index
:
~tstellar/llvm
9.1-abi-fix
Nov13-test
Oct18-backup
assembler
assembler-Jan-06-2015
assembler-push
backup-Oct15
backup-Oct18
bfgminer
bfgminer-perf
cayman-only-bfgminer
clover-elf
clover-elf-v2
hazard-rec
hsa
image-support
indirect-addressing
indirect-wip
indirect-wip-2
indirect-wip-3
indirect-wip-4
indirect-wip-5
kernel-args-WIP
lds
lds-v2
long-alu
madk
master
master-testing
master-testing-patches
master-testing-patches-v2
master-testing-si
master-testing-v2
mi-sched-experimental
native
opencv-Sep18-patches
perf-Dec31-2014
perf-Jan-08-2015
push-jan16
r600
r600-May09
r600-alu-encoding
r600-final-push
r600-gen-fixes
r600-imm-flags
r600-initial-review
r600-initial-review-May11
r600-master
r600-private-mem-fixes
r600-private-memory
r600-review-v10
r600-review-v3
r600-review-v7
r600-review-v8
r600-review-v9
r600-rewrite-pats
r600-structurizer
r600-structurizer-v2
r600-tablegen-hwreg
r600-tablegen-reg-encoding
r600-vliw
remove-fold-operands
sched-fixes
sched-perf-Mar-27-2015
si-compute
si-compute-v3
si-fold
si-lowercase
si-scheduler
si-scheduler-v2
si-scheduler-v3
si-sgpr-copies
si-spill-fixes
si-spill-fixes-v2
si-spill-fixes-v3
si-spill-fixes-v4
smrd-cluster
struct-divergence
struct-divergence-v1
vgpr-spilling-Jan07-2014
vinterp-fix
vliw5-rebase
vlj-bottom-up
Unnamed repository; edit this file 'description' to name the repository.
tstellar
summary
refs
log
tree
commit
diff
log msg
author
committer
range
path:
root
/
lib
/
Transforms
/
Vectorize
/
LoopVectorize.cpp
Age
Commit message (
Expand
)
Author
Files
Lines
2013-01-07
Move TargetTransformInfo to live under the Analysis library. This no
Chandler Carruth
1
-1
/
+1
2013-01-05
Switch the loop vectorizer from VTTI to just use TTI directly.
Chandler Carruth
1
-49
/
+45
2013-01-05
iLoopVectorize: Non commutative operators can be used as reduction variables ...
Nadav Rotem
1
-4
/
+13
2013-01-04
Do not vectorize loops with subtraction reductions
Paul Redmond
1
-1
/
+0
2013-01-04
Fix a warning
Nadav Rotem
1
-2
/
+2
2013-01-04
LoopVectorizer:
Nadav Rotem
1
-4
/
+162
2013-01-03
LoopVectorizer: Add support for loop-unrolling during vectorization for incre...
Nadav Rotem
1
-155
/
+267
2013-01-02
Avoid vectorization when the function has the "noimplicitflot" attribute.
Nadav Rotem
1
-3
/
+11
2013-01-02
Move all of the header files which are involved in modelling the LLVM IR
Chandler Carruth
1
-10
/
+10
2013-01-01
Add IRBuilder::CreateVectorSplat and use it to simplify code.
Benjamin Kramer
1
-12
/
+1
2012-12-30
Remove the Function::getFnAttributes method in favor of using the AttributeSet
Bill Wendling
1
-1
/
+2
2012-12-30
LoopVectorizer: Fix a bug in the code that updates the loop exiting block.
Nadav Rotem
1
-0
/
+13
2012-12-26
If all of the write objects are identified then we can vectorize the loop eve...
Nadav Rotem
1
-1
/
+5
2012-12-26
LoopVectorizer: Optimize the vectorization of consecutive memory access when ...
Nadav Rotem
1
-22
/
+63
2012-12-25
LoopVectorize: Enable vectorization of the fmuladd intrinsic
Hal Finkel
1
-0
/
+1
2012-12-24
LoopVectorizer: When checking for vectorizable types, also check
Nadav Rotem
1
-1
/
+8
2012-12-24
LoopVectorizer: Fix an endless loop in the code that looks for reductions.
Nadav Rotem
1
-7
/
+8
2012-12-23
LoopVectorize: Fix accidentaly inverted condition.
Benjamin Kramer
1
-1
/
+1
2012-12-23
LoopVectorize: For scalars and void types there is no need to compute vector ...
Benjamin Kramer
1
-12
/
+10
2012-12-23
Loop Vectorizer: Update the cost model of scatter/gather operations and make
Nadav Rotem
1
-13
/
+29
2012-12-22
Change 'AttrVal' to 'AttrKind' to better reflect that it's a kind of attribut...
Bill Wendling
1
-1
/
+1
2012-12-21
Remove duplicate includes.
Roman Divacky
1
-1
/
+0
2012-12-21
Enable if-conversion.
Nadav Rotem
1
-1
/
+1
2012-12-21
Fix a bug in the code that checks if we can vectorize loops while using dynamic
Nadav Rotem
1
-19
/
+24
2012-12-20
LoopVectorize: Fix a bug in the scalarization of instructions.
Nadav Rotem
1
-1
/
+1
2012-12-20
Loop Vectorizer: turn-off if-conversion.
Nadav Rotem
1
-1
/
+1
2012-12-20
Loop Vectorizer: Enable if-conversion.
Nadav Rotem
1
-1
/
+1
2012-12-19
Rename the 'Attributes' class to 'Attribute'. It's going to represent a singl...
Bill Wendling
1
-1
/
+1
2012-12-18
LoopVectorize: Emit reductions as log2(vectorsize) shuffles + vector ops inst...
Benjamin Kramer
1
-12
/
+31
2012-12-13
Enable the Loop Vectorizer by default for O2 and O3. Disable if-conversion by...
Nadav Rotem
1
-1
/
+1
2012-12-13
Teach the cost model about the optimization in r169904: Truncation of inducti...
Nadav Rotem
1
-2
/
+17
2012-12-12
Fix indentation.
Nadav Rotem
1
-4
/
+3
2012-12-12
LoopVectorizer: Use the "optsize" attribute to decide if we are allowed to in...
Nadav Rotem
1
-6
/
+11
2012-12-12
Fix the ascii drawing that was ruined when I split the H and CPP
Nadav Rotem
1
-10
/
+10
2012-12-12
fix a typo.
Nadav Rotem
1
-1
/
+1
2012-12-12
LoopVectorizer: When -Os is used, vectorize only loops that dont require a ta...
Nadav Rotem
1
-22
/
+60
2012-12-11
PR14574. Fix a bug in the code that calculates the mask the converted PHIs in...
Nadav Rotem
1
-1
/
+1
2012-12-11
Loop Vectorize: optimize the vectorization of trunc(induction_var). The trunc...
Nadav Rotem
1
-1
/
+13
2012-12-11
Fix PR14565. Don't if-convert loops that have switch statements in them.
Nadav Rotem
1
-0
/
+4
2012-12-10
Split the LoopVectorizer into H and CPP.
Nadav Rotem
1
-951
/
+535
2012-12-10
Add support for reverse induction variables. For example:
Nadav Rotem
1
-90
/
+191
2012-12-09
LoopVectorize: support vectorizing intrinsic calls
Paul Redmond
1
-2
/
+55
2012-12-09
test commit.
Paul Redmond
1
-1
/
+1
2012-12-04
LoopVectorizer: Increase the number of pointers that can be tested at runtime...
Nadav Rotem
1
-1
/
+1
2012-12-04
Enable if-conversion during vectorization.
Nadav Rotem
1
-1
/
+1
2012-12-04
Fix a bug in vectorization of if-converted reduction variables. If the
Nadav Rotem
1
-14
/
+20
2012-12-04
Add support for reduction variables when IF-conversion is enabled.
Nadav Rotem
1
-10
/
+23
2012-12-04
Give scalar if-converted blocks half the score because they are not always ex...
Nadav Rotem
1
-5
/
+5
2012-12-04
Add the last part that is needed for vectorization of if-converted code.
Nadav Rotem
1
-162
/
+251
2012-12-04
LoopVectorize.cpp: Suppress a warning. [-Wunused-variable]
NAKAMURA Takumi
1
-2
/
+2
[prev]
[next]