Active-Routing: Compute on the Way for Near-Data Processing
Authors:
- Jiayi HuangJHJiayi Huang
- Ramprakash Reddy PuliRPRamprakash Reddy Puli
- Pritam MajumderPMPritam Majumder
- Sungkeun KimSKSungkeun Kim
- Rahul BoyapatiRBRahul Boyapati
- Ki Hwan YumKYKi Hwan Yum
- Eun Jung KimEKEun Jung Kim
- 1 February 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 674-686
Abstract
The explosion of data availability and the demand for faster data analysis have led to the emergence of applications exhibiting large memory footprint and low data reuse rate. These workloads, ranging from neural networks to graph processing, expose compute kernels that operate over myriads of data. Significant data movement requirements of these kernels impose heavy stress on modern memory subsystems and communication fabrics. To mitigate the worsening gap between high CPU computation density and deficient memory bandwidth, solutions like memory networks and near-data processing designs are being architected to improve system performance substantially. In this work, we examine the idea of mapping compute kernels to the memory network so as to leverage in-network computing in data-flow style, by means of near-data processing. We propose Active-Routing, an in-network compute architecture that enables computation on the way for near-data processing by exploiting patterns of aggregation over intermediate results of arithmetic operators. The proposed architecture leverages the massive memory-level parallelism and network concurrency to optimize the aggregation operations along a dynamically built Active-Routing Tree. Our evaluations show that Active-Routing can achieve upto 7× speedup with an average of 60% performance improvement, and reduce the energy-delay product by 80% across various benchmarks compared to the state-of-the-art processing-in-memory architecture.Keywords
This publication has 34 references indexed in Scilit:
- PIM-enabled instructions2015
- A scalable processing-in-memory accelerator for parallel graph processing2015
- Active Memory Cube: A processing-in-memory architecture for exascale systemsIBM Journal of Research and Development, 2015
- NDA: Near-DRAM acceleration architecture leveraging commodity DRAM devices and standard memory modules2015
- NDC: Analyzing the impact of 3D-stacked memory+logic devices on MapReduce workloads2014
- 25.2 A 1.2V 8Gb 8-channel 128GB/s high-bandwidth memory (HBM) stacked DRAM with effective microbump I/O test methods using 29nm process and TSV2014
- McSimA+: A manycore simulator with application-level+ simulation and detailed microarchitecture modeling2013
- Active Messages: A Mechanism for Integrated Communication and Computation2005
- Pin2005
- Global reduction in wormhole k-ary n-cube networks with multidestination exchange worms2002