review.tizen.org Git - platform/upstream/llvm.git/history - llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp

projects / platform / upstream / llvm.git / history

[platform/upstream/llvm.git] / llvm / lib / Target / AMDGPU / AMDGPUISelLowering.cpp

2022-08-03	David Truby	[llvm] Always use TargetConstant for FP_ROUND ISD Nodes	blob \| commitdiff
2022-07-06	Shilei Tian	[LLVM] Add the support for fmax and fmin in atomicrmw...	blob \| commitdiff \| diff to current
2022-06-30	Piotr Sobczak	[AMDGPU] Make v16i16/v16f16 legal	blob \| commitdiff \| diff to current
2022-06-20	Guillaume Chatelet	[NFC][Alignment] Remove max functions between Align...	blob \| commitdiff \| diff to current
2022-06-07	Guillaume Chatelet	[Alignment][NFC] Remove usage of MemSDNode::getAlignment	blob \| commitdiff \| diff to current
2022-05-18	Shao-Ce SUN	[NFC][AMDGPU][CodeGen] Use ArrayRef in TargetLowering...	blob \| commitdiff \| diff to current
2022-04-22	Matt Arsenault	AMDGPU: Directly implement computeKnownBits for workite...	blob \| commitdiff \| diff to current
2022-04-11	Nicolai Hähnle	AMDGPU/SDAG: Custom SETCC (i.e. ballot) is always uniform	blob \| commitdiff \| diff to current
2022-04-07	Stanislav Mekhanoshin	[AMDGPU] Split unaligned LDS access instead of scalarizing	blob \| commitdiff \| diff to current
2022-03-29	Shao-Ce SUN	[NFC][CodeGen] Add a setTargetDAGCombine use ArrayRef	blob \| commitdiff \| diff to current
2022-03-17	Changpeng Fang	AMDGPU: Use the implicit kernargs for code object version 5	blob \| commitdiff \| diff to current
2022-03-16	serge-sans-paille	Cleanup codegen includes	blob \| commitdiff \| diff to current
2022-03-10	Nico Weber	Revert "Cleanup codegen includes"	blob \| commitdiff \| diff to current
2022-03-10	serge-sans-paille	Cleanup codegen includes	blob \| commitdiff \| diff to current
2022-03-09	Venkata Ramanaiah...	[AMDGPU] Move call clobbered return address registers...	blob \| commitdiff \| diff to current
2022-02-11	Julien Pages	[AMDGPU] Add a new intrinsic to control fp_trunc roundi...	blob \| commitdiff \| diff to current
2022-02-08	Simon Pilgrim	[ADT] Add APInt/MathExtras isShiftedMask variant return...	blob \| commitdiff \| diff to current
2022-01-24	Stanislav Mekhanoshin	[AMDGPU] Make v8i16/v8f16 legal	blob \| commitdiff \| diff to current
2022-01-14	Craig Topper	[AMDGPU] Correct the known bits calculation for MUL_I24.	blob \| commitdiff \| diff to current
2022-01-11	Maksim Panchenko	Merge BOLT into LLVM monorepo	blob \| commitdiff \| diff to current
2022-01-08	Jay Foad	[GlobalISel] Fix legality checks for G_UBFX combines	blob \| commitdiff \| diff to current
2022-01-07	Jay Foad	[GlobalISel] Fix typo Extact to Extract in function...	blob \| commitdiff \| diff to current
2022-01-03	Craig Topper	[ValueTracking][SelectionDAG] Rename ComputeMinSignedBi...	blob \| commitdiff \| diff to current
2021-12-22	Ron Lieberman	Revert "[AMDGPU] Move call clobbered return address...	blob \| commitdiff \| diff to current
2021-12-22	RamNalamothu	[AMDGPU] Move call clobbered return address registers...	blob \| commitdiff \| diff to current
2021-11-24	Jay Foad	[AMDGPU] Implement widening multiplies with v_mad_i64_i...	blob \| commitdiff \| diff to current
2021-11-13	Kazu Hirata	[Target] Use SDNode::uses (NFC)	blob \| commitdiff \| diff to current
2021-11-12	Jay Foad	[AMDGPU] Simplify 64-bit division/remainder expansion	blob \| commitdiff \| diff to current
2021-11-08	Simon Pilgrim	[DAG] Add SelectionDAG::ComputeMinSignedBits helper	blob \| commitdiff \| diff to current
2021-11-04	Thomas Symalla	[AMDGPU] Changes the AMDGPU_Gfx calling convention...	blob \| commitdiff \| diff to current
2021-10-29	Jay Foad	[AMDGPU] Change numBitsSigned for simplicity and docume...	blob \| commitdiff \| diff to current
2021-10-29	Kazu Hirata	[AMDGPU] Remove hasDefinedInitializer (NFC)	blob \| commitdiff \| diff to current
2021-10-28	Abinav Puthan Purayil	[AMDGPU] Add 24-bit mulhi intrinsics in INTRINSIC_WO_CH...	blob \| commitdiff \| diff to current
2021-10-11	Roman Lebedev	[KnownBits] Introduce `countMaxActiveBits()` and use...	blob \| commitdiff \| diff to current
2021-09-24	Christudasan Devadasan	[AMDGPU] Legalize initialized LDS variables	blob \| commitdiff \| diff to current
2021-09-20	Jacob Lambert	[AMDGPU][NFC] Correct typos in lib/Target/AMDGPU/AMDGPU...	blob \| commitdiff \| diff to current
2021-09-09	Craig Topper	[SelectionDAG] Add isZero/isAllOnes methods to Constant...	blob \| commitdiff \| diff to current
2021-08-06	Michael Liao	[amdgpu] Revise the conversion from i64 to f32.	blob \| commitdiff \| diff to current
2021-08-05	Jay Foad	[AMDGPU][SDag] Better lowering for 32-bit ctlz/cttz	blob \| commitdiff \| diff to current
2021-08-05	Jay Foad	[AMDGPU][SDag] Better lowering for 64-bit ctlz/cttz	blob \| commitdiff \| diff to current
2021-08-05	Jay Foad	[AMDGPU] Make more use of getHiHalf64 and split64BitVal...	blob \| commitdiff \| diff to current
2021-08-04	Michael Liao	[amdgpu] Add an enhanced conversion from i64 to f32.	blob \| commitdiff \| diff to current
2021-07-05	David Stuttard	[AMDGPU] Stop mulhi from doing 24 bit mul for uniform...	blob \| commitdiff \| diff to current
2021-06-28	Brendon Cahoon	[AMDGPU][GlobalISel] Legalize and select G_SBFX and...	blob \| commitdiff \| diff to current
2021-06-24	Carl Ritson	[AMDGPU] Add 224-bit vector types and link 192-bit...	blob \| commitdiff \| diff to current
2021-06-22	Matt Arsenault	AMDGPU: Move zeroed FP high bits optimization to patterns	blob \| commitdiff \| diff to current
2021-06-19	Michael Liao	[amdgpu] Improve the from f32 to i64.	blob \| commitdiff \| diff to current
2021-06-18	Matt Arsenault	AMDGPU: Fix infinite loop in DAG combine with fneg...	blob \| commitdiff \| diff to current
2021-06-03	Julien Pagès	[AMDGPU] Fix a crash when selecting a particular case...	blob \| commitdiff \| diff to current
2021-05-28	Sebastian Neubauer	[AMDGPU] Fix function calls with flat scratch	blob \| commitdiff \| diff to current
2021-05-20	Stanislav Mekhanoshin	[AMDGPU] Fix module LDS selection	blob \| commitdiff \| diff to current
2021-05-05	Julien Pagès	[AMDGPU] Select V_CVT_*16_F16 more often	blob \| commitdiff \| diff to current
2021-02-23	Nicolai Hähnle	[AMDGPU][SelectionDAG] Don't combine uniform multiplies...	blob \| commitdiff \| diff to current
2021-02-18	Stanislav Mekhanoshin	[AMDGPU] gfx90a support	blob \| commitdiff \| diff to current
2021-02-17	Jay Foad	[AMDGPU] Rename simplifyI24 to simplifyMul24	blob \| commitdiff \| diff to current
2021-02-05	Craig Topper	[TargetLowering] Use Align in allowsMisalignedMemoryAcc...	blob \| commitdiff \| diff to current
2021-01-20	dfukalov	[NFC][AMDGPU] Split AMDGPUSubtarget.h to R600 and GCN...	blob \| commitdiff \| diff to current
2021-01-07	dfukalov	[NFC][AMDGPU] Reduce include files dependency.	blob \| commitdiff \| diff to current
2020-12-14	Sebastian Neubauer	[AMDGPU] Mark amdgpu_gfx functions as module entry...	blob \| commitdiff \| diff to current
2020-11-09	Sebastian Neubauer	[AMDGPU] Add amdgpu_gfx calling convention	blob \| commitdiff \| diff to current
2020-11-01	Christudasan Devadasan	[AMDGPU] Some refactoring after D90404. NFC.	blob \| commitdiff \| diff to current
2020-10-22	Piotr Sobczak	[AMDGPU] Fix expansion of i16 MULH	blob \| commitdiff \| diff to current
2020-10-19	Jay Foad	[AMDGPU] Remove MUL_LOHI_U24/MUL_LOHI_I24	blob \| commitdiff \| diff to current
2020-10-16	Jay Foad	[AMDGPU] Add new llvm.amdgcn.fma.legacy intrinsic	blob \| commitdiff \| diff to current
2020-10-15	David Sherwood	[SVE][NFC] Replace some TypeSize comparisons in non...	blob \| commitdiff \| diff to current
2020-09-28	Jay Foad	[AMDGPU] Reformat AMDGPUTargetLowering::isSDNodeAlwaysU...	blob \| commitdiff \| diff to current
2020-09-14	Craig Topper	[SelectionDAG] Use Align/MaybeAlign in calls to getLoad...	blob \| commitdiff \| diff to current
2020-08-13	Ruiling Song	[AMDGPU] Fix crash when dag-combining bitcast	blob \| commitdiff \| diff to current
2020-08-11	Kerry McLaughlin	[CodeGen] Refactor getMemBasePlusOffset & getObjectPtrO...	blob \| commitdiff \| diff to current
2020-08-06	Matt Arsenault	AMDGPU: Remove ATOMIC_PK_FADD	blob \| commitdiff \| diff to current
2020-08-05	Matt Arsenault	AMDGPU: Eliminate BUFFER_ATOMIC_PK_ADD_F16 node	blob \| commitdiff \| diff to current
2020-08-05	Jay Foad	[AMDGPU] Propagate fast math flags in frem lowering	blob \| commitdiff \| diff to current
2020-08-05	Jay Foad	[AMDGPU] Lower frem f16	blob \| commitdiff \| diff to current
2020-08-04	Jay Foad	[AMDGPU] Use fma for lowering frem	blob \| commitdiff \| diff to current
2020-08-03	Cameron McInally	[FPEnv] Don't transform FSUB(-0,X)->FNEG(X) in Selectio...	blob \| commitdiff \| diff to current
2020-07-29	Matt Arsenault	AMDGPU/GlobalISel: Select llvm.amdgcn.global.atomic...	blob \| commitdiff \| diff to current
2020-07-23	Sebastian Neubauer	[AMDGPU] Fix typo. NFC	blob \| commitdiff \| diff to current
2020-07-22	Petar Avramovic	AMDGPU: Simplify f16 to i64 custom lowering	blob \| commitdiff \| diff to current
2020-07-21	Matt Arsenault	AMDGPU: Start interpreting byref on kernel arguments	blob \| commitdiff \| diff to current
2020-07-14	Jay Foad	[AMDGPU] Fix typos in performCtlz_CttzCombine()	blob \| commitdiff \| diff to current
2020-07-08	Jay Foad	[AMDGPU] Fix and simplify AMDGPUTargetLowering::LowerUD...	blob \| commitdiff \| diff to current
2020-06-29	Guillaume Chatelet	[Alignment][NFC] Migrate AMDGPU backend to Align	blob \| commitdiff \| diff to current
2020-06-24	Eli Friedman	Remove GlobalValue::getAlignment().	blob \| commitdiff \| diff to current
2020-06-23	Eli Friedman	[AArch64][SVE] Add legalization support for i32/i64...	blob \| commitdiff \| diff to current
2020-06-17	Matt Arsenault	AMDGPU: Remove intermediate DAG node for trig_preop...	blob \| commitdiff \| diff to current
2020-06-15	Stanislav Mekhanoshin	[AMDGPU] Add gfx1030 target	blob \| commitdiff \| diff to current
2020-06-10	Matt Arsenault	AMDGPU: Stop using getSelectCC in division lowering	blob \| commitdiff \| diff to current
2020-05-29	Jay Foad	[AMDGPU] Better use of llvm::numbers	blob \| commitdiff \| diff to current
2020-05-26	Matt Arsenault	AMDGPU: Update store node checks for atomics	blob \| commitdiff \| diff to current
2020-05-20	QingShan Zhang	[DAGCombine] Remove the getNegatibleCost to avoid the...	blob \| commitdiff \| diff to current
2020-05-18	Stanislav Mekhanoshin	[AMDGPU] Fixed selection error for 64 bit extract_subvector	blob \| commitdiff \| diff to current
2020-05-14	Stanislav Mekhanoshin	[AMDGPU] Make v16f64/v16i64 legal	blob \| commitdiff \| diff to current
2020-05-14	Stanislav Mekhanoshin	Add v16f64 value type	blob \| commitdiff \| diff to current
2020-05-13	Matt Arsenault	AMDGPU: Use Register	blob \| commitdiff \| diff to current
2020-05-12	Stanislav Mekhanoshin	[AMDGPU] Make v4i64/v4f64/v8i64/v8f64 legal	blob \| commitdiff \| diff to current
2020-05-11	Sam McCall	Revert "[DAGCombine] Remove the getNegatibleCost to...	blob \| commitdiff \| diff to current
2020-05-11	QingShan Zhang	[DAGCombine] Remove the getNegatibleCost to avoid the...	blob \| commitdiff \| diff to current
2020-04-17	Matt Arsenault	AMDGPU: Remove custom node for RSQ_LEGACY	blob \| commitdiff \| diff to current
2020-04-09	David Truby	[flang] Merge flang-compiler/f18	blob \| commitdiff \| diff to current
2020-04-02	Matt Arsenault	AMDGPU: Remove denormal subtarget features	blob \| commitdiff \| diff to current
next

Domain: System / Toolchain;

RSS Atom