Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userPsPIN: A high-performance low-power architecture for flexible in-network compute
75
0
0.0
(
0
)
Added by
Salvatore Di Girolamo
Publication date
2020
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
The capacity of offloading data and control tasks to the network is becoming increasingly important, especially if we consider the faster growth of network speed when compared to CPU frequencies. In-network compute alleviates the host CPU load by running tasks directly in the network, enabling additional computation/communication overlap and potentially improving overall application performance. However, sustaining bandwidths provided by next-generation networks, e.g., 400 Gbit/s, can become a challenge. sPIN is a programming model for in-NIC compute, where users specify handler functions that are executed on the NIC, for each incoming packet belonging to a given message or flow. It enables a CUDA-like acceleration, where the NIC is equipped with lightweight processing elements that process network packets in parallel. We investigate the architectural specialties that a sPIN NIC should provide to enable high-performance, low-power, and flexible packet processing. We introduce PsPIN, a first open-source sPIN implementation, based on a multi-cluster RISC-V architecture and designed according to the identified architectural specialties. We investigate the performance of PsPIN with cycle-accurate simulations, showing that it can process packets at 400 Gbit/s for several use cases, introducing minimal latencies (26 ns for 64 B packets) and occupying a total area of 18.5 mm 2 (22 nm FDSOI).
rate research
Read More
An optical circuit-switched network core has the potential to overcome the inherent challenges of a conventional electrical packet-switched core of todays compute clusters. As optical circuit switches (OCS) directly handle the photon beams without any optical-electrical-optical (O/E/O) conversion and packet processing, OCS-based network cores have the following desirable properties: a) agnostic to data-rate, b) negligible/zero power consumption, c) no need of transceivers, d) negligible forwarding latency, and e) no need for frequent upgrade. Unfortunately, OCS can only provide point-to-point (unicast) circuits. They do not have built-in support for one-to-many (multicast) communication, yet multicast is fundamental to a plethora of data-intensive applications running on compute clusters nowadays. In this paper, we propose Shufflecast, a novel optical network architecture for next-generation compute clusters that can support high-performance multicast satisfying all the properties of an OCS-based network core. Shufflecast leverages small fanout, inexpensive, passive optical splitters to connect the Top-of-rack (ToR) switch ports, ensuring data-rate agnostic, low-power, physical-layer multicast. We thoroughly analyze Shufflecasts highly scalable data plane, light-weight control plane, and graceful failure handling. Further, we implement a complete prototype of Shufflecast in our testbed and extensively evaluate the network. Shufflecast is more power-efficient than the state-of-the-art multicast mechanisms. Also, Shufflecast is more cost-efficient than a conventional packet-switched network. By adding Shufflecast alongside an OCS-based unicast network, an all-optical network core with the aforementioned desirable properties supporting both unicast and multicast can be realized.
We propose that clusters interconnected with network topologies having minimal mean path length will increase their overall performance for a variety of applications. We approach our heuristic by constructing clusters of up to 36 nodes having Dragonfly, torus, ring, Chvatal, Wagner, Bidiakis and several other topologies with minimal mean path lengths and by simulating the performance of 256-node clusters with the same network topologies. The optimal (or sub-optimal) low-latency network topologies are found by minimizing the mean path length of regular graphs. The selected topologies are benchmarked using ping-pong messaging, the MPI collective communications, and the standard parallel applications including effective bandwidth, FFTE, Graph 500 and NAS parallel benchmarks. We established strong correlations between the clusters performances and the network topologies, especially the mean path lengths, for a wide range of applications. In communication-intensive benchmarks, clusters with optimal network topologies out-perform those with mainstream topologies by several folds. It is striking that a mere adjustment of the network topology suffices to reclaim performance from the same computing hardware.
Despite the proliferation of mobile devices in various wide-area Internet of Things applications (e.g., smart city, smart farming), current Low-Power Wide-Area Networks (LPWANs) are not designed to effectively support mobile nodes. In this paper, we propose to handle mobility in SNOW (Sensor Network Over White spaces), an LPWAN that operates in the TV white spaces. SNOW supports massive concurrent communication between a base station (BS) and numerous low-power nodes through a distributed implementation of OFDM. In SNOW, inter-carrier interference (ICI) is more pronounced under mobility due to its OFDM based design. Geospatial variation of white spaces also raises challenges in both intra- and inter-network mobility as the low-power nodes are not equipped to determine white spaces. To handle mobility impacts on ICI, we propose a dynamic carrier frequency offset estimation and compensation technique which takes into account Doppler shifts without requiring to know the speed of the nodes. We also propose to circumvent the mobility impacts on geospatial variation of white space through a mobility-aware spectrum assignment to nodes. To enable mobility of the nodes across different SNOWs, we propose an efficient handoff management through a fast and energy-efficient BS discovery and quick association with the BS by combining time and frequency domain energy-sensing. Experiments through SNOW deployments in a large metropolitan city and indoors show that our proposed approaches enable mobility across multiple different SNOWs and provide robustness in terms of reliability, latency, and energy consumption under mobility.
The recent line of research into topology design focuses on lowering network diameter. Many low-diameter topologies such as Slim Fly or Jellyfish that substantially reduce cost, power consumption, and latency have been proposed. A key challenge in realizing the benefits of these topologies is routing. On one hand, these networks provide shorter path lengths than established topologies such as Clos or torus, leading to performance improvements. On the other hand, the number of shortest paths between each pair of endpoints is much smaller than in Clos, but there is a large number of non-minimal paths between router pairs. This hampers or even makes it impossible to use established multipath routing schemes such as ECMP. In this work, to facilitate high-performance routing in modern networks, we analyze existing routing protocols and architectures, focusing on how well they exploit the diversity of minimal and non-minimal paths. We first develop a taxonomy of different forms of support for multipathing and overall path diversity. Then, we analyze how existing routing schemes support this diversity. Among others, we consider multipathing with both shortest and non-shortest paths, support for disjoint paths, or enabling adaptivity. To address the ongoing convergence of HPC and Big Data domains, we consider routing protocols developed for both HPC systems and for data centers as well as general clusters. Thus, we cover architectures and protocols based on Ethernet, InfiniBand, and other HPC networks such as Myrinet. Our review will foster developing future high-performance multipathing routing protocols in supercomputers and data centers.
This paper proposes a simple and flexible storage model for use in a variety of multi-period optimal power flow problems. The proposed model is designed for research use in a broad assortment of contexts enabled by the following key features: (i) the model can represent the dynamics of an energy buffer at a wide range of scales, from residential battery storage to grid-scale pumped hydro; (ii) it is compatible with both balanced and unbalanced formulations of the power flow equations; (iii) convex relaxations and linear approximations to allow seamless integration of the proposed model into applications where convexity or linearity is required are developed; (iv) a minimalist and standardized data model is presented, to facilitate easy of use by the research community. The proposed model is validated using a proof-of-concept twenty-four hour storage scheduling task that demonstrates the value of the models key features. An open-source implementation of the model is provided as part of the PowerModels and PowerModelsDistribution optimization toolboxes.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
