System architecture
Explore the source record for details and available documents.
HTMT system architecture↗
Engineering topics
Sterling, T.
Publications and source records attributed to Sterling, T..
An introduction to the Gilgamesh PIM architecture
The focus of the work conducted is on a class of structures made possible by the merger of logic and memory. Processing In Memory (PIM) extends the design space much farther by closely associating the logic with the memory interface to realize innovative structures never previously possible and thus exposing entirely new opportunities for computer architecture.
Gilgamesh PIM CMOS↗
The use of cluster computer systems for NASA/JPL applications
In this paper we outline the results of using three generations of cluster machines at JPL for a select set of applications drawn from a larger development effort.
cluster↗
An Examination of the Performance of Parallel Calculation of the Radiation Integral on a Beowulf-Class Computer
This paper uses the parallel calculation of the radiation integral for examination of performance and compiler issues on a Beowulf-class computer. This type of computer, built from mass-market, commodity, off-the-shelf components, has limited communications performance and therefore also has a limited regime of codes for which it is suitable.
Beowulf cluster pile of PCs parallel computation p↗
An Examination of the Performance of Two Electromagnetic Simulations on A Beowulf-Class Computer
This paper uses two electromagnetic simulations to examine some performance and compiler issues on a Beowulf-Class computer.
Beowulf-Class Computer cluster pile of PCs paralle↗
Pentium Pro inside: A treecode at 430 Gigaflops on ASCI Red - 1
As an entry for the 1997 Gordon Bell performance prize, we present results from two methods of solving the gravitational N-body problem on the Intel Teraflops system at Sandia National Laboratory (ASCI Red). The first method, an O(N2) algorithm, obtained 635 Gigaflops for a 1 million particle problem on 6800 Pentium Pro processors. The second solution method, a tree-code which scales as O(N log N), sustained 170 Gigaflops over a continuous 9.4 hour period on 4096 processors, integrating the motion of 322 million mutually interacting particles in a cosmology simulation, while saving over 100 Gigabytes of raw data. Additionally, the tree-code sustained 430 Gigaflops on 6800 processors for the first 5 time-steps of that simulation. This tree-code solution is approximately 105 times more efficient than the O(N2) algorithm for this problem. As an entry for the 1997 Gordon Bell price/performance prize, we present two calculations from the disciplines of astrophysics and fluid dynamics. The simulations were performed on two 16 Pentium Pro processor Beowulf-class computers (Loki and Hyglac) constructed entirely from commodity personal computer technology, at a cost of roughly $50k each in September, 1996. The price of an equivalent system in August 1997 is less than $30. At Los Alamos, Loki performed a gravitational tree-code N-body simulation of galaxy formation using 9.75 million particles, which sustained an average of 879 Mflops over a ten day period, and produced roughly 10 Gbytes of raw data.
Warren, M. S.↗