[PATCH] D141079: [SelectionDAG] Improve constant folding in the presence of SPLAT_VECTOR

[Philip Reames via Phabricator via llvm-commits]

reames added inline comments.


================
Comment at: llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp:14018
+    // fold it that way
+    if (N0.getOpcode() == ISD::SPLAT_VECTOR &&
+        DAG.isConstantValueOfAnyType(N0.getOperand(0))) {
----------------
luke wrote:
> reames wrote:
> > This looks to be assuming fixed width splat_vectors.  The primary use of splat_vector are scalable vectors.  
> That makes sense, I was wondering what the difference was between a splat_vector and a splatted build_vector. 
> In this case then is it still possible to fold here?
To my knowledge, we're a bit inconsistent about this.  RISCV uses SPLAT_VECTOR only for scalable vectors.  Hexagaon (and per your other comment, WebAssembly) use them for both fixed and scalable.  I'm also unclear on when they use SPLAT_VECTOR vs BUILD_VECTOR.  

Longer term, I do think that having one canonical representation for a splat vector makes sense, and that it'll probably be SPLAT_VECTOR.  We're just not there yet.  In particular, DAGCombine has various weaknesses for SPLAT_VECTOR that need to be worked through.  


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D141079/new/

https://reviews.llvm.org/D141079