Runs the linpack benchmark on your system.
1.3K
Source is available on GitHub.
This repository contains an implementation of the Linpack benchmark obtained from netlib. It has been lightly modified to not expect any keyboard input.
To run the benchmark:
docker run -it --rm 0x000edd1e/linpack
It is possible to customize the array size use by the benchmark code (size is 200 by default). To do this, set an environment variable when running the container:
docker run -it --rm -e LINPACK_ARRAY_SIZE=600 0x000edd1e/linpack
Here are some sample results from my system with the default array size of 200:
$ docker run -it --rm 0x000edd1e/linpack
Memory required: 315K.
LINPACK benchmark, Double precision.
Machine precision: 15 digits.
Array size 200 X 200.
Average rolled and unrolled performance:
Reps Time(s) DGEFA DGESL OVERHEAD KFLOPS
----------------------------------------------------
2048 0.71 78.02% 2.89% 19.09% 4917805.960
4096 1.43 78.02% 2.88% 19.11% 4870465.484
8192 2.86 78.00% 2.87% 19.13% 4863107.385
16384 5.70 77.98% 2.87% 19.14% 4882638.725
32768 11.41 77.98% 2.87% 19.14% 4878150.976
Content type
Image
Digest
Size
406.5 MB
Last updated
almost 10 years ago
docker pull 0x000edd1e/linpack