ None,
                                  /*Threshold*/ None, /*AllowPartial*/ false,
                                  /*Runtime*/ false, /*UpperBound*/ false,
-                                 /*AllowPeeling*/ false,
+                                 /*AllowPeeling*/ true,
                                  /*AllowProfileBasedPeeling*/ false,
                                  /*FullUnrollMaxCount*/ None) !=
                  LoopUnrollResult::Unmodified;
Index: llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
===================================================================
--- llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
+++ llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
@@ -453,7 +453,7 @@
     MPM.add(createLoopSimplifyCFGPass());
   }
 
-  // Unroll small loops
+  // Unroll small loops and perform peeling.
   MPM.add(createSimpleLoopUnrollPass(OptLevel, DisableUnrollLoops,
                                      ForgetAllSCEVInLoopUnroll));
   addExtensionsToPM(EP_LoopOptimizerEnd, MPM);
@@ -1046,7 +1046,7 @@
   if (EnableLoopFlatten)
     PM.add(createLoopFlattenPass());
 
-  // Unroll small loops
+  // Unroll small loops and perform peeling.
   PM.add(createSimpleLoopUnrollPass(OptLevel, DisableUnrollLoops,
                                     ForgetAllSCEVInLoopUnroll));
   PM.add(createLoopVectorizePass(true, !LoopVectorize));
Index: llvm/include/llvm/Transforms/Scalar/LoopUnrollPass.h
===================================================================
--- llvm/include/llvm/Transforms/Scalar/LoopUnrollPass.h
+++ llvm/include/llvm/Transforms/Scalar/LoopUnrollPass.h
@@ -22,7 +22,7 @@
 class Loop;
 class LPMUpdater;
 
-/// Loop unroll pass that only does full loop unrolling.
+/// Loop unroll pass that only does full loop unrolling and peeling.
 class LoopFullUnrollPass : public PassInfoMixin<LoopFullUnrollPass> {
   const int OptLevel;
 
Index: llvm/include/llvm/Transforms/Scalar.h
===================================================================
--- llvm/include/llvm/Transforms/Scalar.h
+++ llvm/include/llvm/Transforms/Scalar.h
@@ -184,7 +184,8 @@
                            int Count = -1, int AllowPartial = -1,
                            int Runtime = -1, int UpperBound = -1,
                            int AllowPeeling = -1);
-// Create an unrolling pass for full unrolling that uses exact trip count only.
+// Create an unrolling pass for full unrolling that uses exact trip count only
+// and also does peeling.
 Pass *createSimpleLoopUnrollPass(int OptLevel = 2, bool OnlyWhenForced = false,
                                  bool ForgetAllSCEV = false);
 


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D88471.295788.patch
Type: text/x-patch
Size: 3934 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20201002/d013875e/attachment.bin>