Chip Multiprocessor Architecture: Techniques to Improve Throughput and Latency Ebook
Publication Date: December 2007
File Size: 5694 Kbytes
Restrictions set by Publisher:
- Text-to-speech feature not available.
- Printing is not permitted.
- You cannot copy text from file.
- Free application Adobe Digital Editions, Aldiko reader, or Bluefire reader required .
- Check Supported devices and software requirements .
- Ebooks once downloaded are non-refundable. View return policy .
Chip multiprocessors – also called multi-core microprocessors or CMPs for short- are now the only way to build high-performance microprocessors, for a variety of reasons. Large uniprocessors are no longer scaling in performance, because it is only possible to extract a limited amount of parallelism from a typical instruction stream using conventional superscalar instruction issue techniques. In addition, one cannot simply ratchet up the clock speed on today’s processors, or the power dissipation will become prohibitive in all but water-cooled systems. Compounding these problems is the simple fact that with the immense numbers of transistors available on today’s microprocessor chips, it is too costly to design and debug ever-larger processors every year or two. CMPs avoid these problems by filling up a processor die with multiple, relatively simpler processor cores instead of just one huge core. The exact size of a CMP’s cores can vary from very simple pipelines to moderately complex superscalar processors, but once a core has been selected the CMP’s performance can easily scale across silicon process generations simply by stamping down more copies of the hard-to-design, high-speed processor core in each successive chip generation. In addition, parallel code execution, obtained by spreading multiple threads of execution across the various cores, can achieve significantly higher performance than would be possible using only a single core. While parallel threads are already common in many useful workloads, there are still important workloads that are hard to divide into parallel threads. The low inter-processor communication latency between the cores in a CMP helps make a much wider range of applications viable candidates for parallel execution than was possible with conventional, multi-chip multiprocessors; nevertheless, limited parallelism in key applications is the main factor limiting acceptance of CMPs in some types of systems. After a discussion of the basic pros and cons of CMPs when they are compared with conventional uniprocessors, this book examines how CMPs can best be designed to handle two radically different kinds of workloads that are likely to be used with a CMP: highly parallel, throughput-sensitive applications at one end of the spectrum, and less parallel, latency-sensitive applications at the other. Throughput-sensitive applications, such as server workloads that handle many independent transactions at once, require careful balancing of all parts of a CMP that can limit throughput, such as the individual cores, on-chip cache memory, and off-chip memory interfaces. Several studies and example systems, such as the Sun Niagara, that examine the necessary tradeoffs are presented here. In contrast, latency-sensitive applications- many desktop applications fall into this category – require a focus on reducing inter-core communication latency and applying techniques to help programmers divide their programs into multiple threads as easily as possible. This book discusses many techniques that can be used in CMPs to simplify parallel programming, with an emphasis on research directions proposed at Stanford University. To illustrate the advantages possible with a CMP using a couple of solid examples, extra focus is given to thread-level speculation (TLS), a way to automatically break up nominally sequential applications into parallel threads on a CMP, and transactional memory. This model can greatly simplify manual parallel programming by using hardware- instead of conventional software locks – to enforce atomic code execution of blocks of instructions, a technique that makes parallel coding much less error-prone. Contents: The Case for CMPs / Improving Throughput / Improving Latency Automatically / Improving Latency using Manual Parallel Programming / A Multicore World: The Future of CMPs
Should you buy this Ebook?
We've put together a collection of resources to help you make a decision regarding whether you should buy this Ebook from us.
- We retrieve ratings from several sources on the web for your convenience. They are often good enough indicator of the work. In addition, you can also read Reviews.
- Is your device one of these? Ebook reading software will work on the following devices: Windows, Mac, Android 2.2+ Devices, IPad (iOS 3+), IPhone (iOS 3+), Kindle Fire. Several other devices are also supported by the software.
- Compare prices. Our price is $39.16. If you would like to research our competitors to see their prices. Here're some places to look:
Why should you buy Ebooks from onlinebookplace.com?
We've had 1000s of downloads so far and with over 300000+ Ebooks to choose from, onlinebookplace.com is becoming a favorite Ebook Store for many. Allow us to win you over with our competitive pricing, upfront policies and diligent customer service.
- Every Ebook page on onlinebookplace.com has information on restrictions that publishers have placed on the Ebook along with a clear indication of software required to read the Ebooks.
- If ratings for an Ebook are available from one of several sources online, then we've attempted to get those to help you make a better purchasing decision about the Ebook. Reviews from Goodreads (a popular reviews site) are provided on the same if they're available.
- In most cases, we've also attempted to get you links to the Ebook on our competitor's site so that you can compare prices with relative ease.
- We use McAfee to scan for any vulnerabilities in the system to ensure that any information that you give us does not fall into the wrong hands.
- We use Paypal, a trusted 3rd party payment provider to accept Payments -- your payment information doen't reside with us. Any information that does end up with us is safe.
Check below for device compatibility and any free 3rd-party software requirements. You should be able to transfer your purchase to more than one (usually between 3 to 6) compatible devices.
Windows/Mac PC or Laptop
Free app Adobe Digital Editions required. Note that this software is not the same as Adobe Reader.
IPad or IPhone
Free app Bluefire Reader required.