CULAtools™ is EM Photonics’ library family comprised of CULA™ Basic, Premium, and Commercial. CULA is a GPU-accelerated implementation of the LAPACK numerical linear algebra library, containing several of the most popular LAPACK functions. After developing accelerated linear algebra solvers since 2004 for our clients, EM Photonics partnered with NASA Ames Research Center in 2007 to extend and unify these libraries into a single, GPU-accelerated package. Through a partnership with NVIDIA®, GPU Gurus™ focused on developing a commercially available implementation of accelerated LAPACK routines. The primary goal of these tools is to help a wide range of users experience computational performance previously available only on supercomputers. By leveraging NVIDIA’s CUDA™ architecture, CULA provides users linear algebra functions with unsurpassed performance.
CULA Basic contains LAPACK routines including LU Decomposition, QR Factorization, Singular Value Decomposition, and Least Squares. The Beta is available for free download here. Performance results of CULA tools are available here.
2 responses so far ↓
1 Math World | CULA Tools: GPU Accelerated LAPACK // Aug 14, 2009 at 4:33 am
[...] Read more here: CULA Tools: GPU Accelerated LAPACK [...]
2 Multicore Review: Best Multicore Posts of 2009 // Dec 20, 2009 at 9:27 am
[...] CULA Tools: GPU Accelerated LAPACK: Model of providing libraries to utilize GPUs is growing. There are many CUDA libraries including CUDPP (CUDA Data Parallel Primitives Library), SpMV (Sparse Matrix-Vector Multiplication in CUDA). A lot more libraries can be found at CUDA Zone. [...]