LoopDistribute/LAA: Respect convergent

This case is slightly tricky, because loop distribution should be
allowed in some cases, and not others. As long as runtime dependency
checks don't need to be introduced, this should be OK. This is further
complicated by the fact that LoopDistribute partially ignores if LAA
says that vectorization is safe, and then does its own runtime pointer
legality checks.

Note this pass still does not handle noduplicate correctly, as this
should always be forbidden with it. I'm not going to bother trying to
fix it, as it would require more effort and I think noduplicate should
be removed.

https://reviews.llvm.org/D62607

llvm-svn: 363160

1 files changed, 76 insertions, 0 deletions

diff --git a/llvm/test/Transforms/LoopDistribute/basic.ll b/llvm/test/Transforms/LoopDistribute/basic.ll
index 97296c2d123..0d7b6f21824 100644
--- a/llvm/test/Transforms/LoopDistribute/basic.ll
+++ b/llvm/test/Transforms/LoopDistribute/basic.ll
@@ -18,6 +18,7 @@
 target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-apple-macosx10.10.0"
 
+; CHECK-LABEL: @f(
 define void @f(i32* noalias %a,
                i32* noalias %b,
                i32* noalias %c,
@@ -81,3 +82,78 @@ for.body:                                         ; preds = %for.body, %entry
 for.end:                                          ; preds = %for.body
   ret void
 }
+
+declare i32 @llvm.convergent(i32) #0
+
+; It is OK to distribute with a convergent operation, since in each
+; new loop the convergent operation has the ssame control dependency.
+; CHECK-LABEL: @f_with_convergent(
+define void @f_with_convergent(i32* noalias %a,
+                               i32* noalias %b,
+                               i32* noalias %c,
+                               i32* noalias %d,
+                               i32* noalias %e) {
+entry:
+  br label %for.body
+
+; Verify the two distributed loops.
+
+; CHECK: entry.split.ldist1:
+; CHECK:    br label %for.body.ldist1
+; CHECK: for.body.ldist1:
+; CHECK:    %mulA.ldist1 = mul i32 %loadB.ldist1, %loadA.ldist1
+; CHECK:    br i1 %exitcond.ldist1, label %entry.split, label %for.body.ldist1
+
+; CHECK: entry.split:
+; CHECK:    br label %for.body
+; CHECK: for.body:
+; CHECK:    %convergentD = call i32 @llvm.convergent(i32 %loadD)
+; CHECK:    %mulC = mul i32 %convergentD, %loadE
+; CHECK: for.end:
+
+
+; ANALYSIS: for.body:
+; ANALYSIS-NEXT: Has convergent operation in loop
+; ANALYSIS-NEXT: Report: cannot add control dependency to convergent operation
+; ANALYSIS: for.body.ldist1:
+; ANALYSIS-NEXT: Report: unsafe dependent memory operations in loop
+
+; convergent instruction happens to block vectorization
+; VECTORIZE: call i32 @llvm.convergent
+; VECTORIZE: mul i32
+
+for.body:                                         ; preds = %for.body, %entry
+  %ind = phi i64 [ 0, %entry ], [ %add, %for.body ]
+
+  %arrayidxA = getelementptr inbounds i32, i32* %a, i64 %ind
+  %loadA = load i32, i32* %arrayidxA, align 4
+
+  %arrayidxB = getelementptr inbounds i32, i32* %b, i64 %ind
+  %loadB = load i32, i32* %arrayidxB, align 4
+
+  %mulA = mul i32 %loadB, %loadA
+
+  %add = add nuw nsw i64 %ind, 1
+  %arrayidxA_plus_4 = getelementptr inbounds i32, i32* %a, i64 %add
+  store i32 %mulA, i32* %arrayidxA_plus_4, align 4
+
+  %arrayidxD = getelementptr inbounds i32, i32* %d, i64 %ind
+  %loadD = load i32, i32* %arrayidxD, align 4
+
+  %arrayidxE = getelementptr inbounds i32, i32* %e, i64 %ind
+  %loadE = load i32, i32* %arrayidxE, align 4
+
+  %convergentD = call i32 @llvm.convergent(i32 %loadD)
+  %mulC = mul i32 %convergentD, %loadE
+
+  %arrayidxC = getelementptr inbounds i32, i32* %c, i64 %ind
+  store i32 %mulC, i32* %arrayidxC, align 4
+
+  %exitcond = icmp eq i64 %add, 20
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+attributes #0 = { nounwind readnone convergent }