[llvm] 829c1b6 - [LoopInterchange] fix tightlyNested() in LoopInterchange legality

[via llvm-commits]

Author: Congzhe Cao
Date: 2021-03-24T15:49:25-04:00
New Revision: 829c1b644390e35bd179c06f45223f778dfc5ab2

URL: https://github.com/llvm/llvm-project/commit/829c1b644390e35bd179c06f45223f778dfc5ab2
DIFF: https://github.com/llvm/llvm-project/commit/829c1b644390e35bd179c06f45223f778dfc5ab2.diff

LOG: [LoopInterchange] fix tightlyNested() in LoopInterchange legality

This is yet another attempt to fix tightlyNested().

Add checks in tightlyNested() for the inner loop exit block,
such that 1) if there is control-flow divergence in between the inner
loop exit block and the outer loop latch, or 2) if the inner loop exit
block contains unsafe instructions, tightlyNested() returns false.

The reasoning behind is that after interchange, the original inner loop
exit block, which was part of the outer loop, would be put into the new
inner loop, and will be executed different number of times before and
after interchange. Thus it should be dealt with appropriately.

Reviewed By: Whitney

Differential Revision: https://reviews.llvm.org/D98263

Added: 
    

Modified: 
    llvm/lib/Transforms/Scalar/LoopInterchange.cpp
    llvm/test/Transforms/LoopInterchange/not-interchanged-tightly-nested.ll

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Transforms/Scalar/LoopInterchange.cpp b/llvm/lib/Transforms/Scalar/LoopInterchange.cpp
index 0162bf1307af0..5da619fc08f26 100644
--- a/llvm/lib/Transforms/Scalar/LoopInterchange.cpp
+++ b/llvm/lib/Transforms/Scalar/LoopInterchange.cpp
@@ -19,6 +19,7 @@
 #include "llvm/ADT/StringRef.h"
 #include "llvm/Analysis/DependenceAnalysis.h"
 #include "llvm/Analysis/LoopInfo.h"
+#include "llvm/Analysis/LoopNestAnalysis.h"
 #include "llvm/Analysis/LoopPass.h"
 #include "llvm/Analysis/OptimizationRemarkEmitter.h"
 #include "llvm/Analysis/ScalarEvolution.h"
@@ -617,6 +618,22 @@ bool LoopInterchangeLegality::tightlyNested(Loop *OuterLoop, Loop *InnerLoop) {
       containsUnsafeInstructions(InnerLoopPreHeader))
     return false;
 
+  BasicBlock *InnerLoopExit = InnerLoop->getExitBlock();
+  // Ensure the inner loop exit block flows to the outer loop latch possibly
+  // through empty blocks.
+  const BasicBlock &SuccInner =
+      LoopNest::skipEmptyBlockUntil(InnerLoopExit, OuterLoopLatch);
+  if (&SuccInner != OuterLoopLatch) {
+    LLVM_DEBUG(dbgs() << "Inner loop exit block " << *InnerLoopExit
+                      << " does not lead to the outer loop latch.\n";);
+    return false;
+  }
+  // The inner loop exit block does flow to the outer loop latch and not some
+  // other BBs, now make sure it contains safe instructions, since it will be
+  // moved into the (new) inner loop after interchange.
+  if (containsUnsafeInstructions(InnerLoopExit))
+    return false;
+
   LLVM_DEBUG(dbgs() << "Loops are perfectly nested\n");
   // We have a perfect loop nest.
   return true;

diff  --git a/llvm/test/Transforms/LoopInterchange/not-interchanged-tightly-nested.ll b/llvm/test/Transforms/LoopInterchange/not-interchanged-tightly-nested.ll
index 167d4bfdc8bb5..82f661502f573 100644
--- a/llvm/test/Transforms/LoopInterchange/not-interchanged-tightly-nested.ll
+++ b/llvm/test/Transforms/LoopInterchange/not-interchanged-tightly-nested.ll
@@ -103,3 +103,41 @@ for.inc10:
 for.end12:
   ret void
 }
+
+;; The following Loop is not considered tightly nested and is not interchanged.
+;; The outer loop header does not branch to the inner loop preheader, or the
+;; inner loop header, or the outer loop latch.
+; CHECK: Not interchanging loops. Cannot prove legality.
+define void @interchange_07(i32 %k, i32 %N, i32 %ny) {
+entry:
+  br label %for1.header
+
+for1.header:
+  %j23 = phi i32 [ 0, %entry ], [ %j.next24, %for1.inc10 ]
+  %cmp21 = icmp slt i32 0, %ny
+  br label %singleSucc
+
+singleSucc:
+  br i1 %cmp21, label %preheader.j, label %for1.inc10
+
+preheader.j:
+  br label %for2
+
+for2:
+  %j = phi i32 [ %j.next, %for2 ], [ 0, %preheader.j ]
+  %arrayidx5 = getelementptr inbounds [100 x [100 x i32]], [100 x [100 x i32]]* @A, i32 0, i32 %j, i32 %j23
+  %lv = load i32, i32* %arrayidx5
+  %add = add nsw i32 %lv, %k
+  store i32 %add, i32* %arrayidx5
+  %j.next = add nuw nsw i32 %j, 1
+  %exitcond = icmp eq i32 %j, 99
+  br i1 %exitcond, label %for1.inc10, label %for2
+
+for1.inc10:
+  %j.next24 = add nuw nsw i32 %j23, 1
+  %exitcond26 = icmp eq i32 %j23, 99
+  br i1 %exitcond26, label %for.end12, label %for1.header
+
+for.end12:
+  ret void
+}