CPU/GPU Implementation of the SCAMP algorithm for computing the matrix profile





GitHub Stars



Last Commit

1yr ago









Travis Build Status Docker Build Status RTD Build Status

SCAMP: SCAlable Matrix Profile

Table of Contents

Overview \ Documentation \ Performance \ Python Module \ Run Using Docker \ Distributed Operation \ Reference


This is a GPU/CPU implementation of the SCAMP algorithm. SCAMP takes a time series as input and computes the matrix profile for a particular window size. You can read more at the Matrix Profile Homepage This is a much improved framework over GPU-STOMP which has the following additional features:

  • Tiling for large inputs
  • Computation in fp32, mixed fp32/fp64, or fp64 (double is recommended for most datasets, single precision will work for some)
  • fp32 version should get good performance on GeForce cards
  • AB joins (you can produce the matrix profile from 2 different time series)
  • Distributable (we use GCP but other cloud platforms can work) with verified scalability to billions of datapoints
  • More types of matrix profiles! See the Docs!
  • Extremely Efficient Implementation
  • Extensible to adding optimized versions of custom join operations.
  • Can compute joins with the CPU (Only enabled for double precision and does not support all-neighbors joins or distance matrix summaries yet)
  • Handles NaN input values. The matrix profile will be computed while excluding any subsequence with a NaN value
  • Python module: Use SCAMP in Python with pyscamp


SCAMP's documentation can be found at readthedocs.


SCAMP is extremely fast, especially on Tesla series GPUs. I belive this repository contains the fastest code in existance for computing the matrix profile. If you find a way to improve the speed of SCAMP, or compute matrix profiles any faster than SCAMP does, please let me know, I would be glad to point to your work and incorporate any improvements that can be made to SCAMP.

More details on the performance of SCAMP can be found in the documentation.

Python module

A source distribution for a python3 module using pybind11 is available on to install run:

# Python 3; python 2 can work but is unsupported
# cmake is required (if you don't have it you can pip install cmake)
pip install pyscamp

then you can use SCAMP in Python as follows:

import pyscamp as mp # Uses GPU if available and CUDA was available during the build

# Allows checking if pyscamp was built with CUDA and has GPU support
has_gpu_support = mp.gpu_supported()

# Self join
profile, index = mp.selfjoin(a, sublen)
# AB join using 4 threads, outtputing pearson correlation.
profile, index = mp.abjoin(a, b, sublen, pearson=True, threads=4)

More information and the API documentation for pyscamp is available on readthedocs

Run Using Docker

You can run SCAMP via nvidia-docker using the prebuilt image on dockerhub.

In order to expose the host GPUs nvidia-docker must be installed correctly. Please follow the directions provided on the nvidia-docker github page. The following example uses docker 19.03 functionality:

docker pull zpzim/scamp:latest
docker run --gpus all \
   --volume /path/to/host/input/data/directory:/data \
   --volume /path/to/host/output/directory:/output \
   zpzim/scamp:latest /SCAMP/build/SCAMP \
   --window=<window_size> --input_a_file_name=/data/<filename> \
   --output_a_file_name=/output/<mp_filename> \

Distributed Operation

We have a client/server architecture built using grpc. Tested on GKE but should be possible to get working on Amazon EKS as well.

For more information on how to use the scamp client and server, please take a look at the documentation


If you use SCAMP in your work, please reference the following paper:

Zimmerman, Zachary, et al. "Matrix Profile XIV: Scaling Time Series Motif Discovery with GPUs to Break a Quintillion Pairwise Comparisons a Day and Beyond." Proceedings of the ACM Symposium on Cloud Computing. 2019.

Rate & Review

Great Documentation0
Easy to Use0
Highly Customizable0
Bleeding Edge0
Responsive Maintainers0
Poor Documentation0
Hard to Use0
Unwelcoming Community0
No reviews found
Be the first to rate


No alternatives found


No tutorials found
Add a tutorial