[PATCH] D57779: [SLP] Add support for throttling.

[Dinar Temirbulatov via Phabricator via llvm-commits]

dtemirbulatov added a comment.

> Why do we need MinVecNodes? MinTreeSize  and all associated analysis must be enough

it is Transforms/SLPVectorizer/X86/tiny-tree.ll transform that scared me. 
From:
define void @tiny_tree_not_fully_vectorizable(double* noalias nocapture %dst, double* noalias nocapture readonly %src, i64 %count) #0 { 
entry:

  %cmp12 = icmp eq i64 %count, 0
  br i1 %cmp12, label %for.end, label %for.body

for.body:                                         ; preds = %entry, %for.body

  %i.015 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
  %dst.addr.014 = phi double* [ %add.ptr4, %for.body ], [ %dst, %entry ]
  %src.addr.013 = phi double* [ %add.ptr, %for.body ], [ %src, %entry ]
  %0 = load double, double* %src.addr.013, align 8
  store double %0, double* %dst.addr.014, align 8
  %arrayidx2 = getelementptr inbounds double, double* %src.addr.013, i64 2
  %1 = load double, double* %arrayidx2, align 8
  %arrayidx3 = getelementptr inbounds double, double* %dst.addr.014, i64 1
  store double %1, double* %arrayidx3, align 8
  %add.ptr = getelementptr inbounds double, double* %src.addr.013, i64 %i.015
  %add.ptr4 = getelementptr inbounds double, double* %dst.addr.014, i64 %i.015
  %inc = add i64 %i.015, 1
  %exitcond = icmp eq i64 %inc, %count
  br i1 %exitcond, label %for.end, label %for.body

for.end:                                          ; preds = %for.body, %entry

  ret void

}
to:
define void @tiny_tree_not_fully_vectorizable(double* noalias nocapture %dst, double* noalias nocapture readonly %src, i64 %count) #0 {
entry:

  %cmp12 = icmp eq i64 %count, 0
  br i1 %cmp12, label %for.end, label %for.body

for.body:                                         ; preds = %for.body, %entry

  %i.015 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
  %dst.addr.014 = phi double* [ %add.ptr4, %for.body ], [ %dst, %entry ]
  %src.addr.013 = phi double* [ %add.ptr, %for.body ], [ %src, %entry ]
  %0 = load double, double* %src.addr.013, align 8
  %arrayidx2 = getelementptr inbounds double, double* %src.addr.013, i64 2
  %1 = load double, double* %arrayidx2, align 8
  %arrayidx3 = getelementptr inbounds double, double* %dst.addr.014, i64 1
  %2 = insertelement <2 x double> poison, double %0, i32 0
  %3 = insertelement <2 x double> %2, double %1, i32 1
  %4 = bitcast double* %dst.addr.014 to <2 x double>*
  store <2 x double> %3, <2 x double>* %4, align 8
  %add.ptr = getelementptr inbounds double, double* %src.addr.013, i64 %i.015
  %add.ptr4 = getelementptr inbounds double, double* %dst.addr.014, i64 %i.015
  %inc = add i64 %i.015, 1
  %exitcond = icmp eq i64 %inc, %count
  br i1 %exitcond, label %for.end, label %for.body

for.end:                                          ; preds = %for.body, %entry

  ret void

}

but now with llvm-mca with -mattr=+corei7-avx, I see the change from 1111 to 1014 cycles, so it looks good. I will check other cases.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D57779/new/

https://reviews.llvm.org/D57779