An efficient PIM (processor-in-memory) architecture for motion estimation

Abstract

Motion estimation is the most time consuming stage of MPEG family encodings and it has been shown to absorb up to 90% of the total execution time of MPEG processing. Therefore, we propose a hardware/software co-design paradigm that uses a PIM module to efficiently execute motion estimation operations by reducing the memory access penalty caused by a large number of memory accesses.We segment the PIM module into small pieces so that each smaller piece can execute the operations in parallel. However, in order to execute the operations in parallel, there are critical overhead operations which involve replicating a huge amount of data to many of these smaller PIM modules. Not only do these replications require a large amount of additional memory accesses but also require calculations when generating addresses. Therefore, we also present an efficient data distribution mechanism to effectively support parallel executions among these smaller PIM modules.With our paradigm, the host processor can be relieved from computationally-intensive and data-intensive workloads of motion estimation. We observed a reduction of up to 2034 × of improvement in the number of memory accesses and a performance improvement of up to 439 × for the execution of motion estimation operations when using our computing paradigm.

A Logarithmic Time Method for Two’s Complementation

“…This is indeed true for applications which require to find the absolute value of signed binary numbers. For instance, motion estimation operations of MPEG encodings [9,10,15,17] require to find the absolute value of the difference (of pixel values) for each pixel position for each block comparison. Another example would be multipliers [2,8,13] that need to find the two's complement of the multiplicand for the negative encodings of Booth algorithms [2,3,13,14,18].…”

Multi-GPU based on multicriteria optimization for motion estimation system

“…When considering MPEG processing, motion estimation is acknowledged as the most time-consuming [1], creating up to 90% of the total execution time [2,3]. Additionally, motion estimation has several applications regarding multimedia scope as segmentation, extraction of 3D structure, pattern tracking, filtering, compression, and de-blurring.…”