oneMKL
oneMKL copied to clipboard
oneAPI Math Kernel Library (oneMKL) Interfaces
# Description This PR is intended to extend the HIP backend of RNG domain, which is currently supported for hipSYCL compiler to Intel’s LLVM compiler. - Added the build config...
Signed-off-by: JackAKirk # Description This is a bug fix for failures first identified since the multi-streams implementation of the cuda backend in intel/llvm (failures identified here https://github.com/oneapi-src/oneMKL/pull/209#issuecomment-1192001880): The failed tests...
# Description From https://github.com/intel/llvm/pull/6407, it moves almost all headers from CL/sycl to sycl I followed https://github.com/oneapi-src/oneMKL/pull/199 way make the header can use sycl/* if they exist and allow the old...
RE: #215
# Summary [Intel llvm](https://github.com/intel/llvm/commit/dd418459868a976cd2eeae367fea6b92795ea611 ) introduced multiple CUDA streams per SYCL queue which broke the cuSOLVER scope handler that assumed one stream per device per thread. This broke asynchronous submissions,...
# Description This PR extends `potrf_batch` to additional overloads. Additionally it implements all `getrs_batch` overloads. This change fully implements both `potrf_batch` and `getrs_batch` for USM and Buffer for both group...
# Summary When trying a new library we encountered an unexpected behaviour, as it seems that for BLAS (at least), most tests are actually comparing the reference libblas to itself...
# Summary I tried to build the oneMKL tests. But some rot/rotg tests failed because they don't find (and therefore don't load) `libblas.so`, and therefore the functions are not executed...
# Description This PR will add a github CI to test compilation and the CPU target for the BLAS domain with hipSYCL # Checklist ## New features - [ ]...
# Description Replaces calls to internal oneMKL functions with calls to the usual external interface. This should make the mklcpu and mklgpu backends more robust and predictable. Fixes #114 112...