summaryrefslogtreecommitdiffstats
path: root/llvm/lib/Target/AMDGPU/SIISelLowering.h
Commit message (Expand)AuthorAgeFilesLines
* AMDGPU: Custom lower more vector operationsMatt Arsenault2017-01-231-0/+5
* AMDGPU: Add Assert[SZ]Ext during argument load creationMatt Arsenault2017-01-091-1/+2
* AMDGPU: Check fast math flags in fadd/fsub combinesMatt Arsenault2016-12-221-1/+2
* AMDGPU: Form more FMAs if fusion is allowedMatt Arsenault2016-12-221-0/+1
* AMDGPU: Move combines into separate functionsMatt Arsenault2016-12-221-0/+5
* AMDGPU: Custom lower f16 fdivMatt Arsenault2016-12-221-0/+1
* AMDGPU: Make f16 ConstantFP legalMatt Arsenault2016-12-081-3/+0
* [AMDGPU] Scalarization of global uniform loads.Alexander Timofeev2016-12-081-0/+1
* AMDGPU: Implement isCheapAddrSpaceCastMatt Arsenault2016-12-021-0/+1
* [AMDGPU] Custom lower f16 = fp_round f64Konstantin Zhuravlyov2016-11-171-0/+3
* [AMDGPU] Promote f16/i16 conversions to f32/i32Konstantin Zhuravlyov2016-11-171-6/+0
* [AMDGPU] Add f16 support (VI+)Konstantin Zhuravlyov2016-11-131-0/+16
* [AMDGPU] Emit constant address space data in .rodata section and use relocati...Konstantin Zhuravlyov2016-10-201-0/+13
* AMDGPU: Fix broken FrameIndex handlingMatt Arsenault2016-09-171-1/+0
* AMDGPU: Improve splitting 64-bit bit ops by constantsMatt Arsenault2016-09-141-0/+6
* AMDGPU: Remove analyzeImmediateMatt Arsenault2016-07-281-1/+0
* AMDGPU: Change fdiv lowering based on !fpmath metadataMatt Arsenault2016-07-191-1/+2
* AMDGPU: Follow up to r275203Matt Arsenault2016-07-121-0/+3
* CodeGen: Use MachineInstr& in TargetLowering, NFCDuncan P. N. Exon Smith2016-06-301-3/+4
* [AMDGPU] Emit debugger prologue and emit the rest of the debugger fields in t...Konstantin Zhuravlyov2016-06-251-0/+2
* AMDGPU/SI: Make sure not to fold offsets into local address space globalsTom Stellard2016-06-251-0/+2
* AMDGPU: Cleanup subtarget handling.Matt Arsenault2016-06-241-1/+3
* AMDGPU: Add implicitarg.ptr intrinsic.Jan Vesely2016-06-211-1/+3
* AMDGPU: Temporarily select trap to s_endpgmMatt Arsenault2016-06-171-0/+1
* AMDGPU/SI: Refactor fixup handling for constant addrspace variablesTom Stellard2016-06-141-1/+2
* Revert "AMDGPU/SI: Refactor fixup handling for constant addrspace variables"Tom Stellard2016-06-141-2/+1
* AMDGPU/SI: Refactor fixup handling for constant addrspace variablesTom Stellard2016-06-141-1/+2
* Pass DebugLoc and SDLoc by const ref.Benjamin Kramer2016-06-121-14/+11
* AMDGPU: Unify LowerGlobalAddressJan Vesely2016-05-131-2/+0
* AMDGPU: Implement addrspacecastMatt Arsenault2016-04-251-0/+3
* AMDGPU: Implement canonicalizeMatt Arsenault2016-04-141-0/+1
* AMDGPU: Add atomic_inc + atomic_dec intrinsicsMatt Arsenault2016-04-121-0/+4
* AMDGPU: Implement {BUFFER,FLAT}_ATOMIC_CMPSWAP{,_X2}Tom Stellard2016-04-011-0/+1
* AMDGPU: R600 code splitting cleanupMatt Arsenault2016-03-111-3/+3
* AMDGPU/SI: Detect uniform branches and emit s_cbranch instructionsTom Stellard2016-02-121-0/+2
* AMDGPU: Match some med3 patternsMatt Arsenault2016-01-281-1/+2
* AMDGPU: Remove old sample intrinsicsMatt Arsenault2016-01-261-2/+0
* AMDGPU: Implement read_register and write_register intrinsicsMatt Arsenault2016-01-261-0/+3
* AMDGPU/SI: Prevent the DAGCombiner from creating setcc with i1 inputsTom Stellard2016-01-201-0/+2
* AMDGPU/SI: Add support for non-void functionsMarek Olsak2016-01-131-0/+7
* AMDGPU/SI: Select constant loads with non-uniform addresses to MUBUF instruct...Tom Stellard2015-12-151-0/+1
* AMDGPU/SI: Add support for sgpr and vgpr inline assembly constraintsTom Stellard2015-12-101-0/+1
* AMDGPU: Implement isNoopAddrSpaceCastMatt Arsenault2015-12-011-0/+2
* AMDGPU: Remove SIPrepareScratchRegsMatt Arsenault2015-11-301-4/+0
* AMDGPU: Use assert zext for workgroup sizesMatt Arsenault2015-11-301-0/+3
* AMDGPU: Assume SMRD access for constant address spaceMatt Arsenault2015-08-071-0/+1
* AMDGPU/SI: Add VI patterns to select FLAT instructions for global memory opsTom Stellard2015-07-201-0/+1
* Re-instate the EVT parameter to getScalarShiftAmountTy() for OOT userMehdi Amini2015-07-091-1/+1
* Make isLegalAddressingMode() taking DataLayout as an argumentMehdi Amini2015-07-091-2/+2
* Make TargetLowering::getShiftAmountTy() taking DataLayout as an argumentMehdi Amini2015-07-091-1/+1
OpenPOWER on IntegriCloud