Search Results - "Kannan, Sudarsun"
-
1
Optimizing Checkpoints Using NVM as Virtual Memory
Published in 2013 IEEE 27th International Symposium on Parallel and Distributed Processing (01-05-2013)“…Rapid checkpointing will remain key functionality for next generation high end machines. This paper explores the use of node-local nonvolatile memories (NVM)…”
Get full text
Conference Proceeding -
2
HeteroOS - OS design for heterogeneous memory management in datacenter
Published in 2017 ACM/IEEE 44th Annual International Symposium on Computer Architecture (ISCA) (01-06-2017)“…Heterogeneous memory management combined with server virtualization in datacenters is expected to increase the software and OS management complexity…”
Get full text
Conference Proceeding -
3
Mosaic Pages: Big TLB Reach With Small Pages
Published in IEEE MICRO (01-07-2024)“…This article introduces mosaic pages, which increase translation lookaside buffer (TLB) reach by compressing multiple, discrete translations into one TLB…”
Get full text
Journal Article -
4
Energy aware persistence: Reducing energy overheads of memory-based persistence in NVMs
Published in 2016 International Conference on Parallel Architecture and Compilation Techniques (PACT) (01-09-2016)“…Next generation byte addressable nonvolatile memories (NVMs) such as PCM, Memristor, and 3D X-Point are attractive solutions for mobile and other end-user…”
Get full text
Conference Proceeding -
5
Reducing the cost of persistence for nonvolatile heaps in end user devices
Published in 2014 IEEE 20th International Symposium on High Performance Computer Architecture (HPCA) (01-02-2014)“…This paper explores the performance implications of using future byte addressable non-volatile memory (NVM) like PCM in end client devices. We explore how to…”
Get full text
Conference Proceeding -
6
Energy Aware Persistence: Reducing the Energy Overheads of Persistent Memory
Published in IEEE computer architecture letters (01-07-2016)“…Next generation byte addressable nonvolatile memory (NVM) technologies like PCM are attractive for end-user devices as they offer memory scalability as well as…”
Get full text
Journal Article -
7
HeteroCheckpoint: Efficient Checkpointing for Accelerator-Based Systems
Published in 2014 44th Annual IEEE/IFIP International Conference on Dependable Systems and Networks (18-09-2014)“…Moving toward exascale, the number of GPUs in HPC machines is bound to increase, and applications will spend increasing amounts of time running on those GPU…”
Get full text
Conference Proceeding -
8
Cloud4Home -- Enhancing Data Services with @Home Clouds
Published in 2011 31st International Conference on Distributed Computing Systems (01-06-2011)“…Mobile devices, net books and laptops, and powerful home PCs are creating ever-growing computational capacity at the periphery of the Internet, and this…”
Get full text
Conference Proceeding -
9
Accelerating Filesystem Checking and Repair with pFSCK
Published 11-04-2020“…File system checking and recovery (C/R) tools play a pivotal role in increasing the reliability of storage software, identifying and correcting file system…”
Get full text
Journal Article -
10
Efficient Kernel Object Management for Tiered Memory Systems with KLOC
Published 09-04-2020“…Software-controlled heterogeneous memory systems have the potential to improve performance, efficiency, and cost tradeoffs in emerging systems. Delivering on…”
Get full text
Journal Article -
11
SCTuner: An Autotuner Addressing Dynamic I/O Needs on Supercomputer I/O Subsystems
Published in 2021 IEEE/ACM Sixth International Parallel Data Systems Workshop (PDSW) (01-11-2021)“…In high-performance computing (HPC), scientific applications often manage a massive amount of data using I/O libraries. These libraries provide convenient data…”
Get full text
Conference Proceeding -
12
Phoenix: Memory Speed HPC I/O with NVM
Published in 2016 IEEE 23rd International Conference on High Performance Computing (HiPC) (01-12-2016)“…In order to bridge the gap between the applications' I/O needs on future exascale platforms, and thecapabilities of conventional memory and storage…”
Get full text
Conference Proceeding -
13
Using Active NVRAM for Cloud I/O
Published in 2011 Sixth Open Cirrus Summit (01-10-2011)“…A well-known problem for large scale cloud applications is how to scale their I/O performance. While next generation storage class memories like phase change…”
Get full text
Conference Proceeding