LMS ÜberNIC | NIC Cards Leveraging PCIe 5.0 + CXL

Fully Hardware-Accelerated Network Stack

First Use Case Targets Financial Services Industry (FSI)

The First FPGA-Powered CXL NIC

PCIe 5.0 + CXL

Liquid-Markets-Solutions (LMS) have done something unique: moved the full network stack into an FPGA. What’s even better is that FPGA is Agilex I-Series from Intel, with the groundbreaking performance of PCIe 5.0 + CXL.

Called ÜberNIC, this family of NIC cards is built on BittWare hardware for enterprise-class deployment in datacenters.

Game-Changing Performance for Fintech

ÜberNIC for Low-Latency Trading

Today's NICs Don't Stack Up for Market Trading

Fact: today’s market feeds regularly pass 850 Mb/s—the point at which even the best competitive NIC’s network stack begin to dramatically lose sufficient latency performance.

Enter ÜberNIC, the first commercially-available FPGA NIC with the entire network stack in accelerated hardware, allowing for consistent low latency—ready for today’s markets and the future.

Key Features at a Glance for Financial Services Industry (FSI)

Performance

Raw performance improvement that’s consistent through the critical peak market feed moments when you need it most!

Utility

More fiber pairs per card means getting more out of each server. Powerful enough for ancillary services like PCAP and timestamping on the same card.

Future Compatible

Support for latest PCIe 5.0, CXL, and link speeds up to 400G.

Foundation

100% Offload

By moving the complete network stack into FPGA hardware, the ÜberNIC achieves unmatched performance.

RFC & IEEE Compliant

Fiber Port Density Leader

Single-slot card supports up to 16× 10/25G fiber pairs

Multi-GB On-board Memory

Single-Slot, Compact Form Factor

Tap into the Power of Agilex^® 7

Central to the performance gains of ÜberNIC over competitors is the Intel Agilex 7 FPGA. This chip brings the core features like PCIe 5.0 and CXL—plus I/O giving double (or more) the port density of even top competitors.

Performance & Usability

Full RTT (95th percentile): Sub-Microsecond Latency

At its core, ÜberNIC is a low-latency focused NIC. With the combination of full hardware acceleration and low-latency PCIe transfers, you get unmatched performance—even during peak market times.

267% Higher Throughput Without Performance Loss

Highly Consistent; 95th Percentile Latency StDev 2.19%

Multi-GB DDR Buffer Ensures Lossless Reception

Plug & Play x86 I/O (BSD/POSIX; Raw Frame; Custom API)

Built on BittWare

BittWare brings enterprise-class products to market using the latest technology such as Agilex FPGAs. Today’s high-speed interfaces require significant care in the design and manufacturing process to make a reliable, high-quality product at scale.

Pictured is our manufacturing facility at ISI, a Molex company, in California.

Extensibility

FPGA-Exclusive Functions

Only FPGA-based solutions with bundled hardware network allows for all these extensible functions.

MAC-based Timestamping

Market Data Handling & Line Arbitrage

Data Preprocessing, Filtering, & Enhancement

MAC-based PCAP & Port Spanning

Simultaneous Network I/O Support for SW & HW EUC

Ultra-Low Latency Performance

Showing RTT latency ÜberNIC up to 10 Gb/s. The cards can run in servers without CXL, but CXL is also a supported option.

ÜberNIC Network I/O RTT Latency

FSI Focus (64B UDP Payload) | Ultra-Low Latency | Full 10GbE Throughput | Zero Frames Dropped

Tested By Naros.TaSR

Each Test 5,495,000 Frames | Multi-Step Variable Throughput Rate | 10GbE

Configuration Overview

Each ÜberNIC configuration is single width and passively cooled.

ÜberNIC Ultra | ÜberNIC Ultra+

Single Width, Low Profile | Up to 8× 1/10/25G Links

ÜberNIC Ultra Wide | ÜberNIC Ultra+ Wide

Single Width, FH ¾L | Up to 16× 1/10/25G Links

Product Features

ÜberNIC is Available in a Variety of Configurations

PCIe 3/4/5 x16 | CXL x16

ÜberNIC Bitstream
Full Network Stack in Hardware
Low Profile (HHHL)
Intel Agilex I-Series
FPGA: AGI 019
Link Speeds
1/10/25/40/50/100/200/400 GbE
QSFP-DD up to 8× 1/10/25G,
or 1× 400G, or 2× 200G, or 4× 100G
16GB DDR4 Total (Two Banks)

PCIe 3/4/5 x16 | CXL x16

User-Programmable ÜberNIC
Full Network Stack in Hardware
Low Profile (HHHL)
Intel Agilex I-Series
FPGA: AGI 023
Link Speeds
1/10/25/40/50/100/200/400 GbE
QSFP-DD up to 8× 1/10/25G,
or 1× 400G, or 2× 200G, or 4× 100G
16GB DDR4 Total (Two Banks)

PCIe 3/4/5 x16 | CXL x16

ÜberNIC Bitstream
Full Network Stack in Hardware
Single Slot, FH ¾L
Intel Agilex I-Series
FPGA: AGI 019
Link Speeds
1/10/25/40/50/100/200/400 GbE
QSFP-DD up to 16× 1/10/25G,
or 1× 400G, or 2× 200G, or 4× 100G
Up to 64GB DDR4 Total (Two Banks)

PCIe 3/4/5 x16 | CXL x16

User-Programmable ÜberNIC
Full Network Stack in Hardware
Single Slot, FH ¾L
Intel Agilex I-Series
FPGA: AGI 023
Link Speeds
1/10/25/40/50/100/200/400 GbE
QSFP-DD up to 16× 1/10/25G,
or 1× 400G, or 2× 200G, or 4× 100G
Up to 64GB DDR4 Total (Two Banks)

Get in Touch

Ready to learn more about ÜberNIC? Reach out to BittWare to learn more!

"*" indicates required fields

Name*

First Last

Email*

Phone

If we can reach you by phone, please provide a number in addition to email.

Company Division

Company/Organization

If you are requesting pricing, please provide a company/organization name.

This field is hidden when viewing the form

Address and City

Street Address Address Line 2 City ZIP / Postal Code

Country*

Required field for directing your inquiry to the correct team

Country

US State*

State

Canadian Province*

Province

How can we help you?

LMS ÜberNIC | NIC Cards Leveraging PCIe 5.0 + CXL

Fully Hardware-Accelerated Network Stack

First Use Case Targets Financial Services Industry (FSI)

PCIe 5.0 + CXL

Game-Changing Performance for Fintech

ÜberNIC for Low-Latency Trading

Today's NICs Don't Stack Up for Market Trading

Key Features at a Glance for Financial Services Industry (FSI)

Performance

Utility

Future Compatible

Foundation

100% Offload

RFC & IEEE Compliant

Fiber Port Density Leader

Multi-GB On-board Memory

Single-Slot, Compact Form Factor

Tap into the Power of Agilex® 7

Performance & Usability

Full RTT (95th percentile): Sub-Microsecond Latency

267% Higher Throughput Without Performance Loss

Highly Consistent; 95th Percentile Latency StDev 2.19%

Multi-GB DDR Buffer Ensures Lossless Reception

Plug & Play x86 I/O (BSD/POSIX; Raw Frame; Custom API)

Built on BittWare

Extensibility

FPGA-Exclusive Functions

MAC-based Timestamping

Market Data Handling & Line Arbitrage

Data Preprocessing, Filtering, & Enhancement

MAC-based PCAP & Port Spanning

Simultaneous Network I/O Support for SW & HW EUC

Ultra-Low Latency Performance

ÜberNIC Network I/O RTT Latency

FSI Focus (64B UDP Payload) | Ultra-Low Latency | Full 10GbE Throughput | Zero Frames Dropped

Configuration Overview

Each ÜberNIC configuration is single width and passively cooled.

ÜberNIC Ultra | ÜberNIC Ultra+

Single Width, Low Profile | Up to 8× 1/10/25G Links

ÜberNIC Ultra Wide | ÜberNIC Ultra+ Wide

Single Width, FH ¾L | Up to 16× 1/10/25G Links

Product Features

ÜberNIC is Available in a Variety of Configurations

ÜberNIC

ÜberNIC

ÜberNIC

ÜberNIC

Get in Touch

Where to Next?

FPGA Acceleration of Binary Weighted Neural Network Inference

TeraBox 1400B Family of 1U FPGA Servers, Four Cards, U.2 Storage and AMD or Intel CPU

IA-440i PCIe Accelerator with Intel Agilex FPGA

PCIe Data Capture White Paper

Follow Us

Tap into the Power of Agilex^® 7