English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
 Release HistoryDetailsSummary
  Automatic generation of CUDA code performing tensor manipulations using C++ expression templates

Lewis, A. G. M., & Pfeiffer, H. P. (in preparation). Automatic generation of CUDA code performing tensor manipulations using C++ expression templates.

Item is

 

show all hide all

Basic

show hide
Item Permalink: https://hdl.handle.net/21.11116/0000-0003-652B-C Version Permalink: https://hdl.handle.net/21.11116/0000-0003-652C-B
Genre: Paper

Files

show Files
hide Files
:
1804.10120.pdf (Preprint), 2MB
View   Save
File Permalink:
https://hdl.handle.net/21.11116/0000-0003-652D-A
Name:
1804.10120.pdf
Description:
File downloaded from arXiv at 2019-04-15 09:20
OA-Status:
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
View
Copyright Date:
-
Copyright Info:
-
License:
http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Locators

show

Creators

show
hide
 Creators:
Lewis, Adam G. M., Author
Pfeiffer, Harald P.1, Author           
Affiliations:
1Astrophysical and Cosmological Relativity, AEI-Golm, MPI for Gravitational Physics, Max Planck Society, ou_1933290              

Content

show
hide
Free keywords: Computer Science, Mathematical Software, cs.MS,General Relativity and Quantum Cosmology, gr-qc
 Abstract: We present a C++ library, TLoops, which uses a hierarchy of expression
templates to represent operations upon tensorial quantities in single lines of
C++ code that resemble analytic equations. These expressions may be run as-is,
but may also be used to emit equivalent low-level C or CUDA code, which either
performs the operations more quickly on the CPU, or allows them to be rapidly
ported to run on NVIDIA GPUs. We detail the expression template and C++-class
hierarchy that represents the expressions and which makes automatic
code-generation possible. We then present benchmarks of the expression-template
code, the automatically generated C code, and the automatically generated CUDA
code running on several generations of NVIDIA GPU.

Details

show
hide
Language(s):
 Dates: 2018-04-24
 Publication Status: Not specified
 Pages: 46 pages, 5 figures
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: arXiv: 1804.10120
URI: http://arxiv.org/abs/1804.10120
 Degree: -

Event

show

Legal Case

show

Project information

show

Source

show