{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:41:10Z","timestamp":1759333270648,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":97,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,4,4]],"date-time":"2019-04-04T00:00:00Z","timestamp":1554336000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Huawei"},{"name":"Google"},{"name":"Applica- tions Driving Architectures (ADA) Research Center by SRC and DARPA"},{"name":"Hewlett Packard Labs"},{"name":"Intel"},{"name":"VMware"},{"name":"AliBaba"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,4,4]]},"DOI":"10.1145\/3297663.3310305","type":"proceedings-article","created":{"date-parts":[[2019,4,5]],"date-time":"2019-04-05T13:27:26Z","timestamp":1554470846000},"page":"79-90","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":28,"title":["Analysis and Modeling of Collaborative Execution Strategies for Heterogeneous CPU-FPGA Architectures"],"prefix":"10.1145","author":[{"given":"Sitao","family":"Huang","sequence":"first","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Urbana, IL, USA"}]},{"given":"Li-Wen","family":"Chang","sequence":"additional","affiliation":[{"name":"Microsoft & University of Illinois at Urbana-Champaign, Bellevue, WA, USA"}]},{"given":"Izzat","family":"El Hajj","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Urbana, IL, USA"}]},{"given":"Simon","family":"Garcia de Gonzalo","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Urbana, IL, USA"}]},{"given":"Juan","family":"G\u00f3mez-Luna","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland"}]},{"given":"Sai Rahul","family":"Chalamalasetti","sequence":"additional","affiliation":[{"name":"Hewlett Packard Labs, Palo Alto, CA, USA"}]},{"given":"Mohamed","family":"El-Hadedy","sequence":"additional","affiliation":[{"name":"Cal Poly Pomona, Pomona, CA, USA"}]},{"given":"Dejan","family":"Milojicic","sequence":"additional","affiliation":[{"name":"Hewlett Packard Labs, Palo Alto, CA, USA"}]},{"given":"Onur","family":"Mutlu","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland"}]},{"given":"Deming","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Urbana, IL, USA"}]},{"given":"Wen-mei","family":"Hwu","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Urbana, IL, USA"}]}],"member":"320","published-online":{"date-parts":[[2019,4,4]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Top500 List","author":"Strohmaier Erich","year":"2018","unstructured":"Erich Strohmaier , Jack Dongarra , Simon Horst , and Martin Meuer . Top500 List June 2018 . Erich Strohmaier, Jack Dongarra, Simon Horst, and Martin Meuer. Top500 List June 2018."},{"key":"e_1_3_2_1_2_1","volume-title":"Green500 List","author":"Wu Feng","year":"2018","unstructured":"Feng Wu and Tom Scogland . Green500 List June 2018 . Feng Wu and Tom Scogland. Green500 List June 2018."},{"key":"e_1_3_2_1_3_1","unstructured":"RightScale. Rightscale 2018 state of the cloud report.  RightScale. Rightscale 2018 state of the cloud report."},{"volume-title":"Programming Guide","year":"2016","key":"e_1_3_2_1_4_1","unstructured":"Intel. Intel FPGA SDK for OpenCL . Programming Guide , October 2016 . Intel. Intel FPGA SDK for OpenCL. Programming Guide, October 2016."},{"key":"e_1_3_2_1_5_1","unstructured":"Xilinx. SDAccel Development Environment. https:\/\/www.xilinx.com\/products\/design-tools\/software-zone\/sdaccel.html.  Xilinx. SDAccel Development Environment. https:\/\/www.xilinx.com\/products\/design-tools\/software-zone\/sdaccel.html."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2847263.2847276"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2012.6189226"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2009.2013353"},{"key":"e_1_3_2_1_9_1","volume-title":"https:\/\/aws.amazon.com\/ec2\/instance-types\/f1\/","author":"Amazon","year":"2018","unstructured":"Amazon EC2 F1 instances. https:\/\/aws.amazon.com\/ec2\/instance-types\/f1\/ , 2018 . Amazon EC2 F1 instances. https:\/\/aws.amazon.com\/ec2\/instance-types\/f1\/, 2018."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.5555\/3195638.3195647"},{"key":"e_1_3_2_1_11_1","volume-title":"ISCA","author":"Putnam Andrew","year":"2014","unstructured":"Andrew Putnam , Adrian M. Caulfield , Eric S. Chung , Derek Chiou , Kypros Constantinides , John Demme , Hadi Esmaeilzadeh , Jeremy Fowers , Gopi Prashanth Gopal , Jan Gray , Michael Haselman , Scott Hauck , Stephen Heil , Amir Hormati , Joo-Young Kim , Sitaram Lanka , James Larus , Eric Peterson , Simon Pope , Aaron Smith , Jason Thong , Phillip Yi Xiao , and Doug Burger . A reconfigurable fabric for accelerating large-scale datacenter services . In ISCA , 2014 . Andrew Putnam, Adrian M. Caulfield, Eric S. Chung, Derek Chiou, Kypros Constantinides, John Demme, Hadi Esmaeilzadeh, Jeremy Fowers, Gopi Prashanth Gopal, Jan Gray, Michael Haselman, Scott Hauck, Stephen Heil, Amir Hormati, Joo-Young Kim, Sitaram Lanka, James Larus, Eric Peterson, Simon Pope, Aaron Smith, Jason Thong, Phillip Yi Xiao, and Doug Burger. A reconfigurable fabric for accelerating large-scale datacenter services. In ISCA, 2014."},{"key":"e_1_3_2_1_12_1","volume-title":"http:\/\/www-03.ibm.com\/press\/us\/en\/pressrelease\/47082.wss","author":"New","year":"2015","unstructured":"New OpenPOWER cloud boosts ecosystem for innovation and development. http:\/\/www-03.ibm.com\/press\/us\/en\/pressrelease\/47082.wss , 2015 . New OpenPOWER cloud boosts ecosystem for innovation and development. http:\/\/www-03.ibm.com\/press\/us\/en\/pressrelease\/47082.wss, 2015."},{"volume-title":"July","year":"2017","key":"e_1_3_2_1_13_1","unstructured":"Intel. Intel Deep Learning Inference Accelerator Product Specification and User's Guide. https:\/\/www.intel.com\/content\/dam\/support\/us\/en\/documents\/server-products\/server-accessories\/Intel_DLIA_UserGuide_1.0.pdf , July 2017 . Intel. Intel Deep Learning Inference Accelerator Product Specification and User's Guide. https:\/\/www.intel.com\/content\/dam\/support\/us\/en\/documents\/server-products\/server-accessories\/Intel_DLIA_UserGuide_1.0.pdf, July 2017."},{"key":"e_1_3_2_1_14_1","volume-title":"http:\/\/fortune.com\/2015\/11\/18\/intel-xeon-fpga-chips\/","author":"Intel's The","year":"2015","unstructured":"The first chip from Intel's Altera buy will be out in 2016. http:\/\/fortune.com\/2015\/11\/18\/intel-xeon-fpga-chips\/ , 2015 . The first chip from Intel's Altera buy will be out in 2016. http:\/\/fortune.com\/2015\/11\/18\/intel-xeon-fpga-chips\/, 2015."},{"key":"e_1_3_2_1_15_1","volume-title":"Microsoft Research","author":"Burger Doug","year":"2017","unstructured":"Doug Burger . Microsoft unveils Project Brainwave for real-time AI . Microsoft Research , 2017 . Doug Burger. Microsoft unveils Project Brainwave for real-time AI. Microsoft Research, 2017."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/FPT.2011.6132716"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.5555\/2060099.2060301"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021749"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.23919\/FPL.2017.8056833"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/HOTI.2010.24"},{"key":"e_1_3_2_1_21_1","first-page":"111","article-title":"Hypertransport i\/o link specification","volume":"1","author":"HyperTransport Technology Consortium et al","year":"2008","unstructured":"HyperTransport Technology Consortium et al . Hypertransport i\/o link specification . Revision , 1 : 111 -- 118 , 2008 . HyperTransport Technology Consortium et al. Hypertransport i\/o link specification. Revision, 1:111--118, 2008.","journal-title":"Revision"},{"key":"e_1_3_2_1_22_1","unstructured":"Altera. Accelerating High-Performance Computing With FPGAs. https:\/\/www.intel.com\/content\/dam\/www\/programmable\/us\/en\/pdfs\/literature\/wp\/wp-01029.pdf.  Altera. Accelerating High-Performance Computing With FPGAs. https:\/\/www.intel.com\/content\/dam\/www\/programmable\/us\/en\/pdfs\/literature\/wp\/wp-01029.pdf."},{"key":"e_1_3_2_1_23_1","unstructured":"Accelerator Coherency Port. http:\/\/infocenter.arm.com\/help\/index.jsp?topic=\/com.arm.doc.ddi0434a\/BABGHDHD.html.  Accelerator Coherency Port. http:\/\/infocenter.arm.com\/help\/index.jsp?topic=\/com.arm.doc.ddi0434a\/BABGHDHD.html."},{"key":"e_1_3_2_1_24_1","unstructured":"AXI Coherency Extensions. http:\/\/infocenter.arm.com\/help\/index.jsp?topic=\/com.arm.doc.ddi0438i\/BABIAFAJ.html.  AXI Coherency Extensions. http:\/\/infocenter.arm.com\/help\/index.jsp?topic=\/com.arm.doc.ddi0438i\/BABIAFAJ.html."},{"key":"e_1_3_2_1_25_1","unstructured":"Arm CoreLink Interconnect. https:\/\/developer.arm.com\/products\/system-ip\/corelink-interconnect.  Arm CoreLink Interconnect. https:\/\/developer.arm.com\/products\/system-ip\/corelink-interconnect."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1147\/JRD.2014.2380198"},{"key":"e_1_3_2_1_27_1","volume-title":"http:\/\/www.ccixconsortium.com","author":"Cache Coherent","year":"2016","unstructured":"Cache Coherent Interconnect for Accelerators (CCIX). http:\/\/www.ccixconsortium.com , 2016 . Cache Coherent Interconnect for Accelerators (CCIX). http:\/\/www.ccixconsortium.com, 2016."},{"key":"e_1_3_2_1_28_1","unstructured":"Xilinx. Zynq UltraScale  Xilinx. Zynq UltraScale"},{"key":"e_1_3_2_1_29_1","unstructured":"MPSoCs. White Paper June 2016.  MPSoCs. White Paper June 2016."},{"volume-title":"Altera's User-Customizable ARM-Based SoC","year":"2015","key":"e_1_3_2_1_30_1","unstructured":"Altera. Altera's User-Customizable ARM-Based SoC , 2015 . Altera. Altera's User-Customizable ARM-Based SoC, 2015."},{"key":"e_1_3_2_1_31_1","volume-title":"AMD and HP: Protocol enhancements for tightly coupled accelerators","author":"Hummel Mark","year":"2007","unstructured":"Mark Hummel , Mike Krause , and Douglas O'Flaherty . AMD and HP: Protocol enhancements for tightly coupled accelerators . 2007 . Mark Hummel, Mike Krause, and Douglas O'Flaherty. AMD and HP: Protocol enhancements for tightly coupled accelerators. 2007."},{"key":"e_1_3_2_1_32_1","series-title":"Preprint Series of the Engineering Mathematics and Computing Lab","volume-title":"Convey HC-1 -- the potential of FPGAs in numerical simulation","author":"Augustin Werner","year":"2010","unstructured":"Werner Augustin , Vincent Heuveline , and Jan-Philipp Weiss . Convey HC-1 -- the potential of FPGAs in numerical simulation . Preprint Series of the Engineering Mathematics and Computing Lab , (07), 2010 . Werner Augustin, Vincent Heuveline, and Jan-Philipp Weiss. Convey HC-1 -- the potential of FPGAs in numerical simulation. Preprint Series of the Engineering Mathematics and Computing Lab, (07), 2010."},{"key":"e_1_3_2_1_33_1","volume-title":"The Convey HC-2 computer. Architectural overview","author":"Computer Convey","year":"2012","unstructured":"Convey Computer . The Convey HC-2 computer. Architectural overview , 2012 . Convey Computer. The Convey HC-2 computer. Architectural overview, 2012."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2017.7975269"},{"volume-title":"DE5-Net User Manual","year":"2018","key":"e_1_3_2_1_35_1","unstructured":"Terasic. DE5-Net User Manual , 2018 . Terasic. DE5-Net User Manual, 2018."},{"volume-title":"Nallatech 510T Product Brief","year":"2018","key":"e_1_3_2_1_36_1","unstructured":"Nallatech. Nallatech 510T Product Brief , 2018 . Nallatech. Nallatech 510T Product Brief, 2018."},{"key":"e_1_3_2_1_37_1","unstructured":"Intel. Intel Stratix V FPGAs. https:\/\/www.intel.com\/content\/www\/us\/en\/products\/programmable\/fpga\/stratix-v.html.  Intel. Intel Stratix V FPGAs. https:\/\/www.intel.com\/content\/www\/us\/en\/products\/programmable\/fpga\/stratix-v.html."},{"key":"e_1_3_2_1_38_1","unstructured":"Intel. Intel Arria 10 FPGAs. https:\/\/www.intel.com\/content\/www\/us\/en\/products\/programmable\/fpga\/arria-10.html.  Intel. Intel Arria 10 FPGAs. https:\/\/www.intel.com\/content\/www\/us\/en\/products\/programmable\/fpga\/arria-10.html."},{"key":"e_1_3_2_1_39_1","unstructured":"Intel. Intel Xeon Processor E3--1240 v3. https:\/\/ark.intel.com\/products\/75055\/Intel-Xeon-Processor-E3--1240-v3--8M-Cache-3--40-GHz-.  Intel. Intel Xeon Processor E3--1240 v3. https:\/\/ark.intel.com\/products\/75055\/Intel-Xeon-Processor-E3--1240-v3--8M-Cache-3--40-GHz-."},{"key":"e_1_3_2_1_40_1","unstructured":"Intel. Intel Xeon Processor E5--2650 v3. https:\/\/ark.intel.com\/products\/81705\/Intel-Xeon-Processor-E5--2650-v3--25M-Cache-2--30-GHz-.  Intel. Intel Xeon Processor E5--2650 v3. https:\/\/ark.intel.com\/products\/81705\/Intel-Xeon-Processor-E5--2650-v3--25M-Cache-2--30-GHz-."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1986.4767851"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/358669.358692"},{"key":"e_1_3_2_1_43_1","volume-title":"PARCO","author":"G\u00f3mez-Luna Juan","year":"2011","unstructured":"Juan G\u00f3mez-Luna , Holger Endt , Walter Stechele , Jos\u00e9 Mar\u00eda Gonz\u00e1lez-Linares , Jos\u00e9 Ignacio Benavides , and Nicol\u00e1s Guil . Egomotion compensation and moving objects detection algorithm on GPU . In PARCO , 2011 . Juan G\u00f3mez-Luna, Holger Endt, Walter Stechele, Jos\u00e9 Mar\u00eda Gonz\u00e1lez-Linares, Jos\u00e9 Ignacio Benavides, and Nicol\u00e1s Guil. Egomotion compensation and moving objects detection algorithm on GPU. In PARCO, 2011."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10766-017-0506-1"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-012-0443-3"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2012.319"},{"key":"e_1_3_2_1_47_1","volume-title":"USENIX SECURITY","author":"Moscibroda T.","year":"2007","unstructured":"T. Moscibroda and O. Mutlu . Memory performance attacks: Denial of memory service in multi-core systems . In USENIX SECURITY , 2007 . T. Moscibroda and O. Mutlu. Memory performance attacks: Denial of memory service in multi-core systems. In USENIX SECURITY, 2007."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2007.40"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2013.6522356"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830803"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2010.51"},{"key":"e_1_3_2_1_52_1","volume-title":"HPCA","author":"Kim Y.","year":"2010","unstructured":"Y. Kim , D. Han , O. Mutlu , and M. Harchol-Balter . ATLAS: A scalable and high-performance scheduling algorithm for multiple memory controllers . In HPCA , 2010 . Y. Kim, D. Han, O. Mutlu, and M. Harchol-Balter. ATLAS: A scalable and high-performance scheduling algorithm for multiple memory controllers. In HPCA, 2010."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2008.7"},{"key":"e_1_3_2_1_54_1","volume-title":"The OpenCL specification. Version 2.0","author":"Khronos","year":"2015","unstructured":"Khronos group. The OpenCL specification. Version 2.0 , 2015 . Khronos group. The OpenCL specification. Version 2.0, 2015."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2015.40"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897937.2897972"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/2847263.2847269"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2016.21"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2016.61"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2016.117"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3174243.3174987"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3035954"},{"key":"e_1_3_2_1_63_1","unstructured":"Herman Schmit and Randy Huang. Dissecting Xeon  Herman Schmit and Randy Huang. Dissecting Xeon"},{"key":"e_1_3_2_1_64_1","volume-title":"ISLPED","author":"FPGA","year":"2016","unstructured":"FPGA : Why the integration of CPUs and FPGAs makes a power difference for the datacenter . In ISLPED , 2016 . FPGA: Why the integration of CPUs and FPGAs makes a power difference for the datacenter. In ISLPED, 2016."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056017"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.5555\/2648668.2648744"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/2744769.2744794"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/2847255"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/2791321.2791331"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1145\/2847263.2847343"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446058"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2016.7577351"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2016.7577329"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2015.2509972"},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1145\/1669112.1669121"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2016.7581262"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2016.7482093"},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1145\/2791321.2791326"},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1145\/3030207.3030244"},{"key":"e_1_3_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2017.8167781"},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2018.00034"},{"key":"e_1_3_2_1_83_1","volume-title":"W.-H. Chung, J.M. Gonz\u00e1lez-Linares, and N. Guil","author":"G\u00f3mez-Luna J.","year":"2016","unstructured":"J. G\u00f3mez-Luna , I.-J. Sung , A. J. L\u00e1zaro-Mu noz , W.-H. Chung, J.M. Gonz\u00e1lez-Linares, and N. Guil . Chapter 8 - Application use cases: Platform atomics. In Heterogeneous System Architecture . 2016 . J. G\u00f3mez-Luna, I.-J. Sung, A.J. L\u00e1zaro-Mu noz, W.-H. Chung, J.M. Gonz\u00e1lez-Linares, and N. Guil. Chapter 8 - Application use cases: Platform atomics. In Heterogeneous System Architecture. 2016."},{"key":"e_1_3_2_1_84_1","volume-title":"Heterogeneous System Architecture: A New Compute Platform Infrastructure","author":"Hwu W.","year":"2015","unstructured":"Wen-mei W. Hwu . Heterogeneous System Architecture: A New Compute Platform Infrastructure . 2015 . Wen-mei W. Hwu. Heterogeneous System Architecture: A New Compute Platform Infrastructure. 2015."},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1145\/3075564.3075567"},{"key":"e_1_3_2_1_86_1","volume-title":"SC","author":"Tang Shanjiang","year":"2016","unstructured":"Shanjiang Tang , BingSheng He , Shuhao Zhang , and Zhaojie Niu . Elastic multi-resource fairness: balancing fairness and efficiency in coupled CPU-GPU architectures . In SC , 2016 . Shanjiang Tang, BingSheng He, Shuhao Zhang, and Zhaojie Niu. Elastic multi-resource fairness: balancing fairness and efficiency in coupled CPU-GPU architectures. In SC, 2016."},{"key":"e_1_3_2_1_87_1","doi-asserted-by":"publisher","DOI":"10.5555\/3049832.3049836"},{"key":"e_1_3_2_1_88_1","doi-asserted-by":"publisher","DOI":"10.1145\/3243176.3243210"},{"key":"e_1_3_2_1_89_1","volume-title":"DATE","author":"Baruah Trinayan","year":"2018","unstructured":"Trinayan Baruah , Yifan Sun , Shi Dong , David Kaeli , and Norm Rubin . Airavat : Improving energy efficiency of heterogeneous applications . In DATE , 2018 . Trinayan Baruah, Yifan Sun, Shi Dong, David Kaeli, and Norm Rubin. Airavat: Improving energy efficiency of heterogeneous applications. In DATE, 2018."},{"key":"e_1_3_2_1_90_1","volume-title":"Energy efficient execution of heterogeneous applications. Master thesis","author":"Baruah Trinayan","year":"2017","unstructured":"Trinayan Baruah . Energy efficient execution of heterogeneous applications. Master thesis . Northeastern University , 2017 . Trinayan Baruah. Energy efficient execution of heterogeneous applications. Master thesis. Northeastern University, 2017."},{"key":"e_1_3_2_1_91_1","doi-asserted-by":"publisher","DOI":"10.1145\/3158641"},{"key":"e_1_3_2_1_92_1","volume-title":"IISWC","author":"Garcia-Flores V.","year":"2016","unstructured":"V. Garcia-Flores , J. G\u00f3mez-Luna , T. Grass , A. Rico , E. Ayguade , and A. J. Pe na. Evaluating the effect of last-level cache sharing on integrated GPU-CPU systems with heterogeneous applications . In IISWC , 2016 . V. Garcia-Flores, J. G\u00f3mez-Luna, T. Grass, A. Rico, E. Ayguade, and A. J. Pe na. Evaluating the effect of last-level cache sharing on integrated GPU-CPU systems with heterogeneous applications. In IISWC, 2016."},{"key":"e_1_3_2_1_93_1","volume-title":"ISCA","author":"Ausavarungnirun R.","year":"2012","unstructured":"R. Ausavarungnirun , K. Chang , L. Subramanian , G. Loh , and O. Mutlu . Staged Memory Scheduling: Achieving high performance and scalability in heterogeneous systems . In ISCA , 2012 . R. Ausavarungnirun, K. Chang, L. Subramanian, G. Loh, and O. Mutlu. Staged Memory Scheduling: Achieving high performance and scalability in heterogeneous systems. In ISCA, 2012."},{"key":"e_1_3_2_1_94_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.62"},{"key":"e_1_3_2_1_95_1","volume-title":"ICPP","author":"Garcia-Flores V.","year":"2017","unstructured":"V. Garcia-Flores , E. Ayguade , and A. J. Pe na. Efficient data sharing on heterogeneous systems . In ICPP , 2017 . V. Garcia-Flores, E. Ayguade, and A. J. Pe na. Efficient data sharing on heterogeneous systems. In ICPP, 2017."},{"key":"e_1_3_2_1_96_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00031"},{"key":"e_1_3_2_1_97_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00075"},{"key":"e_1_3_2_1_98_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2018.8573485"}],"event":{"name":"ICPE '19: Tenth ACM\/SPEC International Conference on Performance Engineering","sponsor":["SIGMETRICS ACM Special Interest Group on Measurement and Evaluation","SIGSOFT ACM Special Interest Group on Software Engineering"],"location":"Mumbai India","acronym":"ICPE '19"},"container-title":["Proceedings of the 2019 ACM\/SPEC International Conference on Performance Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3297663.3310305","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3297663.3310305","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:54:10Z","timestamp":1750204450000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3297663.3310305"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,4,4]]},"references-count":97,"alternative-id":["10.1145\/3297663.3310305","10.1145\/3297663"],"URL":"https:\/\/doi.org\/10.1145\/3297663.3310305","relation":{},"subject":[],"published":{"date-parts":[[2019,4,4]]},"assertion":[{"value":"2019-04-04","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}