The Proc1C10N™ is a compact, ultra-high-performance FPGA accelerator built on Altera Stratix® 10 NX FPGA. Designed for AI-driven, compute-intensive, and high-bandwidth applications, it not only integrates embedded Tensor blocks with HBM2 memory but also delivers 143 INT8 TOPS / FP16 TFLOPS of processing power. As a result, this FPGA accelerator provides exceptional throughput and efficiency for advanced AI workloads.
This AI-focused compute accelerator combines 16 × 25 Gb/s full-duplex transceivers with a robust multi-level memory architecture. Additionally, it features embedded MLABs and M20K, tightly coupled HBM2 and eSRAM, and supports up to 128 GB DDR4. Therefore, the Proc1C10N achieves ultra-low latency and high bandwidth, making it ideal for AI acceleration, HPC, networking, and edge-compute environments.
The half-length PCIe Gen3 x16 board includes 4 × QSFP28 ports, a Gidel PHS connector for daughterboards, and 19 GPIOs for peripheral control. Furthermore, the PHS enables up to 128 Gb/s Rx/Tx, ensuring seamless integration with 8× CoaXPress-12 cameras via a Gidel CXP daughterboard. Consequently, the Proc1C10N is well-suited for real-time vision and edge AI applications.
Supported by Gidel’s advanced development suite, the Proc1C10N FPGA accelerator streamlines integration and shortens development cycles. Moreover, it supports C and HDL-based design, reducing engineering effort, enhancing reliability, and accelerating time-to-market.
Embedded Tensor blocks for optimized AI performance
HBM2 memory for 10X more DRAM and SRAM bandwidth
143 INT8 TOPS / FP16 TFLOPS for high-demand AI workloads
Compact PCIe design for versatile system integration
For more accelerator card options, visit FPGA Compute Acceleration – Gidel
The Proc1C10N™ system is based on the Proc10N module mounted on the Gidel Proc1C carrier board.
For additional Proc10N carrier board options models, including options that utilize the Proc10N’s full resources, contact the Gidel Sales.
| Name | Description | Type | Size | |
|---|---|---|---|---|
|
Proc10N: Datasheet
|
FPGA module | 194.4 KB | ||
|
Proc10N: Block Diagram
|
FPGA module | JPG | 73.9 KB | |
|
Proc1C: Datasheet
|
Carrier Board | 133.5 KB | ||
|
Proc1C: Block Diagram
|
Carrier Board | Link | — | Open |
The Proc1C10N is specifically AI-optimized. Built on the Altera Stratix 10 NX, it features embedded Tensor Blocks that deliver an incredible 143 INT8 TOPS / FP16 TFLOPS of processing power. This architecture is designed to provide maximum throughput and efficiency for the most demanding deep learning and AI-driven workloads.
The integration of 8 GB HBM2 provides a memory bandwidth of 300 GB/s, which is up to 10X more than traditional DRAM and SRAM solutions. This massive bandwidth, tightly coupled with the FPGA fabric and embedded M20K and MLAB blocks, eliminates data bottlenecks, enabling ultra-low latency for real-time AI acceleration and High-Performance Computing (HPC).
The board features 4 × QSFP28 ports providing up to 400 Gb/s aggregate bandwidth, alongside a PCIe Gen3 x16 host interface. It also includes 16 × 26 Gb/s full-duplex transceivers and Gidel’s PHS connector, which supports up to 128 Gb/s for seamless integration with daughterboards, such as the 8× CoaXPress-12 module.
Yes. By combining its massive AI processing power with the ability to acquire high-speed camera data through the PHS connector, the Proc1C10N is an ideal platform for Real-Time Edge AI. It can perform complex image analysis, object detection, or signal processing “on-the-fly” as data is acquired, without needing to offload tasks to a separate CPU/GPU.
Despite its extreme performance, the Proc1C10N typically consumes less than 100W (depending on the application). It is built for mission-critical reliability with an MTBF exceeding 1 million hours (with passive cooling) and includes comprehensive board management tools for monitoring temperature, voltage, and clocking.
The card is fully supported by the Gidel ProcDev Kit (FPGA Programming SDK). It streamlines development by supporting both C and HDL-based design, allowing engineers to efficiently map their AI models and algorithms to the Stratix 10 NX’s Tensor blocks while automating the creation of drivers and host APIs.
The Proc1C10N is the premier choice for:
Advanced AI Acceleration: Deep learning inference, neural networks, and AI-driven data analytics.
High-End Vision: Real-time surveillance, autonomous systems, and medical imaging.
Networking & Security: Deep Packet Inspection and low-latency network analysis.
Scientific Computing: Linear Algebra, 3D applications, and High-Performance Reconfigurable Computing (HPRC).
All Gidel products come with a 12-month warranty, dedicated technical support, and regular firmware and driver updates to ensure high-performance reliability in demanding, long-term deployments.
