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/SI: Remove v_sub_f64 pseudo
Matt Arsenault
2015-02-20
1
-0
/
+3
*
R600: Use new fmad node.
Matt Arsenault
2015-02-20
1
-1
/
+7
*
R600/SI: Fix implicit vcc operand to v_div_fmas_*
Matt Arsenault
2015-02-14
1
-3
/
+2
*
R600/SI: Make more store operations legal
Tom Stellard
2015-02-04
1
-3
/
+0
*
R600: Don't promote i64 stores to v2i32 during DAG legalization
Tom Stellard
2015-02-04
1
-3
/
+0
*
Reuse a bunch of cached subtargets and remove getSubtarget calls
Eric Christopher
2015-01-30
1
-7
/
+4
*
Move DataLayout back to the TargetMachine from TargetSubtargetInfo
Eric Christopher
2015-01-26
1
-2
/
+2
*
R600/SI: Move i64 -> v2i32 load promotion into AMDGPUDAGToDAGISel::Select()
Tom Stellard
2015-01-23
1
-3
/
+0
*
R600: Try to use lower types for 64bit division if possible
Jan Vesely
2015-01-22
1
-12
/
+38
*
R600: Simplify LowerUDIVREM
Jan Vesely
2015-01-22
1
-19
/
+11
*
R600/SI: Custom lower fround
Matt Arsenault
2015-01-21
1
-10
/
+113
*
Implement new way of expanding extloads.
Matt Arsenault
2015-01-14
1
-18
/
+8
*
R600: Implement getRecipEstimate
Matt Arsenault
2015-01-13
1
-0
/
+23
*
R600: Implement getRsqrtEstimate
Matt Arsenault
2015-01-13
1
-0
/
+18
*
R600: Make cttz / ctlz cheap to speculate
Matt Arsenault
2015-01-13
1
-0
/
+12
*
[SelectionDAG] Allow targets to specify legality of extloads' result
Ahmed Bougacha
2015-01-08
1
-13
/
+16
*
R600/SI: Add class intrinsic
Matt Arsenault
2015-01-06
1
-0
/
+5
*
R600: Remove outdated comment
Matt Arsenault
2014-12-19
1
-4
/
+0
*
R600/SI: Only form min/max with 1 use.
Matt Arsenault
2014-12-19
1
-1
/
+1
*
R600: Fix min/max matching problems with unordered compares
Matt Arsenault
2014-12-12
1
-42
/
+43
*
Add target hook for whether it is profitable to reduce load widths
Matt Arsenault
2014-12-12
1
-0
/
+23
*
R600/SI: Update instruction conversions for VI
Marek Olsak
2014-12-07
1
-1
/
+19
*
R600/SI: Use ZeroOrNegativeOneBooleanContent
Matt Arsenault
2014-11-26
1
-0
/
+3
*
R600: Fix assert on copy of an i1 on pre-SI
Matt Arsenault
2014-11-23
1
-1
/
+2
*
R600: Permute operands when selecting legacy min/max
Matt Arsenault
2014-11-15
1
-6
/
+9
*
R600: Fix 64-bit integer division
Tom Stellard
2014-11-15
1
-2
/
+2
*
R600: Factor i64 UDIVREM lowering into its own fuction
Tom Stellard
2014-11-15
1
-0
/
+81
*
R600/SI: Combine min3/max3 instructions
Matt Arsenault
2014-11-14
1
-0
/
+6
*
R600/SI: Match integer min / max instructions
Matt Arsenault
2014-11-14
1
-21
/
+69
*
R600/SI: Fix fmin_legacy / fmax_legacy matching for SI
Matt Arsenault
2014-11-13
1
-19
/
+50
*
We can get the TLOF from the TargetMachine - so constructor no longer require...
Aditya Nandakumar
2014-11-13
1
-1
/
+1
*
R600: Error on initializer for LDS.
Matt Arsenault
2014-11-13
1
-2
/
+21
*
This patch changes the ownership of TLOF from TargetLoweringBase to TargetMac...
Aditya Nandakumar
2014-11-13
1
-1
/
+1
*
Add minnum / maxnum codegen
Matt Arsenault
2014-10-21
1
-0
/
+2
*
R600/SI: Add missing parameter to div_fmas intrinsic
Matt Arsenault
2014-10-21
1
-0
/
+2
*
R600: Fix nonsensical implementation of computeKnownBits for BFE
Matt Arsenault
2014-10-16
1
-5
/
+1
*
R600: Remove dead function
Matt Arsenault
2014-10-16
1
-12
/
+0
*
R600: Remove unnecessary part of computeKnownBitsForTargetNode
Matt Arsenault
2014-10-15
1
-5
/
+0
*
Move variable down to use
Matt Arsenault
2014-10-15
1
-4
/
+4
*
R600: Fix miscompiles when BFE has multiple uses
Matt Arsenault
2014-10-15
1
-7
/
+10
*
R600: Use existing variable
Matt Arsenault
2014-10-15
1
-1
/
+1
*
R600: Remove outdated comment
Matt Arsenault
2014-10-15
1
-3
/
+0
*
R600/SI: Custom lower f64 -> i64 conversions
Matt Arsenault
2014-10-03
1
-0
/
+53
*
R600: Custom lower [s|u]int_to_fp for i64 -> f64
Matt Arsenault
2014-10-03
1
-2
/
+43
*
R600/SI: Fix ftrunc f64 conformance failures.
Matt Arsenault
2014-10-03
1
-1
/
+1
*
R600/SI: Add a note about the order of the operands to div_scale
Matt Arsenault
2014-09-26
1
-0
/
+6
*
R600: Don't set BypassSlowDiv for 64-bit division
Tom Stellard
2014-09-22
1
-3
/
+0
*
R600/SI: Use ISD::MUL instead of ISD::UMULO when lowering division
Tom Stellard
2014-09-22
1
-3
/
+3
*
R600: Better fix for bug 20982
Matt Arsenault
2014-09-19
1
-6
/
+3
*
R600: Bug 20982 - Avoid undefined left shift of negative value
Matt Arsenault
2014-09-18
1
-3
/
+10
[next]