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
/
Target
/
R600
/
SIISelLowering.cpp
Age
Commit message (
Expand
)
Author
Files
Lines
2014-08-09
R600/SI: Custom lower CONCAT_VECTORS
Tom Stellard
1
-1
/
+3
2014-08-06
Remove the target machine from CCState. Previously it was only used
Eric Christopher
1
-2
/
+2
2014-08-04
Remove the TargetMachine forwards for TargetSubtargetInfo based
Eric Christopher
1
-27
/
+26
2014-08-02
R600/SI: Fix formatting.
Matt Arsenault
1
-22
/
+28
2014-08-01
[SDAG] MorphNodeTo recursively deletes dead operands of the old
Chandler Carruth
1
-1
/
+3
2014-08-01
R600/SI: Do abs/neg folding with ComplexPatterns
Tom Stellard
1
-25
/
+7
2014-07-28
R600/SI: Implement getOptimalMemOpType
Matt Arsenault
1
-0
/
+20
2014-07-28
R600/SI: Make argument loads invariant
Matt Arsenault
1
-9
/
+17
2014-07-27
Add alignment value to allowsUnalignedMemoryAccess
Matt Arsenault
1
-8
/
+10
2014-07-26
R600: Move intrinsic lowering to separate functions
Matt Arsenault
1
-109
/
+123
2014-07-24
R600: Add new functions for splitting vector loads and stores.
Matt Arsenault
1
-3
/
+3
2014-07-21
R600/SI: Clean up some of the unused REGISTER_{LOAD,STORE} code
Tom Stellard
1
-148
/
+24
2014-07-21
R600/SI: Use scratch memory for large private arrays
Tom Stellard
1
-8
/
+86
2014-07-21
R600/SI: Store constant initializer data in constant memory
Tom Stellard
1
-0
/
+28
2014-07-20
SIISelLowering.cpp: Define _USE_MATH_DEFINES to let M_PI provided on MS <cmath>.
NAKAMURA Takumi
1
-0
/
+6
2014-07-20
R600/SI: Remove dead code and add missing tests.
Matt Arsenault
1
-14
/
+0
2014-07-19
R600/SI: implement range reduction for sin/cos
Matt Arsenault
1
-0
/
+23
2014-07-15
R600/SI: Allow using f32 rcp / rsq when denormals not handled.
Matt Arsenault
1
-8
/
+29
2014-07-15
R600/SI: Fix select on i1
Matt Arsenault
1
-0
/
+3
2014-07-15
R600/SI: Implement less wrong f32 fdiv
Matt Arsenault
1
-0
/
+76
2014-07-13
R600: Make ShaderType private
Matt Arsenault
1
-6
/
+7
2014-07-10
R600: Implement float to long/ulong
Jan Vesely
1
-0
/
+3
2014-07-07
R600: Fix mishandling of load / store chains.
Matt Arsenault
1
-24
/
+33
2014-07-03
[codegen,aarch64] Add a target hook to the code generator to control
Chandler Carruth
1
-2
/
+6
2014-07-02
R600: Promote i64 loads to v2i32
Tom Stellard
1
-1
/
+8
2014-06-24
R600: Promote i64 stores to v2i32
Tom Stellard
1
-1
/
+6
2014-06-23
R600: Move more out of AMDILISelLowering
Matt Arsenault
1
-1
/
+3
2014-06-23
R600/SI: Handle i64 sub.
Matt Arsenault
1
-0
/
+2
2014-06-23
R600: Rename AMDIL file
Matt Arsenault
1
-1
/
+1
2014-06-18
R600/SI: Prettier operand printing for 64-bit ops.
Matt Arsenault
1
-11
/
+12
2014-06-18
R600/SI: Temporary fix for f64 fneg
Matt Arsenault
1
-0
/
+4
2014-06-11
R600/SI: Use v_cvt_f32_ubyte* instructions
Matt Arsenault
1
-0
/
+118
2014-06-10
R600: Use BCNT_INT for evergreen
Matt Arsenault
1
-3
/
+0
2014-06-10
R600/SI: Implement i64 ctpop
Matt Arsenault
1
-0
/
+1
2014-06-10
R600/SI: Use bcnt instruction for ctpop
Matt Arsenault
1
-0
/
+2
2014-06-10
R600/SI: Handle sign_extend and zero_extend to i64 with patterns.
Matt Arsenault
1
-40
/
+0
2014-06-10
SelectionDAG: Expand SELECT_CC to SELECT + SETCC
Tom Stellard
1
-18
/
+4
2014-06-05
Use nullptr
Matt Arsenault
1
-3
/
+2
2014-06-03
Fix typos
Matt Arsenault
1
-6
/
+6
2014-05-22
R600: Add dag combine for BFE
Matt Arsenault
1
-1
/
+2
2014-05-16
R600/SI: Promote f32 SELECT to i32
Tom Stellard
1
-0
/
+2
2014-05-15
Use range for
Matt Arsenault
1
-3
/
+2
2014-05-15
R600/SI: Stop using VSrc_* as the default register class for types.
Tom Stellard
1
-42
/
+7
2014-05-10
R600/SI: Fold fabs/fneg into src input modifier
Vincent Lejeune
1
-2
/
+31
2014-05-10
R600/SI: Prettier display of input modifiers
Vincent Lejeune
1
-5
/
+11
2014-05-10
R600/SI: Use pseudo instruction for fabs/clamp/fneg
Vincent Lejeune
1
-0
/
+44
2014-05-09
R600: Move MIN/MAX matching from LowerOperation() to PerformDAGCombine()
Tom Stellard
1
-6
/
+0
2014-04-30
R600/SI: Use VALU instructions for copying i1 values
Tom Stellard
1
-1
/
+1
2014-04-29
R600/SI: Custom lower SI_IF and SI_ELSE to avoid machine verifier errors
Tom Stellard
1
-9
/
+40
2014-04-29
R600: Change UDIV/UREM to UDIVREM when legalizing types
Tom Stellard
1
-0
/
+4
[prev]
[next]