Accelerating Scientific Applications With SambaNova Reconfigurable Dataflow Architecture

Emani, Murali; Vishwanath, Venkatram; Adams, C.; Papka, Michael E.; Florescu, Laura; Jairath, Sumti; Liu, William; Nama, Tejas; Sujeeth, Arvind K.; Kindratenko, Volodymyr; Elster, Anne C.

doi:10.1109/mcse.2021.3057203

Cited by 39 publications

(12 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Rocki et al [2020] discussed the possibility of using DCAI systems for PDE codes in scientific applications, and demonstrated the benefit over using conventional CPU or GPU based solutions. Emani et al [2021] explored the suitability of SambaNova, another DCAI system, for diverse AI for Science workloads and observed significant performance gains over traditional hardware. Acciarri et al [2020] advanced state-of-the-art accuracy for an important neutrino physics image segmentation problem leveraging the large memory of DCAI systems which are not possible to fit on the highest-end GPU because of the large tensor size (convolutions neural networks with images beyond 50k x 50k resolution).…”

Section: Resultsmentioning

confidence: 99%

Bridging Data Center AI Systems with Edge Computing for Actionable Information Retrieval

Liu¹,

Yang²,

Kenesei³

et al. 2021

Preprint

View full text Add to dashboard Cite

Extremely high data rates at modern synchrotron and X-ray free-electron lasers (XFELs) light source beamlines motivate the use of machine learning methods for data reduction, feature detection, and other purposes. Regardless of the application, the basic concept is the same: data collected in early stages of an experiment, data from past similar experiments, and/or data simulated for the upcoming experiment are used to train machine learning models that, in effect, learn specific characteristics of those data; these models are then used to process subsequent data more efficiently than would general-purpose models that lack knowledge of the specific dataset or data class. Thus, a key challenge is to be able to train models with sufficient rapidity that they can be deployed and used within useful timescales. We describe here how specialized data center AI systems can be used for this purpose.

show abstract

Section: Resultsmentioning

confidence: 99%

Bridging Data Center AI Systems with Edge Computing for Actionable Information Retrieval

Liu¹,

Yang²,

Kenesei³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…NPUs: Examples of NPUs include Google's Tensor Processing Unit (TPU) [20], tensor cores in NVIDIA A100 Ampere architecture, Samsung NPU [21], Sambanova's RDU [22], IBM's AI Accelerator [23], Microsoft Brainwave [24], Tesla's Self-Driving computer [25], Facebook's ML accelerator [26], etc. NPU architectures can be standalone, a co-processor, or a near-data processing engine [27]- [29].…”

Section: A Npu Design Requirements and Challengesmentioning

confidence: 99%

Special Session: Towards an Agile Design Methodology for Efficient, Reliable, and Secure ML Systems

Dave,

Marchisio,

Hanif

et al. 2022

Preprint

View full text Add to dashboard Cite

The real-world use cases of Machine Learning (ML) have exploded over the past few years. However, the current computing infrastructure is insufficient to support all realworld applications and scenarios. Apart from high efficiency requirements, modern ML systems are expected to be highly reliable against hardware failures as well as secure against adversarial and IP stealing attacks. Privacy concerns are also becoming a first-order issue. This article summarizes the main challenges in agile development of efficient, reliable and secure ML systems, and then presents an outline of an agile design methodology to generate efficient, reliable and secure ML systems based on user-defined constraints and objectives.

show abstract

“…For multi-user facilities, reconfigurability is essential; thus our interest in an architecture that can be programmed specifically for any model application but nevertheless results in an application-specific optimized accelerator. The core of the SambaNova Reconfigurable Dataflow Architecture TM (RDA) [14,15] is a dataflow-optimized processor, the Reconfigurable Dataflow Unit TM (RDU). It has a tiled architecture that is made up of a network of programmable compute (PCUs), memory (PMUs) and communication units.…”

Section: Sambanova Reconfigurable Dataflow Architecturementioning

confidence: 99%

“…The SambaFlow framework automatically handles the parallelization used here for data parallel training with the DataScale ® platform, a rack-level, datacenter accelerated computing platform. The platform consists of one or more DataScale SN10-8 nodes with integrated networking and management infrastructure in a standards-compliant data center rack-the DataScale SN10-8R [15]. We used up to 4 SN10-8 nodes for the results presented here, each consisting of a host module and 8 RDUs.…”

Section: Distributed Trainingmentioning

confidence: 99%

Enabling real-time adaptation of machine learning models at x-ray Free Electron Laser facilities with high-speed training optimized computational hardware

Milan¹,

Rong²,

Michaud³

et al. 2022

Front. Phys.

View full text Add to dashboard Cite

The emergence of novel computational hardware is enabling a new paradigm for rapid machine learning model training. For the Department of Energy’s major research facilities, this developing technology will enable a highly adaptive approach to experimental sciences. In this manuscript we present the per-epoch and end-to-end training times for an example of a streaming diagnostic that is planned for the upcoming high-repetition rate x-ray Free Electron Laser, the Linac Coherent Light Source-II. We explore the parameter space of batch size and data parallel training across multiple Graphics Processing Units and Reconfigurable Dataflow Units. We show the landscape of training times with a goal of full model retraining in under 15 min. Although a full from scratch retraining of a model may not be required in all cases, we nevertheless present an example of the application of emerging computational hardware for adapting machine learning models to changing environments in real-time, during streaming data acquisition, at the rates expected for the data fire hoses of accelerator-based user facilities.

show abstract

Accelerating Scientific Applications With SambaNova Reconfigurable Dataflow Architecture

Cited by 39 publications

References 2 publications

Bridging Data Center AI Systems with Edge Computing for Actionable Information Retrieval

Bridging Data Center AI Systems with Edge Computing for Actionable Information Retrieval

Special Session: Towards an Agile Design Methodology for Efficient, Reliable, and Secure ML Systems

Enabling real-time adaptation of machine learning models at x-ray Free Electron Laser facilities with high-speed training optimized computational hardware

Contact Info

Product

Resources

About