Search Results - "Ganger, Gregory R."

TVARAK: Software-Managed Hardware Offload for Redundancy in Direct-Access NVM Storage by Kateja, Rajat, Beckmann, Nathan, Ganger, Gregory R.

“…Production storage systems complement device-level ECC (which covers media errors) with system-checksums and cross-device parity. This system-level redundancy…”
Get full text

Open Cirrus: A Global Cloud Computing Testbed by Avetisyan, Arutyun I, Campbell, Roy, Gupta, Indranil, Heath, Michael T, Ko, Steven Y, Ganger, Gregory R, Kozuch, Michael A, O'Hallaron, David, Kunze, Marcel, Kwan, Thomas T, Lai, Kevin, Lyons, Martha, Milojicic, Dejan S, Hing Yan Lee, Yeng Chai Soh, Ng Kwang Ming, Luke, Jing-Yuan, Han Namgoong

“…Open Cirrus is a cloud computing testbed that, unlike existing alternatives, federates distributed data centers. It aims to spur innovation in systems and…”
Get full text

Visualizing Request-Flow Comparison to Aid Performance Diagnosis in Distributed Systems by Sambasivan, Raja R., Shafer, Ilari, Mazurek, Michelle L., Ganger, Gregory R.

“…Distributed systems are complex to develop and administer, and performance problem diagnosis is particularly challenging. When performance degrades, the…”
Get full text

Compact Filters for Fast Online Data Partitioning by Zheng, Qing, Cranor, Charles D., Jain, Ankush, Ganger, Gregory R., Gibson, Garth A., Amvrosiadis, George, Settlemyer, Bradley W., Grider, Gary

“…We are approaching a point in time when it will be infeasible to catalog and query data after it has been generated. This trend has fueled research on in-situ…”
Get full text

Survivable information storage systems by Wylie, J.J., Bigrigg, M.W., Strunk, J.D., Ganger, G.R., Kiliccote, H., Khosla, P.K.

“…As society increasingly relies on digitally stored and accessed information, supporting the availability, integrity and confidentiality of this information is…”
Get full text

On IO Latency Prediction Accuracy and Automated Load Balancing in Consolidated VM Environments by Nemoto, Jun, Ganger, Gregory R.

“…Manually managing IO workloads and performance in consolidated VM environments is often difficult and error prone. Thus, automated IO workload (re) placement…”
Get full text

Disk arrays: high-performance, high-reliability storage subsystems by Ganger, G.R., Worthington, B.L., Hou, R.Y., Patt, Y.N.

“…As the performance of other system components continues to improve rapidly, storage subsystem performance becomes increasingly important. Storage subsystem…”
Get full text

Efficient Byzantine-tolerant erasure-coded storage by Goodson, G.R., Wylie, J.J., Ganger, G.R., Reiter, M.K.

“…This paper describes a decentralized consistency protocol for survivable storage that exploits local data versioning within each storage-node. Such versioning…”
Get full text

Dynamic quarantine of Internet worms by Wong, C., Chenxi Wang, Song, D., Bielski, S., Ganger, G.R.

“…If we limit the contact rate of worm traffic, can we alleviate and ultimately contain Internet worms? This paper sets out to answer this question…”
Get full text

PipeFill: Using GPUs During Bubbles in Pipeline-parallel LLM Training by Arfeen, Daiyaan, Zhang, Zhen, Fu, Xinwei, Ganger, Gregory R, Wang, Yida

“…Training Deep Neural Networks (DNNs) with billions of parameters generally involves pipeline-parallel (PP) execution. Unfortunately, PP model training can use…”
Get full text

Scheduling speculative tasks in a compute farm by Petrou, David, Gibson, Garth A., Ganger, Gregory R.

“…Users often behave speculatively, submitting work that initially they do not know is needed. Farm computing often consists of single node speculative tasks…”
Get full text

Vilamb: Low Overhead Asynchronous Redundancy for Direct Access NVM by Kateja, Rajat, Pavlo, Andy, Ganger, Gregory R

“…Vilamb provides efficient asynchronous systemredundancy for direct access (DAX) non-volatile memory (NVM) storage. Production storage deployments often use…”
Get full text

Zzyzx: Scalable fault tolerance through Byzantine locking by Hendricks, J, Sinnamohideen, S, Ganger, G R, Reiter, M K

“…Zzyzx is a Byzantine fault-tolerant replicated state machine protocol that outperforms prior approaches and provides near-linear throughput scaling. Using a…”
Get full text

Tvarak: Software-managed hardware offload for DAX NVM storage redundancy by Kateja, Rajat, Beckmann, Nathan, Ganger, Gregory R

“…Tvarak efficiently implements system-level redundancy for direct-access (DAX) NVM storage. Production storage systems complement device-level ECC (which covers…”
Get full text

Co-scheduling of Disk Head Time in Cluster-Based Storage by Wachs, M., Ganger, G.R.

“…Disk time slicing is a promising technique for storage performance insulation. To work with cluster based storage, however, time slices associated with striped…”
Get full text

GraphPipe: Improving Performance and Scalability of DNN Training with Graph Pipeline Parallelism by Jeon, Byungsoo, Wu, Mengdi, Cao, Shiyi, Kim, Sunghyun, Park, Sunghyun, Aggarwal, Neeraj, Unger, Colin, Arfeen, Daiyaan, Liao, Peiyuan, Miao, Xupeng, Alizadeh, Mohammad, Ganger, Gregory R, Chen, Tianqi, Jia, Zhihao

“…Deep neural networks (DNNs) continue to grow rapidly in size, making them infeasible to train on a single device. Pipeline parallelism is commonly used in…”
Get full text

DeltaFS: A Scalable No-Ground-Truth Filesystem For Massively-Parallel Computing by Zheng, Qing, Cranor, Charles D., Ganger, Gregory R., Gibson, Garth A., Amvrosiadis, George, Settlemyer, Bradley W., Grider, Gary A.

“…High-Performance Computing (HPC) is known for its use of massive concurrency. But it can be challenging for a parallel filesystem's control plane to utilize…”
Get full text

PACEMAKER: Avoiding HeART attacks in storage clusters with disk-adaptive redundancy by Kadekodi, Saurabh, Maturana, Francisco, Subramanya, Suhas Jayaram, Yang, Juncheng, Rashmi, K. V, Ganger, Gregory R

“…14th USENIX Symposium on Operating Systems Design and Implementation (OSDI), 2020, (pp. 369-385) Data redundancy provides resilience in large-scale storage…”
Get full text

Scaling Embedded In-Situ Indexing with DeltaFS by Zheng, Qing, Cranor, Charles D., Guo, Danhao, Ganger, Gregory R., Amvrosiadis, George, Gibson, Garth A., Settlemyer, Bradley W., Grider, Gary, Guo, Fan

“…Analysis of large-scale simulation output is a core element of scientific inquiry, but analysis queries may experience significant I/O overhead when the data…”
Get full text

MLtuner: System Support for Automatic Machine Learning Tuning by Cui, Henggang, Ganger, Gregory R, Gibbons, Phillip B

“…MLtuner automatically tunes settings for training tunables (such as the learning rate, the momentum, the mini-batch size, and the data staleness bound) that…”
Get full text