summaryrefslogtreecommitdiffstats
path: root/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.h
Commit message (Expand)AuthorAgeFilesLines
...
* [AMDGPU] Initialize instruction itinerary from GCNSubtargetStanislav Mekhanoshin2018-09-171-0/+5
* [AMDGPU] Ensure trig range reduction only used for subtargets that require itDavid Stuttard2018-09-141-0/+5
* AMDGPU: Re-apply r341982 after fixing the layering issueKonstantin Zhuravlyov2018-09-121-47/+78
* Revert "AMDGPU: Move isa version and EF_AMDGPU_MACH_* determination into Targ...Ilya Biryukov2018-09-121-78/+47
* AMDGPU: Move isa version and EF_AMDGPU_MACH_* determinationKonstantin Zhuravlyov2018-09-111-47/+78
* AMDGPU: Remove remnants of old address space mappingMatt Arsenault2018-08-311-8/+0
* [AMDGPU] Add support for a16 modifiear for gfx9Ryan Taylor2018-08-281-0/+5
* AMDGPU: Address todo for handling 1/(2 pi)Matt Arsenault2018-08-151-4/+5
* AMDGPU: Add feature vi-instsMatt Arsenault2018-08-071-0/+1
* Reapply "AMDGPU: Fix handling of alignment padding in DAG argument lowering"Matt Arsenault2018-07-201-14/+14
* Revert "AMDGPU: Fix handling of alignment padding in DAG argument lowering"Evgeniy Stepanov2018-07-141-14/+14
* AMDGPU: Fix handling of alignment padding in DAG argument loweringMatt Arsenault2018-07-131-14/+14
* AMDGPU/SI: Initialize InstrInfo before TargetLoweringInfo in GCNSubtargetTom Stellard2018-07-111-1/+1
* AMDGPU: Refactor Subtarget classesTom Stellard2018-07-111-78/+37
* AMDGPU: Fix UBSan error caused by r335942Tom Stellard2018-07-061-22/+18
* AMDGPU: Don't use struct type for argument layoutMatt Arsenault2018-06-291-1/+2
* AMDGPU: Separate R600 and GCN TableGen filesTom Stellard2018-06-281-238/+375
* AMDGPU: Remove ability to reserve VGPRs for debuggerKonstantin Zhuravlyov2018-06-211-12/+1
* [AMDGPU][Waitcnt] Fix handling of flat instrsMark Searles2018-06-041-0/+4
* AMDGPU: Pass function directly instead of MachineFunctionMatt Arsenault2018-05-291-13/+12
* AMDGPU: Remove #include "MCTargetDesc/AMDGPUMCTargetDesc.h" from common headersTom Stellard2018-05-221-5/+1
* AMDGPU: Add D16 instructions preserve unused bits featureKonstantin Zhuravlyov2018-05-041-0/+5
* AMDGPU: Remove remnants of gfx901 (it was deprecated some time ago)Konstantin Zhuravlyov2018-05-011-2/+1
* Remove \brief commands from doxygen comments.Adrian Prantl2018-05-011-2/+2
* AMDGPU: Add Vega12 and Vega20Matt Arsenault2018-04-301-1/+14
* [AMDGPU][Waitcnt] As of gfx7, VMEM operations do not increment the export cou...Mark Searles2018-04-261-0/+4
* AMDGPU: enable 128-bit for local addr space under an optionMarek Olsak2018-04-101-2/+3
* Revert "AMDGPU: enable 128-bit for local addr space under an option"Alex Shlyapnikov2018-04-091-3/+2
* AMDGPU: enable 128-bit for local addr space under an optionMarek Olsak2018-04-091-2/+3
* [AMDGPU][MC][GFX9] Added s_atomic_* and s_buffer_atomic_* instructionsDmitry Preobrazhensky2018-04-021-0/+5
* Revert r328975, it makes TableGen assert on the bots.Nico Weber2018-04-021-5/+0
* [AMDGPU][MC][GFX9] Added s_atomic_* and s_buffer_atomic_* instructionsDmitry Preobrazhensky2018-04-021-0/+5
* AMDGPU: Increase default stack alignmentMatt Arsenault2018-03-291-1/+6
* [AMDGPU] Remove use of OpenCL triple environment and replace with function at...Tony Tye2018-03-231-8/+4
* [AMDGPU] Supported ds_read_b128 generation; Widened vector length for local a...Farhana Aleen2018-03-091-0/+6
* AMDGPU/GlobalISel: Pass subtarget + TM to LegalizerInfoMatt Arsenault2018-03-081-1/+1
* [AMDGPU] Scratch setup fix on AMDPAL gfx9+ merge shaderTim Renouf2018-02-261-0/+6
* AMDGPU: Bring processors and features in sync with the specKonstantin Zhuravlyov2018-02-161-1/+0
* AMDGPU: Remove the s_buffer workaround for GFX9 chipsMarek Olsak2018-02-071-8/+0
* [AMDGPU][MC] Added validation of d16 and r128 modifiers of MIMG opcodesDmitry Preobrazhensky2018-02-051-0/+5
* AMDGPU/SI: Add d16 support for buffer intrinsics.Changpeng Fang2018-01-121-0/+5
* MachineFunction: Return reference from getFunction(); NFCMatthias Braun2017-12-151-4/+4
* AMDGPU/GCN: Bring processors in sync with AMDGPUUsageKonstantin Zhuravlyov2017-12-081-4/+2
* AMDGPU/EG: Add a new FeatureFMA and use it to selectively enable FMA instructionJan Vesely2017-12-041-0/+5
* AMDGPU: Disable fp64 support on pre GCN asicsJan Vesely2017-12-041-1/+1
* AMDGPU: Allow negative MUBUF vaddr for gfx9Matt Arsenault2017-11-301-0/+6
* AMDGPU: Select DS insts without m0 initializationMatt Arsenault2017-11-291-0/+6
* AMDGPU: Move hazard avoidance out of waitcnt pass.Matt Arsenault2017-11-171-1/+5
* AMDGPU: Don't use MUBUF vaddr if address may overflowMatt Arsenault2017-11-151-0/+5
* AMDGPU: Implement computeKnownBitsForTargetNode for mbcntMatt Arsenault2017-11-131-0/+4
OpenPOWER on IntegriCloud