Read an Excerpt
Programming Massively Parallel Processors
A Hands-on Approach
By David B. Kirk Wen-mei W. Hwu
ELSEVIER
Copyright © 2013 David B. Kirk/NVIDIA Corporation and Wen-mei Hwu
All right reserved.
ISBN: 978-0-12-391418-7
Chapter One
Introduction
CHAPTER OUTLINE
1.1 Heterogeneous Parallel Computing 2
1.2 Architecture of a Modern GPU 8
1.3 Why More Speed or Parallelism? 10
1.4 Speeding Up Real Applications 12
1.5 Parallel Programming Languages and Models 14
1.6 Overarching Goals 16
1.7 Organization of the Book 17
References 21
Microprocessors based on a single central processing unit (CPU), such as those in the Intel Pentium family and the AMD Opteron family, drove rapid performance increases and cost reductions in computer applications for more than two decades. These microprocessors brought GFLOPS, or giga (1012) floating-point operations per second, to the desktop and TFLOPS, or tera (1015) floating-point operations per second, to cluster servers. This relentless drive for performance improvement has allowed application software to provide more functionality, have better user interfaces, and generate more useful results. The users, in turn, demand even more improvements once they become accustomed to these improvements, creating a positive (virtuous) cycle for the computer industry.
This drive, however, has slowed since 2003 due to energy consumption and heat dissipation issues that limited the increase of the clock frequency and the level of productive activities that can be performed in each clock period within a single CPU. Since then, virtually all microprocessor vendors have switched to models where multiple processing units, referred to as processor cores, are used in each chip to increase the processing power. This switch has exerted a tremendous impact on the software developer community [Sutter2005].
Traditionally, the vast majority of software applications are written as sequential programs, as described by von Neumann in his seminal report in 1945 [vonNeumann1945]. The execution of these programs can be understood by a human sequentially stepping through the code. Historically, most software developers have relied on the advances in hardware to increase the speed of their sequential applications under the hood; the same software simply runs faster as each new generation of processors is introduced. Computer users have also become accustomed to the expectation that these programs run faster with each new generation of microprocessors. Such expectation is no longer valid from this day onward. A sequential program will only run on one of the processor cores, which will not become significantly faster than those in use today. Without performance improvement, application developers will no longer be able to introduce new features and capabilities into their software as new microprocessors are introduced, reducing the growth opportunities of the entire computer industry.
Rather, the applications software that will continue to enjoy performance improvement with each new generation of microprocessors will be parallel programs, in which multiple threads of execution cooperate to complete the work faster. This new, dramatically escalated incentive for parallel program development has been referred to as the concurrency revolution [Sutter2005]. The practice of parallel programming is by no means new. The high-performance computing community has been developing parallel programs for decades. These programs run on large-scale, expensive computers. Only a few elite applications can justify the use of these expensive computers, thus limiting the practice of parallel programming to a small number of application developers. Now that all new microprocessors are parallel computers, the number of applications that need to be developed as parallel programs has increased dramatically. There is now a great need for software developers to learn about parallel programming, which is the focus of this book.
1.1 HETEROGENEOUS PARALLEL COMPUTING
Since 2003, the semiconductor industry has settled on two main trajectories for designing microprocessors [Hwu2008]. The multicore trajectory seeks to maintain the execution speed of sequential programs while moving into multiple cores. The multicores began with two core processors with the number of cores increasing with each semiconductor process generation. A current exemplar is the recent Intel Core i7™ microprocessor with four processor cores, each of which is an out-of-order, multiple instruction issue processor implementing the full X86 instruction set, supporting hyper-threading with two hardware threads, designed to maximize the execution speed of sequential programs. In contrast, the many-thread trajectory focuses more on the execution throughput of parallel applications. The many-threads began with a large number of threads, and once again, the number of threads increases with each generation. A current exemplar is the NVIDIA GTX680 graphics processing unit (GPU) with 16,384 threads, executing in a large number of simple, in-order pipelines.
Many-threads processors, especially the GPUs, have led the race of floating-point performance since 2003. As of 2012, the ratio of peak floating-point calculation throughput between many-thread GPUs and multicore CPUs is about 10. These are not necessarily application speeds, but are merely the raw speed that the execution resources can potentially support in these chips: 1.5 teraflops versus 150 gigaflops double precision in 2012.
Such a large performance gap between parallel and sequential execution has amounted to a significant "electrical potential" build-up, and at some point, something will have to give. We have reached that point now. To date, this large performance gap has already motivated many application developers to move the computationally intensive parts of their software to GPUs for execution. Not surprisingly, these computationally intensive parts are also the prime target of parallel programmingwhen there is more work to do, there is more opportunity to divide the work among cooperating parallel workers.
One might ask why there is such a large peak-performance gap between many-threads GPUs and general-purpose multicore CPUs. The answer lies in the differences in the fundamental design philosophies between the two types of processors, as illustrated in Figure 1.1. The design of a CPU is optimized for sequential code performance. It makes use of sophisticated control logic to allow instructions from a single thread to execute in parallel or even out of their sequential order while maintaining the appearance of sequential execution. More importantly, large cache memories are provided to reduce the instruction and data access latencies of large complex applications. Neither control logic nor cache memories contribute to the peak calculation speed. As of 2012, the high-end general-purpose multicore microprocessors typically have six to eight large processor cores and multiple megabytes of on-chip cache memories designed to deliver strong sequential code performance.
Memory bandwidth is another important issue. The speed of many applications is limited by the rate at which data can be delivered from the memory system into the processors. Graphics chips have been operating at approximately six times the memory bandwidth of contemporaneously available CPU chips. In late 2006, GeForce 8800 GTX, or simply G80, was capable of moving data at about 85 gigabytes per second (GB/s) in and out of its main dynamic random-access memory (DRAM) because of graphics frame buffer requirements and the relaxed memory model (the way various system software, applications, and input/output (I/O) devices expect how their memory accesses work). The more recent GTX680 chip supports about 200 GB/s. In contrast, general-purpose processors have to satisfy requirements from legacy operating systems, applications, and I/O devices that make memory bandwidth more difficult to increase. As a result, CPUs will continue to be at a disadvantage in terms of memory bandwidth for some time.
The design philosophy of GPUs is shaped by the fast-growing video game industry that exerts tremendous economic pressure for the ability to perform a massive number of floating-point calculations per video frame in advanced games. This demand motivates GPU vendors to look for ways to maximize the chip area and power budget dedicated to floating-point calculations. The prevailing solution is to optimize for the execution throughput of massive numbers of threads. The design saves chip area and power by allowing pipelined memory channels and arithmetic operations to have long latency. The reduced area and power of the memory access hardware and arithmetic units allows the designers to have more of them on a chip and thus increase the total execution throughput.
The application software is expected to be written with a large number of parallel threads. The hardware takes advantage of the large number of threads to find work to do when some of them are waiting for long-latency memory accesses or arithmetic operations. Small cache memories are provided to help control the bandwidth requirements of these applications so that multiple threads that access the same memory data do not need to all go to the DRAM. This design style is commonly referred to as throughput-oriented design since it strives to maximize the total execution throughput of a large number of threads while allowing individual threads to take a potentially much longer time to execute.
The CPUs, on the other hand, are designed to minimize the execution latency of a single thread. Large last-level on-chip caches are designed to capture frequently accessed data and convert some of the long-latency memory accesses into short-latency cache accesses. The arithmetic units and operand data delivery logic are also designed to minimize the effective latency of operation at the cost of increased use of chip area and power. By reducing the latency of operations within the same thread, the CPU hardware reduces the execution latency of each individual thread. However, the large cache memory, low-latency arithmetic units, and sophisticated operand delivery logic consume chip area and power that could be otherwise used to provide more arithmetic execution units and memory access channels. This design style is commonly referred to as latency-oriented design.
It should be clear now that GPUs are designed as parallel, throughput-oriented computing engines and they will not perform well on some tasks on which CPUs are designed to perform well. For programs that have one or very few threads, CPUs with lower operation latencies can achieve much higher performance than GPUs. When a program has a large number of threads, GPUs with higher execution throughput can achieve much higher performance than CPUs. Therefore, one should expect that many applications use both CPUs and GPUs, executing the sequential parts on the CPU and numerically intensive parts on the GPUs. This is why the CUDA programming model, introduced by NVIDIA in 2007, is designed to support joint CPUGPU execution of an application. The demand for supporting joint CPUGPU execution is further reflected in more recent programming models such as OpenCL (see Chapter 14), OpenACC (see Chapter 15), and C++AMP (see Chapter 18).
(Continues...)
Excerpted from Programming Massively Parallel Processors by David B. Kirk Wen-mei W. Hwu Copyright © 2013 by David B. Kirk/NVIDIA Corporation and Wen-mei Hwu. Excerpted by permission of ELSEVIER. All rights reserved. No part of this excerpt may be reproduced or reprinted without permission in writing from the publisher.
Excerpts are provided by Dial-A-Book Inc. solely for the personal use of visitors to this web site.