2 papers
cs.DC2020
Vyasa: A High-Performance Vectorizing Compiler for Tensor Convolutions on the Xilinx AI Engine
Prasanth Chatarasi, Stephen Neuendorffer, Samuel Bayliss +2
Xilinx's AI Engine is a recent industry example of energy-efficient vector processing that includes novel support for 2D SIMD datapaths and shuffle interconnection network. The cur…
cs.DC2014
ADHA: Automatic Data layout framework for Heterogeneous Architectures
Deepak Majeti, Kuldeep S. Meel, Rajkishore Barik +1
Data layouts play a crucial role in determining the performance of a given application running on a given architecture. Existing parallel programming frameworks for both multicore…