Book contents
- Frontmatter
- Contents
- Preface
- 1 Introduction
- 2 The Basics
- 3 Superscalar Processors
- 4 Front-End: Branch Prediction, Instruction Fetching, and Register Renaming
- 5 Back-End: Instruction Scheduling, Memory Access Instructions, and Clusters
- 6 The Cache Hierarchy
- 7 Multiprocessors
- 8 Multithreading and (Chip) Multiprocessing
- 9 Current Limitations and Future Challenges
- Bibliography
- Index
- References
3 - Superscalar Processors
Published online by Cambridge University Press: 05 June 2012
Book contents
- Frontmatter
- Contents
- Preface
- 1 Introduction
- 2 The Basics
- 3 Superscalar Processors
- 4 Front-End: Branch Prediction, Instruction Fetching, and Register Renaming
- 5 Back-End: Instruction Scheduling, Memory Access Instructions, and Clusters
- 6 The Cache Hierarchy
- 7 Multiprocessors
- 8 Multithreading and (Chip) Multiprocessing
- 9 Current Limitations and Future Challenges
- Bibliography
- Index
- References
Summary
From Scalar to Superscalar Processors
In the previous chapter we introduced a five-stage pipeline. The basic concept was that the instruction execution cycle could be decomposed into nonoverlapping stages with one instruction passing through each stage at every cycle. This so-called scalar processor had an ideal throughput of 1, or in other words, ideally the number of instructions per cycle (IPC) was 1.
If we return to the formula giving the execution time, namely,
EXCPU = Number of instructions × CPI × cycle time
we see that in order to reduce EXCPU in a processor with the same ISA – that is, without changing the number of instructions, N – we must either reduce CPI (increase IPC) or reduce the cycle time, or both. Let us look at the two options.
The only possibility to increase the ideal IPC of 1 is to radically modify the structure of the pipeline to allow more than one instruction to be in each stage at a given time. In doing so, we make a transition from a scalar processor to a superscalar one. From the microarchitecture viewpoint, we make the pipeline wider in the sense that its representation is not linear any longer. The most evident effect is that we shall need several functional units, but, as we shall see, each stage of the pipeline will be affected.
- Type
- Chapter
- Information
- Microprocessor ArchitectureFrom Simple Pipelines to Chip Multiprocessors, pp. 75 - 128Publisher: Cambridge University PressPrint publication year: 2009
References
, , , , , and , “TRANQUIL: A Language for an Array Processing Computer,” Proc. AFIPS SJCC, 1969, 57–73Google Scholar
, , , , , , , , and , “Integrated Predicated and Speculative Execution in the IMPACT EPIC Architecture,” Proc. 25th Int. Symp. on Computer Architecture, 1998, 227–237CrossRefGoogle Scholar
, , and , “Machine Philosophy and Instruction Handling,” IBM Journal of Research and Development, 11, 1, Jan. 1967, 8–24CrossRefGoogle Scholar
, “Analysis of Programs for Parallel Processing,” IEEE Trans. on Elec. Computers, Ec03-76992, Oct. 1966, 746–757Google Scholar
, Alpha Implementations and Architecture. Complete Reference and Guide, Digital Press, Boston, 1995Google Scholar
, , , , , , , , and , “The Microarchitecture of the Pentium 4 Processor on 90nm Technology,” Intel Tech. Journal, 8, 1, Feb. 2004, 1–17Google Scholar
and , “Performance Characterization of the Alpha 21164 Microprocessor Using TP and SPEC Workloads,” Proc. 2nd Int. Symp. on High-Performance Computer Architecture, 1996, 270–280CrossRefGoogle Scholar
, , , , and , “Intel's P6 Microarchitecture,” Chapter 7 in and , Eds., Modern Processor Design, 2005, 329–367Google Scholar
, , , and , “Superscalar Instruction Execution in the 21164 Alpha Microprocessor,” IEEE Micro, 15, 2, Apr. 1995, 33–43CrossRefGoogle Scholar
, “Brainiacs, Speed Demons, and Farewell,” Microprocessor Report Newsletter, 13, 7, Dec. 1999Google Scholar
, , , , , , , , and , “The Intel Pentium M Processor: Microarchitecture and Performance,” Intel Tech. Journal, 07, 2, May 2003, 21–39Google Scholar
, , , , , and , “Introducing the IA-64 Architecture,” IEEE Micro, 20, 5, Sep. 2000, 12–23CrossRefGoogle Scholar
and , “HPSm, A High-Performance Restricted Data Flow Architecture Having Minimal Functionality,” Proc. 13th Int. Symp. on Computer Architecture, 1986, 297–307CrossRefGoogle Scholar
, , , , , , and , “The Microarchitecture of the Pentium4 Processor,” Intel Tech. Journal, 1, Feb. 2001Google Scholar
, “A Tour of the P6 Microarchitecture,” 1995, http://www.x86.org/ftp/manuals/686/p6tour.pdf
and , “Pentium III Processor Implementation Tradeoffs,” Intel Tech. Journal, 2, May 1999Google Scholar
, “Software Pipelining: An Effective Scheduling Technique for VLIW Machines,” Proc. ACM SIGPLAN Conf. on Programming Language Design and Implementation, SIGPLAN Notices, 23, 7, Jul. 1988, 318–328Google Scholar
and , “Itanium 2 Processor Microarchitecture,” IEEE Micro, 23, 2, Mar. 2003, 44–55CrossRefGoogle Scholar
, “Tuning the Pentium Pro Microarchitecture,” IEEE Micro, 16, 2, Mar. 1996, 8–15CrossRefGoogle Scholar
and , “RISC I: A Reduced Instruction Set VLSI Computer,” Proc. 8th Int. Symp. on Computer Architecture, 1981, 443–457Google Scholar
and , “The Inhibition of Potential Parallelism by Conditional Jumps,” IEEE Trans. on Computers, C-12, 12, Dec. 1972, 1405–1411CrossRefGoogle Scholar
, “Instruction Issue Logic for High-Performance, Interruptible, Multiple Functional Unit, Pipelined Computers,” IEEE Trans. on Computers, C-39, 3, Mar. 1990, 349–359 (an earlier version with coauthor S. Vajapeyam was published in Proc. 14th Int. Symp. on Computer Architecture, 1987)CrossRefGoogle Scholar
and , “Itanium Processor Microarchitecture,” IEEE Micro, 20, 5, Sep. 2000, 24–43CrossRefGoogle Scholar
and , “Implementation of Precise Interrupts in Pipelined Processors,” IEEE Trans. on Computers, C-37, 5, May 1988, 562–573 (an earlier version was published in Proc. 12th Int. Symp. on Computer Architecture, 1985)CrossRefGoogle Scholar
and , “EPIC: Explicitly Parallel Instruction Computing,” IEEE Computer, 33, 2, Feb. 2000, 37–45CrossRefGoogle Scholar
and , “The Microarchitecture of Superscalar Processors,” Proc. IEEE, 83, 12, Dec. 1995, 1609–1624CrossRefGoogle Scholar
, “Parallel Operation in the Control Data 6600,” AFIPS Proc. FJCC, pt. 2, vol. 26, 1964, 33–40 (reprinted as Chapter 39 of C. Bell and A. Newell, Computer Structures: Readings and Examples, McGraw-Hill, New York, 1971, and Chapter 43 of D. Siewiorek, C. Bell, and A. Newell, Computer Structures: Principles and Examples, McGraw-Hill, New York, 1982)Google Scholar
, “An Efficient Algorithm for Exploiting Multiple Arithmetic Units,” IBM Journal of Research and Development, 11, 1, Jan. 1967, 25–33CrossRefGoogle Scholar
, Design of a Computer: The Control Data 6600, Scott, Foresman and Co., Glenview, IL, 1970Google Scholar
and , “Detection and Parallel Execution of Independent Instructions,” IEEE Trans. on Computers, C-19, 10, Oct. 1970, 889–895CrossRefGoogle Scholar