TY  - RPRT
TI  - An efficient tensor transpose algorithm for multicore CPU, Intel Xeon Phi, and NVidia Tesla GPU
AU  - Lyakh, Dmitry I.
PY  - 2015
DO  - 10.1016/j.cpc.2014.12.013
UR  - https://www.osti.gov/biblio/1185465
ID  - 1185465
ER  -