llvm-project.git - Unnamed repository; edit this file 'description' to name the repository.

Age	Commit message (Expand)	Author
2025-09-29	[mlir][GPU] Generalize gpu.printf to not need gpu.module (#161266)	Krzysztof Drewniak
2025-09-12	[mlir][AMDGPU] Updated `PermlaneSwapOp` to select correct val (#157586)	Gaurav Verma
2025-09-08	[mlir][gpu] Revert gpu.subgroup_broadcast with any_lane (#157373)	Jakub Kuderski
2025-08-30	[mlir][gpu] Add `subgroup_broadcast` op (#152808)	Ivan Butygin
2025-08-24	[mlir][amdgpu] Promote gpu.shuffle to amdgpu.permlane_swap (#154933)	Tim Gymnich
2025-08-13	[mlir][ROCDL] Annotate lane ID functions with noundef, ranges (#151396)	Krzysztof Drewniak
2025-05-20	[mlir] Check for int limits when converting gpu dims (#140747)	Max191
2025-05-19	[AMDGPU] Set AS8 address width to 48 bits	Alexander Richardson
2025-04-25	[MLIR][ROCDL] Lower `gpu.subgroup_size` to `wavefrontsize` (#137360)	Alan Li
2025-04-25	[mlir] added gpu.shuffle mode UP support (#137300)	Gaurav Verma
2025-04-18	[mlir] GPUToROCDL: Add support for non-i32/f32 shuffle types (#136320)	Ivan Butygin
2025-04-13	[mlir] GPUToROCDL: Fix crashes with unsupported shuffle datatypes (#135504)	Ivan Butygin
2025-02-13	[mlir][gpu] GPUToROCDL/NVVM: use generic llvm conversion interface instead of...	Ivan Butygin
2025-02-06	[mlir][LLVM] Switch `undef` for `poison` for uninitialized values (#125629)	Krzysztof Drewniak
2025-01-08	[MLIR][GPU] Fix gpu.printf (#121940)	Guray Ozen
2024-11-20	[MLIR][AMDGPU] Support gpu::ShuffleMode::DOWN lowering in ROCDL (#106237)	Dragan Mladjenovic
2024-09-23	[mlir][AMDGPU] Add support for AMD f16 math library calls (#108809)	Daniel Hernandez-Juarez
2024-09-12	[mlir][AMDGPU] Remove an old bf16 workaround (#108409)	Krzysztof Drewniak
2024-09-12	[MLIR][ROCDL] Add dynamically legal ops to LowerGpuOpsToROCDLOpsPass (#108302)	Nirvedh Meshram
2024-09-12	[mlir][LLVM] Refactor how range() annotations are handled for ROCDL intrinsic...	Krzysztof Drewniak
2024-09-04	[MLIR][ROCDL] Remove patterns for ops supported as intrinsics in the AMDGPU b...	Jan Leyonberg
2024-06-17	[mlir][GPU] Improve handling of GPU bounds (#95166)	Krzysztof Drewniak
2024-05-28	[mlir][ROCDL] Update the LLVM data layout for ROCDL lowering. (#92127)	stefankoncarevic
2024-02-27	[mlir][ROCDL] Set the LLVM data layout when lowering to ROCDL LLVM (#74501)	Krzysztof Drewniak
2023-11-01	[MLIR][GPUToROCDL] Remove typed pointer support (#70908)	Christian Ulmann
2023-09-28	[MLIR][LLVM] Add vararg support in LLVM::CallOp and InvokeOp (#67274)	Ivan R. Ivanov
2023-09-04	[mlir][GPUToROCDL] Lower arith.remf to GPU intrinsic.	Adrian Kuegel
2023-08-24	[mlir][ROCM] Add Wave/Warp shuffle lowering and op for ROCM.	Stanley Winata
2023-08-17	[mlir][AMDGPU] Improve BF16 handling through AMDGPU compilation	Krzysztof Drewniak
2023-07-26	[MLIR][ROCDL] Add conversion for gpu.lane_id to ROCDL	SJW
2023-07-03	[mlir][Conversion/GPUCommon] Fix bug in conversion of `math` ops	Christopher Bate
2023-05-15	[MLIR][ROCDL] add gpu to rocdl erf support	Manupa Karunaratne
2023-02-21	[mlir][GPUToLLVM] Add support for emitting opaque pointers	Markus Böck
2023-01-22	Add missing dependent dialects to "convert-gpu-to-rocdl"	Mehdi Amini
2023-01-16	Check for FunctionOpInterface when looking up a parent function in GPU lowering	Mehdi Amini
2023-01-12	Lower math.tan to __nv_tan[f] / __ocml_tan_f{32\|64}	Goran Flegar
2023-01-09	Lower math.cbrt to NVVM/ROCDL.	Johannes Reifferscheid
2023-01-02	[mlir][ROCDL] Translate known block size attributes to ROCDL	Krzysztof Drewniak
2022-10-28	[mlir][gpu] Unroll ops on vectors which map to intrinsic calls	Christian Sigg
2022-08-08	[mlir][math] Rename math.abs -> math.absf	Jeff Niu
2022-08-02	[mlir][GPU] Allow bare pointer memrefs when calling GPU kernels	Krzysztof Drewniak
2022-08-01	[mlir][flang] Make use of the new `GEPArg` builder of GEP Op to simplify code	Markus Böck
2022-03-16	[mlir] Move the Builtin FuncOp to the Func dialect	River Riddle
2022-03-01	[mlir] Rename the Standard dialect to the Func dialect	River Riddle
2022-01-18	[mlir] Replace StrEnumAttr -> EnumAttr in core dialects	Mogball
2021-12-09	[MLIR][GPU] Define gpu.printf op and its lowerings	Krzysztof Drewniak
2021-10-13	[MLIR] Replace std ops with arith dialect ops	Mogball
2021-08-31	Add a new interface allowing to set a default dialect to be used for printing...	Mehdi Amini
2021-07-15	[mlir][rocdl] Add math::Exp2Op lowering to ROCDL	Adrian Kuegel
2021-02-16	Lower math.expm1 to intrinsics in the GPUToNVVM and GPUToROCDL conversions.	Adrian Kuegel