ericlars comments

Results 8 comments of


                                            ericlars

[LAPACK][CUSOLVER] Add potrf and getrs batch functions to cuSolver

Thanks for the PR @AidanBeltonS Can you provide more details on the non batch failures? Setting the environment variable CTEST_OUTPUT_ON_FAILURE=1 with ctest can provide more details. Unusual errors are sometimes...

[LAPACK][CUSOLVER] Add potrf and getrs batch functions to cuSolver

@AidanBeltonS My logs were from a build of llvm from 3/19, and it looks like the multistream patch was committed on 5/17, but for sanity I'll try building from your...

[LAPACK][CUSOLVER] Add potrf and getrs batch functions to cuSolver

Looks good to me! [log_llvm_cusolver_.txt](https://github.com/oneapi-src/oneMKL/files/9561469/log_llvm_cusolver_.txt)

add queue.wait() to sync interop stream

One solution would be to only sync the stream used by the interop `onemkl_cusolver_host_task` by calling: > > ``` > cudaStream_t currentStreamId; > CUSOLVER_ERROR_FUNC(cusolverDnGetStream, err, handle, &currentStreamId); > cuStreamSynchronize(currentStreamId); >...

add queue.wait() to sync interop stream

attaching log: [log_llvm_cusolver_.txt](https://github.com/oneapi-src/oneMKL/files/9476192/log_llvm_cusolver_.txt)

[CUDA][HIP] Use device to get native context

Thanks! LGTM

[Specification] oneMKL lapack to allow asynchronous functions

Hi @JackAKirk, thanks for the RFC. The oneMKL LAPACK team has had an ongoing discussion on the issue you raise which I'll summarize here. We agree with your assessment of...

[Specification] oneMKL lapack to allow asynchronous functions

Glad to hear the host_task issues have been worked around, if at least for some backends. We support this change; do you plan on driving the spec update over on...