1 / 7

Parallel Architectures

Parallel Architectures. Why build parallel machines? To help build even bigger parallel machines To help solve important problems Speed – more trials, less time Cost Larger problems Accuracy Must understand typical problems. Introduction.

Télécharger la présentation

Parallel Architectures

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Parallel Architectures • Why build parallel machines? • To help build even bigger parallel machines • To help solve important problems • Speed – more trials, less time • Cost • Larger problems • Accuracy • Must understand typical problems

  2. Introduction • A parallel computer is “a collection of processing elements that communicate and cooperate to solve large problems fast” Speedup(p processors)=performance (p processors)/performance (1 processor) Speedup(p processors)=time(p processors)/time(1 processor)

  3. Can run a single parallel application • Speed up the application • Can run multiple independent applications in multiprogramming environment • High throughput • Combination of the two

  4. Numeric Symbolic Combinatorial Applications ---> Requirements • Processing • Communication • Memory • I/O • Synchronization • Architect must provide all of the above

  5. Requirements ---> Examples • Relaxation - near-neighbor communication • Multigrid - 1, 2, 4, 8, ... communication • Numeric comp - Floating point • Symbolic - Tags, branches • Database - I/O • Data parallel - Barrier synchronicity • Dictionary - Memory, I/O

  6. Communication requirements ---> Example • Relaxation • So, let’s build a special machine! • But ... pitfalls!

  7. Specialized machines: Pitfalls • Faster algorithms appear … with different communication requirements • Cost effectiveness • Economies of scale • Simpler hardware & software mechanisms • More flexible • May even be faster! • e.g. Specialized support for synchronization across multiple processors

More Related