index
:
ampere-computing/llvm.git
release_60-f1b37feef3d-amp-20180630
release_70-e8af9b4c407-amp-20181130
LLVM including Ampere Computing toolchain specific patches
summary
refs
log
tree
commit
diff
log msg
author
committer
range
path:
root
/
test
/
CodeGen
/
AArch64
/
f16-instructions.ll
Age
Commit message (
Expand
)
Author
2017-10-03
Revert "Re-enable "[MachineCopyPropagation] Extend pass to do COPY source for...
Geoff Berry
2017-10-02
Re-enable "[MachineCopyPropagation] Extend pass to do COPY source forwarding"
Geoff Berry
2017-09-04
Revert "Re-enable "[MachineCopyPropagation] Extend pass to do COPY source for...
Sam McCall
2017-09-01
Re-enable "[MachineCopyPropagation] Extend pass to do COPY source forwarding"
Geoff Berry
2017-08-30
Revert r312154 "Re-enable "[MachineCopyPropagation] Extend pass to do COPY so...
Hans Wennborg
2017-08-30
Re-enable "[MachineCopyPropagation] Extend pass to do COPY source forwarding"
Geoff Berry
2017-08-24
[AArch64] Custom lowering of copysign f16
Sjoerd Meijer
2017-08-18
[AArch64] Do not promote f16 when subtarget HasFullFP16
Sjoerd Meijer
2017-08-18
Revert "[MachineCopyPropagation] Extend pass to do COPY source forwarding" ro...
Geoff Berry
2017-08-17
Re-enable "[MachineCopyPropagation] Extend pass to do COPY source forward...
Geoff Berry
2017-08-17
Revert "[MachineCopyPropagation] Extend pass to do COPY source forwarding"
Geoff Berry
2017-08-16
[MachineCopyPropagation] Extend pass to do COPY source forwarding
Geoff Berry
2016-08-26
[AArch64] Avoid materializing constant 1 by using csinc, rather than csel.
Chad Rosier
2016-05-13
add support for -print-imm-hex for AArch64
Paul Osmialowski
2016-05-06
[CodeGen] Round [SU]INT_TO_FP result when promoting from f16.
Ahmed Bougacha
2016-03-02
[AArch64] Enable non-leaf frame pointer elimination.
Geoff Berry
2015-12-21
[AArch64] Enable PostRAScheduler for AArch64 generic build.
Chad Rosier
2015-11-17
[AArch64] Promote f16 SELECT_CC CC operands when op is legal.
Ahmed Bougacha
2015-08-13
[CodeGen] Mark the promoted FCOPYSIGN result FP_ROUND as TRUNCating.
Ahmed Bougacha
2015-08-13
[AArch64] Also custom-lowering mismatched vector/f16 FCOPYSIGN.
Ahmed Bougacha
2015-08-13
[CodeGen] When Promoting, don't extend the 2nd FCOPYSIGN operand.
Ahmed Bougacha
2015-08-11
[AArch64] Match fminnum/fmaxnum for vector fminnm/fmaxnm instead of an intrin...
James Molloy
2015-07-16
AArch64: make inexact signalling on round Darwin-specific
Tim Northover
2015-04-10
[AArch64] Promote f16 operations to f32.
Ahmed Bougacha
