llvm
llvm copied to clipboard
intel
Intel staging area for llvm.org contribution. Home for Intel LLVM-based projects.
### Describe the bug SYCL kernels are identified by their kernel name, which means kernel names have to be globally unique. This requirement is enforced within translation units, but not...
Is "sycl::complex" mentioned in the SYCL specification ? Which type is recommended for Intel, AMD, and NVIDIA GPUs ? Thanks. ``` no template named 'complex' in namespace 'sycl'; did you...
### Describe the bug Affected tests: ``` TaskSequence/concurrent-loops.cpp TaskSequence/in-order-async-get.cpp TaskSequence/mult-and-add.cpp TaskSequence/multi-kernel-task-function-reuse.cpp TaskSequence/producer-consumer.cpp TaskSequence/struct-array-args-and-return.cpp ``` They all fail during compilation with `Segmentation fault` both on Linux and Windows. Linux: ``` user@host:/llvm/sycl/test-e2e/TaskSequence$...
device global code conflict with 6e45fa95be9db5318ac7037c673c9b18a48ac5b1 Fix failure: Clang::CodeGenSYCL/device_global.cpp
The aspect is supported since [OpenCL CPU 2024.2](https://github.com/intel/llvm/releases/download/2024-WW25/oclcpuexp-2024.18.6.0.02_rel.tar.gz)
Added proper handling of exceptions propagated to the outermost level.
This PR adds support for device image compression for the old offloading model. I'll make another follow-up PR to extend support for the new offload model. **Design summary**: ``` ZSTD...
We've observed some failures due to produced results being not exact 180/`M_PI`, e.g. due to the use of FMA instructions. `half` versions of the test cases already used a delta...
