intel/mlir-extensions
Intel® Extension for MLIR. A staging ground for MLIR dialects and tools for Intel devices using the MLIR toolchain.
MLIRNOASSERTION
Issues
- 1
RFC - introducing tile attribute to support cooperative prefetch and load at SG level XeTile dialect IR
#678 opened by Jianhui-Li - 3
TEST 'IMEX :: Integration/Dialect/XeGPU/gemm_4kx4kx4k_f16_f16_f16_w_8x32xf16_stores.mlir' FAILED
#682 opened by chsasank - 4
Build failure on main branch.
#663 opened by Menooker - 0
Unsupported operations in ConvertGPUtoSPIRV
#665 opened by fschlimb - 0
- 0
Level-Zero system installs don't work
#652 opened by fschlimb - 9
- 2
- 0
Checking Test Suite Gives error: failed to legalize operation 'xegpu.load_2d'
#661 opened by Scarlet1ssimo - 3
Add dynamic shape handling for GPU to SPIRV lowering.
#653 opened by silee2 - 3
- 0
- 0
Support atomic operations for low precision
#654 opened by tye1 - 6
The SPIRV constant translation has issue in translating the signless value
#638 opened by chengjunlu - 1
- 6
- 2
It seems the SPIRV serialization has issue in translating the block parameter (SSA in MLIR) into the Phi node (SSA in SPIRV IR)
#646 opened by chengjunlu - 4
Triton reduce kernel get incorrect results on PVC while it is correct on Gen9. Need IGC help to narrow down the root cause.
#647 opened by chengjunlu - 1
Failure in GPU pass pipeline
#651 opened by fschlimb - 1
To support printf in SPIRV dialect which could be landing to the OCL printf.
#643 opened by chengjunlu - 2
- 1
To support assert
#644 opened by chengjunlu - 2
- 5
Add external call capability in SPIRV dialect
#636 opened by chengjunlu - 1
- 4
- 2
- 0
- 1
IR print seems corrupted.
#589 opened by chencha3 - 2
Rename main to numba-dev and refactor to main
#551 opened by silee2 - 1
cmake config needs fixing
#289 opened by fschlimb - 3
- 0
- 0
- 0
Sycl vs level zero runtime pros & cons
#508 opened by nbpatel - 0
Convert linalg.generic to linalg.matmul
#489 opened by mshahneo - 0
runtime error: symbols not found [memrefcopy]
#486 opened by Dewei-Wang-sh - 2
- 1
Complex Type is not supported on GPU
#468 opened by nbpatel - 1
Lowering of arith.cmpi "ult" op is not supported by upstream ArithToSpirv pass.
#469 opened by nbpatel - 0
GPU Kernel Fusion
#481 opened by chencha3 - 0
- 0
ExplicitPadding Test case fails on GPU pipeline
#456 opened by nbpatel - 0
Jax test case failure on GPU pipeline
#464 opened by nbpatel - 0
Enable Mobilenet and Resnet Models on CPU and GPU
#470 opened by nbpatel - 0
[ptensor] Better IR for elementwise ops
#380 opened by fschlimb - 0
[ptensor] Add elementwise unary ops
#317 opened by fschlimb - 0
[ptensor] add missing elementwise binary operations
#316 opened by fschlimb - 1
New execution engine for Python E2E pipleine
#313 opened by Hardcode84 - 1
Debugging support in Python E2E pipeline
#312 opened by Hardcode84