CUDA processing module : responsible with the execution of the GPGPU
programs on the graphics hardware
These cards boast 576 GFLOPs of peak single precision floating point performance and are designed for GPGPU
applications such as image analysis, radar, sonar, and video surveillance.
Converged architecture blade server E9000-- The expansion blade CH220 V3 of the E9000 which provides two dual-slot GPGPUs
in a 1.
In our solution we will run the Ray Tracing algorithm directly on the streaming processors of 2 GPUs as a GPGPU
program thus bypassing the standard usage of the graphics pipeline with shader programs.
Ripeanu, "Size Matters: Space/Time Tradeoffs to Improve GPGPU
Applications Performance," IEEE/ACM International Conference for High Performance Computing, Networking, Storage, and Analysis (SC 2010), New Orleans, LA, November 2010.
Figure 1 illustrates performance increases reported by 438 of these research efforts (along with some commercial companies) that decided to showcase their GPGPU
performance on the NVIDIA Web site.
NextIO simplifies enterprise datacenters by consolidating and sharing networking, GPGPU
computing, and storage devices within the compute rack.
Extraordinary performance improvements for many problems can be achieved by plugging GPGPU
technology into commodity workstations and computational nodes.
The Adreno 430 is designed to deliver up to 30% faster graphics performance and 100% faster GPGPU
compute performance, while reducing power consumption by up to 20%, as compared to its predecessor, the Adreno 420 GPU.
Acronyms ACML AMD Core Math Library | COTS Commodity off the Shelf | CUDA Compute United Device Archtecture | GPGPU
General-Purpose Computation on Graphics Processing Units | GPU Graphics Processing Unit | MKL Math Kernel Library | NSSP Single Source Shorfest Path Problem with Non-negative Weights | SIMD Single Instruction, Multiple Data | SSE Streaming SIMD Extensions | TLB Translation Lookaside Buffer
Analogic used OpenCL standard to gain access to the GPU for general-purpose computing, referred to as GPGPU
, delivering exceptional performance and offering system and development cost reduction through cross-platform portability.
If you are interested in programming in CUDA, two professors at the University of Illinois Urbana-Champaign, David Kirk and Wen-mei Hwu, have placed their course materials on line (see GPGPU