Technology Leadership in Enabling Advanced Host CPU Offload

Accolade’s line of ANIC (Advanced NIC) FPGA based 1-100GE PCIe adapters and ATLAS 1U platform enable Intelligent Host CPU Offload features such as 100% packet capture, flow classification, flow shunting, deduplication, packet filtering and more. Our customers are global leaders in network monitoring & cybersecurity applications as well as in the network test and measurement, telecom and video stream monitoring markets.

Utilizing Accolade’s universal API, customers can seamlessly migrate across the entire ANIC product line from 1 – 100GE.

Nov 2017 – Flow ShuntingGain complete, dynamic control over which traffic flows are forwarded from ANIC adapter to applicaton. – “Flow Shunting” preserves critical CPU cycles to enable unprecedented application performance and significant cost savings. It reduces the number of packets an application must process to provide complete, dynamic control over traffic flows forwarded from the FPGA to the application. CPU bound network monitoring and cyber security applications such as Suricata, Wireshark, ntop and others will now be able to take advantage of this capability in hardware, optimizing packet processing in order to scale such software applications at 10, 40 and 100GE.

June 2017 – ANIC-200KFlexFlexible 25/40/50/100G QSFP28 Host CPU Offload Packet Capture NIC – The ANIC-200KFlex is an FPGA-based PCIe NIC designed for demanding cyber security / network monitoring applications. Featuring dual QSFP28 (or QSFP+) interfaces, ports can be mixed and matched to support 25,40,50,100G configurations. The ANIC-200KFlex comes complete with an array of packet processing features such as precise timestamping (4nS precision), packet merging, tunnel decapsulation, packet slicing, packet filtering, deduplication, packet steering, direct memory access (DMA) and more.

February 2017 – ATLAS-1000Fully Integrated 1U, OEM Host CPU Offload Platform – The ATLAS-1000 strategically enables OEM customers to develop leading edge, value added network security and monitoring software applications through a turnkey model. The ATLAS-1000 features a powerful multi-core Intel CPU, memory and storage simultaneously integrating Accolade’s APP (Advanced Packet Processor) onboard FPGA with acceleration features that include lossless packet capture, flow classification, packet steering, packet merging, packet filtering, nanosecond precision timestamping and more.

October 2016 – ANIC-200KuThird Generation Dual 100G PCIe Application Acceleration Adapter – Designed for demanding network monitoring and security applications, the ANIC-200Ku provides sophisticated flow classification and flow filtering capabilities enabling up to 32 million unique (based on 3 or 5-tuple) IP flows to be tracked. Flow filtering enables security features such as blacklist matching by allowing individual flows to be programmatically forwarded to the CPU, dropped or redirected out of either CFP4 port. This adapter features dual 100GbE CFP4 interfaces supporting SR4 and LR4 optical modules and is designed for NEBS compliance.

February 2016 – ANIC-80KuDual 40GbE/8 X 10GbE State-of-the-Art Application Acceleration Adapter – The ANIC-80Ku is an advanced PCIe Gen 3 adapter featuring two QSFP+ Interfaces which support operations as a Dual 40GbE or 8 X 10GbE adapter. The ANIC-80Ku enables OEM customers to fast-track product time-to-market through software innovation for next generation network monitoring and security solutions utilizing advanced feature sets such as Flow Classification, Fast Lookup Table & much more.

January 2016 – ANIC-40KuQuad port 10GbE Advanced Flow Processor – The ANIC-40Ku features unprecedented flow processing functions such as an onboard Fast Look-up Table, Flow based Filtering, Flow Classification & Tracking in addition to unmatched scalability and ultra-low latency at the absolute best value per 10G port.

April 2015 – ANIC-200K4Dual 100GbE lossless packet capture network adapter with CFP4 Support – Designed for demanding Network Monitoring and Security Applications, the ANIC-200K4 is a state of the art 100G PCIe NIC featuring CFP4 Interfaces supporting LR4 and SR4 Modules.

August 2014 – ANIC 200kDual 100GbE FPGA based deep packet analysis adapter – The ANIC-200K, a breakthrough product, features 200 Gbps lossless packet capture and processing along with deep on-board memory buffers and a high performance TX-DMA engine which operates on a Ring Buffer or in Scatter-gather Mode.

February 2013 – ANIC-40K3 4 X 10 GbE, PCIe Gen 3, FPGA based adapter – The market’s first FPGA based PCIe Gen 3 adapter achieves breakthrough performance with 40Gbps packet transfers across the PCIe bus with zero packet loss.

In the News

100% Packet Capture

At the core of all ANIC adapters is the FPGA based Advanced Packet Processor (APP) which features a high performance pipe-lined packet processing engine, a high performance DDR3 memory and PCIe DMA interface.

Learn More »

Packet Slicing

The APP features a flexible approach for packet header slicing in applications that only need to process and forward a selected offset into the Ethernet Frame without need to process and forward packet payload data.

Learn More »

Hardware Based Flow Classification

The APP hash-based classifier generates a 24 bit hash key using the Layer 3/4  five-tuple (IP source address, UDP/TCP source port, IP destination address, UDP/TCP destination port, protocol id).

Learn More »

Packet Merging

In applications where a single receive port is connected to an aggregation Tap, Mirror or SPAN port of a Switch, packets are time stamped in order of arrival, processed by the APP and forwarded to the Host CPU.

Learn More »

Packet Filtering

At the core of all ANIC adapters is the FPGA based Advanced Packet Processor (APP) which features a high performance pipe-lined packet processing engine, a high performance DDR3 memory and PCIe DMA interface.

Learn More »

Traffic Shaping

Traffic shaping is applied on traffic sources entering a network to ensure the traffic complies with a contract which may be enforced in the network.

Learn More »