All IPs > Graphic & Peripheral > GPU
Graphics Processing Units (GPUs) have revolutionized the way we interact with digital content, making it more immersive and visually engaging. At the core of modern graphics technology lies GPU semiconductor IPs, which are integral to delivering outstanding visual performance across a wide array of devices. Whether it’s for rendering the latest video game graphics, enhancing multimedia playback, or powering complex computational tasks, these semiconductor IPs play a crucial role.
GPU semiconductor IPs are designed to efficiently handle a myriad of operations, predominantly focusing on parallel processing. This capability allows GPUs to process multiple tasks simultaneously, making them ideal for graphics rendering, high-definition video playback, and complex simulations. This category includes essential components like shaders, compute engines, and video encoders, which work in harmony to deliver seamless graphics experience.
Products within the GPU semiconductor IP category serve a diverse range of industries. In consumer electronics, GPUs are deployed in smartphones and tablets to enhance user interfaces and enable applications like augmented reality. In high-performance computing, they are an essential part of servers and workstations for tasks such as artificial intelligence, machine learning, and big data analytics. Furthermore, the gaming industry benefits from these semiconductor IPs by providing photorealistic graphics and smooth gameplay.
Selecting the right GPU semiconductor IP can significantly impact the performance and efficiency of the final product. With the rapid advancement of display technologies and the increasing demand for richer visual content, developers and manufacturers seek the most innovative and adaptable GPU IP solutions to remain competitive. By incorporating cutting-edge semiconductor IPs, they can deliver the next generation of visually stunning and energy-efficient products.
The KL730 is a sophisticated AI System on Chip (SoC) that embodies Kneron's third-generation reconfigurable NPU architecture. This SoC delivers a substantial 8 TOPS of computing power, designed to efficiently handle CNN network architectures and transformer applications. Its innovative NPU architecture significantly optimizes DDR bandwidth, providing powerful video processing capabilities, including supporting 4K resolution at 60 FPS. Furthermore, the KL730 demonstrates formidable performance in noise reduction and low-light imaging, positioning it as a versatile solution for intelligent security, video conferencing, and autonomous applications.
The GH310 is specialized GPU IP tailored for 2D sprite graphics with an emphasis on high pixel processing capabilities. It achieves minimal gate count, ensuring it occupies less silicon area while delivering robust graphic outputs. Designed to handle large volumes of sprite graphics efficiently, the GH310 is perfect for applications requiring rapid rendering and minimal hardware overhead. This makes it favorable for systems where space and power savings are crucial yet high-quality graphics are needed. Its architecture allows for optimized performance tailored for specific graphical needs, translating into a resource-efficient solution for developers seeking to integrate intricate graphical features in their products without excessive resource consumption.
The Chimera GPNPU from Quadric is designed as a general-purpose neural processing unit intended to meet a broad range of demands in machine learning inference applications. It is engineered to perform both matrix and vector operations along with scalar code within a single execution pipeline, which offers significant flexibility and efficiency across various computational tasks. This product achieves up to 864 Tera Operations per Second (TOPs), making it suitable for intensive applications including automotive safety systems. Notably, the GPNPU simplifies system-on-chip (SoC) hardware integration by consolidating hardware functions into one processor core. This unification reduces complexity in system design tasks, enhances memory usage profiling, and optimizes power consumption when compared to systems involving multiple heterogeneous cores such as NPUs and DSPs. Additionally, its single-core setup enables developers to efficiently compile and execute diverse workloads, improving performance tuning and reducing development time. The architecture of the Chimera GPNPU supports state-of-the-art models with its Forward Programming Interface that facilitates easy adaptation to changes, allowing support for new network models and neural network operators. It’s an ideal solution for products requiring a mix of traditional digital signal processing and AI inference like radar and lidar signal processing, showcasing a rare blend of programming simplicity and long-term flexibility. This capability future-proofs devices, expanding their lifespan significantly in a rapidly evolving tech landscape.
The KL520 was Kneron's first foray into AI SoCs, characterized by its small size and energy efficiency. This chip integrates a dual ARM Cortex M4 CPU architecture, which can function both as a host processor and as a supportive AI co-processor for diverse edge devices. Ideal for smart devices such as door locks and cameras, it is compatible with various 3D sensor technologies, offering a balance of compact design and high performance. As a result, this SoC has been adopted by multiple products in the smart home and security sectors.
The Mixed-Signal CODEC offered by Archband Labs integrates advanced analog and digital audio processing to deliver superior sound quality. Designed for a variety of applications such as portable audio devices, automotive systems, and entertainment systems, this CODEC provides efficiency and high performance. With cutting-edge technologies, it handles complex signal conversions with minimal power consumption. This CODEC supports numerous interface standards, making it a versatile component in numerous audio architectures. It's engineered to offer precise sound reproduction and maintains audio fidelity across all use cases. The integrated components within the CODEC streamline design processes and reduce the complexity of audio system implementations. Furthermore, the Mixed-Signal CODEC incorporates features that support high-resolution audio, ensuring compatibility with high-definition sound systems. It's an ideal choice for engineers looking for a reliable and comprehensive audio processing solution.
The KL630 chip stands out with its pioneering NPU architecture, making it the industry's first to support Int4 precision alongside transformer networks. This unique capability enables it to achieve exceptional computational efficiency and low energy consumption, suitable for a wide variety of applications. The chip incorporates an ARM Cortex A5 CPU, providing robust support for all major AI frameworks and delivering superior ISP capabilities for handling low light conditions and HDR applications, making it ideal for security, automotive, and smart city uses.
The PDM-to-PCM Converter from Archband Labs leads in transforming pulse density modulation signals into pulse code modulation signals. This converter is essential in applications where high fidelity of audio signal processing is vital, including digital audio systems and communication devices. Archband’s solution ensures accurate conversion, preserving the integrity and clarity of the original audio. This converter is crafted to seamlessly integrate with a wide array of systems, offering flexibility and ease-of-use in various configurations. Its robust design supports a wide range of input frequencies, making it adaptable to different signal environments. The PDM-to-PCM Converter also excels in minimizing latency and reducing overhead processing times. It’s engineered for environments where precision and sound quality are paramount, ensuring that audio signals remain crisp and undistorted during conversion processes.
The GV380 is a compact and powerful GPU IP designed to handle complex vector graphics with ease. This OpenVG 1.1 compliant GPU leverages a fourth generation architecture that minimizes CPU load while maximizing pixel performance in vector processing. The IP is ideal for embedded systems needing enhanced 2D graphics performance. It can seamlessly integrate with digital cameras and similar devices to render high-quality graphics without burdening the central processing unit. This efficiency is crucial in environments where processing capacity and battery life are valued. By offering substantial gains in pixel processing through innovative architectural improvements, the GV380 enables richer graphics and smoother interactions in embedded applications, supporting enhanced user experiences.
The KL530 is built with an advanced heterogeneous AI chip architecture, designed to enhance computing efficiency while reducing power usage. Notably, it is recognized as the first in the market to support INT4 precision and transformers for commercial applications. The chip, featuring a low-power ARM Cortex M4 CPU, delivers impressive performance with 1 TOPS@INT 4 computing power, providing up to 70% higher processing efficiency compared to INT8 architectures. Its integrated smart ISP optimizes image quality, supporting AI models like CNN and RNN, suitable for IoT and AIoT ecosystems.
The 2D FFT core is engineered to deliver fast processing for two-dimensional FFT computations, essential in image and video processing applications. By utilizing both internal and external memory effectively, this core is capable of handling large data sets typical in medical imaging or aerial surveillance systems. This core leverages Dillon Engineering’s ParaCore Architect utility to maximize flexibility and efficiency. It takes advantage of a two-engine design, where data can flow between stages without interruption, ensuring high throughput and minimal memory delays. Such a robust setup is vital for applications where swift processing of extensive data grids is crucial. The architecture is structured to provide consistent, high-quality transform computations that are essential in applications where accuracy and speed are non-negotiable. The 2D FFT core, with its advanced design parameters, supports the varied demands of modern imaging technology, providing a reliable tool for developers and engineers working within these sectors.
The DB9000AXI Display Controller is an advanced solution for LCD and OLED panels, supporting resolutions ranging from 320x240 up to 1920x1080 in its standard release, with capabilities expanding to 4K and 8K in advanced modes. This controller integrates with frame buffer memory via the AMBA AXI protocol fabric, offering programmable resolutions. Optional features include overlay windows, hardware cursor, and advanced color space conversion.
The Hyperspectral Imaging System developed by Imec represents a significant advancement in the realm of imaging technology. This sophisticated system is capable of capturing and processing a wide spectrum of wavelengths simultaneously, making it ideal for detailed spectral analysis in both industrial and research applications. This imaging system is instrumental in providing accurate and high-resolution data that can be crucial in fields like agriculture, environmental monitoring, and medical diagnostics. Imec's Hyperspectral Imaging System is notable for its integration into small and efficient devices, enabling portable and flexible use in various scenarios. The system's design leverages cutting-edge nanoelectronics to ensure that it is both lightweight and highly functional, offering unparalleled performance on the go. Its ability to capture detailed spectral information expands its utility across multiple disciplines, making it a versatile tool for addressing complex analytical challenges. The unique technology behind this system is grounded in Imec's expertise in photonics and CMOS sensors, ensuring superior sensitivity and precision. This hyperspectral imaging technology is designed to provide real-time, reliable information with a high degree of accuracy, supporting applications that require detailed spectroscopic data, thus empowering industries to make more informed decisions.
GSHARK is a high-performance GPU IP designed to accelerate graphics on embedded devices. Known for its extreme power efficiency and seamless integration, this GPU IP significantly reduces CPU load, making it ideal for use in devices like digital cameras and automotive systems. Its remarkable track record of over one hundred million shipments underscores its reliability and performance. Engineered with TAKUMI's proprietary architecture, GSHARK integrates advanced rendering capabilities. This architecture supports real-time, on-the-fly graphics processing similar to that found in PCs, smartphones, and gaming consoles, ensuring a rich user experience and efficient graphics applications. This IP excels in environments where power consumption and performance balance are crucial. GSHARK is at the forefront of embedded graphics solutions, providing significant improvements in processing speed while maintaining low energy usage. Its architecture easily handles demanding graphics rendering tasks, adding considerable value to any embedded system it is integrated into.
The KL720 is engineered for high efficiency, achieving up to 0.9 TOPS per Watt, setting it apart in the edge AI marketplace. Designed for real-world scenarios where power efficiency is paramount, this chip supports high-end IP cameras, smart TVs, and AI-enabled devices like glasses and headsets. Its ARM Cortex M4 CPU facilitates the processing of complex tasks like 4K image handling, full HD video, and 3D sensing, making it versatile for applications that include gaming and AI-assisted interactions.
The RegSpec tool from Dyumnin Semiconductors is a sophisticated code generation solution designed to create comprehensive CCSR codes from various input formats including SystemRDL, IP-XACT, CSV, Excel, XML, and JSON. This tool not only outputs Verilog RTL, System Verilog UVM code, and SystemC header files but also generates documentation in multiple formats such as HTML, PDF, and Word. Unlike traditional CSR code generators, RegSpec covers intricate scenarios involving synchronization across multiple clock domains, hardware handshakes, and interrupt setups, which typically require manual coding. It aids designers by offering full support for complex CCSR features, potentially reducing the design cycle time and improving accuracy. For verification purposes, RegSpec generates UVM-compatible code, enabling seamless integration into your verification environment. It also supports RALF file format generation, which aligns with VMM methodologies, thus broadening its applicability across various verification frameworks. In terms of system design, the tool extends its capabilities by generating standard C/C++ headers essential for firmware access and creating SystemC models for comprehensive system simulations. Furthermore, RegSpec ensures compatibility and interoperability with existing industry tools through import and export functionalities in SystemRDL and IP-XACT formats. The tool's versatility is highlighted by its ability to handle custom data formats, offering robust flexibility for designers working in unique environments. Overall, RegSpec is an indispensable asset for those looking to streamline their register design processes with enhanced automation and reduced manual effort.
The RAIV General Purpose GPU (GPGPU) epitomizes versatility and cutting-edge technology in the realm of data processing and graphics acceleration. It serves as a crucial technology enabler for various prominent sectors that are central to the fourth industrial revolution, such as autonomous driving, IoT, virtual reality/augmented reality (VR/AR), and sophisticated data centers. By leveraging the RAIV GPGPU, industries are able to process vast amounts of data more efficiently, which is paramount for their growth and competitive edge. Characterized by its advanced architectural design, the RAIV GPU excels in managing substantial computational loads, which is essential for AI-driven processes and complex data analytics. Its adaptability makes it suitable for a wide array of applications, from enhancing automotive AI systems to empowering VR environments with seamless real-time interaction. Through optimized data handling and acceleration, the RAIV GPGPU assists in realizing smoother and more responsive application workflows. The strategic design of the RAIV GPGPU focuses on enabling integrative solutions that enhance performance without compromising on power efficiency. Its functionality is built to meet the high demands of today’s tech ecosystems, fostering advancements in computational efficiency and intelligent processing capabilities. As such, the RAIV stands out not only as a tool for improved graphical experiences but also as a significant component in driving innovation within tech-centric industries worldwide. Its pioneering architecture thus supports a multitude of applications, ensuring it remains a versatile and indispensable asset in diverse technological landscapes.
ISPido on VIP Board is a customized runtime solution tailored for Lattice Semiconductors’ Video Interface Platform (VIP) board. This setup enables real-time image processing and provides flexibility for both automated configuration and manual control through a menu interface. Users can adjust settings via histogram readings, select gamma tables, and apply convolutional filters to achieve optimal image quality. Equipped with key components like the CrossLink VIP input bridge board and ECP5 VIP Processor with ECP5-85 FPGA, this solution supports dual image sensors to produce a 1920x1080p HDMI output. The platform enables dynamic runtime calibration, providing users with interface options for active parameter adjustments, ensuring that image settings are fine-tuned for various applications. This system is particularly advantageous for developers and engineers looking to integrate sophisticated image processing capabilities into their devices. Its runtime flexibility and comprehensive set of features make it a valuable tool for prototyping and deploying scalable imaging solutions.
GSV3100 integrates a versatile shader architecture designed to support both 2D and 3D graphics applications seamlessly. Compatible with OpenGL ES 2.0, 1.1, and OpenVG 1.1 standards, it combines multiple rendering techniques suitable for the latest generation of embedded devices. This IP excels in providing high-quality graphical output with efficient resource management. Its design is optimal for applications demanding precise, intricate graphics without offsetting performance with excessive CPU strain. Further enhancing its utility, the GSV3100 ensures that both high-performance and energy-intensive tasks can be handled with ease, positioning it as a cornerstone for advanced embedded system designs.
The GV580 stands out as a hybrid GPU IP, merging 2D and 3D rendering strengths to deliver optimum performance. Supporting both OpenVG 1.1 and OpenGL ES 1.1 standards, this GPU IP ensures comprehensive compatibility and advanced graphics rendering. A significant feature of the GV580 is its capability to provide high-resolution graphics that demand low power, making it suitable for applications in energy-constrained environments. This GPU IP allows devices to manage complex graphical processing tasks efficiently, thereby alleviating pressure from the main processor. With a focus on reducing power requirements while increasing processing efficiency, the GV580 is an essential component in developing advanced user interfaces for embedded systems, providing flexibility and adaptability across diverse applications.
The UltraLong FFT is designed specifically for handling lengthy data sequences and is optimized for Xilinx FPGAs. This core utilizes external memory to enable the processing of very large block sizes, suitable for applications requiring extensive data handling. Performance is typically constrained by the bandwidth of the external memory, making this a robust option for demanding applications where memory resources are a pivotal consideration. By leveraging Dillon Engineering's sophisticated ParaCore Architect utility, the UltraLong FFT Core is tailored to individual project needs. This core provides engineers with a flexible tool, capable of adapting to variable lengths and data throughput requirements. As such, it plays a vital role in numerous fields including astrophysics and remote sensing, where large-scale data manipulation is essential. The core's architecture is finely tuned to achieve optimal data throughput while balancing memory usage. This makes it highly desirable in scenarios where efficiency and scale are crucial, enabling extensive and complex computations to be conducted seamlessly on FPGA platforms.
The Universal DSP Library offers a comprehensive suite of digital signal processing components optimized for FPGA implementations. This library integrates seamlessly with the AMD Vivado ML Design Suite, providing essential components such as FIR filters, CIC decimating filters, mixers, and CORDIC function approximations. It includes tools that facilitate the connection of DSP systems together, allowing for rapid assembly of signal processing chains using Vivado’s GUI or direct VHDL instantiation. Each component within the library is accessible in both raw VHDL code and as an AMD Vivado ML Design Suite IPI block. This dual availability enables quick development and simulation of processing chains before moving to FPGA implementation. The Universal DSP Library is equipped with bit-true software models for each DSP block, allowing developers to evaluate and optimize systems in software to ensure precise functioning when deployed on hardware. Key features include support for multiple data channels, continuous wave, and pulse processing, as well as real and complex signal support. It utilizes the AXI4-Stream protocol, providing a standardized interface that simplifies integration and enhances the development of specific DSP solutions. The library is suitable for applications ranging from software-defined radio and communication systems to robotics and medical diagnostics, showcasing its versatility in various high-tech fields.
The MVUM1000 ultrasound sensor array is an advanced medical imaging module that incorporates 256 linear capacitive micromachined ultrasound transducers (CMUTs). This makes it highly suitable for modern medical applications, offering superior versatility and integration.<br><br>Its capacitive transduction mechanism enhances the sensor's power efficiency while maintaining high sensitivity to acoustic pressure, essential for precise imaging. The device supports various imaging modes, broadening its applicability in complex medical diagnostics.<br><br>The design accommodates advanced interface electronics for streamlined integration into point-of-care and hand-held ultrasound devices, as well as traditional cart-based ultrasound systems. Built to accommodate compact and energy-conscious operations, it is available with customizable features to meet specific medical requirements.
Primex Wireless' Bluetooth Digital Clock in the Levo Series represents a modern approach to maintaining synchronized time. Utilizing Bluetooth Low Energy technology, these clocks form mesh networks that ensure precise timekeeping across various spaces. Ideal for dynamic environments such as educational institutions or medical centers, they provide flexibility with their ability to be placed virtually anywhere within Bluetooth range without the need for wiring. The Levo Series clocks are equipped with energy-efficient LED displays available in multiple color options, allowing organizations to choose what best suits their decor while ensuring readability. These clocks are particularly effective in settings that require easy viewing from a distance, such as large lecture halls or hospital corridors, blending functionality with modern aesthetics. Their simplicity in installation and configuration makes them a preferred choice for facilities upgrading their timekeeping systems. Featuring compatibility with the OneVue® software platform, these clocks are part of an intuitive system that allows for remote management via web interfaces, providing administrators the flexibility to update time displays or check device status from any location. This integration supports a cohesive time management strategy, vital for operations where timing ensures effective workflow and patient care.
aiSim 5 is a premier simulation tool tailored for ADAS (Advanced Driver Assistance Systems) and automated driving validations. As the world's first ISO26262 ASIL-D certified simulator, aiSim 5 employs state-of-the-art AI-based digital twin technology. This enhances its capability to simulate complex driving scenarios with high precision, making it an ideal environment for testing AD systems. The simulator boasts a proprietary rendering engine that provides a deterministic and high-fidelity virtual reality where sensor simulations can cover diverse climatic and operational conditions, such as snow, rain, and fog, ensuring results are reproducible and reliable.\n\naiSim 5's architecture is designed for flexibility, allowing seamless integration with existing development toolchains, and thus minimizing the need for expensive real-world testing. It features a comprehensive 3D asset library that includes detailed environments, vehicles, and scenarios, which can be customized to generate synthetic data for testing. The solution supports multi-sensor simulations, providing a rich testing ground for developers looking to refine and validate their software stacks.\n\nThanks to its modular C++ and Python APIs, aiSim 5 can be easily deployed within any System under Test (SuT) and CI/CD pipeline, enhancing its adaptability across various automotive applications. Additionally, its open SDK facilitates developer customizations, ensuring aiSim 5 remains adaptable and user-friendly. With built-in scenario randomization, users can efficiently simulate a wide array of driving conditions, making aiSim 5 a powerful tool for ensuring automotive system safety and accuracy.
The ZIA Image Signal Processing provides a compact imaging solution particularly designed for AI camera systems. Its compatibility with Sony Semiconductor's IMX390 image sensor is notable, offering sophisticated functions even under harsh conditions like rain or backlight. It supports high dynamic range (HDR) capabilities, which enables it to manage noise effectively, maintaining clarity in diverse lighting scenarios. This processor pairs seamlessly with DMP's camera modules to deliver high-fidelity imaging. It features dynamic range compression (DRC) and tone mapping, vital for capturing and processing vibrant images in professional settings. The ISP capabilities are optimized for integrating with advanced AI processing workflows, thus contributing to enhanced object detection processes. Equipped to handle various image settings, including defect pixel correction and auto gain control, the ZIA ISP can adapt to shifts in scene composition, showcasing versatility across different device architectures. It supports multiple video interfaces, ensuring flexibility in deployment across multiple platforms.
The RayCore MC Ray Tracing GPU is a cutting-edge GPU IP known for its real-time path and ray tracing capabilities. Designed to expedite the rendering process efficiently, this GPU IP stands out for its balance of high performance and low power consumption. This makes it ideal for environments requiring advanced graphics processing with minimal energy usage. Capitalizing on world-class ray tracing technology, the RayCore MC ensures seamless, high-quality visual outputs that enrich user experiences across gaming and metaverse applications. Equipped with superior rendering speed, the RayCore MC integrates sophisticated algorithms that handle intricate graphics computations effortlessly. This GPU IP aims to redefine the norms of graphics performance by combining agility in data processing with high fidelity in visual representation. Its real-time rendering finesse significantly enhances user interaction by offering a flawless graphics environment, conducive for both immersive gaming experiences and professional metaverse developments. The RayCore MC GPU IP is also pivotal for developers aiming to push the boundaries of graphics quality and efficiency. With an architecture geared towards optimizing both visual output and power efficiency, it stands as a benchmark for future GPU innovations in high-demand industries. The IP's ability to deliver rapid rendering with superior graphic integrity makes it a preferred choice among developers focused on pioneering graphics-intensive applications.
ELFIS2 represents a leap forward in high-speed imaging, particularly valuable for scientific research that demands rapid capture rates without sacrificing detail or clarity. This sensor enhances image quality under fast-paced conditions, perfect for understanding dynamic processes in both natural and laboratory settings. Its low-noise design further supports clarity in fast imaging scenarios, making it an ideal choice for scientific experiments that necessitate temporal precision along with visual accuracy.
The JH7100 platform is a sophisticated vision processing solution integrating dual-core U74 processors that share a 2MB L2 cache with operational frequencies up to 1.2GHz, featuring Linux OS support. The in-house developed ISP by StarFive is adaptable with mainstream camera sensors, and its built-in image and video processing subsystem supports H264/H265/JPEG encoding. It integrates high-efficiency, low-power vision DSP and neural network engines to deliver exceptional AI and media performance for real-time processing needs, making it suitable for a variety of edge-focused visual applications.
The HUMMINGBIRD Optical Network-on-Chip from Lightelligence is an innovative solution designed to optimize on-chip data communication using photonic technology. This product facilitates smooth and efficient data transfer processes, capitalizing on the speed and bandwidth advantages of optical signals over traditional electronic counterparts. The HUMMINGBIRD is engineered to enhance chip performance, particularly in environments where rapid data exchange is crucial.<br> <br> Targeted at high-performance computing applications, the HUMMINGBIRD product minimizes latency and power consumption. It is strategically developed to address the bottlenecks typically associated with electronic data transfers, providing a robust framework for on-chip networking that supports intensive computational workloads. Its architecture allows for seamless integration with a variety of chip designs, making it adaptable for several usage scenarios.<br> <br> With the HUMMINGBIRD Optical Network-on-Chip, developers and businesses can expect improved performance in processing tasks, contributing to more efficient and powerful computing platforms. As photonic technology becomes increasingly integral to advanced computing solutions, HUMMINGBIRD stands out as a key player, offering competitive advantages that align with future technological trajectories.
Crest Factor Reduction (CFR) is integral to optimizing the power output of RF power amplifiers by reducing the peak-to-average power ratio of input signals. Systems4Silicon’s FlexCFR is designed as a highly configurable solution that adapts seamlessly to any vendor's hardware, providing versatility across different platforms including ASICs, FPGAs, and SoCs.\n\nFlexCFR enables significant improvements in amplifier efficiency by managing the signal envelope. This management leads to lower peak power requirements and hence better energy performance. The technology is agnostic of communication standards, which offers broad compatibility with various wireless protocols and systems, aligning perfectly with the dynamic demands of modern communications markets.\n\nDeploying FlexCFR ensures that telecommunications systems operate more efficiently, with reduced waste energy and extended hardware longevity, maintaining optimal performance across a range of conditions. Systems4Silicon supports the seamless integration of this technology, offering extensive expertise and services to maximize its benefits for clients.
The Video Wall Display Management System is a flexible solution using FPGA technology, designed for high-quality image processing and output across multiple displays. It handles input from HDMI or Display Port sources, delivering processed video synchronized on up to four individual screens. This system is ideal for setups requiring intricate video configurations, such as digital signage or multi-display environments. It supports resolutions up to 3840x2400p60 for input and up to 1920x1200p60 for outputs, providing excellent image clarity and synchronization. Its flexibility is enhanced by supported configuration modes including Stretch, Cloned, and Independent outputs, with customizable bezel compensation. A software API facilitates easy configuration and control, ensuring seamless management of video outputs. The Video Wall System is continually being refined, with future developments aiming at greater support for larger display setups through linked FPGA units. This system provides a robust solution for customizable, high-quality video display management, catering to diverse application needs.
iCEVision facilitates rapid prototyping and evaluation of connectivity features using the Lattice iCE40 UltraPlus FPGA. Designers can take advantage of exposed I/Os for quick implementation and validation of solutions, while enjoying compatibility with common camera interfaces such as ArduCam CSI and PMOD. This flexibility is complemented by software tools such as the Lattice Diamond Programmer and iCEcube2, which allow designers to reprogram the onboard SPI Flash and develop custom solutions. The platform comes preloaded with a bootloader and an RGB demo application, making it quick and easy for users to begin experimenting with their projects. Its design includes features like a 50mmx50mm form factor, LED applications, and multiple connectivity options, ensuring broad usability across various rapid prototyping scenarios. With its user-friendly setup and comprehensive toolkit, iCEVision is perfect for developers who need a streamlined path from initial design to functional prototype, especially in environments where connectivity and sensor integration are key.
The Pipelined FFT core delivers continuous processing of data streams with efficient memory usage, thanks to its innovative pipelined architecture. Designed for scenarios requiring uninterrupted data flow, such as video processing or large-scale sensor networks, this core stands out for its ability to provide high-speed transformations with minimal latency. The pipelined execution style ensures that the core can maintain constant throughput without waiting for a full set of data before starting processing. This means that data can be continuously fed and transformed, making it particularly apt for real-time applications. The architecture effectively reduces memory bottlenecks, supporting seamless integration into systems where consistent data availability is key. Built using Dillon's powerful ParaCore Architect, this IP core allows for customization in terms of bit-width and point sizes to optimize performance across a variety of FPGA platforms. Its efficient use of logic resources makes it suitable for applications with stringent performance requirements, ensuring that it meets the demands of high-speed, low-latency environments like communications and broadcasting.
The High Performance FPGA PCIe Accelerator Card serves as a high-speed addition for enhancing computational capacity in server units, utilizing Intel Arria 10 FPGA technology. It features dual DDR3 memory banks and a PCIe 3.0 interface, making it perfect for tasks that require rapid data transfer. Designed for high-density server environments, it aids in offloading processing tasks, lowering power consumption while maintaining high performance. This card excels in applications that demand high throughput, such as real-time video processing and algorithm acceleration. In addition to video acceleration capabilities, it supports up to 4k UHD through bi-directional Quad 3G SDI interfaces. Available as a standalone solution or combined with other Korusys IPs, this card is versatile enough to replace or enhance GPU solutions, making it a comprehensive tool for various computational disciplines.
The High Performance FPGA PCIe Accelerator Card serves as a high-speed addition for enhancing computational capacity in server units, utilizing Intel Arria 10 FPGA technology. It features dual DDR3 memory banks and a PCIe 3.0 interface, making it perfect for tasks that require rapid data transfer. Designed for high-density server environments, it aids in offloading processing tasks, lowering power consumption while maintaining high performance. This card excels in applications that demand high throughput, such as real-time video processing and algorithm acceleration. In addition to video acceleration capabilities, it supports up to 4k UHD through bi-directional Quad 3G SDI interfaces. Available as a standalone solution or combined with other Korusys IPs, this card is versatile enough to replace or enhance GPU solutions, making it a comprehensive tool for various computational disciplines.
Badge 2D Graphics offers an advanced solution for 2D graphical displays, suitable for systems requiring comprehensive graphical representations. These graphics are developed for seamless integration into platforms such as Xilinx, showcasing exceptional versatility and reliability with more than 5 million units shipped. The product is highly adaptable, enabling varied graphical tasks and delivering consistent performance across applications. This graphics solution is engineered to support a multitude of functionalities, including video display, textual representation, and multimedia interfacing. It stands out in delivering high-performance visual processing, making it a preferred choice for systems where graphical display quality is essential. Designed with the flexibility to adapt to a variety of multimedia needs, Badge 2D Graphics ensures that visual representation in platforms is both vivid and contextually relevant. The robustness of this solution allows it to integrate smoothly with diverse operational architectures, enhancing the visual display capabilities of embedded systems and consumer products.
D/AVE 2D is an advanced graphics IP core designed for smooth rendering of 2D graphics. It boasts a highly efficient architecture that ensures fast processing speeds and high-performance graphics output, making it ideal for a wide range of display and rendering applications. The core is optimized for low power consumption, which is suited for portable and embedded systems such as handheld devices and automotive displays.
The IMG DXT GPU is tailored for the mobile device market, offering a unique blend of high efficiency and cutting-edge technology, including ray tracing capabilities. Utilizing Imagination's Photon architecture, the DXT promises enhanced performance for mobile visual applications, introducing ray tracing in various configurations to cater to different performance needs while keeping silicon costs in check. This GPU is adaptable, providing manufacturers with the option to integrate ray tracing in a cost-effective manner without sacrificing the mobile experience. With offerings that range from single to quad-RAC configurations, the DXT provides manufacturers the flexibility to choose setups that match their device specifications and performance benchmarks, making it a versatile choice for mobile technology companies. By providing realistic lighting effects in mobile devices, the IMG DXT GPU paves the way for unprecedented graphics quality in smartphones and tablets. It supports broader API coverage, including Vulkan and OpenGL, which ensures it can smoothly run a wide array of mobile applications, making it highly compatible with both existing and emerging technologies in the mobile graphics space.
This Mixed Radix FFT Core is specifically constructed to handle FFT lengths beyond the standard radix-2. By incorporating combinations of radix-2, 3, 5, and 7, this core offers flexibility unprecedented in the FFT computing space. It's an excellent choice for DSP applications necessitating variable FFT sizes, such as seismic data processing or multi-carrier communication systems. Leveraging the ParaCore Architect’s adaptability, the Mixed Radix FFT can be configured for both FPGA and ASIC platforms, providing customizable throughput and memory usage to suit individual application demands. The core's ability to utilize a mixed-radix approach means it can efficiently manage a wide range of lengths, ensuring an optimal balance between speed and resource utilization. Built to integrate seamlessly with other systems, the Mixed Radix FFT Core is known for its robustness and flexibility. Its support for varying radix combinations allows it to meet the specific needs of diversified data processing scenarios, making it an invaluable asset in complex digital signal processing tasks.
The Load Unload FFT provides high-speed transformation capabilities tailored for applications with unique input/output loading needs. It is engineered to facilitate seamless transitions in and out of the FFT process, enabling synchrony with high bandwidth and real-time systems. This feature makes it ideal for industries like communications and radar where continuity and speed are paramount. Constructed with precision using Dillon’s ParaCore Architect utility, this core offers adaptability across various platforms. The core's design allows for efficient resource allocation, reducing latency and enhancing performance in critical applications. Respected for its capacity handling and ease of integration, the Load Unload FFT is a valuable tool for developers looking to optimize data flow in signal processing operations. Engineers can expect dependable operation with low logic utilization, ensuring that even as system demands scale, performance remains unaffected. This adaptability is supported by Dillon Engineering's dedicated focus on scalability and precision in digital signal environments, guaranteeing that the Load Unload FFT delivers consistently high performance.
The D/AVE 3D graphics processor is developed to handle complex 3D rendering tasks with high efficiency. It provides exceptional graphics performance with features supporting rich texture mapping and shading effects. This processor is designed to accelerate graphics applications in consumer electronics, offering robust performance while maintaining energy efficiency in high-demand scenarios.
The Prodigy FPGA-Based Emulator by Tachyum offers a versatile platform for testing and evaluating the performance of their universal processors. This hardware emulator uses multiple FPGA and IO boards, networked within a rack configuration, providing a comprehensive environment for performance measurement and debugging. It supports product evaluation at scale, giving users the ability to test and develop applications efficiently. Designed to emulate full processor cores, each board in the system includes vector and matrix fixed and floating-point processing units, ensuring that a wide variety of computational tasks can be accurately simulated. The architecture of the emulator is particularly beneficial for organizations needing to assess software development and compatibility testing across various hardware configurations. Tachyum’s emulator system becomes an invaluable asset for enterprises planning to integrate Prodigy processors into their infrastructure by providing a low-cost, low-risk evaluation method. This platform aids partners and developers in understanding how Prodigy's unique processor capabilities can be fully exploited in real-world applications, thereby facilitating a smoother transition from existing architectures to Tachyum’s advanced computing solutions.
Conceived for high bandwidth and intense data throughput requirements, the G-Series Controller by MEMTECH is at the forefront of graphics and AI compute solutions. This controller offers exceptional support for GDDR6 memory types, which are pivotal in enhancing graphics performance for gaming, advanced driver assistance systems, and other highly demanding applications. The G-Series Controller's design integrates dual-channel support and interfaces seamlessly with existing infrastructure, offering speeds up to 18 Gbps per pin, a vital feature for cutting-edge graphic and AI tasks. Its sophisticated error management system and automatic retry mechanisms ensure operational continuity and data integrity, pivotal in environments where performance cannot be compromised. Beyond functionality, MEMTECH focuses on creating a controller that aligns with market demands for power efficiency. This product stands as a testament to their innovative approach, meshing high-performance needs with the energy-conscious strategies that modern technologies demand.
The Parallel FFT Core is designed for applications where speed and processing power are crucial. Utilizing a full parallel architecture, it allows for rapid computation of FFTs with minimal latency, achieving a potential throughput of 25 GSPS or more in high-end FPGA configurations like Xilinx's Virtex-5. This makes it especially suitable for data-intensive environments such as telecommunications and scientific computing. The core employs constant twiddle factors, simplifying multiplier complexity and reducing overall logic use. It is particularly advantageous for shorter FFT lengths, up to 128 points, providing tremendous speed and efficiency. By minimizing the required memory resources while maximizing throughput, the Parallel FFT Core stands out as an ideal solution for industries where performance and quick, precise calculations are vital. Engineered through the ParaCore Architect utility, this IP can be customized to fit a variety of applications and devices. Its ability to provide high throughput with low memory usage makes it a core component in applications where real-time data processing is non-negotiable. It is an exemplary tool for customers needing to achieve high-speed transformations without compromising on accuracy or resource efficiency.
The IMG DXS GPU represents a significant leap in safe computing, designed specifically for automotive applications. Its architecturally advanced features deliver 1.5 times the peak performance of previous models, focusing on power efficiency and functional safety. With its pioneering Distributed Safety Mechanisms, the IMG DXS GPU effectively minimizes the power, area, and performance overheads typically associated with achieving ASIL-B compliance. This GPU is engineered to meet the rigorous requirements of automotive computing systems, ensuring secure and highly efficient processing. Built to handle the computational demands of both graphics and AI simultaneously, the DXS leverages Imagination's cutting-edge parallel processing architecture. This flexibility makes it suitable for integration into next-generation automotive cockpit and infotainment systems, where reliability is paramount. The IMG DXS is part of Imagination's innovative approach to combining high performance with functionally safe processing, reflecting the company's commitment to leading the automotive GPU market. In addition to its robust safety features, the DXS GPU supports advanced automotive graphics, leading the way in enhancing visual experiences in vehicle displays. Its design and development have followed the ISO 26262 standard, underpinning its reliability and safety, making it a preferred choice for automotive manufacturers seeking cutting-edge technology that doesn’t compromise on safety or performance.
The IMG CXM is a compact and efficient GPU designed to deliver high-quality graphics in space-constrained devices. Standout features include support for HDR user interfaces, providing vibrant and immersive visual experiences even in smaller form factors. This makes it an ideal solution for integrating high-end graphics capabilities into wearables, smart home devices, and other consumer electronics. CXM's architecture supports advanced features such as gesture recognition, providing a more interactive user experience. Its small silicon footprint leaves room for additional AI hardware, enhancing the device’s ability to perform complex functions while keeping power consumption manageable. This GPU is engineered to respond smoothly to user interactions, making it perfect for fast-paced consumer electronics demands. Equipped with functionalities to manage bandwidth efficiently, the CXM GPU is built to deliver efficient graphical processing with enhanced performance, even in devices where space and power availability are restricted. Tailored for the evolving needs of modern devices, it supports the latest API standards, ensuring that it remains relevant and high-performing within diverse technological landscapes.
Meet our high-performance Low SWaP SDR optimized for AI & ML at the RF edge. Optimized for small form factor applications with challenging SWaP-C requirements and superior integration capabilities, it is ideal for applications like UsX payloads.
The Floating Point Library Core from Dillon Engineering provides customizable IEEE 754 compliant operations, a necessity for applications demanding precise mathematical calculations, such as scientific computing and financial analysis. Utilizing the ParaCore Architect technology, this core allows users to tailor the precision and logic used according to their specific needs, thereby optimizing resource use. This library supports both single and double precision calculations, offering pipeline and parallel processing options to enhance the processing speed, a feature critical in high-performance computing environments. By rendering special IEEE 754 cases optional, it reduces resource consumption in applications where these are unnecessary. Designed for easy incorporation into VHDL or Verilog projects, the Floating Point Library modules are engineered to ensure seamless integration, making it a versatile choice for varied applications. The customizability and efficiency of this core help in achieving high computational performance while managing power and area constraints, vital for sophisticated computing challenges.
The IMG B-Series GPU represents Imagination’s most advanced line of multi-core GPU technology designed to span a wide range of applications, from high-end mobile devices to automotive systems and data centers. Featuring a robust multi-core architecture, it offers scalability and flexibility, making it perfectly suited for performing complex computation and rendering tasks across diverse platforms. B-Series GPUs encompass over twenty configurations, enabling manufacturers to tailor and optimize solutions based on specific performance, area, and power targets. This adaptability allows integration into consumer technology such as DTVs and smart home solutions, as well as sophisticated automotive display systems that require ISO 26262 certification for safety. With performance capabilities reaching 6 TFLOPS, the B-Series targets advanced graphics applications, offering features such as volumetric lighting and physically-based shading. These innovations ensure that high-demand environments like data centers and cloud gaming solutions can operate with minimal energy footprints, delivering premier graphical experiences without compromising on efficiency.
The logiCVC-ML is an advanced video controller designed for TFT LCD displays with resolutions up to 2048x2048. This IP is optimized for AMD Zynq 7000 AP SoC and FPGA platforms, ensuring seamless integration and high-quality video output. With compatibility for various operating systems such as Linux, Android, and Windows Embedded Compact 7, it provides versatile options for display applications. The IP is also backed by comprehensive software drivers, facilitating its implementation in diverse projects.
Join the world's most advanced semiconductor IP marketplace!
It's free, and you'll get all the tools you need to discover IP, meet vendors and manage your IP workflow!
Join the world's most advanced AI-powered semiconductor IP marketplace!
It's free, and you'll get all the tools you need to advertise and discover semiconductor IP, keep up-to-date with the latest semiconductor news and more!
Plus we'll send you our free weekly report on the semiconductor industry and the latest IP launches!