Mark Smotherman
Last updated: September 2007
Summary: TBD
(under construction)
... intro to be written ...
The term SIMD was originally defined in 1960s as category of multiprocessor with one control unit and multiple processing elements - each instruction is executed by all processing elements on different data streams, e.g., Illiac IV. Today the term is used to describe partitionable ALUs in which multiple operands can fit in a fixed-width register and are acted upon in parallel.
(other terms include subword parallelism, microSIMD, short vector extensions, split-ALU, SLP / superword-level parallelism, and SIGD / single-instruction-group[ed]-data)
The structure of the arithmetic element can be altered under program
control. Each instruction specifies a particular form of machine in
which to operate, ranging from a full 36-bit computer to four 9-bit
computers with many variations. Not only is such a scheme able to
make more efficient use of the memory in storing data of various word
lengths, but it also can be expected to result in greater over-all
machine speed because of the increased parallelism of operation.
Peak operating rates must then be referred to particular configurations.
For addition and multiplication, these peak rates are given in the
following table:
PEAK OPERATING SPEEDS OF TX-2
Word Lengths Additions Multiplications
(in bits) per second per second
36 150,000 80,000
18 300,000 240,000
9 600,000 600,000
My thanks to Don Alpert for his help.
[History page] [Mark's homepage] [CPSC homepage] [Clemson Univ. homepage]
mark@cs.clemson.edu