Changes between Version 27 and Version 28 of Tutorials/Edge Computing/Alveo Getting Started


Ignore:
Timestamp:
May 21, 2020, 4:02:05 PM (4 years ago)
Author:
prasanthi
Comment:

Legend:

Unmodified
Added
Removed
Modified
  • Tutorials/Edge Computing/Alveo Getting Started

    v27 v28  
    1 = Getting Started with Alveo FPGA acceleration =
    2 
    3 == Description ==
     1[[Include(WikiToC)]]
     2
     3== Getting Started with Alveo FPGA acceleration ==
     4
     5=== Description ===
    46Compute servers in COSMOS, and cloud computing nodes in ORBIT Sandbox 9 are equipped with Alveo U200 accelerator cards (with Virtex UltraScale+ XCU200-2FSGD2104E FPGA). These cards can be used to accelerate compute-intensive applications such as d machine learning, and video processing. They are connected to the Intel Xeon host CPU over PCI Express® (PCIe) Gen3x16 bus.
    57
    68This tutorial demonstrates how to run an accelerated FPGA kernel on the above platform. Vitis unified software platform 2019.2 is used for developing and deploying the application.
    79
    8 == Prerequisites ==
     10=== Prerequisites ===
    911In order to access the test bed, create a reservation and have it approved by the reservation service. Access to the resources is granted after the reservation is confirmed. Please follow the process shown on [wiki:cosmos_workflow the COSMOS work flow page] to get started.
    1012
    11 == Resources required ==
     13=== Resources required ===
    12141 COSMOS compute server or 1 node in ORBIT SB9.
    1315
    14 == Execution ==
     16=== Tutorial Setup ===
     17
     18Follow the steps below to gain access to the [wiki:/hardware/Domains/sb1 sandbox 1 console] and set up nodes with appropriate images.
     19 1. If you don't have one already, sign up for a [https://www.cosmos-lab.org/portal-2/ COSMOS account]
     20 1. [wiki:/GettingStarted#MakeaReservation Create a resource reservation] on sandbox 1
     21 1. [Documentation/Short/Login Login] into sandbox 1 console (console.sb1.cosmos-lab.org) with two SSH sessions.
     22 1. Make sure all the nodes and devices used in the experiment are turned off:
     23{{{#!shell
     24omf tell -a offh -t srv3-lg1,srv4-lg1,rfdev3-1,rfdev3-2,rfdev3-5,rfdev3-6 
     25}}}
     26 1. The image sivers_sb1_cosmos.ndz is [baseline_uhd.ndz] with Sivers control software installed.   
     27  Load sivers_sb1_cosmos.ndz on srv3,srv4. 
     28{{{#!shell
     29omf load -i sivers_sb1_cosmos.ndz -t srv3-lg1,srv4-lg1
     30}}}
     31 1. Turn all the required resources on and check the status
     32{{{#!shell
     33omf tell -a on -t srv3-lg1,srv4-lg1,rfdev3-1,rfdev3-2,rfdev3-5,rfdev3-6
     34}}}
     35{{{#!shell
     36omf stat -t system:topo:allres
     37}}}
     38 1. ssh to the nodes, use option -Y for using GUI.
     39
     40
     41=== Experiment Execution ===
    1542
    1643[[CollapsibleStart(Prepare the node)]]