Commit Graph

5 Commits

Author SHA1 Message Date
Sanjay Patel ecb175608f [InstCombine] remove extract-of-select vector transform (2nd try)
The 1st attempt at this:
https://reviews.llvm.org/rL314117
was reverted at:
https://reviews.llvm.org/rL314118

because of bot fails for clang tests that were checking optimized IR. That should be fixed with:
https://reviews.llvm.org/rL314144
...so try again. 

Original commit message:

The transform to convert an extract-of-a-select-of-vectors was added at:
https://reviews.llvm.org/rL194013

And a question about the validity of this transform was raised in the review:
https://reviews.llvm.org/D1539:
...but not answered AFAICT>

Most of the motivating cases in that patch are now handled by other combines. These are the tests that were added with
the original commit, but they are not regressing even after we remove the transform in this patch.

The diffs we see after removing this transform cause us to avoid increasing the instruction count, so we don't want to do
those transforms as canonicalizations.

The motivation for not turning a vector-select-of-vectors into a scalar operation is shown in PR33301:
https://bugs.llvm.org/show_bug.cgi?id=33301
...in those cases, we'll get vector ops with this patch rather than the vector/scalar mix that we currently see.

Differential Revision: https://reviews.llvm.org/D38006

llvm-svn: 314147
2017-09-25 20:30:53 +00:00
Sanjay Patel aa7f750bec revert r314117 because there are bogus clang tests that depend on the optimizer
llvm-svn: 314118
2017-09-25 17:00:04 +00:00
Sanjay Patel 9639897d77 [InstCombine] remove extract-of-select vector transform
The transform to convert an extract-of-a-select-of-vectors was added at:
rL194013

And a question about the validity of this transform was raised in the review:
https://reviews.llvm.org/D1539:
...but not answered AFAICT>

Most of the motivating cases in that patch are now handled by other combines. These are the tests that were added with
the original commit, but they are not regressing even after we remove the transform in this patch.

The diffs we see after removing this transform cause us to avoid increasing the instruction count, so we don't want to do
those transforms as canonicalizations.

The motivation for not turning a vector-select-of-vectors into a scalar operation is shown in PR33301:
https://bugs.llvm.org/show_bug.cgi?id=33301
...in those cases, we'll get vector ops with this patch rather than the vector/scalar mix that we currently see.

Differential Revision: https://reviews.llvm.org/D38006

llvm-svn: 314117
2017-09-25 16:41:34 +00:00
Sanjay Patel 709a804a0a [InstCombine] auto-generate complete checks; NFC
The code responsible for these transforms has the potential to add 2 
instructions and break min/max patterns (PR33301).

llvm-svn: 313575
2017-09-18 21:57:56 +00:00
Matt Arsenault 243140f2fd Scalarize select vector arguments when extracted.
When the elements are extracted from a select on vectors
or a vector select, do the select on the extracted scalars
from the input if there is only one use.

llvm-svn: 194013
2013-11-04 20:36:06 +00:00