llvm
llvm copied to clipboard
intel
Intel staging area for llvm.org contribution. Home for Intel LLVM-based projects.
This commit adds support for handling invalid kernels. Sometimes kernel cannot be generated for specific platform, when trying to append launch of such faulty kernel exception is now thrown -...
**Describe the bug** Templated code that sometimes passes a local accessor to the kernel and sometimes passes a `nullptr` fails with a runtime error during kernel setup when running on...
This is a move towards the future looking joint_matrix, joint_matrix_load, joint_matrix_store APIs. The aim is to make the CUDA and Intel implementations of the joint_matrix extension use matching interfaces, whilst...
This PR prevents the `buffer_allocator` from being rebound to a const type. Currently when a `buffer` is reinterpreted from type `T` to type `const T` the `buffer_allocator` type is also...
**Describe the bug** A truncated version of the `sycl.hpp` path works when it should not. It should only be able to find the header with `sycl/sycl.hpp`. Bug found when adding...
**Describe the bug** Code that uses `sycl::ext::oneapi::group_ballot` will fail with a linker error when compiling to `amdgcn-amd-amdhsa`. Error message: `lld: error: undefined hidden symbol: __spirv_GroupNonUniformBallot(unsigned int, bool)` **To Reproduce** 1....
CUDA test suite run in CI seems to hang: https://github.com/intel/llvm/runs/8243569878?check_suite_focus=true ATM it is at 4.5 hours, while locally it is usually under 5 minutes. Not sure how to reliably reproduce...
Hi, I migrated CUDA code to SYCL. And the CUDA code is working fine for NVIDIA Multi GPU environment and SYCL migrated code is resulting in a segmentation fault in...
This looks like a recent regression in the ARM build, at least it appeared when I switched from the Raspberry Pi4 Ubuntu 20.04 to Xavier AGX Ubuntu 18.04. I know...
4.9.1.7 of SYCL 2020 does not have get_global_range function definition
