W13_25_ProcessorsAdvOrg1

W13_25_ProcessorsAdvOrg1 - 25 Advanced Processors...

Info iconThis preview shows pages 1–11. Sign up to view the full content.

View Full Document Right Arrow Icon
25 Advanced Processors Organization CSC 230 Department of Computer Science University of Victoria
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Multicore Computers (seen before) ± Two or more cores (CPUs) as a single integrated circuit. ± May have independent or shared on-board caches. ± Each core independently implements optimizations such s superscalar execution and pipelining as superscalar execution and pipelining. ± Number of cores is 2 for Intel Duo, 4 for Intel Core 2 Quad, 8 for PS3, … 32 for Intel Larrabee. CPU 1 CPU 2 CPU 1 CPU 2 Cache Cache MU Cache MU MMU MMU MMU Multicore Design Multiprocessor Design
Background image of page 2
Processor Organization MISD: SISD: SIMD: MIMD: Multiple instruction, single data tream Single instruction, single data tream Single instruction, multiple data tream Multiple instruction, multiple data tream stream stream stream stream Vector array Array processor Uniprocessor Shared memory (tightly coupled) Distributed memory (loosely coupled) Symmetric Multiprocessor (SMP) Nonuniform Memory Access (UMA) Clusters
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Shared Memory or Message Passing? P n-1 P 0 P 1 shared memory Interconnection network M n-1 M 0 M 1 P n-1 P 0 P 1 message passing M n-1 M 0 M 1 Interconnection network
Background image of page 4
Flynn axonomy Taxonomy Classification of rchitectures according architectures according to the Flynn taxonomy: (a) SISD; (b) SIMD; (c) MISD; (d) MIMD. Computer Architecture and Organization by M. Murdocca and V. Heuring © 2007 M. Murdocca and V. Heuring 5
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Flynn Taxonomy: Classification of architectures (a) SISD = Single instruction, ingle data stream single data stream (b) SIMD; c) MISD; (c) MISD; (d) MIMD.
Background image of page 6
Flynn Taxonomy: Classification of architectures (a) SISD; (b) SIMD= Single instruction, multiple data (c) MISD; (d) MIMD.
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Flynn Taxonomy: Classification of architectures (a) SISD; (b) SIMD; (c) MISD= Multiple instruction, single data stream (d) MIMD.
Background image of page 8
Flynn Taxonomy: Classification of architectures (a) SISD; (b) SIMD; (c) MISD; (d) MIMD = Multiple instruction, multiple data stream () p, p
Background image of page 9

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Why SIMD?
Background image of page 10
Image of page 11
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 01/15/2012 for the course CSC 230 taught by Professor Jasond.corless during the Summer '11 term at University of Victoria.

Page1 / 26

W13_25_ProcessorsAdvOrg1 - 25 Advanced Processors...

This preview shows document pages 1 - 11. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online