Amith R. Mamidala

34 papers A* 1A 9B 5C 3Misc 1Journal 8Unranked 7

Year	Rank	Type	Title / Venue / Authors
2024	A*	`conf`	Collage: Light-Weight Low-Precision Strategy for LLM Training. ICML Tao Yu, Gaurav Gupta, Karthick Gopalswamy, Amith R. Mamidala, Hao Zhou, Jeffrey Huynh, Youngsuk Park, Ron Diamant, Anoop Deoras, Luke Huan
2024	J	`jnl`	Collage: Light-Weight Low-Precision Strategy for LLM Training. CoRR Tao Yu, Gaurav Gupta, Karthick Gopalswamy, Amith R. Mamidala, Hao Zhou, Jeffrey Huynh, Youngsuk Park, Ron Diamant, Anoop Deoras, Luke Huan
2018	J	`jnl`	Efficient Embedding of MPI Collectives in MXNET DAGs for scaling Deep Learning. CoRR Amith R. Mamidala
2018	J	`jnl`	MXNET-MPI: Embedding MPI parallelism in Parameter Server Task Model for scaling Deep Learning. CoRR Amith R. Mamidala, Georgios Kollias, Chris Ward, Fausto Artico
2016	C	`conf`	Optimization of Message Passing Services on POWER8 InfiniBand Clusters. EuroMPI Sameer Kumar, Robert Blackmore, Sameh Sharkawi, K. A. Nysal Jan, Amith R. Mamidala, T. J. Chris Ward
2014	J	`jnl`	Optimization of MPI collective operations on the IBM Blue Gene/Q supercomputer. Int. J. High Perform. Comput. Appl. Sameer Kumar, Amith R. Mamidala, Philip Heidelberger, Dong Chen, Daniel Faraj
2013	J	`jnl`	IBM Blue Gene/Q system software stack. IBM J. Res. Dev. Kyung Dong Ryu, Todd Inglett, Ralph Bellofatto, Michael Blocksome, Thomas Gooding, Sameer Kumar, Amith R. Mamidala, Mark Megerian, Sam Miller, Mike Nelson, Bryan S. Rosenburg, Brian E. Smith, James Van Oosten, Amy Wang, Robert W. Wisniewski
2012	A	`conf`	Looking under the hood of the IBM blue gene/Q network. SC Dong Chen, Noel Eisley, Philip Heidelberger, Sameer Kumar, Amith R. Mamidala, Fabrizio Petrini, Robert M. Senger, Yutaka Sugawara, Robert Walkup, Burkhard D. Steinmacher-Burow, Anamitra R. Choudhury, Yogish Sabharwal, Swati Singhal, Jeffrey J. Parker
2012	A	`conf`	PAMI: A Parallel Active Message Interface for the Blue Gene/Q Supercomputer. IPDPS Sameer Kumar, Amith R. Mamidala, Daniel Faraj, Brian E. Smith, Michael Blocksome, Bob Cernohous, Douglas Miller, Jeff Parker, Joseph Ratterman, Philip Heidelberger, Dong Chen, Burkhard D. Steinmacher-Burow
2011	—	`conf`	Optimizing MPI Collectives Using Efficient Intra-node Communication Techniques over the Blue Gene/P Supercomputer. IPDPS Workshops Amith R. Mamidala, Daniel Faraj, Sameer Kumar, Douglas Miller, Michael Blocksome, Thomas Gooding, Philip Heidelberger, Gábor Dózsa
2010	J	`jnl`	Architecture of the Component Collective Messaging Interface. Int. J. High Perform. Comput. Appl. Sameer Kumar, Ahmad Faraj, Amith R. Mamidala, Brian E. Smith, Gábor Dózsa, Bob Cernohous, John A. Gunnels, Douglas Miller, Joseph Ratterman, Philip Heidelberger
2009	C	`conf`	Design alternatives for implementing fence synchronization in MPI-2 one-sided communication for InfiniBand clusters. CLUSTER Gopalakrishnan Santhanaraman, Tejus Gangadharappa, Sundeep Narravula, Amith R. Mamidala, Dhabaleswar K. Panda
2009	B	`conf`	Designing Efficient FTP Mechanisms for High Performance Data-Transfer over InfiniBand. ICPP Ping Lai, Hari Subramoni, Sundeep Narravula, Amith R. Mamidala, Dhabaleswar K. Panda
2009	—	`conf`	MPI Collective Communications on The Blue Gene/P Supercomputer: Algorithms and Optimizations. Hot Interconnects Ahmad Faraj, Sameer Kumar, Brian E. Smith, Amith R. Mamidala, John A. Gunnels
2009	A	`conf`	MPI collective communications on the blue gene/p supercomputer: algorithms and optimizations. ICS Ahmad Faraj, Sameer Kumar, Brian E. Smith, Amith R. Mamidala, John A. Gunnels, Philip Heidelberger
2009	J	`jnl`	Topology agnostic hot-spot avoidance with InfiniBand. Concurr. Comput. Pract. Exp. Abhinav Vishnu, Matthew J. Koop, Adam Moody, Amith R. Mamidala, Sundeep Narravula, Dhabaleswar K. Panda
2008	—	`conf`	Lock-Free Asynchronous Rendezvous Design for MPI Point-to-Point Communication. PVM/MPI Rahul Kumar, Amith R. Mamidala, Matthew J. Koop, Gopalakrishnan Santhanaraman, Dhabaleswar K. Panda
2008	B	`conf`	MPI Collectives on Modern Multicore Clusters: Performance Optimizations and Communication Characteristics. CCGRID Amith R. Mamidala, Rahul Kumar, Debraj De, Dhabaleswar K. Panda
2008	A	`conf`	Scaling alltoall collective on multi-core systems. IPDPS Rahul Kumar, Amith R. Mamidala, Dhabaleswar K. Panda
2007	A	`conf`	Automatic Path Migration over InfiniBand: Early Experiences. IPDPS Abhinav Vishnu, Amith R. Mamidala, Sundeep Narravula, Dhabaleswar K. Panda
2007	B	`conf`	High Performance MPI over iWARP: Early Experiences. ICPP Sundeep Narravula, Amith R. Mamidala, Abhinav Vishnu, Gopalakrishnan Santhanaraman, Dhabaleswar K. Panda
2007	B	`conf`	Hot-Spot Avoidance With Multi-Pathing Over InfiniBand: An MPI Perspective. CCGRID Abhinav Vishnu, Matthew J. Koop, Adam Moody, Amith R. Mamidala, Sundeep Narravula, Dhabaleswar K. Panda
2007	—	`conf`	MPI-2 One-Sided Usage and Implementation for Read Modify Write Operations: A Case Study with HPCC. PVM/MPI Gopalakrishnan Santhanaraman, Sundeep Narravula, Amith R. Mamidala, Dhabaleswar K. Panda
2007	B	`conf`	On using connection-oriented vs. connection-less transport for performance and scalability of collective and one-sided operations: trade-offs and impact. PPoPP Amith R. Mamidala, Sundeep Narravula, Abhinav Vishnu, Gopalakrishnan Santhanaraman, Dhabaleswar K. Panda
2006	A	`conf`	Efficient SMP-aware MPI-level broadcast over InfiniBand's hardware multicast. IPDPS Amith R. Mamidala, Lei Chai, Hyun-Wook Jin, Dhabaleswar K. Panda
2006	—	`conf`	Efficient Shared Memory and RDMA Based Design for MPI_Allgather over InfiniBand. PVM/MPI Amith R. Mamidala, Abhinav Vishnu, Dhabaleswar K. Panda
2006	A	`conf`	Scalable systems software - A software based approach for providing network fault tolerance in clusters with uDAPL interface: MPI level design and performance evaluation. SC Abhinav Vishnu, Prachi Gupta, Amith R. Mamidala, Dhabaleswar K. Panda
2005	—	`conf`	Efficient Hardware Multicast Group Management for Multiple MPI Communicators over InfiniBand. PVM/MPI Amith R. Mamidala, Hyun-Wook Jin, Dhabaleswar K. Panda
2005	J	`jnl`	Evaluating InfiniBand Performance with PCI Express. IEEE Micro Jiuxing Liu, Amith R. Mamidala, Abhinav Vishnu, Dhabaleswar K. Panda
2005	Misc	`conf`	High Performance RDMA Based All-to-All Broadcast for InfiniBand Clusters. HiPC Sayantan Sur, Uday Bondhugula, Amith R. Mamidala, Hyun-Wook Jin, Dhabaleswar K. Panda
2005	A	`conf`	Performance Modeling of Subnet Management on Fat Tree InfiniBand Networks using OpenSM. IPDPS Abhinav Vishnu, Amith R. Mamidala, Hyun-Wook Jin, Dhabaleswar K. Panda
2004	C	`conf`	Efficient Barrier and Allreduce on Infiniband clusters using multicast and adaptive algorithms. CLUSTER Amith R. Mamidala, Jiuxing Liu, Dhabaleswar K. Panda
2004	A	`conf`	Fast and Scalable MPI-Level Broadcast Using InfiniBand?s Hardware Multicast Support. IPDPS Jiuxing Liu, Amith R. Mamidala, Dhabaleswar K. Panda
2004	—	`conf`	Performance evaluation of InfiniBand with PCI Express. Hot Interconnects Jiuxing Liu, Amith R. Mamidala, Abhinav Vishnu, Dhabaleswar K. Panda