New Functions Introduced For LAPACK Version 3.4.0

Most of the users may have known we had introduced C interface for LAPACK in Intel MKL 10.3, which is convenient for developers who used to use c/c++ language feature, like row-major matrix and zero-based index.   Please see the details in /en-us/articles/c-interface-for-lapack  
In the Intel MKL 11.0, we introduced new routines in LAPACK 3.4.x plus a list of additional  auxiliary functions.

1)     The list of new function we added from LAPACK 3.4.x

(for all four data types 's','d','c','z'):
?gemqrt     ?geqrt     ?geqrt2     ?geqrt3    ?la_gerpvgrw*     ?tpmqrt     ?tpqrt      ?tpqrt2     ?tprfb     

And their corresponding C interface.

For example,

Computes a blocked QR factorization of a general real or complex matrix using the compact WY representation of Q.

C inferface:

lapack_int LAPACKE_<?>geqrt( int matrix_order, lapack_int m, lapack_int n, lapack_int nb, <datatype>* a, lapack_int lda, <datatype>* t, lapack_int ldt );

Please notes, for all these functions and functions from previous Netlib releases 3.3.0 and 3.3.1 are already in MKL library. We would like to synchronize LAPACK and LAPACKE so that user can enjoy the C Interface to those latest LAPACK routines.

*Please notes, funtions ?la_gerpvgrw wasn't covered by C interfaces. 
2)   Auxiliary routines we added c interface to

(for all four data types 's','d','c','z'):
?laswp, ?lacpy, ?gelq2, ?geqr2, ?geft2, ?larfb, ?larfg, ?larft, ?lange, ?lansy, ?lantr, ?larnv, ?lagge, ?lagsy, ?lauum, ?trtri, ?laset

(for complex type):
(c/z)lacgv, ?lanhe, ?laghe

(for real type):
?lamch, ?lapy2, ?lapy3

and function 

For example,


Performs a series of row interchanges on a general rectangular matrix.

C interface:

lapack_int LAPACKE_?laswp (int matrix_order, lapack_int n, <datatype> * a, lapack_int lda, lapack_int k1, lapack_int k2, const lapack_int * ipiv, lapack_int incx);

Per informazioni più dettagliate sulle ottimizzazioni basate su compilatore, vedere il nostro Avviso sull'ottimizzazione.