Intel® MKL 10.2 Fixes List

The tables below summarize specific customer issues or feature requests that have been addressed by the indicated product releases.  Some items span multiple architectures and/or operating systems and some relate only to a single architecture or operating system.

NOTE: The issues, defects, bug reports, and feature requests described below represent specific issues with specific test cases.  An item listed here does not imply that it necessarily applies to your application(s).  If your situation does not match the specific test case you may not have experienced the error or problem associated with that update.  It is not possible to describe the details of every issue and its specific test case in these tables.

Providing a complete description of each item in the list below is impractical. For that reason we ask that you post a message on the Intel MKL user forum, /en-us/forums/intel-math-kernel-library/, and reference this page and the "DPD" number associated with the item of interest, if you have questions regarding the information in these tables.

These tables are updated regularly to correct any errors and omissions.

Intel MKL 10.2 update 7 (14 Dec 2010)

DPD200150365Change default threading for Poisson library to match Intel MKL default (threaded)
DPD200192258MKL DSS API should support single precision inputs with F90 interface
DPD200193353DSS out-of-core (OOC) fails for small matrices with message "MKL-DSS-DSS-Error, An unclassifiable error occurred, dss_factor_real failed, return code = -3".
DPD200193362PARDISO OOC fails when solving large problems on the 64-bit Windows 7 operating system.

 

Intel MKL 10.2 update 6 (30 Aug 2010)

DPD200092519mkl_dcscsv produces wrong results for implicit unit diagonal elements in a upper triangular matrix
DPD200186239Problem with multi-threading in mkl_dcsrsymv()
DPD200094225ScaLAPACK - undefined reference to `slasrt2'
DPD200092145PARDISO - Metis doesn't support 64bit integer
DPD200095301CGESDD returns non-unitary U matrix
DPD200096322fftw2x_cdft wrapper problems for multidimensional transforms and use of fftwnd_f77_mpi_create_plan()
DPD200094153Non-optimal descriptor commit performance FFTW2x wrapper use in loops
DPD200087228PARDISO crashes while mtypes == 11 or -2 are solving when macfct > 1
DPD200156141ZGELSD throws an unhandled exception for 100x100 matrix
DPD200157417Intel MKL crash on 256 or greater core count systems for Windows and Linux

 

Intel MKL 10.2 update 5 (23 Apr 2010)

DPD200148543Degradation in MKL/DGEMM performance on large-scale NUMA system based on Xeon/Nehalem
DPD200090099Illegal instruction. 0x0000000000405406 in mkl_vml_core_e9_vml_dSub ()
DPD200085701MKL leaks memory even when freeing buffers with mkl_free_buffers() after each MKL operation
DPD200141955Multiple calls to CGGES return multiple results when multi-threading is enabled
DPD200087662 Incorrect prototype for dcgmrhs_init(..)
DPD200149262OOC DSS crash in factorization phase
DPD200090882Error code is misleading when running PARDISO out-of-core
DPD200090101Illegal instruction Intel® Core™2 Duo CPU E8400 for VML function
DPD200091604Threading functions crash on systems reporting greater than 32 cores
DPD200085780Pardiso’s C prototype should be changed
DPD200083074mpz_mul function produces wrong output for very large multiplicands
DPD200089153PARDISO OOC solver doesn't return a correct error flag
DPD200150187Error in algorithm for working with thread number in PARDISO
DPD200090490PARDISO - incorrect behaviour in deciding whether to use in-core or OOC mode

 

Intel MKL 10.2 update 4 (19 Feb 2010)

DPD200087809Memory leak in OOC PARDISO
DPD200087031Memory leak in PDSYGVX
DPD200084671zgeev code crash with MKL_DISABLE_FAST_MM on
DPD200087322LAPACK dsygv fuction produces different results when run on one or two threads
DPD200130491Compute convolution directly (VSL_CONV_MODE_DIRECT) - performance issue
DPD200087174Duplicated symbols ( ippGenNumCoresOndie) caused the crash
DPD200141956DGEQRF returns incorrect workspace size upon query
DPD200136191Threaded BLAS library runs slower than sequential one
DPD200086305mkl_dcsrmm produces different output when threading / sequential linking
DPD200134986FFT 2D complex performance not what expected
DPD200149061Wrong answers from FFTs for non-square matrices when using FFTW3 interface
DPD200134402DGELSD never stops
DPD200087222pardiso_unsym_complex_c.c throws an exception when iparm(4) is not a multiple of 10.
DPD200086951Incorrect error code for VML function vdCosh

 

Intel MKL 10.2 update 3 (14 Dec 2009)

DPD200082622Segfault in vsRngUniform with sobol QRNG
DPD200083045the file mkl_gmp.h -- While compiling C++ code with this header file included, compile time error occured
DPD2000834711d FFT crashes with the error_message = MKL DFTI ERROR: Not enough memory to allocate
DPD200084053MKL installation permission errors
DPD200084696mkl_deallocate doesn't work if an double precision array of length more than 10,000,000 is allocated
DPD200084747DFT not freeing internal memory in MKL 10.2.1
DPD200084777mp_linpack seg fault with 16G memory per processors
DPD200084797MKLROOT is an environment variable in the bourne shell configuration, but it is a shell variable in the csh configuration
DPD200085170MKL java example for Intel 64 architecture is missing
DPD200085385parallel double precision, complex, out-of-place FFT of size 1024 fails on 8-byte aligned data (Win/IA-32)
DPD200085935vzArg returns wrong values
DPD200086205segmentation fault when calling dsyevr
DPD200086305mkl_dcsrmm produces different output when threading / sequential linking
DPD200086454Unresolved reference in SGI MPT BLACS for Linux/Intel 64
DPD200086513Solution of Nonlinear Least Squares Problem with boundary constraints goes out of bounds
DPD200086955cblas_zhemv and cblas_zgerc error when x step is not 1
DPD200087348segfaults with DSTEMR
DPD200134619mkl_dcscmm computes all of C = alpha*A*B + beta* C even when beta=0
DPD200139153makefile for mkl_lapack95.lib fails due to space in install_dir name
DPD200139584Incorrect Poisson generator for 1D sequence
DPD200139924LAPACK does not have any exceptional shift strategy for QZ
DPD200140261MKL Dependency on Intel compiler library
DPD200141616Eigenvector bug in multi-threaded code of ?STEQR
DPD200141956DGEQRF returns incorrect workspace size upon query
DPD200084290Low performance on 3D FFT with DFTI_NUMBER_OF_TRANSFORMS > 1
DPD200086472Small-size DGEMM performance issue on for 8 threads
DPD200130881Need optimzation for 32-bit version of LAPACK for medium size systems
DPD200138401Distributed FFT doesn't pass verification on large vector sizes

 

Intel MKL 10.2 update 2 (16 Sep 2009)

DPD200082886DFTI_ERROR_MESSAGE_EXTERNAL interface declaration issue
DPD200083603Pardiso error performing several numerical factorizations in ooc mode
DPD200083759Segmentation fault in dsyevr
DPD200083938PARDISO: 32-bit in-core and out-of-core fail during numerical factorization when allocating > 2GB memory block
DPD200083947DSPEV gives erroneous results
DPD200084033function dgeqp3() will hang when the input matrix has NaN
DPD200121194(z/c/s)gemm on IPF made incorrect stack modifications causing Global Register allocation errors
DPD200134123Thread safety issue with DGELSD
DPD200134371Fortran interface for mkl_?imatcopy does not work
DPD200134733dss_reorder hangs program
DPD200135190Cross process synchronisation causes slowdown in FFTs
DPD200135196Zheevd produces different output 'info' on different systems.
DPD200135401cgs iteration always crashes in pardiso
DPD200135409MKL_DCSRCOO routine produces the wrong output
DPD200135919DFTI returns incorrect results when descriptor is shared by more than one thread
DPD200136968ZGEMM crash on Itanuim processors
DPD200140030Intel MKL for Mac OS X is broken on latest OS tools
DPD200082802Unexpected scalability results with mkl_csplblas_dcsrsymv
DPD200083870CPU dispatch problem for P4/Xeon result in bad GFLOPS
DPD200132532PARDISO OOC performance for very large problems
DPD200137664bad performance on DPOTRF with input size 101

 

 

For more complete information about compiler optimizations, see our Optimization Notice.

2 comments

Top
dbacchus's picture

Thanks for the bug list update.

dbacchus's picture

Hmm... Where is the fix list for 10.2 update 3?

Add a Comment

Have a technical question? Visit our forums. Have site or software product issues? Contact support.