Title :
In-Memory Data Rearrangement for Irregular, Data-Intensive Computing
Author :
Lloyd, Scott ; Gokhale, Maya
Abstract :
The data rearrangement engine (DRE) performs in-memory data restructuring to accelerate irregular, data-intensive applications. An emulation on a field-programmable gate array shows how the DRE could improve speedup, memory bandwidth, and energy consumption on three representative benchmarks.
Keywords :
field programmable gate arrays; DRE; data rearrangement engine; energy consumption improvement; field-programmable gate array; in-memory data rearrangement; in-memory data restructuring; irregular-data-intensive application acceleration; memory bandwidth improvement; speedup improvement; Computer applications; Emulation; Field programmable gate arrays; Memory management; Stacked memory; 3D stacked memory; FPGA emulation; active memory; data rearrangement engine; data-intensive computing; irregular applications; processing in memory;
DOI :
10.1109/MC.2015.230
