SciTech Connect

Title: Exascale Monte Carlo R&D

Exascale Monte Carlo R&D Overview of this presentation is (1) Exascale computing - different technologies, getting there; (2) high-performance proof-of-concept MCMini - features and results; and (3) OpenCL toolkit - Oatmeal (OpenCL Automatic Memory Allocation Library) - purpose and features. Despite driver issues, OpenCL seems like a good, hardware agnostic tool. MCMini demonstrates the possibility for GPGPU-based Monte Carlo methods - it shows great scaling for HPC application and algorithmic equivalence. Oatmeal provides a flexible framework to aid in the development of scientific OpenCL codes.
Authors:
Publication Date:
OSTI Identifier:1047104
Report Number(s):LA-UR-12-23349
TRN: US201216%%347
DOE Contract Number:AC52-06NA25396
Resource Type:Technical Report
Data Type:
Research Org:Los Alamos National Laboratory (LANL)
Sponsoring Org:DOE/LANL
Country of Publication:United States
Language:English
Subject: 97 MATHEMATICAL METHODS AND COMPUTING; 99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE; MONTE CARLO METHOD; COMPUTERS; COMPUTER CODES; PROGRAMMING