index
:
bcm5719-llvm
meklort-10.0.0
meklort-10.0.1
ortega-7.0.1
Project Ortega BCM5719 LLVM
Raptor Computing Systems
summary
refs
log
tree
commit
diff
stats
log msg
author
committer
range
path:
root
/
llvm
/
test
/
Analysis
/
CostModel
/
AMDGPU
Commit message (
Expand
)
Author
Age
Files
Lines
*
[AMDGPU] Implemented fma cost analysis
Stanislav Mekhanoshin
2019-12-18
1
-0
/
+120
*
[AMDGPU] Fixed cost model for packed 16 bit ops
Stanislav Mekhanoshin
2019-12-17
7
-102
/
+258
*
AMDGPU: Split test functions to avoid dependency on subtarget
Matt Arsenault
2019-11-19
1
-57
/
+155
*
[AMDGPU] Fix bug introduced in 47a5c36b37f0
dfukalov
2019-11-07
1
-4
/
+15
*
[AMDGPU] Improve code size cost model (part 2)
dfukalov
2019-11-06
10
-1
/
+32
*
[AMDGPU] Improve code size cost model
Daniil Fukalov
2019-10-17
3
-18
/
+24
*
TTI: Improve default costs for addrspacecast
Matt Arsenault
2019-06-03
1
-6
/
+27
*
AMDGPU: Partially fix default device for HSA
Matt Arsenault
2019-03-17
1
-2
/
+2
*
[AMDGPU] Prepare for introduction of v3 and v5 MVTs
Tim Renouf
2019-03-17
8
-7
/
+105
*
[AMDGPU] Switch to the new addr space mapping by default
Yaxun Liu
2018-02-02
1
-24
/
+24
*
AMDGPU: Don't assert in TTI with fp32 denorms enabled
Matt Arsenault
2017-08-31
1
-11
/
+78
*
AMDGPU: Make some packed shuffles free
Matt Arsenault
2017-05-10
3
-41
/
+119
*
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel
Matt Arsenault
2017-03-21
12
-99
/
+99
*
AMDGPU: Cost model for basic integer operations
Matt Arsenault
2016-03-25
4
-0
/
+343
*
AMDGPU: Partially implement getArithmeticInstrCost for FP ops
Matt Arsenault
2016-03-25
4
-0
/
+358
*
TTI: Report 0 cost for free addrspacecasts
Matt Arsenault
2016-03-25
1
-0
/
+45
*
TTI: Use 0 for cost of fabs if free
Matt Arsenault
2016-03-25
1
-0
/
+97
*
AMDGPU: TTI: Make insertelement free.
Matt Arsenault
2016-03-25
1
-0
/
+37
*
AMDGPU: Override getCFInstrCost
Matt Arsenault
2015-12-16
1
-0
/
+45
*
AMDGPU: Report extractelement as free in cost model
Matt Arsenault
2015-12-01
2
-0
/
+112