Intel MKL 11.1 Bug Fixes

Intel® MKL 11.1  Update 2 (02 Feb 2014)

DPD200398565 Fixed Memory leak issue
DPD200390408 ANSYS DMP support for multiple Intel® Many Integrated Core Architecture (Intel® MIC Architecture) cards
DPD200396128 Performance - mkl_dcsrmm shows the scalablity degradation in 11.1 vs 11.0
DPD200248606 FEAST random crashes on intel64
DPD200241919 Provide optimized *GEMM (then other BLAS) for Intel® Atom™ processor
DPD200241920 Provide optimized mkl_dsppfrt2/x (then other LAPACK) for Intel® Atom™ processor
DPD200247333 Improve DGEMM native performance on KNC for non-square matrices
DPD200249529 Improve small matrix GEMM performance for graphics and digital content creation customers
DPD200394473 LAPACKE_dgesdd returns -11
DPD200249555 MKL Link Line Advisor gives wrong linker flags for OS X
DPD200397430 Pardiso OOC - fseek call during the backtransformation
DPD200401058 FFT reports the Error in OOC computation with pardiso
DPD200349785 Performance: spotrf produces the very different performance result with "U" and "L" cases
DPD200388403 Replaced Matrix Order into other wording
DPD200247589 Improve DGEMM performance for matrices with huge K size and tiny M and N size
DPD200388027 there are no declarations of ?lagge, ?laghe and ?lagsy in any of header files
DPD200247749 MKL_DSS_DIAGONAL_SOLVE opt_solve produces garbage results
DPD200395081 OOC ( hybrid mode ) Pardiso should work with twol-level factorization algorithm in the case of small matrix
DPD200509794 Fixed the problem of 1D DataFitting giving the wrong output
DPD200248198 Fixed the Bug in MKL Examples
DPD200249444 Improve GEMM performance for matrices with M=K=6 and large N
DPD200238399 Unusual DGEMM performance
DPD200248270 NAG Confirms DSYGVD on MIC returns incorrect results when using selected numbers of threads

Intel® MKL 11.1  Update 1 (24 Oct 2013)

DPD200385039 DSS API - memory leakage on the factorization stage
DPD200247042 DGEMM seg fault with PGI threading
DPD200344190 pardiso problem with partial solution for right-hand
DPD200245542 Need threaded DSDOT
DPD200351579 Incorrect workspace size returned by query to DGESVD in MKL 11.0.5
DPD200243635 Add service functions to query data fitting task structure
DPD200349748 vsSub fails in compiler offload mode while trying to load CPU specific library (which MKL does not have for MIC native)
DPD200342324 Statically linking to MKL creates executable stack security exposure
DPD200335069 DF -- support of DF_APRIORI_MOST_LIKELY_CELL Computation Types
DPD200344380 sgeqrf returning NaNs
DPD200243791 out of place transpose slower than F intrinsic routine on tall skinny matrices
DPD200383963 Defect: Sparse Matrix Structure leads Zero Pivot Error
DPD200346307 DS: Heap Corruption happensin ?syrdb rouitine when the input size == 1
DPD200246843 DSS solver gives incorrect results (each time different results)
DPD200333995 optimal lwork too large in dormqr
DPD200317576 pblas documentation needs to be amended to explain complex support
DPD200248173 DFEAST_SCSREV crashes with OpenMP error

Intel® MKL 11.1  (3 Sept 2013)

   
DPD200342923 Including MKL MIC library as the default installation in MKL 11.1
DPD200325646 DS: zgelsd generates the error messages:"MKL INTERNAL ERROR: Condition 1 detected in function DLASD4
DPD200237716 Performance regression on HPCC Star DGEMM and Star FFT on KNC
DPD200345891 DS: dgeevx, dggev may return significantly different eigenvalues when eigenvectors are requested
DPD200349748 vsSub fails in compiler offload mode while trying to load CPU specific library (which MKL does not have for MIC native)
DPD200245451 MKL 11.0 Update 4 SIGSEGV regression vs update 2
DPD200242406 unaligned daxpy is slow than plain C on an Intel® Advanced Vector Extensions 2 (Intel® AVX2) box
DPD200313133 DS: performance of mkl's transposition should be improved
DPD200238057 compilervars_arch.sh set some un-existing paths
DPD200243422 FFTW/FORTRAN: ability to set number of threads that execute a plan
DPD200344940 ANSYS request for a query function
DPD200344945 ANSYS Request for a "force this to offload" feature in MKL AO for MIC
DPD200245405 Install Fortran 95 interfaces by default
DPD200338444 Internal buffers grow unlimited while compiling 32 bit with sequential version
DPD200339085 MKL memory leak of 120 bytes
如需更全面地了解编译器优化,请参阅优化注意事项