際際滷

際際滷Share a Scribd company logo
Arkville
DPDK Acceleration
Shep Siegel, CTO
Atomic Rules LLC
1息2017 Atomic Rules LLC
Shepard.Siegel@atomicrules.com
Arkville DPDK Acceleration
2017-08-08
AR Background
 Providing FPGA Design Services since 2008
 Contributions to numerous Open-Source Projects
 Began augmenting services with IP Core products
 UDP Offload Engine (2014)
 Arkville DPDK-Aware Data Mover (2016)
 TimeServo FPGA System Timer (2017)
 Small, but steadily growing
 Currently nine EE/CS engineers across North America
 Passed $1M in Services in CY2015
 Differentiation with Tools and Methodology
 Broad and Agnostic set of Partners
 Growing set of Recurring Customers and Clients
2息2017 Atomic Rules LLC
Arkville: A DPDK Packet Conduit
3息2017 Atomic Rules LLC
Arkville: Why?
 DPDK First
 Not an Afterthought or Adaptation
 Both Higher Throughput and Lower Latency
 DPDK Aware
 Push GPP cycles to specialized FPGA RTL gates
 Zero-Copy GPP Driver = Lowest Possible Overhead
 DPDK Acceleration
 Certain workloads are better in RTL gateware
 Arkville enables a Software-First approach
4息2017 Atomic Rules LLC
Arkville: Where?
 Arkville is used as a building-block component
in products and solutions such as
 Smart-NIC Devices
 Network Appliances
 DPDK Accelerators
 Anywhere there is the need to efficiently
exchange data between DPDK-mbufs and AXI
FPGA gates
5息2017 Atomic Rules LLC
Smart-NIC
6息2017 Atomic Rules LLC 6
Any
Rate
ENET
MAC
NIC
H/W Offload
RTL IP
Arkville
AXI HW
Arkville
DPDK PMD
SW
DPDK Applications
GPP SW
PCIe
FPGA
GPP
AR Arkville HW/SW
DPDK
SW API
AXI
HW API
Network Appliance
7息2017 Atomic Rules LLC 7
Any
Rate
ENET
MAC
Appliance
RTL IP
Arkville
AXI HW
Arkville
DPDK PMD
SW
Appliance
GPP SW
PCIe
FPGA
GPP
AR Arkville HW/SW
DPDK
SW API
AXI
HW API
DPDK Accelerator
8息2017 Atomic Rules LLC 8
AXI Accelerator RTL IP
from HLS, OpenCL, BSV
Arkville
AXI HW
Arkville
DPDK PMD
SW
DPDK Applications or
fd.io/VPP Nodes
GPP SW
PCIe
FPGA
GPP
AR Arkville HW/SW
DPDK
SW API
AXI
HW API
Arkville: How?
 A Software and Gateware Combination:
 Arkville 17.05 DPDK Poll Mode Driver (DPDK PMD)
 Open-Source BSD from The Linux Foundation
 http://dpdk.org/doc/guides/nics/ark.html
 Arkville 17.05 FPGA RTL IP Core (AXI RTL IP)
 Atomic Rules sells named-project and site-based licenses
 http://www.atomicrules.com/arkville
 Arkville performs the data-mover work for
products and solutions that require FPGA/GPP
communication
9息2017 Atomic Rules LLC
High-Level Block Diagram
10息2017 Atomic Rules LLC
Over 150 Gbps Throughput
11息2017 Atomic Rules LLC
1.25 us RTT/2 Latency
12息2017 Atomic Rules LLC
About Arkville Latency
 By Itself, Arkville contributes just 100ns to the
ingress/egress latency budget
 Software: Arkville DPDK PMD:
 Constant Time 20ns per packet (e5-2630v4)
 Zero-Copy  No GPP Cycles moving packet data!
 Hardware: Arkville AXI RTL IP:
 20 Cycles at 250 MHz = 80ns + 4ns/64B
 Deterministic, store-and-forward
13息2017 Atomic Rules LLC
No memcpy()
 Arkville is unique among DPDK Poll Mode
Drivers in that packet data is landed zero-copy
exactly in user-land memory
 Zero CPU cycles are used by net/ark PMD for
packet data movement
 Result is a constant O(1) time for all packets that
fit in a single mbuf (See next slide)
 More CPU cycles for your application
 Fewer CPU cores needed for same amount of work
14息2017 Atomic Rules LLC
Zero-Copy DPDK Driver
15息2017 Atomic Rules LLC
Zero Packets Dropped
16息2017 Atomic Rules LLC
Questions / Feedback
 Is FPGA acceleration of packet-based DPDK
workloads of interest?
 Are there specific challenges you are facing
that perhaps Arkville will help solve?
 How do you measure success?
 Do you have a target platform in mind?
 How would you like to get started?
17息2017 Atomic Rules LLC
Summary and Thank You!
18息2017 Atomic Rules LLC
 Arkville is a GPP/FPGA DPDK-Aware Conduit
 Software is an Open-Source DPDK Poll Mode Driver
 RTL IP Core Gateware is sold by Atomic Rules
 Named-Project and Site-Based Licenses are Available
 Arkville is Agnostic
 Support for Contemporary FPGA Devices
 Support for COTS and Custom FPGA Boards
 Arkville is Supported
 Ongoing developments to the DPDK/LF Community
 AR offers both HW and SW services and support
Roadmap: 17.08
19息2017 Atomic Rules LLC
 August 2017
 Support for DPDK 17.08
 Support for Vivado 2017.2
 Examples include Atomic Rules TimeServo[1]
 Timestamps from MAC to DPDK metadata
[1] TimeServo is a separate IP product that may be purchased
from Atomic Rules.
Roadmap: 17.11
20息2017 Atomic Rules LLC
 November 2017
 Support for DPDK 17.11
 Support for Vivado 2017.3
 Available with 16 RX Queue-Pairs
 Next-Generation MBUF Prefetcher
 Still Zero-Copy and Low-microsecond Twire-to-user
 Expanded DPDK examples for VPP and OVS
Backup Material
21息2017 Atomic Rules LLC
Core Beliefs and Axioms
22息2017 Atomic Rules LLC
 Our Customers Success is Key
 Separation of Concerns
 Divide and Conquer
 Automate or Die
 Write Things Once
 Interface Before Implementation
 Functional Correctness First
 Performance Correctness Improved Iteratively
 Components Must Compose
 Components Must Work as Expected
 IP Should be Portable, Vendor-Agnostic if possible
Partner Roster
23息2017 Atomic Rules LLC
 25G / 50G Ethernet Consortium
 25-50-100 Ethernet Alliance
 Accellera/OCP-IP Community Member
 Amazon F1 Instance Partner
 ARM Connected Community Member
 BittWare Solution Partner
 Bluespec Technology Partner
 DPDK Project Corporate Member
 FPGA, FCCM and FPL F Conference Sponsors
 Intel Network Builders
 Linux Foundation Corporate Member
 MathWorks Connections Partner
 NetFPGA Infrastructure Developer
 OpenCPI Infrastructure Developer
 P4 Language Consortium Member
 PCI-SIG Corporate Member
 VITA Trade Association Member
 Xilinx Alliance Member Partner
100 GbE DPDK Offload
24息2017 Atomic Rules LLC
Ad

Recommended

TC Flower Offload
TC Flower Offload
Netronome
OpenStack Neutron IPv6 Lessons
OpenStack Neutron IPv6 Lessons
Akihiro Motoki
Deploying IPv6 in OpenStack Environments
Deploying IPv6 in OpenStack Environments
Shannon McFarland
DevOps Live Meetup- NetDevOps session with Jay Shah (IEEE Published Paper)
DevOps Live Meetup- NetDevOps session with Jay Shah (IEEE Published Paper)
JAY SHAH
GPON-Fundamentals_Huawei.pdf
GPON-Fundamentals_Huawei.pdf
Enics
Open vSwitch 豌襴 蟲譟
Open vSwitch 豌襴 蟲譟
Seung-Hoon Baek
ECI UTC Webinar MPLS-TP Value for Utilities-dec 2015
ECI UTC Webinar MPLS-TP Value for Utilities-dec 2015
ECI THE ELASTIC NETWORK
Opendaylight SDN Controller
Opendaylight SDN Controller
Sumit Arora
OpenStack DRaaS - Freezer - 101
OpenStack DRaaS - Freezer - 101
Trinath Somanchi
Distributed vnf management architecture and use-cases
Distributed vnf management architecture and use-cases
OPNFV
Deploying IPv6 on OpenStack
Deploying IPv6 on OpenStack
Vietnam Open Infrastructure User Group
Intelligent Power Allocation
Intelligent Power Allocation
Chiou-Nan Chen
Double patterning for 32nm and beyond
Double patterning for 32nm and beyond
Manikandan Sampathkumar
NT_N Guard Ring Noise Analysis
NT_N Guard Ring Noise Analysis
AdrianOShaughnessy
stackconf 2023 | Practical introduction to OpenTelemetry tracing by Nicolas F...
stackconf 2023 | Practical introduction to OpenTelemetry tracing by Nicolas F...
NETWAYS
Intel dpdk Tutorial
Intel dpdk Tutorial
Saifuddin Kaijar
Huawei GPON Fundamentals
Huawei GPON Fundamentals
ibrahimnabil17
Segment Routing: A Tutorial
Segment Routing: A Tutorial
APNIC
Proyecto final Electrodomesticos All in One
claugira
Room 1 - 7 - L棚 Qu畛c 畉t - Upgrading network of Openstack to SDN with Tungste...
Room 1 - 7 - L棚 Qu畛c 畉t - Upgrading network of Openstack to SDN with Tungste...
Vietnam Open Infrastructure User Group
DPDK KNI interface
DPDK KNI interface
Denys Haryachyy
Ason gmpls
Ason gmpls
Anubhuti Shrivastava
Senlin deep dive 2016
Senlin deep dive 2016
Qiming Teng
Flexible Data Centre Fabric - FabricPath/TRILL, OTV, LISP and VXLAN
Flexible Data Centre Fabric - FabricPath/TRILL, OTV, LISP and VXLAN
Cisco Canada
Tesla-Stock-Analysis-and-Forecast.pptx (1).pptx
Tesla-Stock-Analysis-and-Forecast.pptx (1).pptx
moonsony54
Rapid Prototyping for XR: Lecture 5 - Cross Platform Development
Rapid Prototyping for XR: Lecture 5 - Cross Platform Development
Mark Billinghurst
Rapid Prototyping for XR: Lecture 2 - Low Fidelity Prototyping.
Rapid Prototyping for XR: Lecture 2 - Low Fidelity Prototyping.
Mark Billinghurst
machine learning is a advance technology
machine learning is a advance technology
ynancy893
(Continuous Integration and Continuous Deployment/Delivery) is a fundamental ...
(Continuous Integration and Continuous Deployment/Delivery) is a fundamental ...
ketan09101
Industrial internet of things IOT Week-3.pptx
Industrial internet of things IOT Week-3.pptx
KNaveenKumarECE

More Related Content

What's hot (16)

OpenStack DRaaS - Freezer - 101
OpenStack DRaaS - Freezer - 101
Trinath Somanchi
Distributed vnf management architecture and use-cases
Distributed vnf management architecture and use-cases
OPNFV
Deploying IPv6 on OpenStack
Deploying IPv6 on OpenStack
Vietnam Open Infrastructure User Group
Intelligent Power Allocation
Intelligent Power Allocation
Chiou-Nan Chen
Double patterning for 32nm and beyond
Double patterning for 32nm and beyond
Manikandan Sampathkumar
NT_N Guard Ring Noise Analysis
NT_N Guard Ring Noise Analysis
AdrianOShaughnessy
stackconf 2023 | Practical introduction to OpenTelemetry tracing by Nicolas F...
stackconf 2023 | Practical introduction to OpenTelemetry tracing by Nicolas F...
NETWAYS
Intel dpdk Tutorial
Intel dpdk Tutorial
Saifuddin Kaijar
Huawei GPON Fundamentals
Huawei GPON Fundamentals
ibrahimnabil17
Segment Routing: A Tutorial
Segment Routing: A Tutorial
APNIC
Proyecto final Electrodomesticos All in One
claugira
Room 1 - 7 - L棚 Qu畛c 畉t - Upgrading network of Openstack to SDN with Tungste...
Room 1 - 7 - L棚 Qu畛c 畉t - Upgrading network of Openstack to SDN with Tungste...
Vietnam Open Infrastructure User Group
DPDK KNI interface
DPDK KNI interface
Denys Haryachyy
Ason gmpls
Ason gmpls
Anubhuti Shrivastava
Senlin deep dive 2016
Senlin deep dive 2016
Qiming Teng
Flexible Data Centre Fabric - FabricPath/TRILL, OTV, LISP and VXLAN
Flexible Data Centre Fabric - FabricPath/TRILL, OTV, LISP and VXLAN
Cisco Canada
OpenStack DRaaS - Freezer - 101
OpenStack DRaaS - Freezer - 101
Trinath Somanchi
Distributed vnf management architecture and use-cases
Distributed vnf management architecture and use-cases
OPNFV
Intelligent Power Allocation
Intelligent Power Allocation
Chiou-Nan Chen
Double patterning for 32nm and beyond
Double patterning for 32nm and beyond
Manikandan Sampathkumar
NT_N Guard Ring Noise Analysis
NT_N Guard Ring Noise Analysis
AdrianOShaughnessy
stackconf 2023 | Practical introduction to OpenTelemetry tracing by Nicolas F...
stackconf 2023 | Practical introduction to OpenTelemetry tracing by Nicolas F...
NETWAYS
Huawei GPON Fundamentals
Huawei GPON Fundamentals
ibrahimnabil17
Segment Routing: A Tutorial
Segment Routing: A Tutorial
APNIC
Proyecto final Electrodomesticos All in One
claugira
Room 1 - 7 - L棚 Qu畛c 畉t - Upgrading network of Openstack to SDN with Tungste...
Room 1 - 7 - L棚 Qu畛c 畉t - Upgrading network of Openstack to SDN with Tungste...
Vietnam Open Infrastructure User Group
Senlin deep dive 2016
Senlin deep dive 2016
Qiming Teng
Flexible Data Centre Fabric - FabricPath/TRILL, OTV, LISP and VXLAN
Flexible Data Centre Fabric - FabricPath/TRILL, OTV, LISP and VXLAN
Cisco Canada

Recently uploaded (20)

Tesla-Stock-Analysis-and-Forecast.pptx (1).pptx
Tesla-Stock-Analysis-and-Forecast.pptx (1).pptx
moonsony54
Rapid Prototyping for XR: Lecture 5 - Cross Platform Development
Rapid Prototyping for XR: Lecture 5 - Cross Platform Development
Mark Billinghurst
Rapid Prototyping for XR: Lecture 2 - Low Fidelity Prototyping.
Rapid Prototyping for XR: Lecture 2 - Low Fidelity Prototyping.
Mark Billinghurst
machine learning is a advance technology
machine learning is a advance technology
ynancy893
(Continuous Integration and Continuous Deployment/Delivery) is a fundamental ...
(Continuous Integration and Continuous Deployment/Delivery) is a fundamental ...
ketan09101
Industrial internet of things IOT Week-3.pptx
Industrial internet of things IOT Week-3.pptx
KNaveenKumarECE
Introduction to sensing and Week-1.pptx
Introduction to sensing and Week-1.pptx
KNaveenKumarECE
Solar thermal Flat plate and concentrating collectors .pptx
Solar thermal Flat plate and concentrating collectors .pptx
jdaniabraham1
Generative AI & Scientific Research : Catalyst for Innovation, Ethics & Impact
Generative AI & Scientific Research : Catalyst for Innovation, Ethics & Impact
AlqualsaDIResearchGr
How to Un-Obsolete Your Legacy Keypad Design
How to Un-Obsolete Your Legacy Keypad Design
Epec Engineered Technologies
International Journal of Advanced Information Technology (IJAIT)
International Journal of Advanced Information Technology (IJAIT)
ijait
Microwatt: Open Tiny Core, Big Possibilities
Microwatt: Open Tiny Core, Big Possibilities
IBM
NEW Strengthened Senior High School Gen Math.pptx
NEW Strengthened Senior High School Gen Math.pptx
DaryllWhere
Complete University of Calculus :: 2nd edition
Complete University of Calculus :: 2nd edition
Shabista Imam
LECTURE 7 COMPUTATIONS OF LEVELING DATA APRIL 2025.pptx
LECTURE 7 COMPUTATIONS OF LEVELING DATA APRIL 2025.pptx
rr22001247
Rapid Prototyping for XR: Lecture 6 - AI for Prototyping and Research Directi...
Rapid Prototyping for XR: Lecture 6 - AI for Prototyping and Research Directi...
Mark Billinghurst
Rapid Prototyping for XR: Lecture 3 - Video and Paper Prototyping
Rapid Prototyping for XR: Lecture 3 - Video and Paper Prototyping
Mark Billinghurst
IPL_Logic_Flow.pdf Mainframe IPLMainframe IPL
IPL_Logic_Flow.pdf Mainframe IPLMainframe IPL
KhadijaKhadijaAouadi
FUNDAMENTALS OF COMPUTER ORGANIZATION AND ARCHITECTURE
FUNDAMENTALS OF COMPUTER ORGANIZATION AND ARCHITECTURE
Shabista Imam
Abraham Silberschatz-Operating System Concepts (9th,2012.12).pdf
Abraham Silberschatz-Operating System Concepts (9th,2012.12).pdf
Shabista Imam
Tesla-Stock-Analysis-and-Forecast.pptx (1).pptx
Tesla-Stock-Analysis-and-Forecast.pptx (1).pptx
moonsony54
Rapid Prototyping for XR: Lecture 5 - Cross Platform Development
Rapid Prototyping for XR: Lecture 5 - Cross Platform Development
Mark Billinghurst
Rapid Prototyping for XR: Lecture 2 - Low Fidelity Prototyping.
Rapid Prototyping for XR: Lecture 2 - Low Fidelity Prototyping.
Mark Billinghurst
machine learning is a advance technology
machine learning is a advance technology
ynancy893
(Continuous Integration and Continuous Deployment/Delivery) is a fundamental ...
(Continuous Integration and Continuous Deployment/Delivery) is a fundamental ...
ketan09101
Industrial internet of things IOT Week-3.pptx
Industrial internet of things IOT Week-3.pptx
KNaveenKumarECE
Introduction to sensing and Week-1.pptx
Introduction to sensing and Week-1.pptx
KNaveenKumarECE
Solar thermal Flat plate and concentrating collectors .pptx
Solar thermal Flat plate and concentrating collectors .pptx
jdaniabraham1
Generative AI & Scientific Research : Catalyst for Innovation, Ethics & Impact
Generative AI & Scientific Research : Catalyst for Innovation, Ethics & Impact
AlqualsaDIResearchGr
International Journal of Advanced Information Technology (IJAIT)
International Journal of Advanced Information Technology (IJAIT)
ijait
Microwatt: Open Tiny Core, Big Possibilities
Microwatt: Open Tiny Core, Big Possibilities
IBM
NEW Strengthened Senior High School Gen Math.pptx
NEW Strengthened Senior High School Gen Math.pptx
DaryllWhere
Complete University of Calculus :: 2nd edition
Complete University of Calculus :: 2nd edition
Shabista Imam
LECTURE 7 COMPUTATIONS OF LEVELING DATA APRIL 2025.pptx
LECTURE 7 COMPUTATIONS OF LEVELING DATA APRIL 2025.pptx
rr22001247
Rapid Prototyping for XR: Lecture 6 - AI for Prototyping and Research Directi...
Rapid Prototyping for XR: Lecture 6 - AI for Prototyping and Research Directi...
Mark Billinghurst
Rapid Prototyping for XR: Lecture 3 - Video and Paper Prototyping
Rapid Prototyping for XR: Lecture 3 - Video and Paper Prototyping
Mark Billinghurst
IPL_Logic_Flow.pdf Mainframe IPLMainframe IPL
IPL_Logic_Flow.pdf Mainframe IPLMainframe IPL
KhadijaKhadijaAouadi
FUNDAMENTALS OF COMPUTER ORGANIZATION AND ARCHITECTURE
FUNDAMENTALS OF COMPUTER ORGANIZATION AND ARCHITECTURE
Shabista Imam
Abraham Silberschatz-Operating System Concepts (9th,2012.12).pdf
Abraham Silberschatz-Operating System Concepts (9th,2012.12).pdf
Shabista Imam
Ad

DPDK Acceleration with Arkville

  • 1. Arkville DPDK Acceleration Shep Siegel, CTO Atomic Rules LLC 1息2017 Atomic Rules LLC Shepard.Siegel@atomicrules.com Arkville DPDK Acceleration 2017-08-08
  • 2. AR Background Providing FPGA Design Services since 2008 Contributions to numerous Open-Source Projects Began augmenting services with IP Core products UDP Offload Engine (2014) Arkville DPDK-Aware Data Mover (2016) TimeServo FPGA System Timer (2017) Small, but steadily growing Currently nine EE/CS engineers across North America Passed $1M in Services in CY2015 Differentiation with Tools and Methodology Broad and Agnostic set of Partners Growing set of Recurring Customers and Clients 2息2017 Atomic Rules LLC
  • 3. Arkville: A DPDK Packet Conduit 3息2017 Atomic Rules LLC
  • 4. Arkville: Why? DPDK First Not an Afterthought or Adaptation Both Higher Throughput and Lower Latency DPDK Aware Push GPP cycles to specialized FPGA RTL gates Zero-Copy GPP Driver = Lowest Possible Overhead DPDK Acceleration Certain workloads are better in RTL gateware Arkville enables a Software-First approach 4息2017 Atomic Rules LLC
  • 5. Arkville: Where? Arkville is used as a building-block component in products and solutions such as Smart-NIC Devices Network Appliances DPDK Accelerators Anywhere there is the need to efficiently exchange data between DPDK-mbufs and AXI FPGA gates 5息2017 Atomic Rules LLC
  • 6. Smart-NIC 6息2017 Atomic Rules LLC 6 Any Rate ENET MAC NIC H/W Offload RTL IP Arkville AXI HW Arkville DPDK PMD SW DPDK Applications GPP SW PCIe FPGA GPP AR Arkville HW/SW DPDK SW API AXI HW API
  • 7. Network Appliance 7息2017 Atomic Rules LLC 7 Any Rate ENET MAC Appliance RTL IP Arkville AXI HW Arkville DPDK PMD SW Appliance GPP SW PCIe FPGA GPP AR Arkville HW/SW DPDK SW API AXI HW API
  • 8. DPDK Accelerator 8息2017 Atomic Rules LLC 8 AXI Accelerator RTL IP from HLS, OpenCL, BSV Arkville AXI HW Arkville DPDK PMD SW DPDK Applications or fd.io/VPP Nodes GPP SW PCIe FPGA GPP AR Arkville HW/SW DPDK SW API AXI HW API
  • 9. Arkville: How? A Software and Gateware Combination: Arkville 17.05 DPDK Poll Mode Driver (DPDK PMD) Open-Source BSD from The Linux Foundation http://dpdk.org/doc/guides/nics/ark.html Arkville 17.05 FPGA RTL IP Core (AXI RTL IP) Atomic Rules sells named-project and site-based licenses http://www.atomicrules.com/arkville Arkville performs the data-mover work for products and solutions that require FPGA/GPP communication 9息2017 Atomic Rules LLC
  • 11. Over 150 Gbps Throughput 11息2017 Atomic Rules LLC
  • 12. 1.25 us RTT/2 Latency 12息2017 Atomic Rules LLC
  • 13. About Arkville Latency By Itself, Arkville contributes just 100ns to the ingress/egress latency budget Software: Arkville DPDK PMD: Constant Time 20ns per packet (e5-2630v4) Zero-Copy No GPP Cycles moving packet data! Hardware: Arkville AXI RTL IP: 20 Cycles at 250 MHz = 80ns + 4ns/64B Deterministic, store-and-forward 13息2017 Atomic Rules LLC
  • 14. No memcpy() Arkville is unique among DPDK Poll Mode Drivers in that packet data is landed zero-copy exactly in user-land memory Zero CPU cycles are used by net/ark PMD for packet data movement Result is a constant O(1) time for all packets that fit in a single mbuf (See next slide) More CPU cycles for your application Fewer CPU cores needed for same amount of work 14息2017 Atomic Rules LLC
  • 16. Zero Packets Dropped 16息2017 Atomic Rules LLC
  • 17. Questions / Feedback Is FPGA acceleration of packet-based DPDK workloads of interest? Are there specific challenges you are facing that perhaps Arkville will help solve? How do you measure success? Do you have a target platform in mind? How would you like to get started? 17息2017 Atomic Rules LLC
  • 18. Summary and Thank You! 18息2017 Atomic Rules LLC Arkville is a GPP/FPGA DPDK-Aware Conduit Software is an Open-Source DPDK Poll Mode Driver RTL IP Core Gateware is sold by Atomic Rules Named-Project and Site-Based Licenses are Available Arkville is Agnostic Support for Contemporary FPGA Devices Support for COTS and Custom FPGA Boards Arkville is Supported Ongoing developments to the DPDK/LF Community AR offers both HW and SW services and support
  • 19. Roadmap: 17.08 19息2017 Atomic Rules LLC August 2017 Support for DPDK 17.08 Support for Vivado 2017.2 Examples include Atomic Rules TimeServo[1] Timestamps from MAC to DPDK metadata [1] TimeServo is a separate IP product that may be purchased from Atomic Rules.
  • 20. Roadmap: 17.11 20息2017 Atomic Rules LLC November 2017 Support for DPDK 17.11 Support for Vivado 2017.3 Available with 16 RX Queue-Pairs Next-Generation MBUF Prefetcher Still Zero-Copy and Low-microsecond Twire-to-user Expanded DPDK examples for VPP and OVS
  • 22. Core Beliefs and Axioms 22息2017 Atomic Rules LLC Our Customers Success is Key Separation of Concerns Divide and Conquer Automate or Die Write Things Once Interface Before Implementation Functional Correctness First Performance Correctness Improved Iteratively Components Must Compose Components Must Work as Expected IP Should be Portable, Vendor-Agnostic if possible
  • 23. Partner Roster 23息2017 Atomic Rules LLC 25G / 50G Ethernet Consortium 25-50-100 Ethernet Alliance Accellera/OCP-IP Community Member Amazon F1 Instance Partner ARM Connected Community Member BittWare Solution Partner Bluespec Technology Partner DPDK Project Corporate Member FPGA, FCCM and FPL F Conference Sponsors Intel Network Builders Linux Foundation Corporate Member MathWorks Connections Partner NetFPGA Infrastructure Developer OpenCPI Infrastructure Developer P4 Language Consortium Member PCI-SIG Corporate Member VITA Trade Association Member Xilinx Alliance Member Partner
  • 24. 100 GbE DPDK Offload 24息2017 Atomic Rules LLC