[PATCH] D43237: [LoopInterchange] Allow some loops with PHI nodes in the exit block.

[Florian Hahn via Phabricator via llvm-commits]

fhahn added a comment.

Thank you very much for having a look Eli. PHI nodes in the outer loop exit block are used as a proxy for uses of values produced in the loop nest. As we are doing interchanging ATM, I think it is only safe to interchange, if the values used outside of the loop nest are produced in the inner loop. Before and after interchanging, the inner loop block will be executed if both inner and outer loop conditions are true.

The same might not be true for values produced in the outer loop I think. For example, if the inner loop body is never executed. Consider the example below, where the outer loop induction variable is returned. In case `  br i1 undef, label %for.body4, label %for.cond.cleanup3` is always false, we would execute the outer loop latch 1024 times and return 1024. In the interchanged version, we would never execute the outer loop latch, and it is not clear what the values the PHI node should use I think.

Please let me know if that makes sense :)

  define i64 @no_deps_interchange([1024 x i32]* nocapture %Arr, i32 %k, i64 %B) {
  entry:
    br label %for.body
  
  for.body:                                         ; preds = %entry, %for.cond.cleanup3
    %indvars.iv19 = phi i64 [ 0, %entry ], [ %indvars.iv.next20, %for.cond.cleanup3 ]
    br i1 undef, label %for.body4, label %for.cond.cleanup3
  
  for.body4:                                        ; preds = %for.body, %for.body4
    %indvars.iv = phi i64 [ 0, %for.body ], [ %indvars.iv.next, %for.body4 ]
    %arrayidx6 = getelementptr inbounds [1024 x i32], [1024 x i32]* %Arr, i64 %indvars.iv, i64 %indvars.iv19
    store i32 0, i32* %arrayidx6, align 4
    %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
    %exitcond = icmp ne i64 %indvars.iv.next, %B
    br i1 %exitcond, label %for.body4, label %for.cond.cleanup3
  
  for.cond.cleanup3:                                ; preds = %for.body4
    %indvars.iv.next20 = add nuw nsw i64 %indvars.iv19, 1
    %exitcond21 = icmp ne i64 %indvars.iv.next20, 1024
    br i1 %exitcond21, label %for.body, label %for.cond.cleanup
  
  
  for.cond.cleanup:                                 ; preds = %for.cond.cleanup3
    ret i64 %indvars.iv.next20
  }

Which, given we allow PHI nodes with values produced in the outer loop latch, produces the following code after interchanging

  define i64 @no_deps_interchange([1024 x i32]* nocapture %Arr, i32 %k, i64 %B) {
  entry:
    br label %for.body4.preheader
  
  for.body.preheader:                               ; preds = %for.body4
    br label %for.body
  
  for.body:                                         ; preds = %for.body.preheader, %for.cond.cleanup3
    %indvars.iv19 = phi i64 [ %indvars.iv.next20, %for.cond.cleanup3 ], [ 0, %for.body.preheader ]
    br i1 undef, label %for.body4.split1, label %for.cond.cleanup
  
  for.body4.preheader:                              ; preds = %entry
    br label %for.body4
  
  for.body4:                                        ; preds = %for.body4.preheader, %for.body4.split
    %indvars.iv = phi i64 [ %indvars.iv.next, %for.body4.split ], [ 0, %for.body4.preheader ]
    br label %for.body.preheader
  
  for.body4.split1:                                 ; preds = %for.body
    %arrayidx6 = getelementptr inbounds [1024 x i32], [1024 x i32]* %Arr, i64 %indvars.iv, i64 %indvars.iv19
    store i32 0, i32* %arrayidx6, align 4
    br label %for.cond.cleanup3.loopexit
  
  for.body4.split:                                  ; preds = %for.cond.cleanup3
    %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
    %exitcond = icmp ne i64 %indvars.iv.next, %B
    br i1 %exitcond, label %for.body4, label %for.cond.cleanup
  
  for.cond.cleanup3.loopexit:                       ; preds = %for.body4.split1
    br label %for.cond.cleanup3
  
  for.cond.cleanup3:                                ; preds = %for.cond.cleanup3.loopexit
    %indvars.iv.next20 = add nuw nsw i64 %indvars.iv19, 1
    %exitcond21 = icmp ne i64 %indvars.iv.next20, 1024
    br i1 %exitcond21, label %for.body, label %for.body4.split
  
  for.cond.cleanup:                                 ; preds = %for.body4.split, %for.body
    %indvars.iv.next20.lcssa = phi i64 [ %indvars.iv.next20, %for.body4.split ]  ; invalid PHI node
    ret i64 %indvars.iv.next20.lcssa
  }


https://reviews.llvm.org/D43237