I work on the ML Performance team at Google. While a PhD student, I did some of the foundational work on the Matrix Profile.
SCAMP. The fastest way to compute matrix profiles on CPU and GPU!
196STOMPSelfJoin. GPU Implementation of the STOMP algorithm for computing the matrix profile
22MSplitGEMM. Large matrix multiplication in CUDA
17LAMP-ICDM2019. This is sample source code for the Learned Approximate Matrix Profile (LAMP)
2