@inproceedings{awan-mlhpc17, 
 author = {{A. A. Awan} and H. Subramoni and DK Panda},
 title = {{An In-depth Performance Characterization of CPU- and GPU-based DNN
     Training on Modern Architectures}},
 booktitle = {Proceedings of the Machine Learning on HPC Environments},
 series = {MLHPC'17},
 year = {2017},
 isbn = {978-1-4503-5137-9},
 location = {Denver, CO, USA},
 pages = {8:1--8:8},
 articleno = {8},
 numpages = {8},
 url = {http://doi.acm.org/10.1145/3146347.3146356},
 doi = {10.1145/3146347.3146356},
 acmid = {3146356},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {Caffe, Deep Learning, High-Performance Computing, Pascal Architecture, Unified Memory},
}

{"_id":"BHAwr7KMBinBLwu5x","bibbaseid":"aaawan-subramoni-panda-anindepthperformancecharacterizationofcpuandgpubaseddnntrainingonmodernarchitectures-2017","authorIDs":["5457e9b02abc8e9f370008a5","5d816b2ac7d992da01000199","5deec5e50ddb85de010001cf","5dfbfdf4b371afde01000041","5dfc6df34a82f3f201000015","5e018505aa04bede01000052","5e07dadaf1089ddf01000013","5e1aa6089da435de01000018","5e1bc251ce7a9bde0100002c","5e1f88fa08195af30100010a","5e27bd51328b80de01000058","5e3014617e0df1de01000075","5e35147c8c7375de010000a3","5e39e3b23687dddf01000116","5e3a5de81469e8de01000116","5e41c801e7c67ade0100009a","5e45e87bad0603df010001a2","5e4e36c91f1de5de010000af","5e54b109929495df010000a5","5e5eb9da2fd1fade010001d2","5e5ed74a8c261adf01000171","5e6351e1621aabde010000aa","7BiXPwoRaugCi3D96","DxYj85HjoDC5DfQFA","HJ2ZcB8Tmq3i9bCKp","HbnwZQWdHm86qf8ii","MxpjW9DbqtMQ3i6Bu","RMjrxtkcCGRcRccMW","RupBLgDh3seizbcLL","WPFHp8kNXyPgaNaWb","bvTpo9FahLJGkGnbz","izBtMz3tnBH2r6kTC","n9jo2u2e3ALjnhthr","tPryXKj6YtoP6GxKf","xBmfW8bJQ4J9t9kqz"],"author_short":["A. A. Awan","Subramoni, H.","Panda, D."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":[],"propositions":[],"lastnames":["A. A. Awan"],"suffixes":[]},{"firstnames":["H."],"propositions":[],"lastnames":["Subramoni"],"suffixes":[]},{"firstnames":["DK"],"propositions":[],"lastnames":["Panda"],"suffixes":[]}],"title":"An In-depth Performance Characterization of CPU- and GPU-based DNN Training on Modern Architectures","booktitle":"Proceedings of the Machine Learning on HPC Environments","series":"MLHPC'17","year":"2017","isbn":"978-1-4503-5137-9","location":"Denver, CO, USA","pages":"8:1–8:8","articleno":"8","numpages":"8","url":"http://doi.acm.org/10.1145/3146347.3146356","doi":"10.1145/3146347.3146356","acmid":"3146356","publisher":"ACM","address":"New York, NY, USA","keywords":"Caffe, Deep Learning, High-Performance Computing, Pascal Architecture, Unified Memory","bibtex":"@inproceedings{awan-mlhpc17, \n author = {{A. A. Awan} and H. Subramoni and DK Panda},\n title = {{An In-depth Performance Characterization of CPU- and GPU-based DNN\n Training on Modern Architectures}},\n booktitle = {Proceedings of the Machine Learning on HPC Environments},\n series = {MLHPC'17},\n year = {2017},\n isbn = {978-1-4503-5137-9},\n location = {Denver, CO, USA},\n pages = {8:1--8:8},\n articleno = {8},\n numpages = {8},\n url = {http://doi.acm.org/10.1145/3146347.3146356},\n doi = {10.1145/3146347.3146356},\n acmid = {3146356},\n publisher = {ACM},\n address = {New York, NY, USA},\n keywords = {Caffe, Deep Learning, High-Performance Computing, Pascal Architecture, Unified Memory},\n} \n\n","author_short":["A. A. Awan","Subramoni, H.","Panda, D."],"key":"awan-mlhpc17","id":"awan-mlhpc17","bibbaseid":"aaawan-subramoni-panda-anindepthperformancecharacterizationofcpuandgpubaseddnntrainingonmodernarchitectures-2017","role":"author","urls":{"Paper":"http://doi.acm.org/10.1145/3146347.3146356"},"keyword":["Caffe","Deep Learning","High-Performance Computing","Pascal Architecture","Unified Memory"],"metadata":{"authorlinks":{"panda, d":"https://awan-10.github.io/research.html"}},"downloads":0},"bibtype":"inproceedings","biburl":"https://awan-10.github.io/ammar.bib","creationDate":"2019-09-17T23:11:14.084Z","downloads":0,"keywords":["caffe","deep learning","high-performance computing","pascal architecture","unified memory"],"search_terms":["depth","performance","characterization","cpu","gpu","based","dnn","training","modern","architectures","a. a. awan","subramoni","panda"],"title":"An In-depth Performance Characterization of CPU- and GPU-based DNN Training on Modern Architectures","year":2017,"dataSources":["v2ZdBwojDzGkLGftq"]}