Integrating SIMD into the undergraduate curriculum

Authors:
W. D. Maurer
Affiliations:
Department of Computer Science, The George Washington University, Washington, DC
Venue:
CCSC '01 Proceedings of the sixth annual CCSC northeastern conference on The journal of computing in small colleges
Year:
2001

Citing 4
Cited 0

Data parallel algorithms

Communications of the ACM - Special issue on parallelism
The CM-5 Connection Machine: a scalable supercomputer

Communications of the ACM
Computer organization and design (2nd ed.): the hardware/software interface

Computer organization and design (2nd ed.): the hardware/software interface
Connection Machine Lisp: fine-grained parallel symbolic processing

LFP '86 Proceedings of the 1986 ACM conference on LISP and functional programming

Quantified Score

Hi-index	0.00

Visualization

Abstract

Assembly language instruction today, in our view, should include instruction in the newly important area of single-instruction, multiple-data (SIMD) instructions. Such instructions are available on all major platforms, and they considerably speed up operations on arrays, particularly large arrays. This speedup is more pronounced with assembly language than with algebraic language programming, and thus provides another reason for undergraduate students to learn assembly language. We discuss the differences among approaches to SIMD on various platforms; then we describe our own experience with teaching this material.