discussion on ML in FPGAs 1 T RIGGER S YSTEM 2 40 MHz subset data - PowerPoint PPT Presentation

Dec 12, 2023 •293 likes •360 views

discussion on ML in FPGAs 1 T RIGGER S YSTEM 2 40 MHz subset data Level-1 full data Custom Electronics Absorbs ~100s Tb/s Trigger decision in ~10 s 100 kHz High Level Trigger ~13k CPU farm 100 ms/event 500 Hz Offline

discussion on ML in FPGAs 1
T RIGGER S YSTEM 2 40 MHz subset data “Level-1” full data Custom Electronics Absorbs ~100s Tb/s Trigger decision in ~10 μ s 100 kHz “High Level Trigger” ~13k CPU farm 100 ms/event 500 Hz “Offline Computing” Grid, O(10) Pb
G OALS CUSTOM   3 HARDWARE / FIRMWARE Level-1 Trigger : 100s Tb/s, 40MHz pipeline, 10 us/event buffer “ OFF THE High-level Trigger : 100 kHz pipeline, 100 ms/event SHELF ” Offline processing : minutes/event HARDWARE Identify where we can get the biggest gains from ML inference with FPGAs for these very different classes of problems. Physicist “friendly” tools, engineering resources are scarce HLS4ML - better for physicist prototyping, faster development cycles, less expert knowledge needed Level 1 trigger is a custom target for LHC physics problems — not many available tools for O(500 ns) performance, need RTL; preference for HLS over tools like openCL open-source, accessible for academia
S TATUS WITH AWS 4 A first test of SDSoC examples on Zynq works out-of-box https://github.com/Xilinx/SDSoC_Examples/tree/master/cpp/getting_started uses the HLS “parlance” Next: adapt our HLS4ML to work with the AWS F1 examples: https://github.com/aws/aws-fpga/tree/master/SDAccel/examples First tests of SDAccel examples on t2.2xlarge with FPGA AMI looks good too push in this direction in the next month
F OR DISCUSSION 5 Level-1 Trigger : 100s Tb/s, 40MHz pipeline, 10 us/event buffer How optimal is HLS? we have some conceptual idea of the optimization, but… easy to compare a simple example against a verilog implementation? are we missing some obvious improvements? Useful for other fields? is it something other fields would be interested in? are there particular features we are not thinking of? how tied are we to Xilinx design tools? which HLS? we use Vivado HLS right now
F OR DISCUSSION 6 High-level Trigger : 100 kHz pipeline, 100 ms/event Offline processing : minutes/event exploring hardware could we explore AWS F1 for such applications? what are the tools like? language? HLS is ok? comparison to GPUs, other FPGA architectures? throughput some studies by other colleagues from another experiment note that a PCIe interface is a bottleneck. infini-band? parallel input streams? how to paritition/organize multi-FPGA networks? non-ML applications porting some popular physics algorithms like Kalman Filter and cellular automata

Download Presentation

Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

with FP FPGAs: Cas ase Stu tudy on on a a Key-Value Store FPGAs in the Cloud Wider

Zsolt Istvn * , Gustavo Alonso, Ankit Singla Systems Group, Computer Science Dept., ETH Zrich * Now at IMDEA Software Institute, Madrid Providing Multi-tenant Services with FP FPGAs: Cas ase Stu tudy on on a a Key-Value Store FPGAs in

374 views • 15 slides

FPGAs 1 To read more This days papers: Brown and Rose, Architecture of FPGAs and

FPGAs 1 To read more This days papers: Brown and Rose, Architecture of FPGAs and CPLDs: A Tutorial. (no review required) Putnam et al, A Reconfjgurable Fabric for Accelerating Large-Scale Datacenter Services 1

821 views • 43 slides

FPGAs milliseconds+ to reconfjgure custom chips ??? (next week) FPGAs ??? GPUs

FPGAs milliseconds+ to reconfjgure custom chips ??? (next week) FPGAs ??? GPUs vector computations examples: computation second processor specialized for particular the accelerator concept 2 fmexible, slower functional units

423 views • 11 slides

HW/SW Codesign w/ FPGAs The Nature of HW/SW I ECE 522 Hardware Software Codesign with FPGAs

HW/SW Codesign w/ FPGAs The Nature of HW/SW I ECE 522 Hardware Software Codesign with FPGAs Instructor: Prof. Jim Plusquellic Text: A Practical Introduction to Hardware/Software Codesign, 2nd Edition", Patrick Schaumont, Springer,

649 views • 10 slides

FPGAs 1 CMPE691/491: Advanced FPGA Design FPGAs Large array of configurable logic blocks

FPGAs 1 CMPE691/491: Advanced FPGA Design FPGAs Large array of configurable logic blocks (CLB) connected via programmable interconnects Features and Specifications of FPGAs Basic Programmable Devices Features and Specifications of FPGAs

1.13k views • 46 slides

Physical Design For FPGAs Rajeev Jayaraman Physical Implementation Tools Xilinx Inc. ISPD-2001

Physical Design For FPGAs Rajeev Jayaraman Physical Implementation Tools Xilinx Inc. ISPD-2001 Do you know FPGAs? FPGAs are used only in prototyping and emulation systems? Can you design anything real in FPGAs? FPGAs are too

595 views • 48 slides

Efficient Multi-Ported Memories for FPGAs Eric LaForest Greg Steffan University of Toronto

Efficient Multi-Ported Memories for FPGAs Eric LaForest Greg Steffan University of Toronto Computer Engineering Research Group February 22, 2010 Parallelism in FPGAs Larger SoCs on FPGAs Parallel Systems Parallel systems on FPGAs

680 views • 47 slides

A Network of Time Division Multiplexing for FPGAs Rosemary Francis Motivation FPGAs are

A Network of Time Division Multiplexing for FPGAs Rosemary Francis Motivation FPGAs are now home to complex Systems on-Chip Designs require the use of Network-on- Chip FPGA global wiring is simple in comparison with ASIC

2.67k views • 19 slides

FPGAs as Tools and Architectures at ETH Systems FPGAs as Tools and Architectures at ETH Systems

FPGAs as Tools and Architectures at ETH Systems FPGAs as Tools and Architectures at ETH Systems Real-Time Tracing and Verification The FPGA as a tool . Analysing a multi-Gb trace stream in real time. BRISC Research Architecture

804 views • 43 slides

Gigabit Ethernet Gigabit Ethernet implementation for implementation for FPGAs FPGAs Grzegorz

Gigabit Ethernet Gigabit Ethernet implementation for implementation for FPGAs FPGAs Grzegorz Korcyl - Jagiellonian University, Krakw Grzegorz Korcyl PANDA TDAQ Workshop, Giessen April 2010 Outline Motivation 1. 2. General structure

292 views • 16 slides

The BIST History of FPGAs FPGAs The BIST History of The BISTory BISTory of of FPGAs FPGAs

The BIST History of FPGAs FPGAs The BIST History of The BISTory BISTory of of FPGAs FPGAs The Chuck Stroud Chuck Stroud Electrical and Computer Engineering Electrical and Computer Engineering Auburn University Auburn University 1

685 views • 42 slides

High-Speed Computing & Co-Processing with FPGAs FPGAs (Field Programmable Gate Arrays) are

High-Speed Computing & Co-Processing with FPGAs FPGAs (Field Programmable Gate Arrays) are slowly becoming more and more advanced and practical as high-speed computing platforms. In this talk, David will provide an in-depth introduction into

478 views • 43 slides

FPGA What is a FPGA? How FPGAs work How do they work? Manufacturers

2/21/2012 Content FPGA What is a FPGA? How FPGAs work How do they work? Manufacturers Distributed RAM History FPGA vs ASIC FPGA and Microprocessors Alternatives to FPGAs ETI135, Advanced Digital IC Design

123 views • 10 slides

1 FPGAs Attack Model Consider a device capable of implementing the FPGAs allow parallel

Introduction Classic cryptography views the secure problems with mathematical abstractions The classic cryptanalysis has had a great

443 views • 11 slides

Measuring Long Wire Leakage with Ring Oscillators in Cloud FPGAs Ilias Giechaskiel Kasper B.

Measuring Long Wire Leakage with Ring Oscillators in Cloud FPGAs Ilias Giechaskiel Kasper B. Rasmussen Jakub Szefer 9 September 2019 University of Oxford Yale University Cloud FPGAs FPGAs now offered by cloud

622 views • 17 slides

Physical optimization for Physical optimization for FPGAs using post- FPGAs using post-

Physical optimization for Physical optimization for FPGAs using post- FPGAs using post- placement topology placement topology rew riting rew riting Val Pevzner, Andrew Kennings, Andy Fox Introduction (1) Introduction (1) Traditional flow

459 views • 20 slides

Fast FPGA Implementation of Diffie-Hellman on the Kummer Surface of a Genus-2 Curve Philipp

Fast FPGA Implementation of Diffie-Hellman on the Kummer Surface of a Genus-2 Curve Philipp Koppermann, Fabrizio De Santis, Johann Heyszl and Georg Sigl History of High-Speed Curve Cryptography over Prime Fields 1 Point Addition on a

319 views • 16 slides

FPGA-based Multithreading for In-Memory Hash Joins Robert J. Halstead , Ildar Absalyamov , Walid

FPGA-based Multithreading for In-Memory Hash Joins Robert J. Halstead , Ildar Absalyamov , Walid A. Najjar, Vassilis J. Tsotras University of California, Riverside Outline Background What are FPGAs Multithreaded Architectures

343 views • 18 slides

We Well llcom come to TA TACO CO! GCIG/KGOG1027/TGCS2012: Randomized Phase III Clinical

Gynecologic Cancer InterGroup Cervix Cancer Research Network We Well llcom come to TA TACO CO! GCIG/KGOG1027/TGCS2012: Randomized Phase III Clinical Trial Comparing Weekly vs Tri-weekly Cisplatin Based Concurrent Chemoradiation in Locally

645 views • 19 slides

1 Introduction Co-Occurrences Frequent Item Tree Association rule mining FP Growth Ying

1 Introduction Co-Occurrences Frequent Item Tree Association rule mining FP Growth Ying Xu COFI tree mining yx2@cs.ualberta.ca (COFI-tree Mining: A New Approach to Pattern Growth with Reduced Candidacy Generation Hajj,

393 views • 6 slides

FT-UNSHADES2. H.G. Miranda, M.A. Aguirre, J. Barrientos, L. Sanz Electronic Engineering Dpt.

FT-UNSHADES2. H.G. Miranda, M.A. Aguirre, J. Barrientos, L. Sanz Electronic Engineering Dpt. School of Engineering. University of Sevilla (SPAIN) Sevilla, March 2014 FT -UNSHADES goals FT -UNSHADES is a tool for SEE EMULATION, at netlist

477 views • 25 slides

Exchange on Low-Cost FPGAs Tobias Oder and Tim Gneysu Ruhr-University Bochum Latincrypt 2017

Implementing the NewHope-Simple Key Exchange on Low-Cost FPGAs Tobias Oder and Tim Gneysu Ruhr-University Bochum Latincrypt 2017 20.09.2017 Public-Key Crypto and Long-Term Security NewHope on FPGA | Tobias Oder and Tim Gneysu |

562 views • 24 slides

Embedded systems and the role of programmable logic devices in embedded systems Embedded system :

Embedded systems and the role of programmable logic devices in embedded systems Embedded system : a combination of computer hardware and software, and perhaps additional mechanical or other parts, designed to perform a dedicated function. In some

414 views • 20 slides

Fractal Compression Alex Munoz Algorithms Interest Group 29 June 2016 Outline Introduction

Fractal Compression Alex Munoz Algorithms Interest Group 29 June 2016 Outline Introduction Mathematical Background Connecting Mathematics to Compression Fractal Compression Coherent Example Introduction Thinking about

1.1k views • 20 slides