2000 character limit reached
A System Development Kit for Big Data Applications on FPGA-based Clusters: The EVEREST Approach
Published 20 Feb 2024 in cs.AR | (2402.12612v1)
Abstract: Modern big data workflows are characterized by computationally intensive kernels. The simulated results are often combined with knowledge extracted from AI models to ultimately support decision-making. These energy-hungry workflows are increasingly executed in data centers with energy-efficient hardware accelerators since FPGAs are well-suited for this task due to their inherent parallelism. We present the H2020 project EVEREST, which has developed a system development kit (SDK) to simplify the creation of FPGA-accelerated kernels and manage the execution at runtime through a virtualization environment. This paper describes the main components of the EVEREST SDK and the benefits that can be achieved in our use cases.
- “Optuna: A Next-generation Hyperparameter Optimization Framework” In Proc. of ACM SIGKDD, 2019
- Peter Bauer, Alan Thorpe and Gilbert Brunet “The quiet revolution of numerical weather prediction” In Nature 525.7567 Nature Publishing Group, 2015
- Tianqi Chen “TVM: An Automated End-to-End Optimizing Compiler for Deep Learning” In Proc. of OSDI, 2018
- “Compiling for Concise Code and Efficient I/O” In Proc. of CC, 2018, pp. 104–115
- “STCLang: State Thread Composition as a Foundation for Monadic Dataflow Parallelism” In Proc. of Haskell, 2019 DOI: 10.1145/3331545.3342600
- “Bambu: an Open-Source Research Framework for the High-Level Synthesis of Complex Applications” In Proc. of DAC, 2021, pp. 1327–1330
- Karl F.A. Friebel, Jiahong Bi and Jeronimo Castrillon “BASE2: An IR for Binary Numeral Types” In Proc. of HEART, 2023 DOI: 10.1145/3597031.3597048
- “mARGOt: A Dynamic Autotuning Framework for Self-Aware Approximate Computing” In IEEE Transactions on Computers 68.5, 2019 DOI: 10.1109/TC.2018.2883597
- Sven Karol “A Domain-Specific Language and Editor for Parallel Particle Methods” In ACM Trans. on Mathematical Software 44.3, 2018
- “Model-based Autotuning of Discretization Methods in Numerical Simulations of Partial Differential Equations” In Journal of Computational Science, 2021
- “MLIR: Scaling compiler infrastructure for domain specific computation” In Proc. of CGO, 2021
- “Generating Posit-Based Accelerators With High-Level Synthesis” In IEEE TCAS-I 70.10, 2023 DOI: 10.1109/TCSI.2023.3299009
- “A Survey and Evaluation of FPGA High-Level Synthesis Tools” In IEEE TCAD 35.10, 2016 DOI: 10.1109/TCAD.2015.2513673
- John G Papastavridis “Tensor calculus and analytical dynamics” Routledge, 2018
- “EVEREST: A design environment for extreme-scale big data analytics on heterogeneous platforms” In Proc. of DATE, 2021, pp. 1320–1325 DOI: 10.23919/DATE51398.2021.9473940
- “System-Level Optimization of Accelerator Local Memory for Heterogeneous Systems-on-Chip” In TCAD 36.3, 2017 DOI: 10.1109/TCAD.2016.2611506
- “The weather research and forecasting model: Overview, system efforts, and future directions” In Bulletin of the American Meteorological Society 98.8, 2017
- “Advancing Compilation of DNNs for FPGAs Using Operation Set Architectures” In IEEE Computer Architecture Letters 22.1, 2023, pp. 9–12 DOI: 10.1109/LCA.2022.3227643
- “DOSA: Organic Compilation for Neural Network Inference on Distributed FPGAs” In Proc. of EDGE, 2023 DOI: 10.1109/EDGE60047.2023.00019
- “System Architecture for Network-Attached FPGAs in the Cloud using Partial Reconfiguration” In 2019 29th International Conference on Field Programmable Logic and Applications (FPL), 2019, pp. 293–300 DOI: 10.1109/FPL.2019.00054
- “ZRLMPI: A Unified Programming Model for Reconfigurable Heterogeneous Computing Clusters” In 2020 IEEE 28th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM), 2020, pp. 220–220 DOI: 10.1109/FCCM48280.2020.00051
- Norman A. Rink “CFDlang: High-level Code Generation for High-order Methods in Fluid Dynamics” In Proc. of RWDSL, 2018, pp. 1–10
- Norman A. Rink and Jeronimo Castrillon “TeIL: a type-safe imperative Tensor Intermediate Language” In Proc. of ARRAY, 2019
- “Automatic creation of high-bandwidth memory architectures from domain-specific languages: The case of computational fluid dynamics” In ACM TRETS 16.2 ACM New York, NY, 2023
- Stephanie Soldavini, Donatella Sciuto and Christian Pilato “Iris: Automatic Generation of Efficient Data Layouts for High Bandwidth Utilization” In Proc. of ASPDAC, 2023 DOI: 10.48550/ARXIV.2211.04361
- “Platform-Aware FPGA System Architecture Generation based on MLIR”, 2023 arXiv:2309.12917
- “ConDRust: Scalable Deterministic Concurrency from Verifiable Rust Programs” In Proc. of ECOOP, 2023 DOI: 10.4230/LIPIcs.ECOOP.2023.33
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.
