6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2024-12-21 00:32:23 +00:00
Code Issues Projects Releases Wiki Activity
40e071c1eb
llvm-6502/lib/Target/R600
History
Vincent Lejeune 843c6c2d0e R600: Use a refined heuristic to choose when switching clause 
This is using a hint from AMD APP OpenCL Programming Guide with
empirically tweaked parameters.
I used Unigine Heaven 3.0 to determine best parameters on my system
(i7 2600/Radeon 6950/Kernel 3.9.4) the benchmark :
it went from 38.8 average fps to 39.6, which is ~3% gain.
(Lightmark 2008.2 gain is much more marginal: from 537 to 539)

There is no lit test provided as the parameter were determined
empirically and it it would be nearly impossiblet to find a test
program that check for optimal behavior.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@183593 91177308-0d34-0410-b5e6-96231b3b80d8
2013-06-07 23:30:34 +00:00
..
InstPrinter Move passes from namespace llvm into anonymous namespaces. Sort includes while there. 2013-05-23 17:10:37 +00:00
MCTargetDesc R600: Hide symbols of implementation details. 2013-05-23 15:43:05 +00:00
TargetInfo R600: Remove unnecessary include 2013-06-07 20:28:43 +00:00
AMDGPU.h R600: Rework subtarget info and remove AMDILDevice classes 2013-06-07 20:37:48 +00:00
AMDGPU.td R600: Rework subtarget info and remove AMDILDevice classes 2013-06-07 20:37:48 +00:00
AMDGPUAsmPrinter.cpp R600: Rework subtarget info and remove AMDILDevice classes 2013-06-07 20:37:48 +00:00
AMDGPUAsmPrinter.h
AMDGPUCallingConv.td R600: Rework subtarget info and remove AMDILDevice classes 2013-06-07 20:37:48 +00:00
AMDGPUConvertToISA.cpp
AMDGPUFrameLowering.cpp R600: Fix calculation of stack offset in AMDGPUFrameLowering 2013-06-07 20:52:05 +00:00
AMDGPUFrameLowering.h
AMDGPUIndirectAddressing.cpp Don't cache the instruction and register info from the TargetMachine, because 2013-06-07 20:28:55 +00:00
AMDGPUInstrInfo.cpp R600: Rework subtarget info and remove AMDILDevice classes 2013-06-07 20:37:48 +00:00
AMDGPUInstrInfo.h
AMDGPUInstrInfo.td Create an FPOW SDNode opcode def in the target independent .td file rather than in a specific backend. 2013-05-22 06:36:09 +00:00
AMDGPUInstructions.td R600/SI: Add support for global loads 2013-06-03 17:39:43 +00:00
AMDGPUIntrinsics.td
AMDGPUISelLowering.cpp R600/SI: Add a calling convention for compute shaders 2013-06-03 17:40:11 +00:00
AMDGPUISelLowering.h R600/SI: Add support for work item and work group intrinsics 2013-06-03 17:40:18 +00:00
AMDGPUMachineFunction.cpp
AMDGPUMachineFunction.h
AMDGPUMCInstLower.cpp
AMDGPUMCInstLower.h
AMDGPURegisterInfo.cpp Don't cache the instruction and register info from the TargetMachine, because 2013-06-07 20:28:55 +00:00
AMDGPURegisterInfo.h Don't cache the instruction and register info from the TargetMachine, because 2013-06-07 20:28:55 +00:00
AMDGPURegisterInfo.td Make SubRegIndex size mandatory, following r183020. 2013-05-31 23:45:26 +00:00
AMDGPUStructurizeCFG.cpp Silencing an MSVC warning about mixing bool and unsigned int. 2013-06-04 01:03:03 +00:00
AMDGPUSubtarget.cpp R600: Rework subtarget info and remove AMDILDevice classes 2013-06-07 20:37:48 +00:00
AMDGPUSubtarget.h R600: Rework subtarget info and remove AMDILDevice classes 2013-06-07 20:37:48 +00:00
AMDGPUTargetMachine.cpp R600: Rework subtarget info and remove AMDILDevice classes 2013-06-07 20:37:48 +00:00
AMDGPUTargetMachine.h Fix a leak on the r600 backend. 2013-05-23 03:31:47 +00:00
AMDILBase.td R600: Move Subtarget feature definitions into AMDGPU.td 2013-06-07 20:28:49 +00:00
AMDILCFGStructurizer.cpp R600: Rework subtarget info and remove AMDILDevice classes 2013-06-07 20:37:48 +00:00
AMDILInstrInfo.td R600: Rework subtarget info and remove AMDILDevice classes 2013-06-07 20:37:48 +00:00
AMDILIntrinsicInfo.cpp R600: Rework subtarget info and remove AMDILDevice classes 2013-06-07 20:37:48 +00:00
AMDILIntrinsicInfo.h
AMDILIntrinsics.td
AMDILISelDAGToDAG.cpp R600: Rework subtarget info and remove AMDILDevice classes 2013-06-07 20:37:48 +00:00
AMDILISelLowering.cpp R600: Rework subtarget info and remove AMDILDevice classes 2013-06-07 20:37:48 +00:00
AMDILRegisterInfo.td
CMakeLists.txt R600: Rework subtarget info and remove AMDILDevice classes 2013-06-07 20:37:48 +00:00
LLVMBuild.txt
Makefile
Processors.td R600: Rework subtarget info and remove AMDILDevice classes 2013-06-07 20:37:48 +00:00
R600ControlFlowFinalizer.cpp R600: Anti dep better handled in tex clause 2013-06-07 23:30:26 +00:00
R600Defines.h R600: Relax some vector constraints on Dot4. 2013-05-17 16:50:32 +00:00
R600EmitClauseMarkers.cpp Don't cache the instruction and register info from the TargetMachine, because 2013-06-07 20:28:55 +00:00
R600ExpandSpecialInstrs.cpp Don't cache the instruction and register info from the TargetMachine, because 2013-06-07 20:28:55 +00:00
R600InstrInfo.cpp R600: Rework subtarget info and remove AMDILDevice classes 2013-06-07 20:37:48 +00:00
R600InstrInfo.h R600: Rework subtarget info and remove AMDILDevice classes 2013-06-07 20:37:48 +00:00
R600Instructions.td R600: Rework subtarget info and remove AMDILDevice classes 2013-06-07 20:37:48 +00:00
R600Intrinsics.td R600: Improve texture handling 2013-05-17 16:50:20 +00:00
R600ISelLowering.cpp Don't cache the instruction and register info from the TargetMachine, because 2013-06-07 20:28:55 +00:00
R600ISelLowering.h Don't cache the instruction and register info from the TargetMachine, because 2013-06-07 20:28:55 +00:00
R600MachineFunctionInfo.cpp
R600MachineFunctionInfo.h Move passes from namespace llvm into anonymous namespaces. Sort includes while there. 2013-05-23 17:10:37 +00:00
R600MachineScheduler.cpp R600: Use a refined heuristic to choose when switching clause 2013-06-07 23:30:34 +00:00
R600MachineScheduler.h R600: Use a refined heuristic to choose when switching clause 2013-06-07 23:30:34 +00:00
R600OptimizeVectorRegisters.cpp Don't cache the instruction and register info from the TargetMachine, because 2013-06-07 20:28:55 +00:00
R600Packetizer.cpp R600: 3 op instructions have no write bit but the result are store in PV 2013-06-03 15:56:12 +00:00
R600RegisterInfo.cpp Don't cache the instruction and register info from the TargetMachine, because 2013-06-07 20:28:55 +00:00
R600RegisterInfo.h Don't cache the instruction and register info from the TargetMachine, because 2013-06-07 20:28:55 +00:00
R600RegisterInfo.td R600: use capital letter for PV channel 2013-06-03 15:44:35 +00:00
R600Schedule.td
R600TextureIntrinsicsReplacer.cpp Move passes from namespace llvm into anonymous namespaces. Sort includes while there. 2013-05-23 17:10:37 +00:00
SIAnnotateControlFlow.cpp R600: Remove unnecessary include 2013-06-07 20:28:43 +00:00
SIDefines.h
SIInsertWaits.cpp Don't cache the instruction and register info from the TargetMachine, because 2013-06-07 20:28:55 +00:00
SIInstrFormats.td R600/SI: Use the same names for VOP3 operands and encoding fields 2013-05-20 15:02:08 +00:00
SIInstrInfo.cpp Don't cache the instruction and register info from the TargetMachine, because 2013-06-07 20:28:55 +00:00
SIInstrInfo.h
SIInstrInfo.td Cast to the correct type. Pointer, not reference. 2013-06-06 05:39:29 +00:00
SIInstructions.td R600: Rework subtarget info and remove AMDILDevice classes 2013-06-07 20:37:48 +00:00
SIIntrinsics.td
SIISelLowering.cpp R600: Rework subtarget info and remove AMDILDevice classes 2013-06-07 20:37:48 +00:00
SIISelLowering.h Don't cache the instruction and register info from the TargetMachine, because 2013-06-07 20:28:55 +00:00
SILowerControlFlow.cpp Don't cache the instruction and register info from the TargetMachine, because 2013-06-07 20:28:55 +00:00
SIMachineFunctionInfo.cpp
SIMachineFunctionInfo.h
SIRegisterInfo.cpp Don't cache the instruction and register info from the TargetMachine, because 2013-06-07 20:28:55 +00:00
SIRegisterInfo.h Don't cache the instruction and register info from the TargetMachine, because 2013-06-07 20:28:55 +00:00
SIRegisterInfo.td
SISchedule.td