[PATCH] D46193: [LSR] Skip LSR if the cost of input is cheaper than LSR's solution

[Krzysztof Parzyszek via Phabricator via llvm-commits]

kparzysz added a comment.

Here's the IR immediately before LSR:

  define dso_local i32 @foo(%struct.S* nocapture readonly %Data, i32 %Off, i32 %Idx, i32* nocapture %Out) local_unnamed_addr #0 {
  entry:
    %X = getelementptr inbounds %struct.S, %struct.S* %Data, i32 0, i32 0
    %0 = load i32, i32* %X, align 4, !tbaa !2
    %cmp = icmp sgt i32 %0, %Off
    br i1 %cmp, label %while.cond.preheader, label %cleanup
  
  while.cond.preheader:                             ; preds = %entry
    %Y = getelementptr inbounds %struct.S, %struct.S* %Data, i32 0, i32 1
    %1 = load i32, i32* %Y, align 4, !tbaa !8
    br label %while.cond
  
  while.cond:                                       ; preds = %while.cond, %while.cond.preheader
    %Col.0 = phi i32 [ %sub, %while.cond ], [ %Idx, %while.cond.preheader ]
    %cmp1 = icmp slt i32 %Col.0, %1
    %sub = sub nsw i32 %Col.0, %1
    br i1 %cmp1, label %while.end, label %while.cond
  
  while.end:                                        ; preds = %while.cond
    %Ptr = getelementptr inbounds %struct.S, %struct.S* %Data, i32 0, i32 2
    %2 = load i32*, i32** %Ptr, align 4, !tbaa !9
    %add.ptr = getelementptr inbounds i32, i32* %2, i32 %Col.0
    %mul = mul nsw i32 %1, %Off
    %add.ptr4 = getelementptr inbounds i32, i32* %add.ptr, i32 %mul
    %3 = load i32, i32* %add.ptr4, align 4, !tbaa !10
    store i32 %3, i32* %Out, align 4, !tbaa !10
    br label %cleanup
  
  cleanup:                                          ; preds = %entry, %while.end
    %retval.0 = phi i32 [ 0, %while.end ], [ 5, %entry ]
    ret i32 %retval.0
  }


https://reviews.llvm.org/D46193