Simulations of Below-Ground Dynamics of Fungi: 1.184 Pflops Attained by Automated Generation and Autotuning of Temporal Blocking Codes
SessionACM Gordon Bell Finalist I
Session ChairSubhash Saini
Authors
Event Type
ACM Gordon Bell Finalist
Performance
Programming Systems
Scientific Computing
Location255-EF
DescriptionStencil computation has many applications in science and engineering, thus many optimization techniques such as temporal blocking have been developed. They are, however, rarely used in real-world applications, since a large amount of careful programming is required for even the simplest of stencils. We introduce Formura, a domain specific language that provides easy access to optimized stencil computations. Higher-order integration schemes can be defined using mathematical notations. Formura generates C code with MPI calls and performs autotuning. Hence its performance is portable to most distributed-memory computers. We show the scientific applicability of Formura by performing magnetohydrodynamics (MHD) and below-ground biology simulations. Ability to reach bytes-per-flops ratio only attainable by temporal blocking is demonstrated. We also demonstrate scaling up to the full nodes of the K computer, with 1.184 Pflops, 11.62% floating-point-operation efficiency, and 31.26% memory throughput efficiency.
Download PDF
Paper provided by the IEEE Computer SocietyPaper also available from the ACM Digital Library
Authors
Junichiro Makino (presenting)
Keigo Nitadori (presenting)
Masaki Iwasawa (presenting)
Natsuki Hosono (presenting)









