Abraham Addisie
ABSTRACT
Relying on efficient data analytics platforms is increasingly becoming crucial for both small and large scale datasets. While MapReduce implementations, such as Hadoop and Spark, were originally proposed for petascale processing in scale-out clusters, it has been noted that, today, most data centers processes operate on gigabyte-order or smaller datasets, which are best processed in single high-end scale-up machines. In this context, Phoenix++ is a highly optimized MapReduce framework available for chip-multiprocessor (CMP) scale-up machines. In this paper we observe that Phoenix++ suffers from an inefficient utilization of the memory subsystem, and a serialized execution of the MapReduce stages. To overcome these inefficiencies, we propose CASM, an architecture that equips each core in a CMP design with a dedicated instance of a specialized hardware unit (the CASM accelerators). These units collaborate to manage the key-value data structure and minimize both on- and off-chip communication costs. Our experimental evaluation on a 64-core design indicates that CASM provides more than a 4x speedup over the highly optimized Phoenix++ framework, while keeping area overhead at only 6%, and reducing energy demands by over 3.5x.
- Abraham Addisie, Hiwot Kassa, Opeoluwa Matthews, and Valeria Bertacco. 2018. Heterogeneous Memory Subsystem for Natural Graph Analytics. In Proc. IISWC.Google Scholar
Cross Ref
- Shaizeen Aga, Supreet Jeloka, Arun Subramaniyan, Satish Narayanasamy, David Blaauw, and Reetuparna Das. 2017. Compute caches. In Proc. HPCA.Google ScholarCross Ref
- Faraz Ahmad, Seyong Lee, Mithuna Thottethodi, and TN Vijaykumar. 2012. Puma: Purdue mapreduce benchmarks suite. (2012).Google Scholar
- Raja Appuswamy, Christos Gkantsidis, Dushyanth Narayanan, Orion Hodson, and Antony Rowstron. 2013. Scale-up vs scale-out for hadoop: Time to rethink?. In Proc. SOCC. Google ScholarDigital Library
- Nathan Beckmann and Daniel Sanchez. 2013. Jigsaw: Scalable software-defined caches. In Proc. PACT. Google ScholarDigital Library
- Nathan Binkert, Bradford Beckmann, Gabriel Black, Steven K Reinhardt, Ali Saidi, Arkaprava Basu, Joel Hestness, Derek R Hower, Tushar Krishna, Somayeh Sardashti, Rathijit Sen, Korey Sewell, Muhammad Shoaib, Nilay Vaish, Mark Hill, and David Wood. 2011. The gem5 simulator. ACM SIGARCH Computer Architecture News (2011). Google ScholarDigital Library
- Cheng-Tao Chu, Sang K Kim, Yi-An Lin, YuanYuan Yu, Gary Bradski, Kunle Olukotun, and Andrew Y Ng. 2007. Map-reduce for machine learning on multicore. In Advances in neural information processing systems. Google ScholarDigital Library
- Paolo Costa, Austin Donnelly, Antony Rowstron, and Greg O'Shea. 2012. Camdoop: Exploiting in-network aggregation for big data applications. In Proc. NSDI. Google ScholarDigital Library
- Jeffrey Dean and Sanjay Ghemawat. 2004. MapReduce: Simplified Data Processing on Large Clusters. In Proc. OSDI. Google ScholarDigital Library
- Karthi Duraisamy, Ryan Gary Kim, Wonje Choi, Guangshuo Liu, Partha Pratim Pande, Radu Marculescu, and Diana Marculescu. 2015. Energy efficient MapReduce with VFI-enabled multicore platforms. In Proc. DAC. Google ScholarDigital Library
- Wenbin Fang, Bingsheng He, Qiong Luo, and N.K. Govindaraju. 2011. Mars: Accelerating MapReduce with Graphics Processors. TPDS (2011). Google ScholarDigital Library
- Mingyu Gao, Grant Ayers, and Christos Kozyrakis. 2015. Practical near-data processing for in-memory analytics frameworks. In Proc. PACT. Google ScholarDigital Library
- Project Gutenberg. https:/www.gutenberg.org. Accessed: 2017-11-05.Google Scholar
- T. J. Ham, L. Wu, N. Sundaram, N. Satish, and M. Martonosi. 2016. Graphicionado: A high-performance and energy-efficient accelerator for graph analytics. In Proc. MICRO. Google ScholarDigital Library
- T. Hayes, O. Palomar, O. Unsal, A. Cristal, and M. Valero. 2016. Future Vector Microprocessor Extensions for Data Aggregations. In Proc. ISCA. Google ScholarDigital Library
- C. Kachris, G. Sirakoulis, and D. Soudris. 2014. A Reconfigurable MapReduce accelerator for multi-core all-programmable SoCs. In Proc. ISSOC.Google Scholar
- Andreas Klein. 2013. Stream ciphers. Springer. Google ScholarDigital Library
- Onur Kocberber, Boris Grot, Javier Picorel, Babak Falsafi, Kevin Lim, and Parthasarathy Ranganathan. 2013. Meet the walkers: Accelerating index traversals for in-memory databases. In Proc. MICRO. Google ScholarDigital Library
- Mian Lu, Yun Liang, Huynh Phung Huynh, Zhongliang Ong, Bingsheng He, and R.S.M. Goh. 2015. MrPhi: An Optimized MapReduce Framework on Intel Xeon Phi Coprocessors. Parallel and Distributed Systems, IEEE Transactions on 26, 11 (2015). Google ScholarDigital Library
- Z. Metreveli, N. Zeldovich, and M. F. Kaashoek. 2012. Cphash: A cache-partitioned hash table. In Proc. ACM SIGPLAN. Google ScholarDigital Library
- A. K. Mishra, E. Nurvitadhi, G. Venkatesh, J. Pearce, and D. Marr. 2017. Finegrained accelerators for sparse machine learning workloads. In Proc. ASP-DAC.Google Scholar
- Tony Nowatzki, Vinay Gangadhar, Newsha Ardalani, and Karthikeyan Sankaralingam. 2017. Stream-dataflow acceleration. In Proc. ISCA. Google ScholarDigital Library
- Colby Ranger, Ramanan Raghuraman, Arun Penmetsa, Gary Bradski, and Christos Kozyrakis. 2007. Evaluating MapReduce for multi-core and multiprocessor systems. In Proc. HPCA. Google ScholarDigital Library
- Yi Shan, Bo Wang, Jing Yan, Yu Wang, Ningyi Xu, and Huazhong Yang. 2010. FPMR: MapReduce framework on FPGA. In Proc. FPGA. Google ScholarDigital Library
- Justin Talbot, Richard M. Yoo, and Christos Kozyrakis. 2011. Phoenix++: Modular MapReduce for Shared-memory Systems. In Proc. MapReduce. Google ScholarDigital Library
- Tom White. 2012. Hadoop: The definitive guide. Google ScholarDigital Library
- Ahmad Yasin. 2014. A top-down method for performance analysis and counters architecture. In Proc. ISPASS,.Google ScholarCross Ref
- Richard M. Yoo, Anthony Romano, and Christos Kozyrakis. 2009. Phoenix Rebirth: Scalable MapReduce on a Large-scale Shared-memory System. In Proc. IISWC. Google ScholarDigital Library
- Taekyung Yoo, Minsub Yim, Ilgyun Jeong, Yunsu Lee, and Seung-Tae Chun. 2016. Performance evaluation of in-memory computing on scale-up and scale-out cluster. In Proc. ICUFN.Google Scholar
- Matei Zaharia, Mosharaf Chowdhury, Michael J Franklin, Scott Shenker, and Ion Stoica. 2010. Spark: Cluster computing with working sets. HotCloud (2010). Google ScholarDigital Library
- Zhi-Lin Zhao, Chang-Dong Wang, Yuan-Yu Wan, Zi-Wei Huang, and Jian-Huang Lai. 2015. Pipeline item-based collaborative filtering based on MapReduce. In Proc. BDCloud. Google ScholarDigital Library
Recommendations
Petascale computing with accelerators
PPoPP '09: Proceedings of the 14th ACM SIGPLAN symposium on Principles and practice of parallel programmingA trend is developing in high performance computing in which commodity processors are coupled to various types of computational accelerators. Such systems are commonly called hybrid systems. In this paper, we describe our experience developing an ...
Towards achieving performance portability using directives for accelerators
WACCPD '16: Proceedings of the Third International Workshop on Accelerator Programming Using DirectivesIn this paper we explore the performance portability of directives provided by OpenMP 4 and OpenACC to program various types of node architectures with attached accelerators, both self-hosted multicore and offload multicore/GPU. Our goal is to examine ...
Optimizing memory bandwidth exploitation for OpenVX applications on embedded many-core accelerators
In recent years, image processing has been a key application area for mobile and embedded computing platforms. In this context, many-core accelerators are a viable solution to efficiently execute highly parallel kernels. However, architectural ...
Comments