Proceedings of the 3rd International Workshop on Runtime and Operating Systems for Supercomputers 2013
DOI: 10.1145/2491661.2481431
|View full text |Cite
|
Sign up to set email alerts
|

Transparently consistent asynchronous shared memory

Abstract: The advent of many-core processors is imposing many changes on the operating system. The resources that are under contention have changed; previously, CPU cycles were the resource in demand and required fair and precise sharing. Now compute cycles are plentiful, but the memory per core is decreasing. In the past, scientific applications used all the CPU cores to finish as fast as possible, with visualization and analysis of the data performed after the simulation finished. With decreasing memory available per … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
5
0

Year Published

2014
2014
2019
2019

Publication Types

Select...
6

Relationship

2
4

Authors

Journals

citations
Cited by 7 publications
(5 citation statements)
references
References 10 publications
0
5
0
Order By: Relevance
“…TCASM Transparently Consistent Asynchronous Shared Memory (TCASM) [1] is a shared memory based transport that allows a producer process, typically an HPC application, to share read-only data in situ with an observer process, typically analytics or checkpointing, without needing to rely on manual synchronization between the producing and observing process. TCASM is implemented using copy on write semantics: the producer registers a region of memory corresponding to its data and then exports a snapshot of that memory when it reaches a consistent state.…”
Section: Cross Enclave Communication In-frastructurementioning
confidence: 99%
See 1 more Smart Citation
“…TCASM Transparently Consistent Asynchronous Shared Memory (TCASM) [1] is a shared memory based transport that allows a producer process, typically an HPC application, to share read-only data in situ with an observer process, typically analytics or checkpointing, without needing to rely on manual synchronization between the producing and observing process. TCASM is implemented using copy on write semantics: the producer registers a region of memory corresponding to its data and then exports a snapshot of that memory when it reaches a consistent state.…”
Section: Cross Enclave Communication In-frastructurementioning
confidence: 99%
“…It creates no-op stub functions (e.g., functions which do no work and return) for the composition API in our composed applications to find a lower bound for performance. We then try a composed COW approach to composition on Linux using TCASM [1]. Finally we test measure against a "worst case" that uses spinlocks with no backo↵ to serialize the the computation and data exchange in SNAP and its analytics over an XPMEM [20].…”
Section: Composed Snapmentioning
confidence: 99%
“…Our approach provides the runtime provisioning of isolated enclave instances that can be customized to support each application component. Additionally, our approach allows application composition through the use of cross enclave shared memory segments through the XEMEM shared memory system [20], whose application interface can be accessed using existing I/O mechanisms such as ADIOS [24] or TCASM [5].…”
Section: The Hobbes Os/rmentioning
confidence: 99%
“…Memory (TCASM) [5] is a shared memory based transport that allows a producer process, typically an HPC application, to share read-only data in situ with an observer process, typically analytics or checkpointing, without needing to rely on manual synchronization between the producing and observing process. TCASM is implemented using copy on write semantics: the producer registers a region of memory corresponding to its data and then exports a snapshot of that memory when it reaches a consistent state.…”
Section: Tcasm Transparently Consistent Asynchronous Sharedmentioning
confidence: 99%
“…There are several projects that look at combining Linux functionality with an LWK. Kitten/Palacios, Fused OS, McKernel, and mOS are driven by anticipated usage models of future machines [20,4]. The projects differ in how they provide Linux functionality while achieving LWK performance and scalability.…”
Section: Next-generation Lwkmentioning
confidence: 99%