David Nellans ![](/sites/default/files/person/IMG_2133_Y5eqTgG.JPG) Dave Nellans joined NVIDIA in 2013 and leads the Architecture Research Group. Research Area(s) [Artificial Intelligence and Machine Learning ](/index.php/research-area/machine-learning-artificial-intelligence) [Computer Architecture](/index.php/research-area/computer-architecture) [High Performance Computing](/index.php/research-area/high-performance-computing) [Hyperscale Graphics](/index.php/research-area/hyperscale-graphics) [Programming Languages, Systems and Tools](/index.php/research-area/programming-languages-systems) [Storage and Systems](/index.php/research-area/storage-and-systems) Main Field of Interest [Computer Architecture](/index.php/research-area/computer-architecture) Google Scholar [https://scholar.google.com/citations?user=mjvx1GIAAAAJ&hl=en](https://scholar.google.com/citations?user=mjvx1GIAAAAJ&hl=en) ### Publications ### 2023 [Parsimony: Enabling SIMD/Vector Programming in Standard Compiler Flows](/publication/2023-02_parsimony-enabling-simdvector-programming-standard-compiler-flows) Vijay Kandiah, [Daniel Lustig](/person/daniel-lustig), Oreste Villa, [David Nellans](/person/david-nellans), Nikos Hardavellas [International Symposium on Code Generation and Optimization](https://dl.acm.org/doi/10.1145/3579990.3580019) ### 2022 [The Implications of Page Size Management on Graph Analytics](/publication/2022-11_implications-page-size-management-graph-analytics) Aninda Manocha, [Zi Yan](/person/zi-yan), Esin Tureci, Juan Luis Aragón, [David Nellans](/person/david-nellans), Margaret Martonosi [International Symposium on Workload Characterization (IISWC)](https://ieeexplore.ieee.org/document/9975438) ### 2021 [GPU Domain Specialization via Composable On-Package Architecture](/index.php/publication/2021-12_gpu-domain-specialization-composable-package-architecture) [Yaosheng Fu](/index.php/person/yaosheng-fu), Evgeny Bolotin, [Niladrish Chatterjee](/index.php/person/niladrish-chatterjee), [David Nellans](/index.php/person/david-nellans), [Steve Keckler](/index.php/person/stephen-keckler) [ACM Transactions on Architecture and Code Optimization (TACO)](https://dl.acm.org/doi/full/10.1145/3484505) [GPS: A Global Publish-Subscribe Model for Multi-GPU Memory Management](/publication/2021-10_gps-global-publish-subscribe-model-multi-gpu-memory-management) [Harini Muthukrishnan](/person/harini-muthukrishnan), [Daniel Lustig](/person/daniel-lustig), [David Nellans](/person/david-nellans), Thomas Wenisch [International Symposium on Microarchitecture (MICRO)](https://dl.acm.org/doi/10.1145/3466752.3480088) Best Paper nominee, IEEE Micro Top Picks in Computer Architecture (Honorable Mention) [Efficient Multi-GPU Shared Memory via Automatic Optimization of Fine-Grained Transfers](/publication/2021-06_efficient-multi-gpu-shared-memory-automatic-optimization-fine-grained-transfers) [Harini Muthukrishnan](/person/harini-muthukrishnan), [David Nellans](/person/david-nellans), [Daniel Lustig](/person/daniel-lustig), Jeffrey Fessler, Thomas Wenisch [International Symposium on Computer Architecture (ISCA)](https://ieeexplore.ieee.org/document/9499752) [GPU Domain Specialization via Composable On-Package Architecture](/publication/2021-04_gpu-domain-specialization-composable-package-architecture) [Yaosheng Fu](/person/yaosheng-fu), Evgeny Bolotin, [Niladrish Chatterjee](/person/niladrish-chatterjee), [David Nellans](/person/david-nellans), [Steve Keckler](/person/stephen-keckler) [arXiv](https://arxiv.org/abs/2104.02188) [Need for Speed: Experiences Building a Trustworthy System-Level GPU Simulator.](/publication/2021-02_need-speed-experiences-building-trustworthy-system-level-gpu-simulator) Oreste Villa, [Daniel Lustig](/person/daniel-lustig), [Zi Yan](/person/zi-yan), Evgeny Bolotin, [Yaosheng Fu](/person/yaosheng-fu), [Niladrish Chatterjee](/person/niladrish-chatterjee), [Ted Jiang](/person/ted-jiang), [David Nellans](/person/david-nellans) [International Symposium on High Performance Computer Architecture (HPCA)](https://doi.org/10.1109/HPCA51647.2021.00077) ### 2020 [The Architectural Implications of Distributed Reinforcement Learning on CPU-GPU Systems](/publication/2020-12_architectural-implications-distributed-reinforcement-learning-cpu-gpu-systems) Ahmet Inci, Evgeny Bolotin, [Yaosheng Fu](/person/yaosheng-fu), [Gal Dalal](/person/gal-dalal), [Shie Mannor](/person/shie-mannor), [David Nellans](/person/david-nellans), Diana Marculescu [Workshop on Energy Efficient Machine Learning and Cognitive Computing (EMC2)](https://www.emc2-ai.org/virtual-20) [Locality-Centric Data and Threadblock Management for Massive GPUs](/publication/2020-10_locality-centric-data-and-threadblock-management-massive-gpus) Mahmoud Khairy, Vadim Nikiforov, [David Nellans](/person/david-nellans), Timothy G. Rogers [International Symposium on Microarchitecture (MICRO)](https://ieeexplore.ieee.org/document/9251964) [Buddy Compression: Enabling Larger Memory for Deep Learning and HPC Workloads on GPUs](/publication/2020-06_buddy-compression-enabling-larger-memory-deep-learning-and-hpc-workloads-gpus) Esha Chouske, [Michael B. Sullivan](/person/mike-sullivan), [Mike O'Connor](/person/mike-o-connor), Mattan Erez, Jeff Pool, [David Nellans](/person/david-nellans), [Steve Keckler](/person/stephen-keckler) [International Symposium on Computer Architecture (ISCA)](https://ieeexplore.ieee.org/document/9138915) [HMG: Extending Cache Coherence Protocols Across Modern Hierarchical Multi-GPU Systems](/index.php/publication/2020-02_hmg-extending-cache-coherence-protocols-across-modern-hierarchical-multi-gpu) Xiaowei Ren, [Daniel Lustig](/index.php/person/daniel-lustig), Evgeny Bolotin, [Aamer Jaleel](/index.php/person/aamer-jaleel), Oreste Villa, [David Nellans](/index.php/person/david-nellans) [International Symposium on High Performance Computer Architecture (HPCA)](https://ieeexplore.ieee.org/document/9065597) ### 2019 [NVBit: A Dynamic Binary Instrumentation Framework for NVIDIA GPUs](/publication/2019-10_nvbit-dynamic-binary-instrumentation-framework-nvidia-gpus) Oreste Villa, [Mark Stephenson](/person/mark-stephenson), [David Nellans](/person/david-nellans), [Steve Keckler](/person/stephen-keckler) [International Symposium on Microarchitecture (MICRO)](https://doi.org/10.1145/3352460.3358307) [Optimizing Multi-GPU Parallelization Strategies for Deep Learning Training](/publication/2019-08_optimizing-multi-gpu-parallelization-strategies-deep-learning-training) Saptadeep Pal, Eiman Ebrahimi, Arslan Zulfiqar, [Yaosheng Fu](/person/yaosheng-fu), Victor Zhang, Szymon Migacz, [David Nellans](/person/david-nellans), Puneet Gupta [IEEE MICRO: Special Edition on Machine Learning Acceleration](https://ieeexplore.ieee.org/document/8805338) [Optimizing Multi-GPU Parallelization Strategies for Deep Learning Training](/publication/2019-07_optimizing-multi-gpu-parallelization-strategies-deep-learning-training) Saptadeep Pal, Eiman Ebrahimi, Arslan Zulfiqar, [Yaosheng Fu](/person/yaosheng-fu), Victor Zhang, Szymon Migacz, [David Nellans](/person/david-nellans), Puneet Gupta [arXiv](https://arxiv.org/abs/1907.13257) [Translation Ranger: Operating System Support for Contiguity-Aware TLBs](/index.php/publication/2019-06_translation-ranger-operating-system-support-contiguity-aware-tlbs) [Zi Yan](/index.php/person/zi-yan), [Daniel Lustig](/index.php/person/daniel-lustig), [David Nellans](/index.php/person/david-nellans), Abhishek Bhattacharjee [International Symposium on Computer Architecture (ISCA)](https://dl.acm.org/doi/10.1145/3307650.3322223) [Buddy Compression: Enabling Larger Memory for Deep Learning and HPC Workloads on GPUs](/publication/2019-04_buddy-compression-enabling-larger-memory-deep-learning-and-hpc-workloads-gpus) Esha Choukse, [Michael B. Sullivan](/person/mike-sullivan), [Mike O'Connor](/person/mike-o-connor), Mattan Erez, Jeff Pool, [David Nellans](/person/david-nellans), Stephen W. Keckler [arXiv](https://arxiv.org/abs/1903.02596) [Nimble Page Management for Tiered Memory Systems](/index.php/publication/2019-04_nimble-page-management-tiered-memory-systems) [Zi Yan](/index.php/person/zi-yan), [Daniel Lustig](/index.php/person/daniel-lustig), [David Nellans](/index.php/person/david-nellans), Abhishek Bhattacharjee [International Conference on Architectural Support for Programming Languages and…](https://dl.acm.org/doi/10.1145/3297858.3304024) [Understanding the Future of Energy Efficiency in Multi-Module GPUs.](/publication/2019-02_understanding-future-energy-efficiency-multi-module-gpus) Akhil Arunkumar, Evgeny Bolotin, [David Nellans](/person/david-nellans), Carole-Jean Wu [International Symposium on High Performance Computer Architecture (HPCA)](https://ieeexplore.ieee.org/document/8675192) ### 2018 [Combining HW/SW Mechanisms to Improve NUMA Performance of Multi-GPU Systems](/index.php/publication/2018-10_combining-hwsw-mechanisms-improve-numa-performance-multi-gpu-systems) Vinson Young, [Aamer Jaleel](/index.php/person/aamer-jaleel), Evgeny Bolotin, Eiman Ebrahimi, [David Nellans](/index.php/person/david-nellans), Oreste Villa [International Symposium on Microarchitecture (MICRO)](https://dl.acm.org/doi/10.1109/MICRO.2018.00035) ### 2017 [Beyond the Socket: NUMA-Aware GPUs](/index.php/publication/2017-10_beyond-socket-numa-aware-gpus) Ugljesa Milic, Oreste Villa, Evgeny Bolotin, Akhil Arunkumar, Eiman Ebrahimi, [Aamer Jaleel](/index.php/person/aamer-jaleel), Alex Ramirez, [David Nellans](/index.php/person/david-nellans) [International Symposium on Microarchitecture (MICRO)](https://dl.acm.org/citation.cfm?id=3124534) [MCM-GPU: Multi-Chip-Module GPUs for Continued Performance Scalability](/index.php/publication/2017-06_mcm-gpu-multi-chip-module-gpus-continued-performance-scalability) Akhil Arunkumar , Evgeny Bolotin, Benjamin Cho, Ugljesa Milic , Eiman Ebrahimi, Oreste Villa, [Aamer Jaleel](/index.php/person/aamer-jaleel), Carole-Jean Wu , [David Nellans](/index.php/person/david-nellans) [International Symposium on Computer Architecture (ISCA)](https://doi.org/10.1145/3079856.3080231) ### 2016 [Towards High Performance Paged Memory for GPUs](/publication/2016-03_towards-high-performance-paged-memory-gpus) Tianhao Zheng, [David Nellans](/person/david-nellans), Arslan Zulfiqar, [Mark Stephenson](/person/mark-stephenson), [Steve Keckler](/person/stephen-keckler) [International Symposium on High Performance Computer Architecture (HPCA)](https://ieeexplore.ieee.org/document/7446077) [Selective GPU Caches to Eliminate CPU-GPU HW Cache Coherence](/publication/2016-03_selective-gpu-caches-eliminate-cpu-gpu-hw-cache-coherence) Neha Agarwal, [David Nellans](/person/david-nellans), Eiman Ebrahimi, Thomas F. Wenisch, John Danskin, [Steve Keckler](/person/stephen-keckler) [ International Symposium on High Performance Computer Architecture (HPCA)](https://ieeexplore.ieee.org/document/7446089) ### 2015 [Designing Efficient Heterogeneous Memory Architectures](/index.php/publication/2015-08_designing-efficient-heterogeneous-memory-architectures) Evgeny Bolotin, [David Nellans](/index.php/person/david-nellans), Oreste Villa, [Mike O'Connor](/index.php/person/mike-o-connor), Alex Ramirez, [Steve Keckler](/index.php/person/stephen-keckler), [Mike O'Connor](/index.php/person/mike-o-connor) [IEEE Micro](https://ieeexplore.ieee.org/document/7155441) [Flexible Software Profiling of GPU Architectures](/publication/2015-06_flexible-software-profiling-gpu-architectures) [Mark Stephenson](/person/mark-stephenson), [Siva Hari](/person/siva-hari), Yunsup Lee, Eiman Ebrahimi, Daniel Johnson, [David Nellans](/person/david-nellans), [Mike O'Connor](/person/mike-o-connor), [Steve Keckler](/person/stephen-keckler) [International Symposium on Computer Architecture (ISCA)](https://dl.acm.org/doi/10.1145/2749469.2750375) [Page Placement Strategies for GPUs within Heterogeneous Memory Systems](/publication/2015-03_page-placement-strategies-gpus-within-heterogeneous-memory-systems) Neha Agarwal, [David Nellans](/person/david-nellans), [Mark Stephenson](/person/mark-stephenson), [Mike O'Connor](/person/mike-o-connor), [Steve Keckler](/person/stephen-keckler) [International Conference on Architectural Support for Programming Languages and…](http://dl.acm.org/citation.cfm?id=2694381) [Unlocking Bandwidth for GPUs in CC-NUMA systems](/publication/2015-02_unlocking-bandwidth-gpus-cc-numa-systems) Neha Agarwal, [David Nellans](/person/david-nellans), [Mike O'Connor](/person/mike-o-connor), [Steve Keckler](/person/stephen-keckler), Thomas Wenisch [International Symposium on High Performance Computer Architecture (HPCA)](http://ieeexplore.ieee.org/document/7056046/) ### 2014 [Scaling the Power Wall: A Path to Exascale](/publication/2014-11_scaling-power-wall-path-exascale) Oreste Villa, Daniel Johnson, [Mike O'Connor](/person/mike-o-connor), Evgeny Bolotin, [David Nellans](/person/david-nellans), Justin Luitjens, Nikolai Sakharnykh, Peng Wang, Paulius Micikevicius, Anthony Scudiero, [Steve Keckler](/person/stephen-keckler), [William Dally](/person/william-dally) [SC '14](http://ieeexplore.ieee.org/abstract/document/7013055/)