Difference between revisions of "FFTW"
Jump to navigation
Jump to search
Line 1: | Line 1: | ||
− | + | [[Category:Software]] | |
− | + | {|<!--CONFIGURATION: REQUIRED--> | |
− | < | + | |{{#vardefine:app|FFTW}} |
− | + | |{{#vardefine:url|http://http://www.fftw.org}} | |
− | + | <!--CONFIGURATION: OPTIONAL (1=ON)--> | |
+ | |{{#vardefine:mod|1}} <!--MODULES - NOW REQUIRED--> | ||
+ | |{{#vardefine:intel|}} <!-- "11.1" - Compiler Module Choice --> | ||
+ | |{{#vardefine:mpi|}} <!-- "openmpi/1.3.4"- MPI Module Choice --> | ||
+ | |{{#vardefine:exe|1}} <!--RUNNING --> | ||
+ | |{{#vardefine:conf|1}} <!--CONFIGS--> | ||
+ | |{{#vardefine:pbs|1}} <!--PBS SCRIPTS--> | ||
+ | |{{#vardefine:policy|1}} <!--POLICY--> | ||
+ | |{{#vardefine:testing|1}} <!--TESTING/PROFILING--> | ||
+ | |{{#vardefine:faq|1}} <!--FAQ--> | ||
+ | |{{#vardefine:citation|1}} <!--CITATION--> | ||
+ | |{{#vardefine:installation|1}} <!--INSTALLATION--> | ||
+ | |} | ||
+ | <!--BODY--> | ||
+ | <!--Description--> | ||
+ | {{#if: {{#var: url}}| | ||
+ | {{App_Description|app={{#var:app}}|url={{#var:url}}|name={{#var:app}}}}|}} | ||
+ | Fastest Fourier Transform in the West, is a C library for computing the Discrete Fourier Transform (DFT) in one or more dimensions, of arbitrary input size, and of both real and complex data. Developed at MIT, it is by far the fastest implementation of FFT algorithm (upheld by regular benchmarks.) | ||
− | == | + | <!--Modules--> |
− | + | ==Required Modules== | |
+ | [[Modules|Modules documentation]] | ||
+ | *intel | ||
+ | *fftw | ||
+ | <!--Configuration--> | ||
+ | {{#if: {{#var: conf}}|==Configuration== | ||
+ | ./configure --prefix=/apps/fftw/3.3.2 --enable-shared --enable-sse2 | ||
+ | |}} | ||
+ | <!--Run--> | ||
+ | <!--Citation--> | ||
− | + | <!--Turn the Table of Contents and Edit paragraph links ON/OFF--> | |
− | + | __NOTOC____NOEDITSECTION__ | |
− |
Revision as of 20:40, 10 August 2012
Description
FFTW website
Fastest Fourier Transform in the West, is a C library for computing the Discrete Fourier Transform (DFT) in one or more dimensions, of arbitrary input size, and of both real and complex data. Developed at MIT, it is by far the fastest implementation of FFT algorithm (upheld by regular benchmarks.)
Required Modules
- intel
- fftw
Configuration
./configure --prefix=/apps/fftw/3.3.2 --enable-shared --enable-sse2