TY - GEN
T1 - QCDOC:A 10 teraflops computer for tightly-coupled calculations
AU - Boyle, P. A.
AU - Chen, D.
AU - Christ, N. H.
AU - Clark, M.
AU - Cohen, S. D.
AU - Cristian, C.
AU - Dong, Z.
AU - Gara, A.
AU - Joo, B.
AU - Jung, C.
AU - Kim, C.
AU - Levkova, L.
AU - Liao, X.
AU - Liu, G.
AU - Mawhinney, R. D.
AU - Ohta, S.
AU - Petrov, K.
AU - Wettig, T.
AU - Yamaguchi, A.
PY - 2004
Y1 - 2004
N2 - Numerical simulations of the strong nuclear force, known as quantum chromodynamics or QCD, have proven to be a demanding, forefront problem in high-performance computing. In. this report, we describe a new computer, QCDOC (QCD On a Chip), designed for optimal price/performance in the study of QCD. QCDOC uses a six-dimensional, low-latencymesh network to connect processing nodes, each of which includes a single custom ASIC, designed by our collaboration and built by IBM, plus DDR SDRAM. Each node has a peak speed of 1 Gigaflops and two 12,288 node, 10+ Teraflops machines are to be completed in the fall of 2004. Currently, a 512 node machine is running, delivering eciencies as high as 45% of peak on the conjugate gradient solvers that dominate our calculations and a 4096-node machine with a cost of $1.6M is under construction. This should give us a price/performance less than $1 per sustained Megaflops.
AB - Numerical simulations of the strong nuclear force, known as quantum chromodynamics or QCD, have proven to be a demanding, forefront problem in high-performance computing. In. this report, we describe a new computer, QCDOC (QCD On a Chip), designed for optimal price/performance in the study of QCD. QCDOC uses a six-dimensional, low-latencymesh network to connect processing nodes, each of which includes a single custom ASIC, designed by our collaboration and built by IBM, plus DDR SDRAM. Each node has a peak speed of 1 Gigaflops and two 12,288 node, 10+ Teraflops machines are to be completed in the fall of 2004. Currently, a 512 node machine is running, delivering eciencies as high as 45% of peak on the conjugate gradient solvers that dominate our calculations and a 4096-node machine with a cost of $1.6M is under construction. This should give us a price/performance less than $1 per sustained Megaflops.
UR - https://www.scopus.com/pages/publications/23944508737
M3 - Conference contribution
AN - SCOPUS:23944508737
SN - 0769521533
T3 - IEEE/ACM SC2004 Conference, Proceedings
SP - 449
EP - 461
BT - IEEE/ACM SC2004 Conference - Bridging Communities, Proceedings
T2 - IEEE/ACM SC2004 Conference - Bridging Communities
Y2 - 6 November 2004 through 12 November 2004
ER -