[PATCH] D157862: LoopVectorize: handle casted indvars in iv-select-cmp

[Ramkumar Ramachandra via Phabricator via llvm-commits]

artagnon created this revision.
artagnon added reviewers: Mel-Chen, fhahn, Ayal, shiva0217.
Herald added subscribers: StephenFan, hiraditya.
Herald added a project: All.
artagnon requested review of this revision.
Herald added subscribers: llvm-commits, wangpc.
Herald added a project: LLVM.

As a follow-up to D150851 <https://reviews.llvm.org/D150851>, handle casted indvars in cases where a
runtime-check isn't necessary, hence vectorizing:

  int test(int *a, int n) {
    int rdx = 331;
    for (int i = 0; i < n; i++) {
      if (a[i] > 3)
        rdx = i;
    }
    return rdx;
  }

D150851 <https://reviews.llvm.org/D150851> looks for the nsw flag on the increment of the indvar, and
concludes that the indvar can't wrap, and hence can't hit the sentinel
value:

  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1

The issue with vectorizing the above example is that IndVarSimplify
comes along and truncates the indvar as shown below:

  %1 = trunc i64 %indvars.iv to i32
  %spec.select = select i1 %cmp1, i32 %1, i32 %rdx.06

Now, the loop bounds are still on i64, so this truncated indvar may
still overflow, hitting the sentinel value:

  %exitcond.not = icmp eq i64 %indvars.iv.next, %wide.trip.count
  br i1 %exitcond.not, label %for.cond.cleanup, label %for.body

However, the exit condition of the loop, %wide.trip.count, has been
widened from an i32 %n by IndVarSimplify:

  %wide.trip.count = zext i32 %n to i64
  br label %for.body

This tells us that %n was orignally an i32, but we don't know if it is
signed. Now, from the loop guard, we know that %n was originally an i32,
and that is signed:

  %cmp5 = icmp sgt i32 %n, 0
  br i1 %cmp5, label %for.body.preheader, label %for.cond.cleanup

This patch pattern-matches a cast in the select, and an icmp in the loop
guard, which could perhaps be introduced by IndVarSimplify, and
determines when a truncated indvar can't overflow.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D157862

Files:
  llvm/lib/Analysis/IVDescriptors.cpp
  llvm/test/Transforms/LoopVectorize/iv-select-cmp.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D157862.549900.patch
Type: text/x-patch
Size: 39069 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20230814/acbeb8bd/attachment.bin>