[PATCH] D42759: [CGP] Split large data structres to sink more GEPs

[Eli Friedman via Phabricator via llvm-commits]

efriedma added inline comments.


================
Comment at: llvm/trunk/lib/CodeGen/CodeGenPrepare.cpp:3816
+                 TLI.shouldConsiderGEPOffsetSplit() && Depth == 0 &&
+                 ConstantOffset > 0) {
+        // Record GEPs with non-zero offsets as candidates for splitting in the
----------------
jonpa wrote:
> efriedma wrote:
> > jonpa wrote:
> > > Is there any reason to not use '!=' as oppsed to '>' here (which would match the comment below)?
> > > 
> > > On SystemZ negative offsets are not supported on vector instructions.
> > > 
> > > 
> > > 
> > It could work. Would probably need a few other changes to make sure we don't do anything silly like grouping together positive and negative offsets.
> I may be missing something, but as far as I can tell there should not be any problem just because the offset is negative. The type for offsets is already int64_t, and the algorithm of sorting them by offset and inserting a new GEP whenever needed seems to work regardless of a negative offset, since the most negative offset is generated first and then the remainder will be positive, or?
> 
I don't remember exactly how the algorithm for grouping offsets together functions; maybe it just works.


Repository:
  rL LLVM

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D42759/new/

https://reviews.llvm.org/D42759