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
/
Transforms
/
Vectorize
/
LoopVectorize.cpp
Age
Commit message (
Expand
)
Author
2018-02-19
Merging r324195:
Hans Wennborg
2018-01-17
Merging r322473:
Hans Wennborg
2017-12-30
Use phi ranges to simplify code. No functionality change intended.
Benjamin Kramer
2017-12-20
[LV] Remove unnecessary DoExtraAnalysis guard (silent bug)
Florian Hahn
2017-12-16
[LV] Extend InstWidening with CM_Widen_Recursive
Hal Finkel
2017-12-16
[LV] NFC patch for moving VP*Recipe class definitions from LoopVectorize.cpp ...
Hal Finkel
2017-12-14
[LV] Support efficient vectorization of an induction with redundant casts
Dorit Nuzman
2017-12-12
[LV] Ignore the cost of values that will not appear in the vectorized loop
Dorit Nuzman
2017-12-06
[LV] Interleaved access vectorization: fix computing new alias info
Adam Nemet
2017-11-21
Add MemorySSA as loop dependency, disabled by default [NFC].
Alina Sbirlea
2017-11-20
[LV] Model masking in VPlan, introducing VPInstructions
Gil Rapaport
2017-11-14
[LV] Introduce VPBlendRecipe, VPWidenMemoryInstructionRecipe
Gil Rapaport
2017-11-08
Add an @llvm.sideeffect intrinsic
Dan Gohman
2017-11-06
[IR] redefine 'UnsafeAlgebra' / 'reassoc' fast-math-flags and add 'trans' fas...
Sanjay Patel
2017-10-31
[LoopVectorize] Replace manual VPlan memory management with unique_ptr.
Benjamin Kramer
2017-10-26
Do not add discriminator encoding for debug intrinsics.
Dehao Chen
2017-10-12
[Transforms] Fix some Clang-tidy modernize and Include What You Use warnings;...
Eugene Zelenko
2017-10-11
[NFC] Convert OptimizationRemarkEmitter old emit() calls to new closure
Vivek Pandya
2017-10-05
[LV] Fix PR34743 - handle casts that sink after interleaved loads
Ayal Zaks
2017-10-05
[LV] Fix PR34711 - widen instruction ranges when sinking casts
Ayal Zaks
2017-09-29
[LV] Use correct insertion point when type shrinking reductions
Matthew Simpson
2017-09-28
Use a BumpPtrAllocator for Loop objects
Sanjoy Das
2017-09-19
Allow ORE.emit to take a closure to delay building the remark object
Adam Nemet
2017-09-15
This patch fixes https://bugs.llvm.org/show_bug.cgi?id=32352
Vivek Pandya
2017-09-15
This reverts r313381
Vivek Pandya
2017-09-15
This patch fixes https://bugs.llvm.org/show_bug.cgi?id=32352
Vivek Pandya
2017-09-14
[LV] Fix maximum legal VF calculation
Alon Kom
2017-09-13
[LV] Avoid computing the register usage for default VF. NFC
Anna Thomas
2017-09-13
[LV] Fix PR34523 - avoid generating redundant selects
Ayal Zaks
2017-09-12
[LV] Clamp the VF to the trip count
Anna Thomas
2017-09-04
LoopVectorize: MaxVF should not be larger than the loop trip count
Zvi Rackover
2017-09-02
[LoopVectorize] Turn static DenseSet into switch.
Benjamin Kramer
2017-09-01
[LoopVectorizer] Use two step casting for float to pointer types.
Manoj Gupta
2017-08-27
[LV] Fix PR34248 - recommit D32871 after revert r311304
Ayal Zaks
2017-08-20
Revert r311077: [LV] Using VPlan ...
Chandler Carruth
2017-08-20
[Loop Vectorize] Added a separate metadata
Aditya Kumar
2017-08-17
[LV] Using VPlan to model the vectorized code and drive its transformation
Ayal Zaks
2017-08-15
[LV] Minor savings to Sink casts to unravel first order recurrence
Ayal Zaks
2017-08-08
[LoopVectorize] Fix assertion failure in Fcmp vectorization
Anna Thomas
2017-08-02
LV: Don't insert runtime ptr checks on divergent targets
Matt Arsenault
2017-07-31
[LV] Avoid redundant operations manipulating masks
Ayal Zaks
2017-07-19
[LV] Test once if vector trip count is zero, instead of twice
Ayal Zaks
2017-07-12
[LV] Don't allow outside uses of IVs if the SCEV is predicated on loop condit...
Michael Kuperstein
2017-07-01
Revert "r306473 - re-commit r306336: Enable vectorizer-maximize-bandwidth by ...
Teresa Johnson
2017-07-01
re-commit r306336: Enable vectorizer-maximize-bandwidth by default.
Teresa Johnson
2017-07-01
revert r306336 for breaking ppc test.
Teresa Johnson
2017-07-01
Enable vectorizer-maximize-bandwidth by default.
Teresa Johnson
2017-06-30
[LV] Sink casts to unravel first order recurrence
Ayal Zaks
2017-06-30
[LV] Optimize for size when vectorizing loops with tiny trip count
Ayal Zaks
2017-06-30
Revert "r306473 - re-commit r306336: Enable vectorizer-maximize-bandwidth by ...
Daniel Jasper
[next]