-
## Overview
- Intel's Lunar Lake is releasing soon, which has CPU, NPU and iGPU in a single chip
## Tasklist
- [x] https://github.com/janhq/cortex.cpp/issues/677
- [x] https://github.com/janhq/cort…
-
Are there any compilation instructions for the CUDA backend of the sycl branch of Grid? It seems that the build system does not automatically use nvcc where necessary. I've tried messing with `OMPI_MP…
-
# Summary
From the CI, the netlib backend does not compile anymore because of `multi_ptr`.
# Version
Tested with the HEAD of develop branch: https://github.com/oneapi-src/oneMKL/commit/99e85be9bb…
-
# Background
We are upstreaming for Intel GPU ([[RFC] Intel GPU Upstreaming · Issue #114723 · pytorch/pytorch (github.com)](https://github.com/pytorch/pytorch/issues/114723)). For the first step, tar…
-
### Describe the bug
It appears that `icpx` is able to detect unused accessors only when they are created with `buffer.get_access(...)`. For example, creating them with `sycl::accessor{buffer, ...}` …
-
## Summary
I have tested running the BinaryBH example on [Dawn](https://www.hpc.cam.ac.uk/d-w-n) which contains Intel Data Center GPU Max 1550s (codename: 'Ponte Vecchio', often abbreviated to 'PVC…
-
A quick look at the code suggests that cross-compiling SYCL apps isn't currently possible. Is there any plan to add support? x86->ARM would be particularly interesting.
-
Per [SYCL 2020 4.12.2 (Defining kernels as lambda functions)](https://registry.khronos.org/SYCL/specs/sycl-2020/html/sycl-2020.html#sec:interfaces.kernels.as.lambdas), a C++ lambda can be used as a SY…
-
### Describe the bug
[Section 4.17.3](https://registry.khronos.org/SYCL/specs/sycl-2020/html/sycl-2020.html#sec:algorithms) of SYCL 2020 says:
> All algorithms are supported for the fundamental sc…
-
The example stated in `sycl/doc/GettingStartedAlveo.md`:
- sw_emu:
It compiles and runs (indefinitely?) while displaying
```
EXE: /home/rkeryell/sycl_workspace/llvm/sycl/test/xocc_tests/disa…