llvm-project

History

[mlir][Linalg]: Optimize linalg generic in transform::PromoteOp to avoid unnecessary copies (#68555 )

If the operands are not used in the payload of linalg generic operations, there is no need to copy them before the operation.

2023-10-14 10:40:45 +03:00

all-reduce-max.mlir

[mlir][gpu] Migrate hard-coded address space integers to an enum attribute (gpu::AddressSpaceAttr)

2023-01-13 11:00:10 -07:00

all-reduce.mlir

[mlir][gpu] Migrate hard-coded address space integers to an enum attribute (gpu::AddressSpaceAttr)

2023-01-13 11:00:10 -07:00

async-region.mlir

[mlir][GPU] Prevent adding duplicate async tokens

2022-10-18 15:37:20 +00:00

barrier-elimination.mlir

[mlir] add a simple gpu barrier elimination mechanism

2023-07-07 18:51:49 +00:00

bufferization-buffer-deallocation.mlir

[mlir][gpu][bufferization] Implement BufferDeallocationOpInterface for gpu.terminator (#66880 )

2023-09-20 12:28:28 +02:00

canonicalize.mlir

[mlir][gpu] Reduction ops canonicalizatios

2023-05-10 00:33:42 +02:00

decompose-memrefs.mlir

[mlir][gpu] Add DecomposeMemrefsPass

2023-08-10 22:28:05 +02:00

globalId-rewrite.mlir

[mlir][gpu] Add a pattern for transforming gpu.global_id to thread + blockId * blockDim

2023-05-25 20:24:38 +00:00

int-range-interface.mlir

Re-land D139865 "Add known_block_size and known_grid_size to gpu.func"

2023-01-02 16:39:00 +00:00

invalid.mlir

[mlir][gpu] Modifies gpu.launch_func to allow lowering it after gpu-to-llvm.

2023-08-11 21:56:37 +00:00

mapping.mlir

[mlir][gpu] Change ParalellLoopMappingAttr to AttrDef

2022-06-09 22:23:21 +00:00

module-to-binary-nvvm.mlir

[mlir][gpu][NVPTX] Enable NVIDIA GPU JIT compilation path (#66220 )

2023-09-14 18:00:27 -04:00

module-to-binary-rocdl.mlir

[mlir][gpu][NVPTX] Enable NVIDIA GPU JIT compilation path (#66220 )

2023-09-14 18:00:27 -04:00

multiple-all-reduce.mlir

[mlir][gpu] Add uniform flag to gpu reduction ops

2022-12-14 13:15:58 +01:00

ops.mlir

[mlir][llvm] Replace NullOp by ZeroOp (#67183 )

2023-09-25 11:11:52 +02:00

outlining.mlir

[mlir][GPUDialect] Implement memory attributions for LaunchOp

2023-04-26 17:53:18 -05:00

promotion.mlir

[mlir][Linalg]: Optimize linalg generic in transform::PromoteOp to avoid unnecessary copies (#68555 )

2023-10-14 10:40:45 +03:00

shuffle-rewrite.mlir

[mlir][gpu] Add i64 & f64 support to gpu.shuffle

2023-05-25 21:40:25 +00:00

sink-ops.mlir

[mlir][NFC] Update textual references of func to func.func in Bufferization/Complex/EmitC/CF/Func/GPU tests

2022-04-20 22:17:28 -07:00

sparse-roundtrip.mlir

[mlir][sparse][gpu] add CSC and BSR format to cuSparse GPU ops (#67509 )

2023-09-27 09:32:25 -07:00

subgroup-mma-vector-unroll.mlir

[mlir][GPU] Add op for unrolling contractions to a native size

2023-07-25 13:11:32 -04:00

transform-gpu-failing.mlir

[mlir] cleanup of structured.tile* transform ops (#67320 )

2023-09-26 09:14:29 +02:00

transform-gpu.mlir

[mlir][transforms] Revamp the implementation of mapping loops to GPUs

2023-07-26 00:09:08 +02:00