https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Intel-MKL-10-3-update-5-is-now-available/m-p/775517#M978 <P>Intel Math Kernel Library (Intel MKL) is a highly optimized, extensively threaded, and thread-safe library of mathematical functions for engineering, scientific, and financial applications that require maximum performance. The Intel MKL 10.3 Update 5 packages are now ready for download. Intel MKL is available as a <A href="http://software.intel.com/en-us/intel-mkl/">stand-alone product</A> and as a part of the <A href="http://software.intel.com/en-us/articles/intel-parallel-studio-xe/">Intel Parallel Studio XE 2011</A>, <A href="http://software.intel.com/en-us/articles/intel-parallel-studio-xe/">Intel C++ Studio XE 2011</A>, <A href="http://software.intel.com/en-us/articles/intel-composer-xe/">Intel Composer XE 2011</A>, <A href="http://software.intel.com/en-us/articles/intel-composer-xe/">Intel Fortran Composer XE 2011</A>, <A href="http://software.intel.com/en-us/articles/intel-composer-xe/">Intel C++ Composer XE 2011</A>, and <A href="http://software.intel.com/en-us/articles/intel-cluster-studio/">Intel Cluster Studio 2011</A>. Please visit the <A href="http://software.intel.com/en-us/articles/intel-software-evaluation-center/">Intel Software Evaluation Center</A> to evaluate this product. </P><P><STRONG><BR />What's New in Intel MKL 10.3 update 5</STRONG></P><P></P><UL><LI>BLAS: Improved performance: {S,C,Z}TRSM for processors with Intel Advanced Vector Extensions (Intel AVX); {S,D}GEM2VU for processors with Intel AVX as well as the Intel Core i7 processor and the Intel Xeon processor 5500 series </LI><LI>BLAS: Improved scaling: ?TRMV for large matrices on all architectures; DGEMM for odd numbers of threads on Intel Xeon processor 5400 series </LI><LI>LAPACK: Included LAPACK 3.3.1 extensions and the respective LAPACKE interfaces </LI><LI>LAPACK: Improved the performance of ?SYGST and ?HEGST used in generalized eigenvalue problems </LI><LI>LAPACK: Improved the performance of the inverse of an LU factored matrix (?GETRI) </LI><LI>PARDISO: Added transpose and conjugate transpose solve capability (A<SUP>T</SUP>x=b and A<SUP>H</SUP>x=b); facilitates compressed sparse column (CSC) format support </LI><LI>PARDISO: Improve out-of-core PARDISO performance when the memory requirements slightly exceed available memory using MKL_PARDISO_OOC_MAX_SWAP_SIZE environment variable and in-core PARDISO </LI><LI>Optimization Solvers: Added Inf and NaN checks in the RCI Trust-Region solvers </LI><LI>FFTs: Improved the performance of 3D FFTs on small cubes from 2x2x2 to 10x10x10 for all supported precisions and types on all Intel processors supporting Intel SSE3 and later </LI><LI>FFT examples: Re-designed example programs to cover common use cases for Intel MKL DFTI and FFTW </LI><LI>VSL: Improved the performance of the single precision MT19937 and MT2203 basic random number generators on the Intel Core i7-2600 processor on 64-bit operating systems </LI><LI>VSL: Improved the performance of the integer version of the SOBOL quasi-random number generator on the Intel Core i7-2600 processor and Intel Xeon processor 5400 series </LI></UL><P></P><UL>Read the <A href="http://software.intel.com/en-us/articles/intel-mkl-103-release-notes/">release notes</A> online for more information. </UL><P></P><P></P> Fri, 05 Aug 2011 23:56:14 GMT Todd_R_Intel 2011-08-05T23:56:14Z https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Intel-MKL-10-3-update-5-is-now-available/m-p/775517#M978 <P>Intel Math Kernel Library (Intel MKL) is a highly optimized, extensively threaded, and thread-safe library of mathematical functions for engineering, scientific, and financial applications that require maximum performance. The Intel MKL 10.3 Update 5 packages are now ready for download. Intel MKL is available as a <A href="http://software.intel.com/en-us/intel-mkl/">stand-alone product</A> and as a part of the <A href="http://software.intel.com/en-us/articles/intel-parallel-studio-xe/">Intel Parallel Studio XE 2011</A>, <A href="http://software.intel.com/en-us/articles/intel-parallel-studio-xe/">Intel C++ Studio XE 2011</A>, <A href="http://software.intel.com/en-us/articles/intel-composer-xe/">Intel Composer XE 2011</A>, <A href="http://software.intel.com/en-us/articles/intel-composer-xe/">Intel Fortran Composer XE 2011</A>, <A href="http://software.intel.com/en-us/articles/intel-composer-xe/">Intel C++ Composer XE 2011</A>, and <A href="http://software.intel.com/en-us/articles/intel-cluster-studio/">Intel Cluster Studio 2011</A>. Please visit the <A href="http://software.intel.com/en-us/articles/intel-software-evaluation-center/">Intel Software Evaluation Center</A> to evaluate this product. </P><P><STRONG><BR />What's New in Intel MKL 10.3 update 5</STRONG></P><P></P><UL><LI>BLAS: Improved performance: {S,C,Z}TRSM for processors with Intel Advanced Vector Extensions (Intel AVX); {S,D}GEM2VU for processors with Intel AVX as well as the Intel Core i7 processor and the Intel Xeon processor 5500 series </LI><LI>BLAS: Improved scaling: ?TRMV for large matrices on all architectures; DGEMM for odd numbers of threads on Intel Xeon processor 5400 series </LI><LI>LAPACK: Included LAPACK 3.3.1 extensions and the respective LAPACKE interfaces </LI><LI>LAPACK: Improved the performance of ?SYGST and ?HEGST used in generalized eigenvalue problems </LI><LI>LAPACK: Improved the performance of the inverse of an LU factored matrix (?GETRI) </LI><LI>PARDISO: Added transpose and conjugate transpose solve capability (A<SUP>T</SUP>x=b and A<SUP>H</SUP>x=b); facilitates compressed sparse column (CSC) format support </LI><LI>PARDISO: Improve out-of-core PARDISO performance when the memory requirements slightly exceed available memory using MKL_PARDISO_OOC_MAX_SWAP_SIZE environment variable and in-core PARDISO </LI><LI>Optimization Solvers: Added Inf and NaN checks in the RCI Trust-Region solvers </LI><LI>FFTs: Improved the performance of 3D FFTs on small cubes from 2x2x2 to 10x10x10 for all supported precisions and types on all Intel processors supporting Intel SSE3 and later </LI><LI>FFT examples: Re-designed example programs to cover common use cases for Intel MKL DFTI and FFTW </LI><LI>VSL: Improved the performance of the single precision MT19937 and MT2203 basic random number generators on the Intel Core i7-2600 processor on 64-bit operating systems </LI><LI>VSL: Improved the performance of the integer version of the SOBOL quasi-random number generator on the Intel Core i7-2600 processor and Intel Xeon processor 5400 series </LI></UL><P></P><UL>Read the <A href="http://software.intel.com/en-us/articles/intel-mkl-103-release-notes/">release notes</A> online for more information. </UL><P></P><P></P> Fri, 05 Aug 2011 23:56:14 GMT https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Library/Intel-MKL-10-3-update-5-is-now-available/m-p/775517#M978 Todd_R_Intel 2011-08-05T23:56:14Z