{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T08:17:26Z","timestamp":1759133846012,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","license":[{"start":{"date-parts":[[2016,10,5]],"date-time":"2016-10-05T00:00:00Z","timestamp":1475625600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2016,10,5]]},"DOI":"10.1145\/2987550.2987569","type":"proceedings-article","created":{"date-parts":[[2016,9,21]],"date-time":"2016-09-21T12:42:53Z","timestamp":1474461773000},"page":"456-469","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":71,"title":["Programming and Runtime Support to Blaze FPGA Accelerator Deployment at Datacenter Scale"],"prefix":"10.1145","author":[{"given":"Muhuan","family":"Huang","sequence":"first","affiliation":[{"name":"University of California Los Angeles and Falcon Computing Solutions, Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Di","family":"Wu","sequence":"additional","affiliation":[{"name":"University of California Los Angeles and Falcon Computing Solutions, Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cody Hao","family":"Yu","sequence":"additional","affiliation":[{"name":"University of California Los Angeles"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenman","family":"Fang","sequence":"additional","affiliation":[{"name":"University of California Los Angeles"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matteo","family":"Interlandi","sequence":"additional","affiliation":[{"name":"University of California Los Angeles"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tyson","family":"Condie","sequence":"additional","affiliation":[{"name":"University of California Los Angeles"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jason","family":"Cong","sequence":"additional","affiliation":[{"name":"University of California Los Angeles"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2016,10,5]]},"reference":[{"unstructured":"Apache Hadoop. https:\/\/hadoop.apache.org. Accessed: 2016-05-24.  Apache Hadoop. https:\/\/hadoop.apache.org. Accessed: 2016-05-24.","key":"e_1_3_2_1_1_1"},{"unstructured":"Apache parquet. https:\/\/parquet.apache.org\/. Accessed: 2016-05-24.  Apache parquet. https:\/\/parquet.apache.org\/. Accessed: 2016-05-24.","key":"e_1_3_2_1_2_1"},{"unstructured":"Aparapi in amd developer website. http:\/\/developer.amd.com\/tools-and-sdks\/opencl-zone\/aparapi\/. Accessed: 2016-05-24.  Aparapi in amd developer website. http:\/\/developer.amd.com\/tools-and-sdks\/opencl-zone\/aparapi\/. Accessed: 2016-05-24.","key":"e_1_3_2_1_3_1"},{"unstructured":"Facebook engineering (2012) under the hood: Scheduling mapreduce jobs more efficiently with corona. https:\/\/www.facebook.com\/notes\/facebook-engineering\/under-the-hood-scheduling-mapreduce-jobs-more-efficiently-with-corona\/10151142560538920. Accessed: 2016-01-30.  Facebook engineering (2012) under the hood: Scheduling mapreduce jobs more efficiently with corona. https:\/\/www.facebook.com\/notes\/facebook-engineering\/under-the-hood-scheduling-mapreduce-jobs-more-efficiently-with-corona\/10151142560538920. Accessed: 2016-01-30.","key":"e_1_3_2_1_4_1"},{"unstructured":"HTCondor. https:\/\/research.cs.wisc.edu\/htcondor. Accessed: 2016-05-24.  HTCondor. https:\/\/research.cs.wisc.edu\/htcondor. Accessed: 2016-05-24.","key":"e_1_3_2_1_5_1"},{"unstructured":"Intel to Start Shipping Xeons With FPGAs in Early 2016. http:\/\/www.eweek.com\/servers\/intel-to-start-shipping-xeons-with-fpgas-in-early-2016.html. Accessed: 2016-05-17.  Intel to Start Shipping Xeons With FPGAs in Early 2016. http:\/\/www.eweek.com\/servers\/intel-to-start-shipping-xeons-with-fpgas-in-early-2016.html. Accessed: 2016-05-17.","key":"e_1_3_2_1_6_1"},{"unstructured":"Large scale distributed deep learning on Hadoop clusters. http:\/\/yahoohadoop.tumblr.com\/post\/129872361846\/large-scale-distributed-deep-learning-on-hadoop. Accessed: 2016-05-24.  Large scale distributed deep learning on Hadoop clusters. http:\/\/yahoohadoop.tumblr.com\/post\/129872361846\/large-scale-distributed-deep-learning-on-hadoop. Accessed: 2016-05-24.","key":"e_1_3_2_1_7_1"},{"unstructured":"The MNIST database of handwritten digits. https:\/\/www.csie.ntu.edu.tw\/~cjlin\/libsvmtools\/datasets\/multiclass.html#mnist8m. Accessed: 2016-05-24.  The MNIST database of handwritten digits. https:\/\/www.csie.ntu.edu.tw\/~cjlin\/libsvmtools\/datasets\/multiclass.html#mnist8m. Accessed: 2016-05-24.","key":"e_1_3_2_1_8_1"},{"unstructured":"Project Tungsten: Bringing Apache Spark Closer to Bare Metal. https:\/\/databricks.com\/blog\/2015\/04\/28\/project-tungsten-bringing-spark-closer-to-bare-metal.html. Accessed: 2016-08-10.  Project Tungsten: Bringing Apache Spark Closer to Bare Metal. https:\/\/databricks.com\/blog\/2015\/04\/28\/project-tungsten-bringing-spark-closer-to-bare-metal.html. Accessed: 2016-08-10.","key":"e_1_3_2_1_9_1"},{"unstructured":"The snappy-java port. https:\/\/github.com\/xerial\/snappy-java. Accessed: 2016-08-01.  The snappy-java port. https:\/\/github.com\/xerial\/snappy-java. Accessed: 2016-08-01.","key":"e_1_3_2_1_10_1"},{"unstructured":"Spark MLlib. http:\/\/spark.apache.org\/mllib\/. Accessed: 2016-05-24.  Spark MLlib. http:\/\/spark.apache.org\/mllib\/. Accessed: 2016-05-24.","key":"e_1_3_2_1_11_1"},{"unstructured":"Xeon+FPGA Platform for the Data Center. https:\/\/www.ece.cmu.edu\/~calcm\/carl\/lib\/exe\/fetch.php?media=carl15-gupta.pdf. Accessed: 2016-05-17.  Xeon+FPGA Platform for the Data Center. https:\/\/www.ece.cmu.edu\/~calcm\/carl\/lib\/exe\/fetch.php?media=carl15-gupta.pdf. Accessed: 2016-05-17.","key":"e_1_3_2_1_12_1"},{"key":"e_1_3_2_1_13_1","volume-title":"IBM Data Engine for NoSQL - Power Systems Edition. Tech. rep","author":"Brech B.","year":"2015","unstructured":"Brech , B. , Rubio , J. , and Hollinger , M . IBM Data Engine for NoSQL - Power Systems Edition. Tech. rep ., IBM Systems Group , 2015 . Brech, B., Rubio, J., and Hollinger, M. IBM Data Engine for NoSQL - Power Systems Edition. Tech. rep., IBM Systems Group, 2015."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_14_1","DOI":"10.5555\/2650280.2650362"},{"key":"e_1_3_2_1_15_1","volume-title":"The 8th USENIX Workshop on Hot Topics in Cloud Computing (HotCloud 16)","author":"Chen Y.-T.","year":"2016","unstructured":"Chen , Y.-T. , Cong , J. , Fang , Z. , Lei , J. , and Wei ., P. When Apache Spark meets FPGAs: A case study for next-generation dna sequencing acceleration . In The 8th USENIX Workshop on Hot Topics in Cloud Computing (HotCloud 16) ( 2016 ). Chen, Y.-T., Cong, J., Fang, Z., Lei, J., and Wei., P. When Apache Spark meets FPGAs: A case study for next-generation dna sequencing acceleration. In The 8th USENIX Workshop on Hot Topics in Cloud Computing (HotCloud 16) (2016)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_16_1","DOI":"10.1109\/FCCM.2015.27"},{"key":"e_1_3_2_1_17_1","volume-title":"CS-BWAMEM: A fast and scalable read aligner at the cloud scale for whole genome sequencing. High Throughput Sequencing Algorithms and Applications (HITSEQ)","author":"Chen Y.-T.","year":"2015","unstructured":"Chen , Y.-T. , Cong , J. , Li , S. , Peto , M. , Spellman , P. , Wei , P. , and Zhou , P . CS-BWAMEM: A fast and scalable read aligner at the cloud scale for whole genome sequencing. High Throughput Sequencing Algorithms and Applications (HITSEQ) ( 2015 ). Chen, Y.-T., Cong, J., Li, S., Peto, M., Spellman, P., Wei, P., and Zhou, P. CS-BWAMEM: A fast and scalable read aligner at the cloud scale for whole genome sequencing. High Throughput Sequencing Algorithms and Applications (HITSEQ) (2015)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_18_1","DOI":"10.1145\/2897937.2905012"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_19_1","DOI":"10.1109\/TCAD.2011.2110592"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_20_1","DOI":"10.1145\/2600212.2600706"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_21_1","DOI":"10.1145\/2000064.2000108"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_22_1","DOI":"10.1109\/IPDPSW.2013.246"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_23_1","DOI":"10.1145\/2907294.2907307"},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the 8th USENIX Conference on Networked Systems Design and Implementation","author":"Hindman B.","year":"2011","unstructured":"Hindman , B. , Konwinski , A. , Zaharia , M. , Ghodsi , A. , Joseph , A. D. , Katz , R. , Shenker , S. , and Stoica , I . Mesos: A platform for fine-grained resource sharing in the data center . In Proceedings of the 8th USENIX Conference on Networked Systems Design and Implementation ( Berkeley, CA, USA , 2011 ), NSDI'11, USENIX Association, pp. 295--308. Hindman, B., Konwinski, A., Zaharia, M., Ghodsi, A., Joseph, A. D., Katz, R., Shenker, S., and Stoica, I. Mesos: A platform for fine-grained resource sharing in the data center. In Proceedings of the 8th USENIX Conference on Networked Systems Design and Implementation (Berkeley, CA, USA, 2011), NSDI'11, USENIX Association, pp. 295--308."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_25_1","DOI":"10.1145\/1854273.1854303"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_26_1","DOI":"10.1145\/1272998.1273005"},{"key":"e_1_3_2_1_27_1","volume-title":"Caffe: Convolutional architecture for fast feature embedding. arXiv preprint arXiv:1408.5093","author":"Jia Y.","year":"2014","unstructured":"Jia , Y. , Shelhamer , E. , Donahue , J. , Karayev , S. , Long , J. , Girshick , R. , Guadarrama , S. , and Darrell , T . Caffe: Convolutional architecture for fast feature embedding. arXiv preprint arXiv:1408.5093 ( 2014 ). Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., and Darrell, T. Caffe: Convolutional architecture for fast feature embedding. arXiv preprint arXiv:1408.5093 (2014)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_28_1","DOI":"10.1109\/TBCAS.2015.2389266"},{"key":"e_1_3_2_1_29_1","volume-title":"Aligning sequence reads, clone sequences and assembly contigs with BWA-MEM. arXiv preprint arXiv:1303.3997","author":"Li H.","year":"2013","unstructured":"Li , H. Aligning sequence reads, clone sequences and assembly contigs with BWA-MEM. arXiv preprint arXiv:1303.3997 ( 2013 ). Li, H. Aligning sequence reads, clone sequences and assembly contigs with BWA-MEM. arXiv preprint arXiv:1303.3997 (2013)."},{"key":"e_1_3_2_1_30_1","first-page":"347","volume-title":"Architecture and Storage (NAS), 2015 IEEE International Conference on (Aug","author":"Li P.","year":"2015","unstructured":"Li , P. , Luo , Y. , Zhang , N. , and Cao , Y . HeteroSpark: A heterogeneous CPU\/GPU spark platform for machine learning algorithms. In Networking , Architecture and Storage (NAS), 2015 IEEE International Conference on (Aug 2015 ), pp. 347 -- 348 . Li, P., Luo, Y., Zhang, N., and Cao, Y. HeteroSpark: A heterogeneous CPU\/GPU spark platform for machine learning algorithms. In Networking, Architecture and Storage (NAS), 2015 IEEE International Conference on (Aug 2015), pp. 347--348."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_31_1","DOI":"10.1109\/FPT.2013.6718411"},{"key":"e_1_3_2_1_32_1","first-page":"293","volume-title":"12th USENIX Symposium on Networked Systems Design and Implementation (NSDI 15)","author":"Ousterhout K.","year":"2015","unstructured":"Ousterhout , K. , Rasti , R. , Ratnasamy , S. , Shenker , S. , and Chun , B . -G. Making sense of performance in data analytics frameworks . In 12th USENIX Symposium on Networked Systems Design and Implementation (NSDI 15) (Oakland, CA, May 2015 ), USENIX Association , pp. 293 -- 307 . Ousterhout, K., Rasti, R., Ratnasamy, S., Shenker, S., and Chun, B.-G. Making sense of performance in data analytics frameworks. In 12th USENIX Symposium on Networked Systems Design and Implementation (NSDI 15) (Oakland, CA, May 2015), USENIX Association, pp. 293--307."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_33_1","DOI":"10.5555\/2665671.2665678"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_34_1","DOI":"10.1109\/HOTCHIPS.2011.7477495"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_35_1","DOI":"10.1145\/2517349.2522715"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_36_1","DOI":"10.1145\/2749246.2749261"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_37_1","DOI":"10.1145\/2465351.2465386"},{"key":"e_1_3_2_1_38_1","volume-title":"SparkCL: A unified programming framework for accelerators on heterogeneous clusters. CoRR abs\/1505.01120","author":"Segal O.","year":"2015","unstructured":"Segal , O. , Colangelo , P. , Nasiri , N. , Qian , Z. , and Margala , M . SparkCL: A unified programming framework for accelerators on heterogeneous clusters. CoRR abs\/1505.01120 ( 2015 ). Segal, O., Colangelo, P., Nasiri, N., Qian, Z., and Margala, M. SparkCL: A unified programming framework for accelerators on heterogeneous clusters. CoRR abs\/1505.01120 (2015)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_39_1","DOI":"10.1145\/1723112.1723129"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_40_1","DOI":"10.1109\/IPDPS.2011.102"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_41_1","DOI":"10.1145\/1723112.1723134"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_42_1","DOI":"10.1145\/2523616.2523633"},{"key":"e_1_3_2_1_43_1","first-page":"1","volume":"99","author":"Wang Z.","year":"2016","unstructured":"Wang , Z. , Zhang , S. , He , B. , and Zhang , W. Melia : A MapReduce framework on OpenCL-based FPGAs. IEEE Transactions on Parallel and Distributed Systems PP , 99 ( 2016 ), 1 -- 1 . Wang, Z., Zhang, S., He, B., and Zhang, W. Melia: A MapReduce framework on OpenCL-based FPGAs. IEEE Transactions on Parallel and Distributed Systems PP, 99 (2016), 1--1.","journal-title":"OpenCL-based FPGAs. IEEE Transactions on Parallel and Distributed Systems PP"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_44_1","DOI":"10.1109\/FCCM.2008.19"},{"key":"e_1_3_2_1_45_1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"280","DOI":"10.1007\/978-3-642-32686-8_26","volume-title":"-D. Scalable MapReduce framework on FPGA","author":"Yin D.","year":"2012","unstructured":"Yin , D. , Li , G. , and Huang , K . -D. Scalable MapReduce framework on FPGA . In Lecture Notes in Computer Science , S. Andreev, S. Balandin, and Y. Koucheryavy, Eds. Springer Berlin Heidelberg , 2012 , pp. 280 -- 294 . Yin, D., Li, G., and Huang, K.-D. Scalable MapReduce framework on FPGA. In Lecture Notes in Computer Science, S. Andreev, S. Balandin, and Y. Koucheryavy, Eds. Springer Berlin Heidelberg, 2012, pp. 280--294."},{"key":"e_1_3_2_1_46_1","first-page":"2","volume-title":"Proceedings of the 9th USENIX conference on Networked Systems Design and Implementation","author":"Zaharia M.","year":"2012","unstructured":"Zaharia , M. , Chowdhury , M. , Das , T. , Dave , A. , Ma , J. , McCauley , M. , Franklin , M. J. , Shenker , S. , and Stoica , I . Resilient distributed datasets: A fault-tolerant abstraction for in-memory cluster computing . In Proceedings of the 9th USENIX conference on Networked Systems Design and Implementation ( 2012 ), USENIX Association , pp. 2 -- 2 . Zaharia, M., Chowdhury, M., Das, T., Dave, A., Ma, J., McCauley, M., Franklin, M. J., Shenker, S., and Stoica, I. Resilient distributed datasets: A fault-tolerant abstraction for in-memory cluster computing. In Proceedings of the 9th USENIX conference on Networked Systems Design and Implementation (2012), USENIX Association, pp. 2--2."},{"key":"e_1_3_2_1_47_1","first-page":"10","volume-title":"Proceedings of the 2nd USENIX conference on Hot topics in cloud computing","author":"Zaharia M.","year":"2010","unstructured":"Zaharia , M. , Chowdhury , M. , Franklin , M. J. , Shenker , S. , and Stoica , I . Spark: Cluster computing with working sets . In Proceedings of the 2nd USENIX conference on Hot topics in cloud computing ( 2010 ), pp. 10 -- 10 . Zaharia, M., Chowdhury, M., Franklin, M. J., Shenker, S., and Stoica, I. Spark: Cluster computing with working sets. In Proceedings of the 2nd USENIX conference on Hot topics in cloud computing (2010), pp. 10--10."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_48_1","DOI":"10.1145\/2684746.2689060"}],"event":{"sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGOPS ACM Special Interest Group on Operating Systems"],"acronym":"SoCC '16","name":"SoCC '16: ACM Symposium on Cloud Computing","location":"Santa Clara CA USA"},"container-title":["Proceedings of the Seventh ACM Symposium on Cloud Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2987550.2987569","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2987550.2987569","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T03:40:06Z","timestamp":1750218006000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2987550.2987569"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,10,5]]},"references-count":48,"alternative-id":["10.1145\/2987550.2987569","10.1145\/2987550"],"URL":"https:\/\/doi.org\/10.1145\/2987550.2987569","relation":{},"subject":[],"published":{"date-parts":[[2016,10,5]]},"assertion":[{"value":"2016-10-05","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}