[PATCH] D105996: [AArch64] Enable Upper bound unrolling universally

[JinGu Kang via Phabricator via llvm-commits]

jaykang10 updated this revision to Diff 358862.
jaykang10 added a comment.

Following comments from @SjoerdMeijer and @dmgreen, updated patch.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D105996/new/

https://reviews.llvm.org/D105996

Files:
  llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
  llvm/test/Transforms/LoopUnroll/AArch64/unroll-upperbound.ll


Index: llvm/test/Transforms/LoopUnroll/AArch64/unroll-upperbound.ll
===================================================================
--- /dev/null
+++ llvm/test/Transforms/LoopUnroll/AArch64/unroll-upperbound.ll
@@ -0,0 +1,55 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt < %s -S -loop-unroll -mtriple aarch64 | FileCheck %s
+
+define void @test(i1 %cond) {
+; CHECK-LABEL: @test(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
+; CHECK:       for.body:
+; CHECK-NEXT:    switch i32 0, label [[FOR_BODY_IF_END6_CRIT_EDGE:%.*]] [
+; CHECK-NEXT:    i32 2, label [[IF_THEN4:%.*]]
+; CHECK-NEXT:    ]
+; CHECK:       for.body.if.end6_crit_edge:
+; CHECK-NEXT:    br label [[IF_THEN4]]
+; CHECK:       if.then4:
+; CHECK-NEXT:    br i1 false, label [[FOR_END:%.*]], label [[FOR_BODY_1:%.*]]
+; CHECK:       for.end:
+; CHECK-NEXT:    ret void
+; CHECK:       for.body.1:
+; CHECK-NEXT:    switch i32 1, label [[FOR_BODY_IF_END6_CRIT_EDGE_1:%.*]] [
+; CHECK-NEXT:    i32 2, label [[IF_THEN4_1:%.*]]
+; CHECK-NEXT:    ]
+; CHECK:       for.body.if.end6_crit_edge.1:
+; CHECK-NEXT:    br label [[IF_THEN4_1]]
+; CHECK:       if.then4.1:
+; CHECK-NEXT:    br i1 [[COND:%.*]], label [[FOR_END]], label [[FOR_BODY_2:%.*]]
+; CHECK:       for.body.2:
+; CHECK-NEXT:    switch i32 2, label [[FOR_BODY_IF_END6_CRIT_EDGE_2:%.*]] [
+; CHECK-NEXT:    i32 2, label [[IF_THEN4_2:%.*]]
+; CHECK-NEXT:    ]
+; CHECK:       for.body.if.end6_crit_edge.2:
+; CHECK-NEXT:    br label [[IF_THEN4_2]]
+; CHECK:       if.then4.2:
+; CHECK-NEXT:    br label [[FOR_END]]
+;
+entry:
+  %0 = select i1 %cond, i32 2, i32 3
+  br label %for.body
+
+for.body:
+  %i.017 = phi i32 [ 0, %entry ], [ %inc, %if.then4 ]
+  switch i32 %i.017, label %for.body.if.end6_crit_edge [
+  i32 2, label %if.then4
+  ]
+
+for.body.if.end6_crit_edge:
+  br label %if.then4
+
+if.then4:
+  %inc = add nuw nsw i32 %i.017, 1
+  %exitcond.not = icmp eq i32 %inc, %0
+  br i1 %exitcond.not, label %for.end, label %for.body
+
+for.end:
+  ret void
+}
Index: llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
===================================================================
--- llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -1568,6 +1568,8 @@
   // Enable partial unrolling and runtime unrolling.
   BaseT::getUnrollingPreferences(L, SE, UP);
 
+  UP.UpperBound = true;
+
   // For inner loop, it is more likely to be a hot one, and the runtime check
   // can be promoted out from LICM pass, so the overhead is less, let's try
   // a larger threshold to unroll more loops.
@@ -1608,7 +1610,6 @@
       !ST->getSchedModel().isOutOfOrder()) {
     UP.Runtime = true;
     UP.Partial = true;
-    UP.UpperBound = true;
     UP.UnrollRemainder = true;
     UP.DefaultUnrollRuntimeCount = 4;
 


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D105996.358862.patch
Type: text/x-patch
Size: 2879 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20210715/c6f6b5af/attachment.bin>