Intel® MKL 2017 Beta ( 17 Feb 2016)
| DPD200577117 | SP2DP custom library sources created and published in online article |
| DPD200575663 | Fixed the problem of SVD computation of very wide matrix performing significantly slower than SVD computation of its transposition |
| DPD200574694 | Introduced support for major-column format in df?Interpolate1D routines |
| DPD200576806 | Fixed the Pardiso hang problem when called from an OMP critical section |
| DPD200580172 | Problem of Pardiso hanging up on the reordering stage for real and symmetric indefinite matrix |
| DPD200576441 | Fixed the issue - MKL Cluster FFTW and original FFTW produce the different results in the case of out-of-place computation |
| DPD200574978 | Resolved the segmentation fault resulting from a call to pthread_exit(0) |
| DPD200571078 | Introduced mkl_progress support for the parallel direct sparse solver for clusters |
| DPD200372223 | Improved performance of spline interpolation on multiple threads |
| DPD200374978 | Improved performance of GEMM family routines for skinny matrix A(n,k) for n/k > 100 for Intel(R) Xeon Phi™( aka KNL ) |