Industrial Motherboards and SBCs
Industrial-Grade Boards with Various Form Factors
For Diverse Applications
Industrial Touch Panel PCs and Monitors
IP Rated Touchscreen Computers For HMI Integration
13th Gen Intel® Core™ Processors
Industrial x86 Rugged Computers
13th Gen Intel® Core™ Processor Industrial Computers
As Edge AI applications continually become more prevalent and advanced in Industry 4.0, so will the demand for rugged edge solutions to reliably process and consolidate complex AI workflows in real-time.
Premio’s portfolio of Industrial GPU Computers provides a diverse selection of x86 and ARM-based solutions supported by either an NVIDIA GPU or NVIDIA Jetson Modules, providing high performance compute at the rugged edge.
- Tailored solutions for various ranges of Edge AI workloads
- Supports NVIDIA Professional GPUs or Jetson Orin System on Modules (SoM)
- UL Certified for Safety and Reliability
- Super-Rugged & Semi-Rugged computing solutions
Products:
Industrial GPU Computers for Edge AI Workloads
Our portfolio of industrial GPU computers accommodates various edge AI workloads. From standard to high-performance computing, Premio has an edge computing solution that can best suit the deployment application.
JCO-6000-ORN High Performance AI Edge Computer
Jetson AGX Orin Support
Featuring NVIDIA Jetson AGX Orin 32GB/64GB system-on-module (SOM), the JCO-6000 Series offers exceptional AI performance with up to 275 TOPS. With configurable power modes (40W to 60W), rugged design, NVMe data storage and modular I/O, it meets the demands of edge computing in the harshest conditions.
Key Features:
- High-speed Vision Camera support: support GMSL 2 QUAD Port Mini Fakra, PoE+, and USB 3 Vision
- Support EDGEBoost I/O Modules: Mix & Match Modularity
- Out-Of-Band (OOB) device management module
Key Applications:
- AGV & AMR Application
- Rugged Edge AI
- Industrial and Factory Automation
JCO-3000-ORN Mid-Range AI Edge Computer
Jetson Orin NX/Nano Support
Featuring NVIDIA Jetson NX (16GB/8GB) and Nano (8GB/4GB) Orin system-on-module (SOM), the JCO-3000 Series offers mid-range AI performance with up to 100 TOPS. With configurable power modes (7W to 25W), rugged design, NVMe data storage, and rich I/O, it meets the demands of edge computing in the harshest.
Key Features:
- Leverage PoE for Machine Vision: up to 4x PoE Camera
- Multiple DIO Ports with 8x/16x DIO
- Out-of-Band Module for Remote Management
Key Applications:
- Autonomous Vehicle
- Security Surveillance
- Industrial Automation
JCO-1000-ORN Entry-Level AI Edge Computer
Jetson Orin Nano Support
Featuring NVIDIA Jetson Nano (8GB/4GB) Orin system-on-module (SOM), the JCO-1000 Series offers entry-level AI performance with up to 40 TOPS. With a low configurable power (7W to 15W), rugged design, ultra-compact size, balanced I/O, it is well-suited for the IoT and edge processing in Industry 4.0.
Key Features:
- Ultra-Compact Form Factor
- On-Board Isolated DIO (4in/4out)
- 4K Display
Key Applications:
- Drone Inspection
- Smart Gateway
- General Robotics
RCO-6000 Series AI Edge Inference Computer
Low-Profile GPU Support
This industrial GPU computer takes a modular approach by utilizing EDGEBoost technologies. In specific EDGEBoost Node configurations, it offers support for a low-profile GPU to enable various edge AI workloads, along with optional hot-swappable data storage in NVME or SATA.
Key Features:
- Low-profile GPU
- PCIe Gen 4
- Modular EDGEBoost Technologies
Key Applications:
- People & Vehicle Counting
- Traffic Flow Analysis
- Middle-Mile Delivery
VCO-6000 Series Machine Vision Computer
Dual-GPU Support (Full-Height, Full-Length)
Streamline complex AI workloads with support for dual-GPU configurations. This high-performance industrial GPU computer supports full-height, full-length (FHFL) GPUs for unrestricted edge AI processing.
Key Features:
- Dual-GPU (FHFL)
- PCIe Gen 4
- Hot-swappable NVMe Storage Bays
Key Applications:
- Quality & Defect Detection
- Predictive Maintenance
- Digital Twin & Sensor Fusion
BCO-6000-RPL Series High Performance Industrial Computer
Low Profile GPU Support
Supported by 13th Gen Intel TE Processors, the BCO-6000-RPL brings high performance for real time edge AI and IoT workloads. Leveraging additional Gen 4 PCIe expansion accelerates edge performance with GPU integration.
Key Features:
- PCIe 4.0 Expansion (Low-profile GPU Support)
- Rich, High Speed I/O
- Edge AI Ready
Key Applications:
- Industrial Automation & Robotics
- Rugged Edge AI
- IIoT Gateway
KCO-3000 Series 3U Fanned Industrial Computer
Dual-GPU Support
This industrial GPU computer offers a COTS approach for rapid time-to-market while delivering maximized edge AI performance with dual-GPU support. Unlike the VCO, the KCO-3000-RPL is only compatible with mid-sized GPUs up to 8.5” (215.9mm) or smaller.
Key Features:
- Dual-GPU (up to 8.5")
- PCIe Gen 5
- 3U Rack Mountable
Key Applications:
- Industrial Automation Robotics
- Anomaly Detection & Monitoring
- Predictive Maintenance
KCO-2000 Series 2U Fanned Industrial Computer
Low-Profile GPU Support
Purpose-built to seamlessly integrate into existing or new OEM/ODM systems for speedier time-to-market. Leveraging its small form factor, this industrial GPU computer can manage edge AI applications with support for a low-profile GPU.
Key Features:
- Low-profile GPU
- PCIe Gen 5
- 2U Short Depth Chassis
Key Applications:
- Industrial Automation Robotics
- Quality & Defect Detection
- Predictive Maintenance
Industrial GPU Computer Specifications
| Use Case | Processor | System Cooling | Expansion Options | Operating Temp. | Shock & Vibration | Certifications | ||
|---|---|---|---|---|---|---|---|---|
RCO-6000-RPL AI Edge Inference Computer |
Super-Rugged | 13th/12th Gen Intel® ADL & RPL Processor (35W TDP) | Passive Cooling (Fanless) |
- PCIe Gen 4 Expansion - Low-profile GPU - EDGEBoost Nodes - EDGEBoost I/O - Up to 8x Hot-Swappable SATA/NVMe SSDs |
-25°C to 70°C |
With HDD: 1 Grms With SSD: 5 Grms / 20G |
UL 62368 Ed. 3, CE, FCC Class A | See RCO-6000-RPL |
VCO-6000-RPL Machine Vision Computer |
Super-Rugged | 13th/12th Gen Intel® ADL & RPL Processor (35W TDP) | Active Cooling |
- PCIe Gen 4 Expansion - Dual-GPU (FHFL) - Up to 4x Hot-Swappable SATA/NVMe SSDs |
-25°C to 70°C |
With HDD: 1 Grms With SSD: 3 Grms / 50G |
UL 62368 Ed. 3, CE, FCC Class A | See VCO-6000-RPL |
KCO-3000-RPL 3U Industrial Fanned Computer |
Semi-Rugged | 13th/12th Gen Intel® Core™ i9/i7/i5/i3 Alder lake-S, Raptor Lake-S Processor (65W Max TDP) | Active Cooling |
- PCIe Gen 5 Expansion - Dual-GPU |
0°C to 60°C | 1 Grms With SSD: 25G | UL 62368 Ed. 3, CE, FCC | See KCO-3000-RPL |
KCO-2000-RPL 2U Industrial Fanned Computer |
Semi-Rugged | 13th/12th Gen Intel® Core™ i9/i7/i5/i3 Alder lake-S, Raptor Lake-S Processor (65W Max TDP) | Active Cooling |
- PCIe Gen 5 Expansion - Low-profile GPU - 1x Hot-swappable SATA SSD |
0°C to 60°C | 1 Grms With SSD: 25G | UL 62368 Ed. 3, CE, FCC | See KCO-2000-RPL |
BCO-6000-RPL High Performance Industrial Computer |
Semi-Rugged | 13th/12th Gen Intel® IoTG Processor Core i9/i7/i5/i3, Pentium, Celeron (35W only) | Passive Cooling (Fanned w/ GPU) |
- PCIe Gen 4 Expansion - Low-profile GPU |
0°C to 50°C | 1 Grms With SSD: 25G | UL 62368 Ed. 3, CE, FCC | See BCO-6000-RPL |
JCO-6000-ORN High-Performance AI Edge Computer |
Super Rugged | NVIDIA® Jetson Orin AGX 32GB/64GB | Passive Cooling | EDGEBoost I/O Modules | -20°C to 50°C |
With SSD: 50G, half sine, 11ms With SSD: 5 Grms, 5 - 500 Hz, 0.5 hr/axis |
CE, FCC Class A, UL Pending, E-Mark, EMC Conformity | See JCO-6000-ORN |
JCO-3000-ORN Mid-Range AI Edge Computer |
Super Rugged | NVIDIA® Jetson Orin™ NX 8GB/16GB or Nano 4GB/8GB | Passive Cooling | N/A |
-20°C to 55°C (25W, NX Module) -20°C to 60°C (15W, Nano Module) |
With SSD: 50G, half sine, 11ms With SSD: 5 Grms, 5 - 500 Hz, 0.5 hr/axis |
CE, FCC Class A, UL Pending, E-Mark, EMC Conformity | See JCO-3000-ORN |
Entry-level AI Edge Computer |
Super Rugged | NVIDIA® Jetson Orin™ Nano 4GB/8GB | Passive Cooling | N/A | -25°C to 60°C |
With SSD: 50G, half sine, 11ms With SSD: 5 Grms, 5 - 500 Hz, 0.5 hr/axis |
CE, FCC Class A, UL Pending, E-Mark, EMC Conformity |
Download Our Solution Guide For Embedded Computer and Industrial Touch Display Solutions
NVIDIA Hardware Accelerators for Premio’s Industrial GPU Computers
NVIDIA GPUs and Jetson Module Specifications
Supports JCO Series
Supports VCO-6000-RPL, KCO-3000-RPL
Supports RCO-6000-RPL, KCO-2000-RPL
| Model Name | RAM | CUDA Cores | TDP | AI Performance (TOPS/ TFLOPS) | Compatibility |
| Jetson AGX Orin | 32G/64G | 2048/1792 | 15-60 | 200-275 TOPS (5.3 TFLOPS) | |
| Jetson Orin NX | 8G/16G | 1024 | 10-25 | 70-100 TOPS | |
| Jetson Orin Nano | 4G/8G | 512/1024 | 7-15 | 20-40 TOPS | |
| NVIDIA T1000 | 8G | 896 | 50 | 2.5 TFLOPS | |
| NVIDIA RTX A2000 | 12G | 3328 | 70 | 8 TFLOPS | |
| NVIDIA RTX 4000 SFF | 20G | 6144 | 70 | 19.2 TFLOPS | |
| NVIDIA RTX A4000 | 16G | 6144 | 140 | 19.2 TFLOPS | |
| NVIDIA RTX 4070 | 12G | 5888 | 200 | 29 TFLOPS |
How Industrial GPU Computers Streamline Edge AI Workloads
Industrial GPU Computers can accelerate edge AI and machine learning workloads with the help of the parallel processing power, CUDA, and tensor cores of GPUs. These features allow for multiple tasks to be operated simultaneously and with mixed precision, which means that calculations are dynamically adapted to accelerate throughput while preserving accuracy.
Key Technologies:
- Parallel Processing Architecture
- Tensor Cores
- CUDA (Compute Unified Device Architecture)
How NVIDIA Jetson enhances Edge AI computing
NVIDIA Jetson modules are a family of embedded computing platforms designed to bring accelerated AI computing to edge devices. These modules are compact, energy-efficient, and equipped with powerful GPUs designed specifically for running AI and machine learning workloads.
Key Benefits:
- Compact form factor
- Low Power Consumption
- High compute performance for AI & ML tasks
RISC vs CISC Architecture
In rugged edge computing applications, choosing between ARM and x86 architectures depends on the specific requirements of the application. Learn the in-depth differences between the architectures and its key advantages that they provide in edge computing deployments.
Premio is part of NVIDIA Partner Network that provides in-depth knowledge into the latest technologies powering machine learning and artificial intelligence. Our rugged edge computing solutions are validated to support enterprise performance acceleration cards (GPUs) from NVIDIA's portfolio of compute, virtualization, and visualization products.
Learn More
Premio is part of PNY's Pro Partner network of distribution that provides access to NVIDIA's Professional GPUs. PNY is a global technology leader within the OEM, consumer and channel electronics markets. Established in 1985, PNY celebrates its 30th year of business excellence serving consumers, system integrators, OEMs, and B2Bs.
Learn More
Intel® Partner Alliance (IPA) is a program offered by Intel Corporation that provides various benefits and resources to its partners. The program is designed to foster collaboration, support, and growth for businesses that work with Intel products and technologies.
Learn More
Markets
Case Studies
FAQ
NVIDIA Jetson is a family of edge AI computing platforms designed to bring the power of artificial intelligence to embedded systems. These compact and energy-efficient platforms feature high AI performance, enabling real-time AI inferencing for a wide range of applications.
Jetson AGX Orin, Jetson Orin NX, Jetson Orin Nano
An Industrial GPU computer is a rugged, edge computing solution that utilizes a dedicated GPU (Graphics Processing Unit) card for computational intensive applications requiring advanced image processing and machine vision/intelligence. In addition to a performance boost from the GPU, an industrial GPU computer will also have all the key requirements of what makes up an industrial computer, such as support for high shock/vibration ratings, wide operating temperatures, and over voltage/reverse polarity protection. The industrial GPU computer is transforming how factory automation and smart manufacturing verticals are utilizing computational analysis and machine intelligence in real-time.
- Computer / Machine Vision
- Production line inspection
- Medical imaging
- Metrology imaging
- Facial recognition
- Navigation
- Autonomous vehicle
- Pathfinding
- Automation
- Factory automation
- Pathfinding
- Artificial Intelligence
- Deep learning
- Machine learning
Both GPUs (Graphics Processing Unit) and CPUs (Central Processing Unit) have many traits in common; they are both specifically designed microprocessors to handle various tasks. The key difference is HOW they process these tasks. In a computer, the CPU is often referred to as the brain of the system; it is the central processing unit which handles all computing tasks. A GPU, while similar to a CPU, is engineered specifically to process or render graphics. As such, a GPU can work in conjunction with the CPU to help it offload graphics intensive tasks, while freeing up the CPU for other non-graphics related jobs.
The CPU is ideal for serialized, generic tasks, which makes it well-suited for common business or productive applications such as Word, Excel, or a web browser. The number of cores in a given CPU is limited, up to 28 cores for the latest Xeon server class CPU. Conversely, the GPU comes with hundreds or even thousands of cores, which is designed for parallelized, specific tasks; the GPU is optimized for intensive computational applications such as image processing or AI.
As an example, let's examine the fundamentals of image processing. The 4K image of the clock consists of 8.2 million discrete pixels (4K resolution is 3,840 x 2,160, which gives us 8.2 million pixels). From a high level, in order to process the image, we will need to perform some type of computation to each individual pixel. If this task is given to a CPU, with its limited number of cores, the processing time will take very long, as the CPU does not have enough cores to handle the task in parallel. The GPU, which its thousands of specialized cores, can complete the task up to 50-100X faster due to its parallel architecture. This makes the GPU the optimal microprocessor to handle tasks that require parallelism with a high degree of computation.
We begin with a proven embedded system that is engineered to withstand extreme shock and vibration, along with a wide operating temperature range; the inclusion of an industrial class GPU will enable the system to operate reliability in industrial/manufacturing sectors, with the GPU handling AI or image processing applications that require massive parallelism.
One way to compare the performance of various GPUs is by their TFLOP rating. TFLOP stands for "teraflop," which is a measurement of the GPU to performance one trillion floating point operations per second. By adding a GPU to an industrial system, another critical variable we need to consider is the TDP (Thermal Design Power) rating of the GPU. The TDP rating tells us the maximum heat, in watts, generated by the GPU when operating at maximum capacity. This is key in determining the operational temperature range of an industrial GPU system, which should be optimally in the range of -25C to 60C for factory/manufacturing averse conditions. By looking at the Performance versus TDP chart below, we can see the direct correlation between these two values: as the GPU performance increases, so does its corresponding TDP value. When designing an industrial GPU system, there is a fine balance to strike between GPU performance versus overall system operating temperature.
The difference between a GPU and CPU are their computing architecture and task specializations. CPUs are responsible for sequential processing, meaning that it utilizes a smaller number of cores for managing tasks and intensive single-thread applications. GPUs, however, have significantly more cores and leverage parallel processing for simultaneously processing multiple tasks. CPUs are responsible for running the operating system and managing applications while GPUs process machine learning workloads and rendering graphics.
Learn more about CPU vs GPU vs TPU
The key differences between NVIDIA’s professional and consumer GPUs are: workload optimization, memory configuration, and power-to-performance balancing. Professional NVIDIA GPUs, such as Quadro, are catered towards processing AI workloads with relatively lower TDP, while consumer NVIDIA GPUs, like RTX, are focused on general-purpose processing and can have much higher TDP.
Learn more about edge-focused GPUs in our comprehensive GPU guide for industrial computers
Industrial GPU computers work with edge AI by providing the necessary components to enable and process complex workload applications.
First, these computers are purpose-built to withstand the rigorous conditions and environments at the edge. Factory floors and outdoor environments are generally not suitable for consumer desktops as they will eventually fail. Premio’s industrial GPU computers are UL certified, meaning they have undergone thorough testing and validation to ensure safety standard compliance, and select computers have compliance with MIL-STD-810G for shock and vibration.
Secondly, Industrial GPU computers utilize a heterogeneous computing approach to leverage optimized performance through a mixture of specific components, like the CPU and GPU. GPUs are efficient and effective at parallel processing, while the CPU’s strengths are in sequential processing.
Third is IoT connectivity. There are multiple IoT devices in the form of cameras, sensors, and such that need to connect to a centralized computer to process all the incoming data. Industrial GPU computers provide compatible I/O to connect and even power IoT devices.
By balancing both rugged reliability, processing power, and IoT connectivity, industrial GPU computers help drive complex edge AI workloads at the rugged edge.
Learn more about how industrial GPU computers enable Edge AI here
Yes, industrial GPU computers are machine vision systems that deliver the needed processing power and I/O connectivity to enable machine vision applications.