-
Intel mkl based libraries for fftw Blas and scalapack are not tested.
See https://github.com/spack/spack/issues/44904
-
We should enable this for all of Drake if we can confirm with the Eigen developers that it is ABI compatible (will not cause ODR violations).
This was initially PR'd in #16683 with a local change…
-
Using 64-bit BLAS allows removing the fallback for arrays with dimensions larger than the 32-bit supported by regular openblas.
64-bit refers to the index / stride / dimension size used.
bluss updated
4 years ago
-
Hi, after I run python CGVAE.py --dataset qm9, the program failed, the error is
```
InternalError (see above for traceback): Blas xGEMMBatched launch failed : a.shape=[64,10,10], b.shape=[64,10,100…
-
@ChrisRackauckas found out that using CuArrays fails at points like https://github.com/JuliaMath/IterativeSolvers.jl/blob/17ef2613dff1d80724886797160ee01bd1bd2c71/src/simple.jl#L38
where the call t…
-
According to the benchmark results from [this comment](https://github.com/rust-ml/linfa/issues/228#issuecomment-1312491685), `linfa-linear` is faster with BLAS than without. The OLS algorithm isn't to…
-
According to benchmark results from [this comment](https://github.com/rust-ml/linfa/issues/228#issuecomment-1312491685), `linfa-pls` is slightly slower without BLAS. Specifically, the `Regression-Nipa…
-
According to [these results](https://github.com/rust-ml/linfa/issues/228#issuecomment-1304608470), all ICA benchmarks are noticibly faster with BLAS than without, though this is less severe at higher …
-
Have we considered optimize the distance calculation with BLAS & OpenMP vs. SSE/AVX?
The BLAS (e.g.MLK) operations are deeply optimized, and they might be able to outperform our current code with S…
-
Am working on adding two OpenCL BLASes to conda-forge. In particular am adding clBLAS and CLBlast. IIUC libgpuarray can support one or the other. So am opening this issue to discuss how we handle buil…