Numerical computation on massively parallel hypercubes. [Connection machine]

Conference · Wed Jan 01 04:00:00 EST 1986

OSTI ID:6831250

McBryan, O A

We describe numerical computations on the Connection Machine, a massively parallel hypercube architecture with 65,536 single-bit processors and 32 Mbytes of memory. A parallel extension of COMMON LISP, provides access to the processors and network. The rich software environment is further enhanced by a powerful virtual processor capability, which extends the degree of fine-grained parallelism beyond 1,000,000. We briefly describe the hardware and indicate the principal features of the parallel programming environment. We then present implementations of SOR, multigrid and pre-conditioned conjugate gradient algorithms for solving partial differential equations on the Connection Machine. Despite the lack of floating point hardware, computation rates above 100 megaflops have been achieved in PDE solution. Virtual processors prove to be a real advantage, easing the effort of software development while improving system performance significantly. The software development effort is also facilitated by the fact that hypercube communications prove to be fast and essentially independent of distance. 29 refs., 4 figs.

• Research Organization: Los Alamos National Lab., NM (USA)
• DOE Contract Number: AC02-76ER03077; W-7405-ENG-36
• OSTI ID: 6831250
• Report Number(s): LA-UR-86-4218; CONF-8609173-9; ON: DE87003740
• Country of Publication: United States
• Language: English

Related Subjects

99 GENERAL AND MISCELLANEOUS
990210* -- Supercomputers-- (1987-1989)
COMPUTERS
DIFFERENTIAL EQUATIONS
DIGITAL COMPUTERS
EQUATIONS
LISP
NUMERICAL SOLUTION
PARALLEL PROCESSING
PARTIAL DIFFERENTIAL EQUATIONS
PROGRAMMING
PROGRAMMING LANGUAGES
SUPERCOMPUTERS