A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Filters
Reliability-aware Garbage Collection for Hybrid HBM-DRAM Memories
2021
ACM Transactions on Architecture and Code Optimization (TACO)
Preserved Fulltext
This article proposes a new class of reliability-aware garbage collectors for hybrid HBM-DRAM systems that place hot and low-risk objects in HBM and the rest in DRAM. ...
Reliability-aware garbage collection opens up a new opportunity to manage emerging HBM-DRAM memories at fine granularity while requiring no extra hardware support and leaving the programming model unchanged ...
The Reliability-aware Garbage Collection for Hybrid HBM-DRAM Memories 10:3 remaining objects are placed in DRAM to utilize its large capacity. ...
doi:10.1145/3431803
fatcat:let3q6xgmrfv3kuldijuekh3a4
A Survey of Non-Volatile Main Memory Technologies: State-of-the-Arts, Practices, and Future Directions
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
They bring many research opportunities as well as challenges on system architectural designs, memory management in operating systems (OSes), and programming models for hybrid memory systems. ...
Non-Volatile Main Memories (NVMMs) have recently emerged as promising technologies for future memory systems. ...
Miss penalty aware cache replacement for hybrid memory systems. ...
arXiv:2010.04406v1
fatcat:jna5pb7lizhvllmhfle4yikife
Designing, Modeling, and Optimizing Data-Intensive Computing Systems
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Fifth, we propose Sibyl, the first reinforcement learning-based mechanism for data placement in hybrid storage systems. ...
The cost of moving data between the memory units and the compute units is a major contributor to the execution time and energy consumption of modern workloads in computing systems. ...
device (e.g., such as read/write latencies, the latency of garbage collection, queuing delays, and error handling latencies). ...
arXiv:2208.08886v1
fatcat:ledjwayl6jdbfmgp2i45vooore
Survey of Memory Management Techniques for HPC and Cloud Computing
2019
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
However, for this scenario to succeed in practice, resources, including memory, need to be allocated with a vision that includes both the application requirements and the current and future state of the ...
In this survey, challenges of memory management in HPC and Cloud Computing, different memory management systems and optimisation techniques to increase memory utilisation are discussed in detail. ...
The HBM-DRAM system was configured in flat (as an additional NUMA node), cache and hybrid mode. ...
doi:10.1109/access.2019.2954169
fatcat:hwtpltrdrffqdjdofhr3shjkla
Do OS abstractions make sense on FPGAs?
2020
USENIX Symposium on Operating Systems Design and Implementation
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Hybrid computing systems, consisting of a CPU server coupled with a Field-Programmable Gate Array (FPGA) for application acceleration, are today a common facility in datacenters and clouds. ...
Coyote supports secure spatial and temporal multiplexing of the FPGA between tenants, virtual memory, communication, and memory management inside a uniform execution environment. ...
We would like to thank Mohsen Ewaida, Zhenhao He and Amit Kulkarni for some of the use cases and designs, David Sidler for feedback and help with the network stack, the anonymous reviewers for their helpful ...
dblp:conf/osdi/KorolijaRA20
fatcat:qpwo6kurj5ddbot6dn7lwdbjly
Continual Learning Approach for Improving the Data and Computation Mapping in Near-Memory Processing System
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Along with NMP and memory system development, the mapping for placing data and guiding computation in the memory-cube network has become crucial in driving the performance improvement in NMP. ...
To meet the bandwidth and capacity demands of memory-centric computing, 3D memory has been adopted to form a scalable memory-cube network. ...
Consequently, 3D-stacked memory cubes such as the hybrid memory cube (HMC) [3] and high bandwidth memory (HBM) [4] were invented to provide high bandwidth that suffices the tremendous bandwidth requirement ...
arXiv:2104.13671v1
fatcat:fe2slbojkndufibfikgxpajqqe
Energy Efficient Computing Systems: Architectures, Abstractions and Modeling to Techniques and Standards
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We have now entered the era of domain-specific architectures for new workloads like AI and ML. ...
Many research surveys have covered different aspects of techniques in hardware and microarchitecture across devices, servers, HPC, data center systems along with software, algorithms, frameworks for energy ...
, garbage collection, threads and some aspects of the operating system. ...
arXiv:2007.09976v2
fatcat:enrfj2qgerhyteapwykxcb5pni
Practical Mechanisms for Reducing Processor–Memory Data Movement in Modern Workloads
2021
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
(3) redesigning applications aware of PIM capability. ...
Recent advances in memory design enable the opportunity for architects to avoid unnecessary datamovement by performing processing-in-memory (PIM), also known as near-data processing (NDP). ...
Examples of 3D-stacked DRAM available commercially include High-Bandwidth Memory (HBM) [186] , Wide I/O [189] , and the Hybrid Memory Cube (HMC) [174] . ...
doi:10.1184/r1/14642340
fatcat:qtxrwongbzcubh22ifkiwrtwpa
Data-intensive Systems on Modern Hardware : Leveraging Near-Data Processing to Counter the Growth of Data
2022
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Over the last decades, a tremendous change toward using information technology in almost every daily routine of our lives can be perceived in our society, entailing an incredible growth of data collected ...
At the same time, magneto-mechanical HDDs are being replaced by semiconductor storage such as SSDs, equipped with modern Non-Volatile Memories, like Flash, which yield significantly faster access latencies ...
(i.e. garbage collection, compaction). ...
doi:10.26083/tuprints-00023016
fatcat:mmp4keecc5hd7pcolbxif6tdu4
Dagstuhl Reports, Volume 11, Issue 6, July 2021, Complete Issue
[article]
2021
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
We further thank Jules Wulms for helping us collect the contributions and prepare this report. ...
We illustrate how the flexibility of prices is critical for our results. ...
Requirements for hybrid meetings -The participants need to be aware that it is a hybrid meeting, so as to adjust their expectation and behaviour. ...
doi:10.4230/dagrep.11.6
fatcat:4ojdxh5mknhx5op4bxxc7ypgna