ARSC T3D Users' Newsletter 45, July 21, 1995

An Archive Site for High Performance Computing Articles

John Larson ( of the National Environmental Supercomputing Center in Bay City, Michigan sent me the address of the London Parallel Applications Centre Web Server:
This site has an article archive of High Performance Computing articles that can be searched in a simple way. A simple search for the word "T3D" displays five articles:
  1. George Karypis, and Vipin Kumar "A High Performance Sparse Cholesky Factorization Algorithm for Scalable Parallel Computers", Technical report 94-41, Department of Computer Science, University of Minnesota, 94. bibtex, postscript paper
  2. Wayne D. Joubert "Node Performance of the BLAS-1 Routines on the Cray T3D", February 1995. bibtex, html abstract, html paper
  3. Robert van Engelen, and Lex Wolters "A Comparison of Parallel Programming Paradigms and Data Distributions for a Limited Area Numerical Weather Forecast Routine", Technical report TR 95-10, Leiden University, April 1995. bibtex, html abstract, postscript paper
  4. Paolo Marenzoni "Performance Analysis of Cray T3D and Connection Machine CM-5: a Comparison" In High Performance Computing and Networking HPCN Europe 95, pages 8, Lecture Notes in Computer Science 919, pp 110-117, May 1995. bibtex, html abstract, postscript paper
  5. R. Kent Koeninger, Mark Furtney, and Martin Walker "A Shared Memory MPP from Cray Research" Digital Technical Journal, 6(2), Spring 1994. bibtex, ascii abstract, postscript paper
All of these articles are interesting but the last one was particularly comprehensive and insightful. From the title of this article I thought that CRI was announcing a new product because I doubt that most users consider the T3D a shared memory MPP. But the explanation from the article is the following entire paragraph from the first page of the article:

... "A key architectural feature of the CRAY T3D system is the use of physically distributed, logically shared memory (distributed-shared memory). The memory is physically distributed in that each PE contains a processor and a local dynamic random-access memory (DRAM); accesses to local memory are faster than accesses to remote memories. The memory is shared in that any processor can read or write any word in any of the remote PEs without the assistance or knowledge of the remote processors or the operating system. Cray Research provides a shell of circuitry around the processor that allows the local processor to issue machine instructions to read remote memory locations. Distributed-shared memory is a significant advance in balancing the ratio between remote and local memory access speeds. This balance, in conjunction with new programming methods that exploit this new capability, will increase the number of applications that can run efficiently on MPPs and simplify the programming tasks." ...

Release of 1.2.2 CrayLibs_M

ARSC has gotten the 1.2.2 release of CrayLibs_M and is planning to make it available within the next month. Watch this newsletter for further details.

List of Differences Between T3D and Y-MP

The current list of differences between the T3D and the Y-MP is:
  1. Data type sizes are not the same (Newsletter #5)
  2. Uninitialized variables are different (Newsletter #6)
  3. The effect of the -a static compiler switch (Newsletter #7)
  4. There is no GETENV on the T3D (Newsletter #8)
  5. Missing routine SMACH on T3D (Newsletter #9)
  6. Different Arithmetics (Newsletter #9)
  7. Different clock granularities for gettimeofday (Newsletter #11)
  8. Restrictions on record length for direct I/O files (Newsletter #19)
  9. Implied DO loop is not "vectorized" on the T3D (Newsletter #20)
  10. Missing Linpack and Eispack routines in libsci (Newsletter #25)
  11. F90 manual for Y-MP, no manual for T3D (Newsletter #31)
  12. RANF() and its manpage differ between machines (Newsletter #37)
  13. CRAY2IEG is available only on the Y-MP (Newsletter #40)
  14. Missing sort routines on the T3D (Newsletter #41)
I encourage users to e-mail in differences that they have found, so we all can benefit from each other's experience.
Current Editors:
Ed Kornkven ARSC HPC Specialist ph: 907-450-8669
Kate Hedstrom ARSC Oceanographic Specialist ph: 907-450-8678
Arctic Region Supercomputing Center
University of Alaska Fairbanks
PO Box 756020
Fairbanks AK 99775-6020
E-mail Subscriptions: Archives:
    Back issues of the ASCII e-mail edition of the ARSC T3D/T3E/HPC Users' Newsletter are available by request. Please contact the editors.
Back to Top