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
/
lib
/
Target
/
X86
/
X86InstrFMA.td
Age
Commit message (
Expand
)
Author
2017-12-12
[X86] Use Ld scheduler classes for instructions with folded loads.
Craig Topper
2017-11-27
[X86][FMA] Tag all FMA/FMA4 instructions with WriteFMA schedule class
Simon Pilgrim
2017-11-25
[X86] Add separate intrinsics for scalar FMA4 instructions.
Craig Topper
2017-11-20
Fix spelling in comment. NFCI.
Simon Pilgrim
2017-11-09
[X86] Give priority to EVEX FMA instructions over FMA4 instructions.
Craig Topper
2017-11-06
[X86] Use EVEX encoded intrinsics for legacy FMA intrinsics when possible.
Craig Topper
2017-09-06
[X86] Add more FMA3 patterns to cover a load in all 3 possible positions.
Craig Topper
2017-09-04
[X86] Mark the FMA nodes as commutable so tablegen will auto generate the pat...
Craig Topper
2017-09-01
[X86] Add isel patterns for memory forms of FMA3 intrinsic instructions
Craig Topper
2017-09-01
[X86] Remove unnecessary COPY_TO_REGCLASS(VR128) from the output patterns for...
Craig Topper
2017-08-23
[X86] Remove X86ISD::FMADD in favor ISD::FMA
Craig Topper
2017-05-28
[X86] Adding FoldGenRegForm helper field (for memory folding tables tableGen ...
Ayman Musa
2017-03-17
[AVX-512] Give priority to EVEX encoded scalar FMA instructions when we have ...
Craig Topper
2016-11-27
[X86][FMA4] Remove isCommutable from FMA4 scalar intrinsics. They aren't comm...
Craig Topper
2016-11-27
[X86][FMA] Add missing Predicates qualifier around scalar FMA intrinsic patte...
Craig Topper
2016-08-22
[X86] Create a new instruction format to handle MemOp4 encoding. This saves o...
Craig Topper
2016-07-28
[X86] Remove CustomInserter for FMA3 instructions. Looks like since we got fu...
Craig Topper
2016-07-24
[X86] Make the FMA3 instruction names consistent between VEX and EVEX encoded...
Craig Topper
2015-12-09
X86-FMA3: Defined the ExeDomain property for Scalar FMA3 opcodes.
Vyacheslav Klochkov
2015-12-05
[X86][FMA4] Explicitly set the domain of FMA4 float/double scalar instructions
Simon Pilgrim
2015-11-26
X86-FMA3: Improved/enabled the memory folding optimization for scalar loads
Vyacheslav Klochkov
2015-11-25
fix typo; NFC
Sanjay Patel
2015-11-13
X86-FMA3: Implemented commute transformations FMA*_Int instructions.
Vyacheslav Klochkov
2015-11-06
Improved the operands commute transformation for X86-FMA3 instructions.
Andrew Kaylor
2015-11-04
Created new X86 FMA3 opcodes (FMA*_Int) that are used now for lowering of sca...
Andrew Kaylor
2015-05-25
[X86] When pattern-matching scalar FMA3 intrinsics, don't re-arrange the firs...
Michael Kuperstein
2014-11-26
Replace neverHasSideEffects=1 with hasSideEffects=0 in all .td files.
Craig Topper
2014-05-07
[X86] Selectively mark the FMA variants inside a family as isCommutable.
Quentin Colombet
2014-04-02
[X86] Make the VFMA*231 variants commutable and relax the alignment restrictions
Lang Hames
2014-02-04
[X86] Only 213 FMA3 variants should be marked commutable.
Lang Hames
2014-01-31
Replace X86 FMA intrinsic pseduo-instructions with def pats.
Lang Hames
2014-01-23
Replace vfmaddxx213 instructions with their 231-type equivalents in accumulator
Lang Hames
2014-01-05
Add a new x86 specific instruction flag to force some isCodeGenOnly instructi...
Craig Topper
2014-01-02
Mark all x86 Int_ and _Int patterns as isCodeGenOnly so the disassembler tabl...
Craig Topper
2013-09-30
Various x86 disassembler fixes.
Craig Topper
2013-09-21
Remove alignment restrictions from FMA load folding.
Craig Topper
2013-01-14
Simplify nested strconcats in X86 td files since strconcat can take more than...
Craig Topper
2012-12-26
Mark all the _REV instructions as not having side effects. They aren't really...
Craig Topper
2012-11-21
Fix execution domain for packed FMA4 instructions.
Craig Topper
2012-09-19
Add explicit VEX_L tags to all 256-bit instructions. This will allow us to re...
Craig Topper
2012-08-31
Mark FMA4 instructions as commutable and add them to the folding tables.
Craig Topper
2012-08-31
Mark FMA3 instructions as commutable so that the operands to the multiply par...
Craig Topper
2012-08-31
Add support for converting llvm.fma to fma4 instructions.
Craig Topper
2012-08-29
Convert FMA4 patterns to use target specific nodes instead of intrinsics to a...
Craig Topper
2012-08-24
Remove more mayLoad workarounds.
Jakob Stoklund Olesen
2012-08-24
Custom lower FMA intrinsics to target specific nodes and remove the patterns.
Craig Topper
2012-08-21
Cleanup the scalar FMA3 definitions. Add patterns to fold loads with scalar f...
Craig Topper
2012-08-21
Merge FMA3 instructions with and without patterns into single classes using n...
Craig Topper
2012-08-20
Remove FMA3 intrinsic instructions in favor of patterns.
Craig Topper
2012-08-20
Use correct intrinsic for 256-bit VFMSUBADDPS.
Craig Topper
[next]