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
/
AMDGPU
/
SIInstrInfo.cpp
Commit message (
Expand
)
Author
Age
Files
Lines
*
AMDGPU/SI: Emit constant arrays in the .text section
Tom Stellard
2015-12-10
1
-20
/
+28
*
AMDGPU: Optimize VOP2 operand legalization
Matt Arsenault
2015-12-01
1
-45
/
+125
*
AMDGPU: Rework how private buffer passed for HSA
Matt Arsenault
2015-11-30
1
-10
/
+4
*
AMDGPU: Rename enums to be consistent with HSA code object terminology
Matt Arsenault
2015-11-30
1
-8
/
+11
*
AMDGPU: Remove SIPrepareScratchRegs
Matt Arsenault
2015-11-30
1
-8
/
+10
*
AMDGPU/SI: select S_ABS_I32 when possible (v2)
Marek Olsak
2015-11-25
1
-0
/
+29
*
AMDGPU: Create emergency stack slots during frame lowering
Matt Arsenault
2015-11-06
1
-0
/
+1
*
AMDGPU: Remove unused scratch resource operands
Matt Arsenault
2015-11-06
1
-72
/
+129
*
AMDGPU: Fix hardcoded alignment of spill.
Matt Arsenault
2015-11-06
1
-2
/
+1
*
AMDGPU: Also track whether SGPRs were spilled
Matt Arsenault
2015-11-05
1
-0
/
+2
*
AMDGPU: Fix assert when legalizing atomic operands
Matt Arsenault
2015-11-05
1
-15
/
+51
*
AMDGPU: Make findUsedSGPR more readable
Matt Arsenault
2015-11-03
1
-7
/
+18
*
AMDGPU: Simplify VOP3 operand legalization.
Matt Arsenault
2015-10-21
1
-41
/
+49
*
AMDGPU: Fix not checking implicit operands in verifyInstruction
Matt Arsenault
2015-10-21
1
-15
/
+29
*
AMDGPU: Add MachineInstr overloads for instruction format tests
Matt Arsenault
2015-10-20
1
-30
/
+26
*
AMDGPU: Use explicit register size indirect pseudos
Matt Arsenault
2015-10-07
1
-1
/
+1
*
AMDGPU/SI: Add verifier check for exec reads
Matt Arsenault
2015-10-02
1
-0
/
+10
*
AMDGPU/SI: Don't set DATA_FORMAT if ADD_TID_ENABLE is set
Marek Olsak
2015-09-29
1
-0
/
+13
*
AMDGPU: Factor switch into separate function
Matt Arsenault
2015-09-28
1
-21
/
+27
*
AMDGPU: Fix splitting x16 SMRD loads
Matt Arsenault
2015-09-28
1
-2
/
+2
*
AMDGPU: Fix moving SMRD loads with literal offsets on CI
Matt Arsenault
2015-09-28
1
-3
/
+9
*
AMDGPU: Fix splitting SMRD with large offset
Matt Arsenault
2015-09-28
1
-1
/
+1
*
Improved the interface of methods commuting operands, improved X86-FMA3 mem-f...
Andrew Kaylor
2015-09-28
1
-16
/
+37
*
AMDGPU: Construct new buffer instruction when moving SMRD
Matt Arsenault
2015-09-25
1
-30
/
+37
*
AMDGPU: Re-justify workaround and fix worked around problem
Matt Arsenault
2015-09-25
1
-18
/
+42
*
AMDGPU: Don't create REG_SEQUENCE with SGPR dest and VGPR sources
Matt Arsenault
2015-09-25
1
-6
/
+15
*
AMDGPU: Return after instruction is processed.
Matt Arsenault
2015-09-24
1
-0
/
+4
*
AMDGPU: Remove another unnecessary check from commuteInstruction
Matt Arsenault
2015-09-24
1
-5
/
+0
*
AMDGPU: Reduce number of copies emitted
Matt Arsenault
2015-09-24
1
-5
/
+9
*
AMDGPU: Remove unnecessary check
Matt Arsenault
2015-09-22
1
-4
/
+0
*
AMDGPU/SI: Fix more cases of losing exec operands
Matt Arsenault
2015-09-10
1
-3
/
+1
*
AMDGPU: Extract full 64-bit subregister and use subregs
Matt Arsenault
2015-09-09
1
-35
/
+29
*
AMDGPU: Fix adding redundant implicit operands
Matt Arsenault
2015-09-01
1
-11
/
+7
*
AMDGPU: Set mem operands for spill instructions
Matt Arsenault
2015-08-29
1
-13
/
+30
*
AMDGPU: Fix dropping mem operands when moving to VALU
Matt Arsenault
2015-08-29
1
-11
/
+12
*
AMDGPU: Delete dead code
Matt Arsenault
2015-08-26
1
-54
/
+0
*
AMDGPU: Don't reprocess instructions when splitting i64 bcnt
Matt Arsenault
2015-08-26
1
-4
/
+5
*
AMDGPU: Fix not moving users of s_bfe_i64 to VALU
Matt Arsenault
2015-08-26
1
-0
/
+2
*
AMDGPU: Don't create intermediate SALU instructions
Matt Arsenault
2015-08-26
1
-27
/
+40
*
Fix some comment typos.
Benjamin Kramer
2015-08-08
1
-1
/
+1
*
AMDGPU/SI: Remove VCCReg
Matt Arsenault
2015-08-08
1
-1
/
+1
*
AMDGPU/SI: Remove EXECReg
Matt Arsenault
2015-08-05
1
-5
/
+0
*
AMDGPU/SI: Add implicit register operands in the correct order.
Alex Lorenz
2015-07-31
1
-19
/
+1
*
AMDGPU/SI: Simplify moveSMRDToVALU()
Tom Stellard
2015-07-30
1
-11
/
+9
*
AMDGPU/SI: Remove isTriviallyReMaterializable() function from SIInstrInfo
Tom Stellard
2015-07-30
1
-12
/
+0
*
AMDGPU/SI: Fix read2 merging into a super register.
Matt Arsenault
2015-07-14
1
-2
/
+1
*
AMDGPU/SI: Select mad patterns to v_mac_f32
Tom Stellard
2015-07-13
1
-5
/
+51
*
AMDGPU/SI: Fix crash on physical registers in SIInstrInfo::isOperandLegal()
Tom Stellard
2015-07-09
1
-1
/
+4
*
AMDPGU/SI: Use correct resource descriptors for VI on HSA
Tom Stellard
2015-06-26
1
-1
/
+6
*
AMDGPU: really don't commute REV opcodes if the target variant doesn't exist
Marek Olsak
2015-06-26
1
-8
/
+12
[next]