Intel MKL 10.0 Update 4 is now available. Update 4 includes the following improvements:
- Performance Improvements in the BLAS:
- 32-bit improvements
- 40-50% improvement for (Z,C)GEMM on Quad-Core Intel Xeon processor 5300 series
- 10% improvement for all GEMM code on Quad-Core Intel Xeon processor 5400 series
- 64-bit improvements
- 2.5-3% improvement for DGEMM on 1 thread on Quad-Core Intel Xeon processor 5400 series
- 50% improvement for SGEMM on the forthcoming Intel microarchitecture, code named Nehalem
- 3% improvement for CGEMM on 1 thread on the forthcoming Intel microarchitecture, code named Nehalem
- 2-3% improvement for ZGEMM on 1 thread on the forthcoming Intel microarchitecture, code named Nehalem
- 30% improvement for right-side cases of DTRSM on the forthcoming Intel microarchitecture, code named Nehalem
Improvements to the direct sparse solver (DSS/PARDISO):
- The performance of out-of-core PARDISO was improved by 35% on average.
- Performance improvement on the Intel microarchitecture, code named Nehalem:
- 3-17% improvement for the following VML functions: Asin, Asinh, Acos, Acosh, Atan, Atan2, Atanh, Cbrt, CIS, Cos, Cosh, Conj, Div, ErfInv, Exp, Hypot, Inv, InvCbrt, InvSqrt, Ln, Log10, MulByConj, Sin, SinCos, Sinh, Sqrt, Tanh.
- 7-67% improvement for uniform random number generation.
- 3-10% improvement for VSL distribution generators based on Wichmann-Hill, Sobol, and Niederreiter BRNGs (64-bit only).
- On Linux*: When functions in Intel MKL are called from an MPI program they will be run on 1 thread by default (i.e., in the absence of explicit controls).
- On Windows*: It is now possible to create DLLs from the static libraries.
See the release notes for further information
To download, please login at the Intel Registration Center. Intel MKL 10.0 Update 4 is available for Linux*, Windows*, and Mac OS* X.