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
/
lib
/
Target
/
R600
/
AMDGPUISelLowering.cpp
Commit message (
Expand
)
Author
Age
Files
Lines
...
*
R600: Fix vector FMA
Matt Arsenault
2014-06-26
1
-0
/
+1
*
R600: Promote i64 stores to v2i32
Tom Stellard
2014-06-24
1
-0
/
+3
*
R600: Fix inconsistency in rsq instructions.
Matt Arsenault
2014-06-24
1
-0
/
+8
*
R600: Remove DIV_INF
Matt Arsenault
2014-06-24
1
-2
/
+2
*
R600/SI: Fix div_scale intrinsic.
Matt Arsenault
2014-06-23
1
-2
/
+14
*
R600: Remove AMDILISelLowering
Matt Arsenault
2014-06-23
1
-7
/
+0
*
R600: Select is not expensive.
Matt Arsenault
2014-06-23
1
-0
/
+7
*
R600: Move add/sub with overflow out of AMDILISelLowering
Matt Arsenault
2014-06-23
1
-0
/
+4
*
R600: Move more out of AMDILISelLowering
Matt Arsenault
2014-06-23
1
-0
/
+13
*
R600/SI: Handle i64 sub.
Matt Arsenault
2014-06-23
1
-1
/
+0
*
R600: Rename AMDIL file
Matt Arsenault
2014-06-23
1
-1
/
+1
*
R600: Use LowerSDIVREM for i64 node replace
Jan Vesely
2014-06-22
1
-90
/
+0
*
R600: Implement custom SDIVREM.
Jan Vesely
2014-06-22
1
-4
/
+43
*
R600/SI: Add a pattern for f32 ftrunc
Tom Stellard
2014-06-20
1
-0
/
+2
*
R600: Expand vector flog2
Tom Stellard
2014-06-20
1
-0
/
+1
*
R600: Expand vector fexp2
Tom Stellard
2014-06-20
1
-0
/
+1
*
R600/SI: Add intrinsics for various math instructions.
Matt Arsenault
2014-06-19
1
-2
/
+30
*
Use stdint macros for specifying size of constants
Matt Arsenault
2014-06-18
1
-2
/
+3
*
R600: Handle fnearbyint
Matt Arsenault
2014-06-18
1
-0
/
+12
*
Use LL suffix for literal that should be 64-bits.
Matt Arsenault
2014-06-18
1
-1
/
+1
*
R600: Expand vector fceil
Jan Vesely
2014-06-18
1
-0
/
+1
*
Work around ridiculous warning.
Matt Arsenault
2014-06-18
1
-2
/
+5
*
R600/SI: Add intrinsics for brev instructions
Matt Arsenault
2014-06-18
1
-0
/
+4
*
R600: Implement f64 ftrunc, ffloor and fceil.
Matt Arsenault
2014-06-18
1
-0
/
+107
*
R600: Custom lower f64 frint for pre-CI
Matt Arsenault
2014-06-18
1
-0
/
+26
*
R600/SI: Match ctlz_zero_undef
Matt Arsenault
2014-06-17
1
-0
/
+2
*
R600: Use LDS and vectors for private memory
Tom Stellard
2014-06-17
1
-0
/
+1
*
SelectionDAG: Expand i64 = FP_TO_SINT i32
Tom Stellard
2014-06-17
1
-0
/
+1
*
Fix copy paste error
Matt Arsenault
2014-06-15
1
-1
/
+1
*
R600: Remove a few more things from AMDILISelLowering
Matt Arsenault
2014-06-15
1
-19
/
+21
*
R600: Fix assert on vector sdiv
Matt Arsenault
2014-06-15
1
-4
/
+4
*
R600: Move / cleanup more leftover AMDIL stuff.
Matt Arsenault
2014-06-15
1
-5
/
+19
*
R600: Move division custom lowering out of AMDILISelLowering
Matt Arsenault
2014-06-15
1
-2
/
+246
*
R600: Report that integer division is expensive.
Matt Arsenault
2014-06-15
1
-0
/
+7
*
R600: Fix asserts related to constant initializers
Matt Arsenault
2014-06-14
1
-5
/
+20
*
R600: Use address space enum instead of value
Matt Arsenault
2014-06-14
1
-6
/
+7
*
R600: Cleanup some old AMDIL stuff.
Matt Arsenault
2014-06-13
1
-9
/
+31
*
R600/SI: Fix selection error on i64 rotl / rotr.
Matt Arsenault
2014-06-13
1
-3
/
+7
*
R600: Mostly remove remaining AMDIL intrinsics.
Matt Arsenault
2014-06-12
1
-11
/
+15
*
R600/SI: Use v_cvt_f32_ubyte* instructions
Matt Arsenault
2014-06-11
1
-1
/
+16
*
Try to fix the msvc build.
Rafael Espindola
2014-06-11
1
-1
/
+2
*
Use cast instead of assert + dyn_cast
Matt Arsenault
2014-06-11
1
-3
/
+2
*
R600: Add helper functions.
Matt Arsenault
2014-06-11
1
-0
/
+19
*
R600: Use BCNT_INT for evergreen
Matt Arsenault
2014-06-10
1
-2
/
+6
*
R600/SI: Use bcnt instruction for ctpop
Matt Arsenault
2014-06-10
1
-1
/
+11
*
R600: Handle fcopysign
Matt Arsenault
2014-06-10
1
-0
/
+7
*
R600: Fix selection failure for vector bswap
Matt Arsenault
2014-06-09
1
-0
/
+1
*
R600: Set all float vector expands in the same place
Matt Arsenault
2014-06-01
1
-5
/
+2
*
R600: Try to convert BFE back to standard bit ops when possible.
Matt Arsenault
2014-05-22
1
-0
/
+21
*
R600: Add dag combine for BFE
Matt Arsenault
2014-05-22
1
-0
/
+74
[prev]
[next]