학술논문
Anton 3: Twenty Microseconds of Molecular Dynamics Simulation Before Lunch
Document Type
Conference
Author
Shaw, D.E.; Adams, P.J.; Azaria, A.; Bank, J.A.; Batson, B.; Bell, A.; Bergdorf, M.; Bhatt, J.; Butts, J.A.; Correia, T.; Dirks, R.M.; Dror, R.O.; Eastwood, M.P.; Edwards, B.; Even, A.; Feldmann, P.; Fenn, M.; Fenton, C.H.; Forte, A.; Gagliardo, J.; Gill, G.; Gorlatova, M.; Greskamp, B.; Grossman, J.P.; Gullingsrud, J.; Harper, A.; Hasenplaugh, W.; Heily, M.; Heshmat, B.C.; Hunt, J.; Ierardi, D.J.; Iserovich, L.; Jackson, B.L.; Johnson, N.P.; Kirk, M.M.; Klepeis, J.L.; Kuskin, J.S.; Mackenzie, K.M.; Mader, R.J.; McGowen, R.; McLaughlin, A.; Moraes, M.A.; Nasr, M.H.; Nociolo, L.J.; O'Donnell, L.; Parker, A.; Peticolas, J.L.; Pocina, G.; Predescu, C.; Quan, T.; Salmon, J.K.; Schwink, C.; Shim, K.S.; Siddique, N.; Spengler, J.; Szalay, T.; Tabladillo, R.; Tartler, R.; Taube, A.G.; Theobald, M.; Towles, B.; Vick, W.; Wang, S.C.; Wazlowski, M.; Weingarten, M.J.; Williams, J.M.; Yuh, K.A.
Source
SC21: International Conference for High Performance Computing, Networking, Storage and Analysis High Performance Computing, Networking, Storage and Analysis, SC21: International Conference for. :1-11 Nov, 2021
Subject
Language
ISSN
2167-4337
Abstract
Anton 3 is the newest member in a family of supercomputers specially designed for atomic-level simulation of molecules relevant to biology (e.g., DNA, proteins, and drug molecules). Anton 3 achieves order-of-magnitude improvements in time-to-solution over its predecessor, Anton 2 (the current state of the art), and is over 100-fold faster than any other currently available supercomputer, thereby enabling broad new avenues of research on critical questions in biology and drug discovery. This speedup means that a 512-node Anton 3 simulates a million atoms at over 100 microseconds per day. Furthermore, Anton 3 attains this performance while consuming an order of magnitude less energy per simulated microsecond than any other machine. Like its predecessors, Anton 3 was designed from the ground up around a new custom chip to best exploit the capabilities offered by new technologies. We present here the main architectural and algorithmic developments that were necessary to achieve such significant advances.