.\" DO NOT MODIFY THIS FILE!  It was generated by help2man 1.47.17.
.TH PYFAI "1" "February 2021" "pyFAI benchmark version 0.20.0" "User Commands"
.SH NAME
pyFAI \- utility to run the benchmark for azimuthal integration on images of various sizes
.SH DESCRIPTION
usage: benchmark [options]
.PP
Benchmark for Azimuthal integration
.SS "optional arguments:"
.TP
\fB\-h\fR, \fB\-\-help\fR
show this help message and exit
.TP
\fB\-v\fR, \fB\-\-version\fR
show program's version number and exit
.TP
\fB\-d\fR, \fB\-\-debug\fR
switch to verbose/debug mode
.TP
\fB\-c\fR, \fB\-\-cpu\fR
perform benchmark using OpenCL on the CPU
.TP
\fB\-g\fR, \fB\-\-gpu\fR
perform benchmark using OpenCL on the GPU
.TP
\fB\-a\fR, \fB\-\-acc\fR
perform benchmark using OpenCL on the Accelerator
(like XeonPhi/MIC)
.TP
\fB\-s\fR SIZE, \fB\-\-size\fR SIZE
Limit the size of the dataset to X Mpixel images (for
computer with limited memory)
.TP
\fB\-n\fR NUMBER, \fB\-\-number\fR NUMBER
Number of repetition of the test (or time used for
each test), by default 10
.TP
\fB\-2d\fR, \fB\-\-2dimention\fR
Benchmark also algorithm for 2D\-regrouping
.TP
\fB\-\-no\-1dimention\fR
Do not benchmark algorithms for 1D\-regrouping
.TP
\fB\-m\fR, \fB\-\-memprof\fR
Perfrom memory profiling (Linux only)
.TP
\fB\-r\fR REPEAT, \fB\-\-repeat\fR REPEAT
Repeat each benchmark x times to take the best