Monte Carlo Radiative Heat Transfer Simulation on a Reconfigurable Computer

Abstract

Los Alamos National Laboratory, an affirmative actionlequal opportunity employer, is operated by the University of California for the US. Department of Energy under contract W-7405-ENG-36. By acceptance of this article, the publisher recognizes that the US. Government retains a nonexclusive, royalty-free license to publish or reproduce the published form of this contribution, or to allow others to do so, for U.S. Government purposes. Los Alamos National Laboratory requests that the publisher identify this article as work performed under the auspices of the US. Department of Energy. Los Alamos National Laboratory strongly supports academic freedom and a researcher's right to publish; as an institution, however, the Laboratory does not endorse the viewpoint of a publication or guarantee its technical correctness.

Optimizing Logarithmic Arithmetic on FPGAs

“…Radiative Monte Carlo Simulation: M. Gokhale et al [19] presents an acceleration of Monte Carlo radiative heat transfer simulation on FPGA, with FLP numbers. The simulation traces photons emitted from the surfaces of a 2-D enclosure.…”

“…Compared with the single-precision FLP design [19], our design doubles the throughput, uses 42% fewer HMULs, and has 16% smaller error in the photon counts, at the expense of consuming over three times more slices and an additional 49 BRAMs.…”

“…To compare the accuracy, we use 100-digit highprecision calculation of Maple to convert the LNS results into FLP values and evaluate the maximum and average errors. For the radiative Monte Carlo simulation, we compare with the FLP designs in [19]. As the design needs to communicate with software part that uses FLP, convertors from and to FLP numbers are included.…”

A Domain Specific Language for Reconfigurable Path-based Monte Carlo Simulations

“…FPGAs have previously been used for Monte-Carlo simulations [4,5,1,8], but these were all developed from scratch using application-specific HDL. An automated method for compiling simulations into hardware was described in [7], but the actual implementation steps were performed by hand.…”

Accelerating molecular dynamics simulations with configurable circuits

“…Probably for this reason, researchers have avoided applications that are "canonically" double precision floating point, including MD. Recent exceptions include [2,7].…”