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

[Alexey Bataev via Phabricator via llvm-commits]

ABataev added inline comments.


================
Comment at: llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp:672-676
+  /// Save current tree for possible later vectorization.
+  void saveTree() {
+    BuiltTrees.push_back(std::make_unique<TreeState>());
+    Tree = BuiltTrees.back().get();
   }
----------------
dtemirbulatov wrote:
> dtemirbulatov wrote:
> > ABataev wrote:
> > > dtemirbulatov wrote:
> > > > ABataev wrote:
> > > > > Why do we need to save intermediate results? Cannot it be solved in a single iteration loop without saving the intermediate results in the class instance?
> > > > I have noticed many regressions if we decide right away and rebuilding the tree afterward is expensive.
> > > What is the cause of those regressions? If I understand it correctly, you're just trying to find the subtree, exclude its cost, compare, repeat if it is not profitable. What does not allow to do it in the loop without saving intermediate results in the class, but save the result in the stack vectors, if it is needed?
> > For example, if we could partially vectorize at vectorizeStoreChain(), or later it is possilble to fully vectorize the same tree tryToVectorizeList() or tryToReduce()
> For example, if we could partially vectorize at vectorizeStoreChain(), or later it is possilble to fully vectorize the same tree with tryToVectorizeList() or tryToReduce()
Could you give an example, please?


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

https://reviews.llvm.org/D57779