Intel Software Adrenaline

Programming CodeBook

Issue link:

Contents of this Issue


Page 12 of 16

Clustering 13 CLUSTERING Intel is the leading vendor of Message Passing Interface (MPI) implementations and tools. The ease of use of the Intel® MPI Library and related tools, such as Intel® Trace Analyzer and Collector, extends from the Intel® Xeon® architecture to the Intel® Many Integrated Core (Intel® MIC) architecture. With MPI, Intel® Xeon Phi™ Coprocessor acts as a network node, providing: • Optimized MPI application performance • Cluster and hybrid computing • Thread parallelism • Load balancing • Automatic and application-specific tuning • Industry leading low latency • Interconnect independence and runtime selection For in-depth coverage, view the webinar: Message Passing Interface (MPI) on Intel® Xeon Phi™ Coprocessor webinar » Applications CFD Crash Climate QCD BIO Other... Develop applications for one fabric Intel® MPI Library Select interconnect fabric at runtime TCP/IP Myrinet Infiniband IWARP Shared Memory ...Other Networks Fabrics Cluster Intel® MPI library eliminates the need to develop, maintain, and test applications running on multiple fabrics. For more information regarding performance and optimization choices in Intel® software products, visit: Privacy | Terms of Use | Learn More

Articles in this issue

Links on this page

view archives of Intel Software Adrenaline - Programming CodeBook