DeACT: Architecture-Aware Virtual Memory Support for Fabric Attached Memory Systems

Kommareddy, Vamsee Reddy; Hughes, Clayton; Hammond, Simon David; Awad, Amro

doi:10.1109/hpca51647.2021.00046

Cited by 7 publications

(4 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our evaluation of Āpta is driven by a simulator based methodology (similar to DM proposals [8], [44], [45]). We now set out the configuration parameters and workloads used in the simulation of such a system.…”

Section: B Evaluation Methodologymentioning

confidence: 99%

“…2 CXL uses Address Translation Services (ATS) defined in PCIe Specification for translation of cPA→mPA. The compute server OS sets the translation table base address register -ZMMU [26] or extended page table pointer [45]. 3 Other object cache allocation policies can be employed -e.g., fraction of LLC capacity per CPU, dynamically based on predictors of object hotness or reuse potential [64] etc.…”

Section: (A 1 ) Sharing Objects Between Faas Functions Through Dmmentioning

confidence: 99%

See 1 more Smart Citation

Āpta: Fault-tolerant object-granular CXL disaggregated memory for accelerating FaaS

Patil

Nagarajan

Nikoleris

et al. 2023

2023 53rd Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN)

View full text Add to dashboard Cite

As cloud workloads increasingly adopt the faulttolerant Function-as-a-Service (FaaS) model, demand for improved performance has increased. Alas, the performance of FaaS applications is heavily bottlenecked by the remote object store in which FaaS objects are maintained. We identify that the upcoming CXL-based cache-coherent disaggregated memory is a promising technology for maintaining FaaS objects. Our analysis indicates that CXL's low-latency, high-bandwidth access characteristics coupled with compute-side caching of objects, provides significant performance potential over an in-memory RDMA-based object store.We observe however that CXL lacks the requisite level of faulttolerance necessary to operate at an inter-server scale within the datacenter. Furthermore, its cache-line granular accesses impose inefficiencies for object-granular data store accesses.We propose Āpta, a CXL-based object-granular memory interface for maintaining FaaS objects. Āpta's key innovation is a novel fault-tolerant coherence protocol for keeping the cached objects consistent without compromising availability in the face of compute server failures. Our evaluation of Āpta using 6 full FaaS application workflows (totaling 26 functions) indicates that it outperforms a state-of-the-art fault-tolerant object caching protocol on an RDMA-based system by 21-90% and an uncached CXL-based system by 15-42%.

show abstract

Section: B Evaluation Methodologymentioning

confidence: 99%

Section: (A 1 ) Sharing Objects Between Faas Functions Through Dmmentioning

confidence: 99%

Āpta: Fault-tolerant object-granular CXL disaggregated memory for accelerating FaaS

Patil

Nagarajan

Nikoleris

et al. 2023

2023 53rd Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN)

View full text Add to dashboard Cite

show abstract

“…Locally attached memories to a CPU can act as a cache to the remote pool of memory. Given the promise of memory pooling, there is an increased interest in research on disaggregated memory systems recently [30], [24], [31], [32]. We anticipate more research in this direction in the near future.…”

Section: Related Workmentioning

confidence: 99%

Enabling Design Space Exploration of DRAM Caches in Emerging Memory Systems

Babaie¹,

Akram²,

Lowe-Power³

2023

Preprint

View full text Add to dashboard Cite

The increasing growth of applications' memory capacity and performance demands has led the CPU vendors to deploy heterogeneous memory systems either within a single system or via disaggregation. For instance, systems like Intel's Knights Landing and Sapphire Rapids can be configured to use high bandwidth memory as a cache to main memory. While there is significant research investigating the designs of DRAM caches, there has been little research investigating DRAM caches from a full system point of view, because there is not a suitable model available to the community to accurately study largescale systems with DRAM caches at a cycle-level. In this work we describe a new cycle-level DRAM cache model in the gem5 simulator which can be used for heterogeneous and disaggregated systems. We believe this model enables the community to perform a design space exploration for future generation of memory systems supporting DRAM caches.

show abstract

“…DeACT [89] also utilizes hardware changes, although this time for the purpose of providing a shared remote memory (as a resource, not data sharing) without manipulating or modifying virtual memory systems. The insight behind DeACT is that the tasks of remote address translation (translation from a fake physical address inside compute nodes to a real address in the remote memory node) and remote data access control are separate and need not be implemented together.…”

Section: D: Other Hardware Modificationsmentioning

confidence: 99%

Disaggregated Memory in the Datacenter: A Survey

Ewais

Chow

2023

IEEE Access

View full text Add to dashboard Cite

Datacenters of today have maintained the same architecture for decades. The building block of the datacenter remains the server, which tightly couples the necessary compute resources, memory, and storage to run its tasks. However, this traditional approach suffers from under-utilization of its resources, often caused by the over-provisioning of these resources when deploying applications. Datacenter operators allocate the worst-case amount of memory required for each deployed application, which lasts for the entirety of the application's lifetime, even when not actually used. This causes servers to quickly, and falsely, run out of memory before their CPUs have been fully utilized. To address these problems, a new shift in the way datacenters are being built has been gaining more traction. Namely, memory disaggregation. Memory disaggregation can address these problems by decoupling the computational elements from the memory resources, allowing each to be provisioned and utilized separately. While the idea of memory disaggregation is not new, an increasing number of different proposals of memory disaggregation have seen the light in recent years. In this paper, we review many of these recent proposals, and study their architectures, implementations, and requirements. We also categorize them based on their features, and attempt to identify their strengths and shortcomings in an effort to highlight possible directions for future work and provide a reference for the research community.

show abstract

DeACT: Architecture-Aware Virtual Memory Support for Fabric Attached Memory Systems

Cited by 7 publications

References 25 publications

Āpta: Fault-tolerant object-granular CXL disaggregated memory for accelerating FaaS

Āpta: Fault-tolerant object-granular CXL disaggregated memory for accelerating FaaS

Enabling Design Space Exploration of DRAM Caches in Emerging Memory Systems

Disaggregated Memory in the Datacenter: A Survey

Contact Info

Product

Resources

About