index
:
llvm
embtk-support-master
embtk-support-release-3.2
embtk-support-release-3.3
embtk-support-release-3.4
master
release-3.2
release-3.4
Unofficial llvm GIT mirror used in EmbToolkit
Git daemon user
summary
refs
log
tree
commit
diff
log msg
author
committer
range
path:
root
/
lib
/
Transforms
/
Vectorize
Commit message (
Expand
)
Author
Age
...
*
SLPVectorize: Put horizontal reductions feeding a store under separate flag
Arnold Schwaighofer
2013-09-25
*
set the cost of tiny trees to INT_MAX in SLP vectorizer to disable vectorizat...
Yi Jiang
2013-09-24
*
Revert "LoopVectorizer: Only allow vectorization of intrinsics."
Arnold Schwaighofer
2013-09-23
*
SLPVectorizer: Fix multiline comment warning
Arnold Schwaighofer
2013-09-21
*
Reapply "SLPVectorizer: Handle more horizontal reductions (disabled)""
Arnold Schwaighofer
2013-09-21
*
LoopVectorizer: Only allow vectorization of intrinsics. We can't know for sur...
Nadav Rotem
2013-09-21
*
Revert "SLPVectorizer: Handle more horizontal reductions (disabled)"
Arnold Schwaighofer
2013-09-21
*
SLPVectorizer: Handle more horizontal reductions (disabled)
Arnold Schwaighofer
2013-09-20
*
Prevent LoopVectorizer and SLPVectorizer running if the target has no vector ...
Robert Lytton
2013-09-18
*
Revert accidental commit I had to make to get the test case in PR17268 to sti...
Craig Topper
2013-09-18
*
Lift alignment restrictions for load/store folding on VINSERTF128/VEXTRACTF12...
Craig Topper
2013-09-18
*
SLPVectorizer: Don't vectorize phi nodes that use invoke values
Arnold Schwaighofer
2013-09-17
*
Don't vectorize if there are outside loop users of the induction variable.
Arnold Schwaighofer
2013-09-16
*
Don't assert on invalid loop vectorization hint.
Eli Friedman
2013-09-10
*
LoopVectorize: PHI nodes are always at the beginning of a block, no need to s...
Benjamin Kramer
2013-09-10
*
In this patch we are trying to do two things:
Yi Jiang
2013-09-03
*
Disable unrolling in the loop vectorizer when disabled in the pass manager
Hal Finkel
2013-08-28
*
Refactor 'vectorizeLoop' no functionality change.
Nadav Rotem
2013-08-27
*
Fix inserting instructions before last in bundle.
Matt Arsenault
2013-08-26
*
LoopVectorize: Implement partial loop unrolling when vectorization is not pro...
Nadav Rotem
2013-08-26
*
test commit. Remove blank line
Yi Jiang
2013-08-26
*
Fix unused variable in release build
Matt Arsenault
2013-08-26
*
Constify functions
Matt Arsenault
2013-08-26
*
Vectorize starting from insertelements building a vector
Matt Arsenault
2013-08-26
*
Check if in set on insertion instead of separately
Matt Arsenault
2013-08-24
*
Teach the SLP vectorizer the correct way to check for consecutive access
Chandler Carruth
2013-08-22
*
Teach LoopVectorize about address space sizes
Matt Arsenault
2013-08-22
*
Use attribute helper function
Matt Arsenault
2013-08-21
*
Fix typo
Matt Arsenault
2013-08-21
*
SLPVectorizer: Fix invalid iterator errors
Arnold Schwaighofer
2013-08-20
*
Add a llvm.copysign intrinsic
Hal Finkel
2013-08-19
*
PR 16899: Do not modify the basic block using the iterator, but keep the
Joerg Sonnenberger
2013-08-17
*
Fix spelling
Matt Arsenault
2013-08-15
*
BBVectorize: Add initial stores to the write set when tracking uses
Hal Finkel
2013-08-13
*
Fix PR16797 - Support PHINodes with multiple inputs from the same basic block.
Nadav Rotem
2013-08-12
*
Add ISD::FROUND for libm round()
Hal Finkel
2013-08-07
*
LoopVectorize: Allow vectorization of loops with lifetime markers
Arnold Schwaighofer
2013-08-06
*
SLPVectorizer: Fix PR16777. PHInodes may use multiple extracted values that c...
Nadav Rotem
2013-08-02
*
80-col
Nadav Rotem
2013-07-31
*
SLPVectorier: update the debug location for the new instructions.
Nadav Rotem
2013-07-29
*
Don't vectorize when the attribute NoImplicitFloat is used.
Nadav Rotem
2013-07-29
*
Update the comment
Nadav Rotem
2013-07-27
*
SLP Vectorier: Don't vectorize really short chains because they are already ...
Nadav Rotem
2013-07-26
*
SLP Vectorizer: Disable the vectorization of non power of two chains, such as...
Nadav Rotem
2013-07-26
*
When we vectorize across multiple basic blocks we may vectorize PHINodes that...
Nadav Rotem
2013-07-22
*
Fix an obvious typo in the loop vectorizer where the cost model uses the wron...
Nadav Rotem
2013-07-22
*
Delete unused helper functions.
Nadav Rotem
2013-07-22
*
Revert a part of r186420. Don't forbid multiple store chains that merge.
Nadav Rotem
2013-07-21
*
fix an 80-col line.
Nadav Rotem
2013-07-19
*
Use LLVMs ADTs that improve the compile time of this pass.
Nadav Rotem
2013-07-19
[prev]
[next]