Is this your business? Claim it to manage your IP and profile
ZIA Stereo Vision (SV) represents DMP's cutting-edge depth sensing solution, engineered to offer high-precision stereo vision for various AI applications. It's designed to process stereo images for advanced depth mapping, utilizing 4K inputs to facilitate distance estimation via stereo matching algorithms like Semi-Global Matching (SGM). Through this technique, ZIA SV ensures that distance information is extracted accurately, a critical capability for applications like autonomous mobile robots or advanced imaging systems. Pre- and post-processing optimization provides the ZIA SV with the tools necessary to refine depth estimates and ensure high accuracy. It supports 8-bit greyscale inputs and outputs a disparity map with an accuracy up to 0.8%, provided by advanced filtering techniques that enhance precision while maintaining a compact form factor crucial in embedded systems. This IP core integrates smoothly into systems requiring reliable depth measurement, utilizing efficient AMBA AXI interfaces for easy integration into diverse applications. With capabilities to support a wide range of hardware platforms and favorable performance-to-size ratios, the ZIA Stereo Vision core embodies DMP's philosophy of compact, high-performance solutions for smarter decision-making in machine vision applications.
The M3000 Graphics Processor is DMP's offering for high-power 3D graphics processing designed for energy-efficient performance. It features sophisticated graphics processing capabilities based on DMP’s proprietary Musashi 3D graphics architecture. This architecture is tailored to deliver state-of-the-art graphics performance, specifically aligning with complex computation requirements found in VR and AR applications, alongside other visual computing demands. The M3000 is crafted to achieve optimal Power, Performance, and Area (PPA) metrics, supporting OpenGL ES 3.0 to ensure compatibility with cutting-edge visual processing standards. Its adaptability stems from a flexible shader cluster architecture that can be adjusted to meet varying client needs for performance and size. This flexibility extends to its implementational capacity across diverse devices such as ASICs, ASSPs, SoCs, and more. Technically, the M3000 supports outputs at resolutions reaching 4k x 2k, with interfaces like AXI 3/4 and APB for communication, suited for numerous applications ranging from IoT devices to automotive infotainment systems. This processor redefines efficiency and power in graphics acceleration, rendered for seamless integration into modern HMI systems.
The ant300 GPU from Digital Media Professionals is a state-of-the-art unit tailored for 2D graphics applications. This GPU showcases a perfect balance between efficiency and performance, integrating a streamlined architecture for high throughput in low-power usage scenarios. Its edge in the graphics domain lies in a refined approach to rendering 2D graphics with a focus on resource optimization, fitting well within embedded systems where space and power efficiency are vital. Designed to meet specific needs of low latency and speed, the ant300 efficiently handles a multitude of graphics operations, ensuring fluid motion and rapid redraws. It plays a crucial role in systems where consistent high-speed graphic operations are critical without incurring excessive power costs. Built with a view towards adaptability, the ant300 fits seamlessly within various industrial domains, including consumer electronics and portable devices. This GPU is engineered to sustain high-performance metrics over extended periods, making it ideal for applications within industrial controls and portable entertainment systems. Its design allows for easy integration within broad device ecosystems, solidifying DMP's reputation for delivering graphics solutions that balance between high performance and energy conservation effortlessly.
ZIA Image Signal Processing (ISP) sets the standard for compact image signal processing solutions, integrating seamlessly into AI camera systems. This ISP excels in handling high sensitivity image sensors like Sony's IMX390, providing superior noise reduction and adaptable dynamic range control in challenging lighting conditions. ZIA ISP's capabilities include handling HDR through its sophisticated noise reduction techniques to maintain image clarity and adaptability even in adverse weather, making it highly reliable for safety-critical high dynamic environments. Leveraging advanced integration techniques, ZIA ISP achieves top-notch performance through pre-processing, ensuring that any image input undergoes rigorous enhancement before analysis. The model enhances pedestrian detection and tracking by maintaining identification post light adjustments, illustrating its resilience and adaptability in dynamic lighting scenarios. Technical specifications of ZIA ISP include support for IMX390 image sensors at full HD 1920 x 1080 30fps, with a dynamic range of 120dB, achieving exceptional clarity in video output. It brings together proprietary image enhancement capabilities, such as automatic white balance correction and scalable output formats, ensuring a complete signal processing package. ZIA ISP delivers dynamically in managing high visual fidelity through real-time corrective processes, confirming its essential role in visual data processing applications targeting robust projects.
The ZIA DV700 Series represents a sophisticated AI processing solution, optimized for a broad range of data types such as images and videos. This product line offers a unique combination of high inference speed and precision, effectively balancing real-time processing, safety, and privacy requirements for edge-based AI systems. Offering support for deep neural network (DNN) models, this series allows seamless inference processing, essential for applications requiring device independence and reliable AI functioning. The core of the ZIA DV700 lies in its ability to handle inference tasks with multiple AI models simultaneously. Known for its Hardware architecture, the DV700 supports a full suite of models like MobileNet and Yolo v3, ensuring robust object detection and segmentation processes. Moreover, it provides a development environment, featuring SDKs and tools compatible with standard AI frameworks, enabling easy model integration and processing tasks. Distinct features of the DV700 include its use of FP16 precision for floating-point computations, retaining the high accuracy rates established during model training from PC or cloud-based servers. As a result, it is an ideal choice for autonomous driving applications and robotics systems, where AI interpretation efficiency directly correlates with system safety and dependability. By facilitating seamless AI inference without retraining models, the DV700 series marks a significant leap in inference processing efficiency and versatility for varied model structures.
The ant200 Vector Graphics Processor from DMP focuses on delivering robust 2D graphic rendering capabilities with efficiency as a central theme. This device suits a wide range of commercial applications, emphasizing high-throughput processing without extensive power demands, making it particularly applicable in compact, portable devices or where thermal constraints are a consideration. Engineered for versatility, the ant200 manages complex vector graphics operations, ensuring that design processes and implemented graphics operate smoothly and responsively. Its architecture supports scalable graphical enhancements and seamlessly fits into applications requiring dynamic graphical representations, such as interface design tools and intricate visualization software. Adopting a lightweight design, the ant200 facilitates cost-effective deployment in a variety of scenarios, from educational tools to industrial machinery interfaces. Its balance of quality and resourcefulness ensures that it retains high operational standards across varying deployment scenarios, reinforcing DMP's commitment to providing adaptable, energy-efficient graphic processing solutions.
Designed for mobile environments, the ant100 Mobile GPU from DMP offers a robust solution for 2D graphics rendering in power-sensitive devices. Prioritizing energy efficiency without sacrificing performance, the ant100 thrives in conditions where battery conservation and compact form factors are crucial. This GPU caters specifically to the needs of portable devices and mobile platforms, enhancing graphical operations by optimizing render processes and minimizing resource footprint. It provides a high-performance output for 2D graphic needs, directly benefiting consumer electronics such as smartphones and tablets where space and energy budgets are constrained. Products leveraging the ant100 realize significant benefits in graphics rendering efficiency, reducing overall energy consumption while maintaining high graphic fidelity. Its architecture is meticulously crafted to meet the unique challenges of mobile computing constraints, ensuring that design sophistication does not compromise on practical usability.
The K3000 Vector Graphics Processor is engineered for enhanced vector handling, delivering comprehensive 2D graphic support within DMP's processor lineup. Built to cater to vector-specific tasks, this processor specializes in rendering and managing vector-based graphics with efficiency. Its architecture ensures that the processor can tackle real-time vector computations with precision, offering scalable performance for diverse applications. Specifically engineered to integrate into systems requiring responsive graphic computations, the K3000 excels in providing high-quality vector rendering with minimal delay. This makes it a prime choice for use in devices where graphic resolution and quality directly impact user interaction, such as media creation tools and educational software. With the capability to handle intricate graphic designs and data transformations, K3000's programming flexibility and operational consistency make it an asset for developers and manufacturers aiming to enhance their graphical offerings. Its energy-efficient nature and robust connection protocols allow for a vast array of deployment opportunities across different hardware infrastructures.
The A3000 V2 Neural Processing Unit (NPU) from DMP is at the forefront of AI processor design, offering remarkable performance per watt in a compact form. Built around high-efficiency cores, it is designed to handle diverse AI inference tasks at remarkable speed and accuracy, exceeding 40TOPS for various reasoning processes. With parallelized multi-core architecture, it efficiently handles computations for varied models, significantly enhancing AI-driven operations. The A3000 V2 is adept at executing mixed precision computing, striking the right balance between performance and precision through hybrid exact computation methods. Supporting a broad array of data formats such as INT4/INT8 and FP8/FP16, it stands out in processing extensive datasets with reduced latency, ensuring seamless AI model adaptability and integration. It is particularly suitable for devices that require top-tier AI processing capabilities, facilitated by a robust data format support system and extensive ONNX operator coverage. Applications in edge devices, robotics, and any platform demanding high computational throughput find a natural fit with the A3000 V2, thanks to its optimized power, performance, and area metrics, thereby allowing for extensive deployment across several AI-centric scenarios.
Join the world's most advanced semiconductor IP marketplace!
It's free, and you'll get all the tools you need to evaluate IP, download trial versions and datasheets, and manage your evaluation workflow!
To evaluate IP you need to be logged into a buyer profile. Select a profile below, or create a new buyer profile for your company.
