Commit Graph

4 Commits

Author SHA1 Message Date
Sam Parker 5338f7aae4 [ARM] Prevent parallel macs for unsigned values
Both zext and sext are currently allowed during the search for narrow
sequences and sexts operands are later added to the mac candidates.
But operands of muls are also added, without checking whether they're
sext or zext, which means we can generate a signed smlad when we
shouldn't.

Differential Revision: https://reviews.llvm.org/D54790

llvm-svn: 347542
2018-11-26 10:22:55 +00:00
Eli Friedman b09c778715 Revert r344693 ("[ARM] bottom-top mul support in ARMParallelDSP")
Still causing failures on the polly-aosp buildbot; I'll follow up
with a reduced testcase.

llvm-svn: 344752
2018-10-18 19:34:30 +00:00
Sam Parker 2ef3c0dad6 [ARM] bottom-top mul support in ARMParallelDSP
Previously reverted in rL343082.

Original commit message:

On failing to find sequences that can be converted into dual macs,
try to find sequential 16-bit loads that are used by muls which we
can then use smultb, smulbt, smultt with a wide load.

Differential Revision: https://reviews.llvm.org/D51983

llvm-svn: 344693
2018-10-17 13:02:48 +00:00
Sam Parker 01db2983cd [ARM] Add smlald support in ARMParallelDSP
Search from i64 reducing phis, as well as i32, to allow the
generation of smlald instructions.

Differential Revision: https://reviews.llvm.org/D51101

llvm-svn: 341941
2018-09-11 14:01:22 +00:00