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
/
CodeGen
/
AMDGPU
/
load-hi16.ll
Commit message (
Expand
)
Author
Age
Files
Lines
*
AMDGPU: Always use s33 for global scratch wave offset
Matt Arsenault
2019-06-20
1
-10
/
+10
*
AMDGPU: Don't fix emergency stack slot at offset 0
Matt Arsenault
2019-06-05
1
-11
/
+11
*
AMDGPU: Invert frame index offset interpretation
Matt Arsenault
2019-06-05
1
-17
/
+17
*
AMDGPU: Assume ECC is enabled by default if supported
Matt Arsenault
2019-04-03
1
-1
/
+1
*
AMDGPU: Make sram-ecc off by default for Vega20
Konstantin Zhuravlyov
2019-03-29
1
-1
/
+1
*
AMDGPU: Move d16 load matching to preprocess step
Matt Arsenault
2019-03-08
1
-0
/
+15
*
AMDGPU: Add more tests for d16 loads
Matt Arsenault
2019-03-08
1
-2
/
+316
*
AMDGPU: Add D16 instructions preserve unused bits feature
Konstantin Zhuravlyov
2018-05-04
1
-200
/
+207
*
[AMDGPU] Change constant addr space to 4
Yaxun Liu
2018-02-13
1
-10
/
+10
*
[AMDGPU] Switch to the new addr space mapping by default
Yaxun Liu
2018-02-02
1
-56
/
+56
*
AMDGPU: Select DS insts without m0 initialization
Matt Arsenault
2017-11-29
1
-2
/
+0
*
AMDGPU: Don't use MUBUF vaddr if address may overflow
Matt Arsenault
2017-11-15
1
-28
/
+27
*
AMDGPU: Fix not converting d16 load/stores to offset
Matt Arsenault
2017-11-13
1
-2
/
+58
*
AMDGPU: Select d16 loads into low component of register
Matt Arsenault
2017-11-13
1
-0
/
+98
*
AMDGPU: Fix potentially incorrectly matching check lines
Matt Arsenault
2017-10-02
1
-8
/
+8
*
AMDGPU: Match load d16 hi instructions
Matt Arsenault
2017-09-20
1
-0
/
+506