|
|
|
Jacket User Guide
MATLAB® GPU Computing
The AccelerEyes’ Jacket software connects MATLAB1 to the graphics processing unit (GPU). With the GPU as a backend computation engine, Jacket brings together the best of three important computational worlds: computational speed, visualization, and the user-friendliness of MATLAB programming.
Click here to access... |
|
|
NVIDIA Tesla
GPU Computing Technical Brief
The GPU has great potential for solving such problems quickly and inexpensively. GPU computing makes supercomputing possible with any PC or workstation and expands the power of server clusters to solve problems that were previously not possible with existing CPU clusters.
The goal of computing with GPUs is to apply the tremendous computational power inherent in the GPU to solve some of the most difficult and important problems in high performance computing.
Click here to access... |
|
|
ScaleMP vSMP Technology
The Versatile SMP™ (vSMP) Architecture
and Solutions Based on vSMP Foundation™ High Performance Computing (HPC) applications have always needed faster and larger systems, historically served by SMP systems. An alternative for large SMP systems evolved in the late 90s when x86 processors exceeded the performance of RISC processors, promoting the adoption of commodity server clusters connected with high-speed interconnects. Cluster solutions deliver more performance than traditional SMPs, but are more difficult to program, implement and manage. ScaleMP developed the Versatile SMP (vSMP) architecture, a software-based computing-architecture that combines the advantages of shared-memory systems and the price points of commodity clusters by leveraging off-the-shelf x86 components. This paper presents a background of the evolution of HPC solutions, a problem statement, and a solution framework for addressing these requirements.
Click here to access.. |
|
|
Star-P Platform
Delivering Interactive Parallel Computing Power to the Desktop
As Simulation replaces physical testing, and increasingly complex phenomena are modeled, high performance computers (HPCs) are growing in importance for science and engineering. Interactive desktop science and engineering tools are critical in new model and algorithm development.. An interactive parallel computing platform will help desktop tool vendors leverage HPCs without having to solve the significant challenges associated with parallel programming and supporting multiple HPC platforms.
Click here to access... |
|
|
Improving HPC Performance, Scalability, and Availability
IDC shows how SGI is responding to HPC challenges, with the new SGI Altix ICE line of bladed servers
This innovative new platform raises the HPC bar, easily scaling to meet virtually any processing requirements without compromise on ease of use, manageability, or price/performance. Learn more by downloading the following whitepaper.
Click here to access.. |
|
|
NVIDIA...Accelerating MATLAB with CUDA™ Using MEX Files
This whitepaper illustrates the use of MEX files to perform computations on the GPU using CUDA. MATLAB provides a script, called mex, to compile a MEX file to a shared object or dll that can be loaded and executed inside a MATLAB session. This script is able to parse C, C++ and FORTRAN code. This script can call CUDA code to create greater optimization on GPUs.
Click here to access... |
|
|
NVIDIA CUDA Compute Unified Device Architecture
The advent of multicore CPUs and manycore GPUs means that mainstream processor chips are now parallel systems. Furthermore, their parallelism continues to scale with Moore’s law. The challenge is to develop application software that transparently scales its parallelism to leverage the increasing number of processor cores, much as 3D graphics applications transparently scale their parallelism to manycore GPUs with widely varying numbers of cores. CUDA is a parallel programming model and software environmenr designed to overcome this challenge while maintaining a low learning curve for programmers familiar with standard programming languages such as C.
Click here to access... |
|
|
Intel® Cluster Ready—
Making HPC simpler
Boost productivity. Solve new problems. The Intel® Cluster
Ready program makes it simpler to experience the power of
high-performance computing.
Developed in conjunction with hardware and software vendors, the Intel Cluster Ready program
simplifies buying, deploying, and managing a high-performance computing (HPC) cluster. Intel
Cluster Ready helps to ensure application and component interoperability from the moment
you power up the cluster through the lifetime of the system.
Click here to access... |
|
|
eXludus....
Does your Multi-Core Cluster Scale?
This brief discusses both the hidden and painfully obvious inefficiencies inherent in current technology commodity clusters and grid computing. Particular emphasis is placed on the impact of multi-core CPUs on efficient scaling. The brief also discusses advances in schedule optimization technology that can deliver throughput performance speed-ups of order 1.5 X to 10 X.
Click here to access... |
|
|
