Paul Stodghill Vladimir Kotlyar, Keshav Pingali. Compiling parallel code for sparse matrix applications. Technical report, Cornell University, 1997.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....linear algebra libraries, such as BlockSolve [8] ScaLAPACK [2] and PLAPACK [14] offer high perforance, but do not necessarily provide flexibility. This is especially problematic for sparse matrix codes, were the optimal matrix format is very problem dependent. The Bernoulli Compiler from Cornell [15] attempts to address this problem with a special purpose compiler that takes dense code and sparse matrix descriptions as input, and creates parallel code. With the Parallel Matrix Template Library we hope to demonstrate that the expressiveness of the C language makes the creation of such ....

Paul Stodghill Vladimir Kotlyar, Keshav Pingali. Compiling parallel code for sparse matrix applications. Technical report, Cornell University, 1997.

No context found.

Paul Stodghill Vladimir Kotlyar, Keshav Pingali. Compiling parallel code for sparse matrix applications. Technical report, Cornell University, 1997.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC