[PATCH] D94015: [LoopIdiom] Replace cttz loop by call to cttz intrinsic.

[Francis laniel via Phabricator via llvm-commits]

eiffel added a comment.

Hi.

I updated my code to adress the `const` nit.

However, I am not really sure of the output for cttz64 when ran with `-O1`.
Indeed, I get:

  ; ./bin/opt -O1 -S < ../llvm-project/llvm/test/Transforms/LoopIdiom/cttz.ll
  ; ModuleID = '<stdin>'
  source_filename = "<stdin>"
  
  ; Function Attrs: nofree norecurse nosync nounwind readnone uwtable
  define i32 @cttz32(i32 %x) local_unnamed_addr #0 {
  entry:
    %0 = call i32 @llvm.cttz.i32(i32 %x, i1 true), !range !0
    ret i32 %0
  }
  
  ; Function Attrs: nofree norecurse nosync nounwind readnone ssp uwtable
  define i32 @cttz64(i64 %x) local_unnamed_addr #1 {
  entry:
    br label %land.rhs
  
  land.rhs:                                         ; preds = %while.body, %entry
    %i.06 = phi i64 [ 0, %entry ], [ %inc, %while.body ]
    %0 = shl nuw i64 1, %i.06
    %1 = and i64 %0, %x
    %cmp1 = icmp eq i64 %1, 0
    br i1 %cmp1, label %while.body, label %while.end.split.loop.exit2
  
  while.body:                                       ; preds = %land.rhs
    %inc = add nuw nsw i64 %i.06, 1
    %cmp = icmp ult i64 %i.06, 63
    br i1 %cmp, label %land.rhs, label %while.end
  
  while.end.split.loop.exit2:                       ; preds = %land.rhs
    %extract.t1.le = trunc i64 %i.06 to i32
    br label %while.end
  
  while.end:                                        ; preds = %while.body, %while.end.split.loop.exit2
    %i.0.lcssa.off0 = phi i32 [ %extract.t1.le, %while.end.split.loop.exit2 ], [ 64, %while.body ]
    ret i32 %i.0.lcssa.off0
  }
  
  ; Function Attrs: nocallback nofree nosync nounwind readnone speculatable willreturn
  declare i32 @llvm.cttz.i32(i32, i1 immarg) #2
  
  attributes #0 = { nofree norecurse nosync nounwind readnone uwtable }
  attributes #1 = { nofree norecurse nosync nounwind readnone ssp uwtable }
  attributes #2 = { nocallback nofree nosync nounwind readnone speculatable willreturn }
  
  !0 = !{i32 0, i32 33}

While the result is correct for cttz32, the intrinsic is not present for cttz64.
Note that, when I ran this, I get an output which is correct for both:

  ; ./bin/opt -loop-idiom -loop-deletion -S < ../llvm-project/llvm/test/Transforms/LoopIdiom/cttz.ll          
  ; ModuleID = '<stdin>'
  source_filename = "<stdin>"
  
  ; Function Attrs: norecurse nounwind readnone uwtable
  define i32 @cttz32(i32 %x) #0 {
  entry:
    br label %while.end
  
  while.end:                                        ; preds = %entry
    %0 = call i32 @llvm.cttz.i32(i32 %x, i1 true)
    ret i32 %0
  }
  
  ; Function Attrs: nounwind readnone ssp uwtable
  define i32 @cttz64(i64 %x) #1 {
  entry:
    br label %while.end
  
  while.end:                                        ; preds = %entry
    %0 = call i64 @llvm.cttz.i64(i64 %x, i1 true)
    %conv = trunc i64 %0 to i32
    ret i32 %conv
  }
  
  ; Function Attrs: nocallback nofree nosync nounwind readnone speculatable willreturn
  declare i32 @llvm.cttz.i32(i32, i1 immarg) #2
  
  ; Function Attrs: nocallback nofree nosync nounwind readnone speculatable willreturn
  declare i64 @llvm.cttz.i64(i64, i1 immarg) #2
  
  attributes #0 = { norecurse nounwind readnone uwtable }
  attributes #1 = { nounwind readnone ssp uwtable }
  attributes #2 = { nocallback nofree nosync nounwind readnone speculatable willreturn }

So, can someone with better experience give me his/her thoughts about this?

Best regards and thank you in advance.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D94015/new/

https://reviews.llvm.org/D94015