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 AI SoC is equipped with a state-of-the-art third-generation reconfigurable NPU architecture, delivering up to 8 TOPS of computational power. This innovative architecture enhances computational efficiency, particularly with the latest CNN networks and transformer applications, while reducing DDR bandwidth demands. The KL730 excels in video processing, offering support for 4K 60FPS output and boasts capabilities like noise reduction, wide dynamic range, and low-light imaging. It is ideal for applications such as intelligent security, autonomous driving, and video conferencing.
The Origin E1 neural engines by Expedera redefine efficiency and customization for low-power AI solutions. Specially crafted for edge devices like home appliances and security cameras, these engines serve ultra-low power applications that demand continuous sensing capabilities. They minimize power consumption to as low as 10-20mW, keeping data secure and eliminating the need for external memory access. The advanced packet-based architecture enhances performance by facilitating parallel layer execution, thereby optimizing resource utilization. Designed to be a perfect fit for dedicated AI functions, Origin E1 is tailored to support specific neural networks efficiently while reducing silicon area and system costs. It supports various neural networks, from CNNs to RNNs, making it versatile for numerous applications. This engine is also one of the most power-efficient in the industry, boasting an impressive 18 TOPS per Watt. Origin E1 also offers a full TVM-based software stack for easy integration and performance optimization across customer platforms. It supports a wide array of data types and networks, ensuring flexibility and sustained power efficiency, averaging 80% utilization. This makes it a reliable choice for OEMs looking for high performance in always-sensing applications, offering a competitive edge in both power efficiency and security.
The Origin E8 NPUs represent Expedera's cutting-edge solution for environments demanding the utmost in processing power and efficiency. This high-performance core scales its TOPS capacity between 32 and 128 with single-core configurations, addressing complex AI tasks in automotive and data-centric operational settings. The E8’s architecture stands apart due to its capability to handle multiple concurrent tasks without any compromise in performance. This unit adopts Expedera's signature packet-based architecture for optimized parallel execution and resource management, removing the necessity for hardware-specific tweaks. The Origin E8 also supports high input resolutions up to 8K and integrates well across standard and custom neural networks, enhancing its utility in future-forward AI applications. Leveraging a flexible, scalable design, the E8 IP cores make use of an exhaustive software suite to augment AI deployment. Field-proven and already deployed in a multitude of consumer vehicles, Expedera's Origin E8 provides a robust, reliable choice for developers needing optimized AI inference performance, ideally suited for data centers and high-power automobile systems.
Origin E2 NPUs focus on delivering power and area efficiency, making them ideal for on-device AI applications in smartphones and edge nodes. These processing units support a wide range of neural networks, including video, audio, and text-based applications, all while maintaining impressive performance metrics. The unique packet-based architecture ensures effective performance with minimal latency and eliminates the need for hardware-specific optimizations. The E2 series offers customization options allowing it to fit specific application needs perfectly, with configurations supporting up to 20 TOPS. This flexibility represents significant design advancements that help increase processing efficiency without introducing latency penalties. Expedera's power-efficient design results in NPUs with industry-leading performance at 18 TOPS per Watt. Further augmenting the value of E2 NPUs is their ability to run multiple neural network types efficiently, including LLMs, CNNs, RNNs, and others. The IP is field-proven, deployed in over 10 million consumer devices, reinforcing its reliability and effectiveness in real-world applications. This makes the Origin E2 an excellent choice for companies aiming to enhance AI capabilities while managing power and area constraints effectively.
The Mixed-Signal CODEC offered by Archband Labs is engineered to enhance the performance of audio and voice devices, handling conversions between analog and digital signals efficiently. Designed to cater to various digital audio interfaces such as PWM, PDM, PCM conversions, I2S, and TDM, it ensures seamless integration into complex audio systems. Well-suited for low-power and high-performance applications, this CODEC is frequently deployed in audio systems across consumer electronics, automotive, and edge computing devices. Its robust design ensures reliable operation within wearables, smart home devices, and advanced home entertainment systems, handling pressing demands for clarity and efficiency in audio signal processing. Engineers benefit from its extensive interfacing capabilities, supporting a spectrum of audio inputs and outputs. The CODEC's compact architecture ensures ease of integration, allowing manufacturers to develop innovative and enhanced audio platforms that meet diverse market needs.
The Chimera GPNPU by Quadric is a versatile processor specifically designed to enhance machine learning inference tasks on a broad range of devices. It provides a seamless blend of traditional digital signal processing (DSP) and neural processing unit (NPU) capabilities, which allow it to handle complex ML networks alongside conventional C++ code. Designed with a focus on adaptability, the Chimera GPNPU architecture enables easy porting of various models and software application programming, making it a robust solution for rapidly evolving AI technologies. A key feature of the Chimera GPNPU is its scalable design, which extends from 1 to a remarkable 864 TOPs, catering to applications from standard to advanced high-performance requirements. This scalability is coupled with its ability to support a broad range of ML networks, such as classic backbones, vision transformers, and large language models, fulfilling various computational needs across industries. The Chimera GPNPU also excels in automotive applications, including ADAS and ECU systems, due to its ASIL-ready design. The processor's hybrid architecture merges Von Neumann and 2D SIMD matrix capabilities, promoting efficient execution of scalar, vector, and matrix operations. It boasts a deterministic execution pipeline and extensive customization options, including configurable instruction caches and local register memories that optimize memory usage and power efficiency. This design effectively reduces off-chip memory accesses, ensuring high performance while minimizing power consumption.
The KL630 AI SoC embodies next-generation AI chip technology with a pioneering NPU architecture. It uniquely supports Int4 precision and transformer networks, offering superb computational efficiency combined with low power consumption. Utilizing an ARM Cortex A5 CPU, it supports a range of AI frameworks and is built to handle scenarios from smart security to automotives, providing robust capability in both high and low light conditions.
The Origin E6 neural engines are built to push the boundaries of what's possible in edge AI applications. Supporting the latest in AI model innovations, such as generative AI and various traditional networks, the E6 scales from 16 to 32 TOPS, aimed at balancing performance, efficiency, and flexibility. This versatility is essential for high-demand applications in next-generation devices like smartphones, digital reality setups, and consumer electronics. Expedera’s E6 employs packet-based architecture, facilitating parallel execution that leads to optimal resource usage and eliminating the need for dedicated hardware optimizations. A standout feature of this IP is its ability to maintain up to 90% processor utilization even in complex multi-network environments, thus proving its robustness and adaptability. Crafted to fit various use cases precisely, E6 offers a comprehensive TVM-based software stack and is well-suited for tasks that require simultaneous running of numerous neural networks. This has been proven through its deployment in over 10 million consumer units. Its design effectively manages power and system resources, thus minimizing latency and maximizing throughput in demanding scenarios.
The xT CDx is an advanced FDA-approved assay designed for tumor and normal DNA sequencing. Incorporating a comprehensive 648-gene panel, this assay provides critical insights for diagnosing and treating solid tumors, with specific functions in guiding targeted therapies in colorectal cancer patients. The test includes a thorough mutation profiling system that allows healthcare professionals to analyze substitutions, insertions, and deletions, delivering a powerful means to refine treatment options. Beyond the standard, the xT CDx offers tumor and normal matched sequencing to distinguish somatic alterations, reducing false-positive results and improving accuracy in clinical assessments. Its integration into clinical practices is supported by its compatibility with various companion diagnostic claims, making it an essential tool for aligning treatment decisions with approved therapeutic products. By utilizing next-generation sequencing technologies, the xT CDx supports the optimization of treatment pathways and enhances patient care through detailed molecular insights. With the capacity to perform detailed analyses on formalin-fixed paraffin-embedded tumor tissues and matched normal samples, this assay promises high specificity and sensitivity in tumor profiling. Leveraging Tempus' cutting-edge bioinformatics infrastructure, the xT CDx ensures healthcare providers can make informed decisions supported by rich genetic data, setting a transformative benchmark in precision oncology.
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.
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 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 Matchstiq™ X40 by Epiq Solutions is a compact, high-performance software-defined radio (SDR) system designed to harness the power of AI and machine learning at the RF edge. Its small form factor makes it suitable for payloads with size, weight, and power constraints. The unit offers RF coverage up to 18GHz with an instantaneous bandwidth up to 450MHz, making it an excellent choice for demanding environments requiring advanced signal processing and direction finding. One of the standout features of the Matchstiq™ X40 is its integration of Nvidia's Orin NX for CPU/GPU operations and an AMD Zynq Ultrascale+ FPGA, allowing for sophisticated data processing capabilities directly at the point of RF capture. This combination offers enhanced performance for real-time signal analysis and machine learning implementations, making it suited for a variety of high-tech applications. The device supports a variety of input/output configurations, including 1 GbE, USB 3.0, and GPSDO, ensuring compatibility with numerous host systems. It offers dual configurations that support up to four receivers and two transmitters, along with options for phase-coherent multi-channel operations, thereby broadening its usability across different mission-critical tasks.
Dream Chip Technologies' Arria 10 System on Module (SoM) emphasizes embedded and automotive vision applications. Utilizing Altera's Arria 10 SoC Devices, the SoM is compact yet packed with powerful capabilities. It features a dual-core Cortex A9 CPU and supports up to 480 KLEs of FPGA logic elements, providing ample space for customization and processing tasks. The module integrates robust power management features to ensure efficient energy usage, with interfaces for DDR4 memory, PCIe Gen3, Ethernet, and 12G SDI among others, housed in a form factor measuring just 8 cm by 6.5 cm. Engineered to support high-speed data processing, the Arria 10 SoM includes dual DDR4 memory interfaces and 12 transceivers at 12 Gbit/s and above. It provides comprehensive connectivity options, including two USB ports, Gigabit Ethernet, and multiple GPIOs with level-shifting capabilities. This level of integration makes it optimal for developing solutions for automotive systems, particularly in scenarios requiring high-speed data and image processing. Additionally, the SoM comes with a suite of reference designs, such as the Intel Arria 10 Golden System Reference Design, to expedite development cycles. This includes pre-configured HPS and memory controller IP, as well as customized U-Boot and Angström Linux distributions, further enriching its utility in automotive and embedded domains.
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.
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 DB9000AXI Display Controller is an adaptable solution for managing display operations, compatible with both LCD and OLED panels. It boasts the capability to handle a wide array of resolutions, from modest configurations like 320x240 up to ultra-high definition (UHD) displays supporting 4K and 8K. Its architecture facilitates connectivity via an AMBA AXI interface to the frame buffer memory and a processor. This integration makes it an ideal choice for devices requiring complex display functionalities across various market segments, including consumer electronics, automotive, and medical devices. Equipped with advanced features like hardware cursors, overlay windows, and high dynamic range (HDR) capabilities, this controller ensures vivid image rendering. Its versatile interface supports various display formats, including YCrCb and RGB, through programmable settings that dictate size, positioning, and display orientation. For system designers, the flexible architecture offers a high degree of control over display parameters without substantial resource overhead. Additionally, the DB9000AXI provides a user-friendly experience with its Linux OS driver support, making it easier for developers to integrate this technology within existing systems. Through these features, the IP core serves as a multifunctional asset that enhances the overall graphical experience of electronic devices. Whether targeting commercialization in cutting-edge consumer devices or critical medical applications, the DB9000AXI's capability to seamlessly blend and display multimedia content ensures it stands out as a key component in modern display environments.
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.
RegSpec is a comprehensive register specification tool that excels in generating Control Configuration and Status Register (CCSR) code. The tool is versatile, supporting various input formats like SystemRDL, IP-XACT, and custom formats via CSV, Excel, XML, or JSON. Its ability to output in formats such as Verilog RTL, System Verilog UVM code, and SystemC header files makes it indispensable for IP designers, offering extensive features for synchronization across multiple clock domains and interrupt handling. Additionally, RegSpec automates verification processes by generating UVM code and RALF files useful in firmware development and system modeling.
The ATEK367P4 is an analog phase shifter designed to operate within the 2 to 4 GHz frequency band. It is engineered for precision phase control, offering a phase range of 0 to 375 degrees. With a low insertion loss of 3 dB, it is equipped to handle high-performance RF applications that require fine phase adjustment and consistent signal integrity.
The HUMMINGBIRD by Lightelligence is an innovative optical Network-on-Chip processor that integrates photonic and electronic dies through advanced vertically stacked packaging technologies. This architecture provides a pathway to overcome conventional digital network limitations, particularly the 'memory wall.' With a 64-core domain-specific AI processor, HUMMINGBIRD uses a cutting-edge waveguide system to propagate light-speed signals, drastically reducing latency and power requirements compared to traditional electronic networks. This high-performance device serves as the communication backbone for data centers, facilitating data management and interconnect topology innovations. HUMMINGBIRD exploits the power of silicon photonics to offer a dense all-to-all data broadcast network that enhances the performance and scalability of AI workloads. HUMMINGBIRD's robust integration into PCIe form factors allows easy deployment onto industry-standard servers, and when paired with the Lightelligence Software Development Kit, it can significantly optimize AI and machine learning processes. This integration fosters a higher utilization of computing power and alleviates complexities associated with mapping workloads to hardware.
The Hyperspectral Imaging System developed by IMEC revolutionizes the observation capabilities of a wide spectrum of wavelengths in just one frame. This system taps into the potential of spectral imaging, advancing Earth and space exploration through its ability to capture detailed environmental data. The hyperspectral imaging system, being chip-based, ensures enhanced efficiency and precision while lowering the energy footprint compared to traditional methods. This cutting-edge technology is capable of transcending applications from Earth monitoring, where it aids in identifying and assessing natural resources, to next-generation satellite observation. By employing advanced methodologies for data acquisition and processing, the hyperspectral imaging system enhances the quality and accuracy of images captured from diverse environments. Moreover, its compact and efficient form factor makes it adaptable for integration into various imaging platforms, providing unparalleled insights with high fidelity. Furthering the realm of optical imaging, IMEC's system is designed for broad adaptability across sectors like agriculture, forestry, and urban planning, facilitating an in-depth understanding of ecological and environmental dynamics. The seamless integration with machine learning algorithms allows for the conversion of vast spectral data into actionable insights, providing users with the tools needed to make informed decisions on conservation, resource management, and urban development. Combining state-of-the-art sensor technologies with robust computing abilities, IMEC's Hyperspectral Imaging System stands as a cornerstone of modern observational science.
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 MVUM1000 features a 256-element linear ultrasound array tailored for medical imaging applications. Capitalizing on capacitive micromachined ultrasound transducers (CMUT), it offers superior sensitivity and low power consumption. The array can be integrated with front-end electronics and supports multiple imaging modes, including time-of-flight and Doppler. This versatility, combined with minimal energy requirements, makes it well-suited for advanced medical imaging, including portable and traditional ultrasound devices.
The KL520 AI SoC by Kneron marked a significant breakthrough in edge AI technology, offering a well-rounded solution with notable power efficiency and performance. This chip can function as a host or as a supplementary co-processor to enable advanced AI features in diverse smart devices. It is highly compatible with a range of 3D sensor technologies and is perfectly suited for smart home innovations, facilitating long battery life and enhanced user control without reliance on external cloud services.
The ISPido on VIP Board is a versatile runtime solution designed for Lattice Semiconductors' Video Interface Platform (VIP). It facilitates real-time image processing using ISPido's robust capabilities. The board supports automatic or manual configuration to optimize image sharpness and balance using advanced filtering and color correction techniques. Equipped with dual Sony IMX 214 sensors, this platform supports high-definition resolution output of 1920x1080p via HDMI. It includes a sophisticated menu interface for runtime calibration, offering dynamic adjustments to gamma tables, convolutional filters, and other image parameters through a user-friendly serial port interface. This adaptable solution enhances the capability to fine-tune imaging outputs, making it ideal for applications requiring precise image processing in varying conditions. Developers can leverage this setup to prototype, test, and deploy advanced imaging solutions efficiently.
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.
The 12G-SDI Playback and Capture System allows for seamless video data capture and playback, optimizing data flow through Quad 3G-SDI interfaces. This suite of FPGA images enables host machine integration via PCIe, coupled with supporting Linux-based software and drivers, to facilitate high-resolution video manipulation in real-time. Offering video pattern generation and data capture, this system functions as both a standalone IP core and with a high-performance PCIe accelerator card for enhanced operability. Its quad-interface design supports both testing and live feeds, catering to both development and operational environments within broadcast and media sectors. The system's architecture ensures easy adaptation to specific operational workflows, lending itself to professional broadcast infrastructure where testing and handling high-throughput video data are routine. This versatile approach exemplifies Korusys' commitment to providing tailored electronic solutions grounded in practical, leading-edge technology.
The 12G-SDI Playback and Capture System allows for seamless video data capture and playback, optimizing data flow through Quad 3G-SDI interfaces. This suite of FPGA images enables host machine integration via PCIe, coupled with supporting Linux-based software and drivers, to facilitate high-resolution video manipulation in real-time. Offering video pattern generation and data capture, this system functions as both a standalone IP core and with a high-performance PCIe accelerator card for enhanced operability. Its quad-interface design supports both testing and live feeds, catering to both development and operational environments within broadcast and media sectors. The system's architecture ensures easy adaptation to specific operational workflows, lending itself to professional broadcast infrastructure where testing and handling high-throughput video data are routine. This versatile approach exemplifies Korusys' commitment to providing tailored electronic solutions grounded in practical, leading-edge technology.
Kneron's KL530 introduces a modern heterogeneous AI chip design featuring a cutting-edge NPU architecture with support for INT4 precision. This chip stands out with its high computational efficiency and minimized power usage, making it ideal for a variety of AIoT and other applications. The KL530 utilizes an ARM Cortex M4 CPU, bringing forth powerful image processing and multimedia compression capabilities, while maintaining a low power footprint, thus fitting well with energy-conscious devices.
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 Video Wall Display Management System builds on the flexible use of FPGAs to simplify multi-display setups from a single video source. It inputs HDMI or DisplayPort signals, processes them for various display configurations, and manages outputs across multiple monitors—ideal for digital signage and event spaces where customized display arrangements are required. Supporting input resolutions up to 3840x2400 at 60 frames per second, the system can output resolutions reaching 1920x1200 per display. The solution features an easy-to-use software interface, enabling bezel compensation and input cloning or stretching over different arrangements, with future expansion plans to link multiple FPGAs for extended display support. Pre-configured modes streamline user control, including cloned or independent display options, with automatic EDID parsing to ensure compatibility with various hardware setups. This scalability and adaptability make it an appealing solution for dynamic digital display environments, supported by Korusys’ acclaimed technical expertise and service.
Designed for high power efficiency, the KL720 AI SoC achieves a superior performance-per-watt ratio, positioning it as a leader in energy-efficient edge AI solutions. Built for use cases prioritizing processing power and reduced costs, it delivers outstanding capabilities for flagship devices. The KL720 is particularly well-suited for IP cameras, smart TVs, and AI glasses, accommodating high-resolution images and videos along with advanced 3D sensing and language processing tasks.
aiSim 5 stands out as the first ISO26262 ASIL-D certified simulator tool designed for validating ADAS (Advanced Driver-Assistance Systems) and AD (Automated Driving) technologies. This simulator offers an unparalleled environment for testing automated driving systems, utilizing a highly optimized sensor simulation framework which ensures robust performance in runtime. Its advanced rendering engine produces realistic and deterministic environments, bypassing limitations typically found in game engine simulators. This tool is pivotal for car manufacturers as it enhances the reliability and safety of automated driving solutions. aiSim 5 boasts a flexible architecture that integrates smoothly with existing toolchains, encouraging a reduction in costly real-road testing. It focuses significantly on multi-sensor simulation, supporting diverse weather conditions and complex driving scenarios, which are essential for developing adaptive driving systems. This simulation environment allows for high mileage tests, vital for understanding and improving the effectiveness of driving systems in various settings. Additionally, aiSim 5 supports the creation of digital twin 3D environments that replicate real-world locations accurately. This enables a high-fidelity simulation of operational design domains, from highways to urban settings. aiSim's capability to simulate adverse scenarios such as snowstorms or heavy rain showcases its comprehensive approach to ensuring that AD systems are tested under every possible real-world condition.
The Catalyst-GPU series heralds a new era of computing flexibility and power in the PXIe/CPCIe arena with its integration of NVIDIA Quadro T600 and T1000 GPUs. These modules offer outstanding compute acceleration and significant graphics capabilities, crucial for detailed signal processing and AI-driven tasks, making them indispensable for Modular Test & Measurement and Electronic Warfare applications. Boasting a significant performance gain, the Catalyst-GPU sets the stage for seamless, real-time processing abilities across a range of programming environments including MATLAB, Python, and popular AI frameworks. With multi-teraflop capabilities, the Catalyst-GPU ensures that even the most computationally demanding processes are handled with precision, thereby eliminating bottlenecks in data acquisition and computational tasks. Different models within this lineup are tailored to diverse application needs, maintaining ease of programmatic interaction and integration across both Windows and Linux platforms. This adaptability, coupled with a focus on cost-effective solutions, positions the Catalyst-GPU as a leading candidate for industries looking to enhance their AI application infrastructures.
The Trifecta-GPU series by RADX Technologies represents a leap forward in processing power with the integration of NVIDIA RTX A2000 Embedded GPUs. Designed specifically for high-demand tasks, these COTS PXIe/CPCIe GPU Modules deliver remarkable compute acceleration through 8.3 FP32 TFLOPS performance, making them ideal for advanced signal processing and machine learning inference applications. Enhanced by its use of MATLAB, Python, and C/C++ programming environments, the Trifecta-GPU is well-suited for both Windows and Linux operating systems, providing maximum versatility in deployment. A hallmark of the Trifecta-GPU is its adaptability to various PXIe chassis configurations, making it an excellent fit for both single and dual-slot requirements, accommodating legacy and modern setups alike. Its peak performance is over 20 times more powerful than typical FPGA modules, underlining its pioneering place in the industry. This makes the Trifecta-GPU exceptionally capable in scenarios requiring extensive data analysis and AI-driven tasks. This prominent GPU option offers features like arbitrary length FFTs and exceptional machine learning support—attributes that positions it as a critical tool for endeavors such as signal classification and geolocation. Its BAA & TAA compliant design, combined with a highly competitive price-per-performance metric, makes the Trifecta-GPU an accessible yet powerful choice for those working in sophisticated test and measurement applications.
aiData serves as a robust data pipeline that optimizes the development process for autonomous driving technologies by facilitating the management and processing of extensive data volumes from real-world driving scenarios. This pipeline covers various stages such as data collection, preparation, and annotation, ensuring high-quality outputs essential for training and validating AI models used in ADAS and AD systems. The emphasis on automation significantly curtails the resource-intensive manual operations traditionally involved in these processes. A key feature of aiData is its versioning system that provides comprehensive oversight over data flow, allowing developers to track and curate datasets with precision. This feature is instrumental in enabling cross-referencing through metadata, ensuring data relevance and accuracy crucial for effective autonomous driving solutions. The aiData platform is designed for seamless integration, either on-premise for enhanced security or in the cloud for ease of collaboration among global teams. This flexibility allows automotive companies to streamline their workflows and accelerate the deployment timeline of their autonomous systems, ensuring data consistency and quality control across all developmental stages.
iCEVision is a powerful evaluation platform for the iCE40 UltraPlus FPGA, providing designers with the tools needed to rapid prototype and confirm connectivity features. The platform is compatible with most camera interfaces like ArduCam CSI and PMOD, allowing seamless integration into various imaging solutions. The board's exposed I/Os make it easy to implement and test user-defined functions, facilitating swift development from concept to production. It is equipped with a programmable SPI Flash and SRAM, supporting flexible programming using Lattice's Diamond Programmer and iCEcube2 software. With its small footprint and robust capabilities, iCEVision is ideal for developers looking to design customized projects. It's a go-to solution for rapid prototyping, ensuring efficient and effective deployment of visual processing applications in diverse arenas.
The RayCore MC is a state-of-the-art graphics processing unit specifically designed for real-time ray tracing and path tracing. It offers a unique combination of speed and efficiency, catering to the demands of high-quality rendering in modern digital applications. This GPU leverages advanced technology to accelerate the rendering process, allowing for realistic lighting and textures in graphics without compromising performance. Incorporating Siliconarts' proprietary ray tracing algorithms, the RayCore MC excels in delivering lifelike visuals essential for industries such as gaming, virtual reality, and film production. Its low power consumption makes it an ideal choice for devices that require high graphics performance but are constrained by power limitations. Additionally, this GPU is crucial for applications that demand real-time interactive graphics, providing developers with the tools to craft immersive visual experiences. The RayCore MC's modular design supports seamless integration into various hardware architectures, making it versatile for a wide array of products. Its technology is a testament to Siliconarts' commitment to innovation, as it continues to set the standard for GPU performance in cutting-edge digital environments.
Granite SemiCom's Sensor Interface Boards are crafted to enhance connectivity with various sensor types. These boards are compatible with small-board computers like the Beagle-Bone Black and Raspberry Pi, facilitating integration of 24-bit A/D converters, temperature/humidity sensors, and accelerometers via I2C and SPI interfaces. Each board includes essential components such as real-time clocks and EEPROMs, with customization options for specific applications. Their compatibility with a wide range of sensors makes them an invaluable asset for monitoring applications requiring precision and adaptability.
The RAIV serves as a General Purpose GPU (GPGPU), designed to provide heightened computational power across a variety of applications. Tailored for data-intensive operations, this GPU plays a vital role in accelerating processes within fields like artificial intelligence, autonomous technology, and complex data centers. It represents a cornerstone of innovation for industries moving into the fourth industrial revolution. Drawing on advanced architecture, the RAIV GPU facilitates rapid data processing, making it a significant player in enhancing the functionality of IoT devices, VR/AR platforms, and cloud computing infrastructures. Its robust performance capabilities not only improve efficiency but also enable new possibilities for developers aiming to create sophisticated applications in these sectors. Siliconarts ensures the RAIV meets the high standards of modern technical environments, providing seamless integration and adaptability. Its design supports scalability across different platforms, offering a versatile solution that keeps pace with the evolving demands of technology-driven industries. The RAIV's focus on general-purpose computations positions it as a critical component for cutting-edge advancements in technology.
The SFA 300 is engineered for scalable, quad-channel video and data processing needs, suitable for more complex applications requiring multiple channel inputs. It provides robust, concurrent data processing capabilities, ensuring each channel is managed efficiently without compromising performance. This product is tailored for scenarios demanding simultaneous processing of high-definition video and data streams, thereby enhancing system agility and responsiveness.
Systems4Silicon's Crest Factor Reduction (CFR) Technology, named FlexCFR, is an advanced solution designed to optimize the performance of RF power amplifiers by limiting transmit signal envelope. This enables significant improvements in amplifier efficiency by increasing the average transmit power while reducing peak-power demands. FlexCFR stands out for its vendor-independence, allowing it to be configured for any FPGA or ASIC platform, and dynamic adaptability to accommodate various communication standards including multi-carrier signals. FlexCFR offers several advantages, such as reducing the costs associated with higher peak-power requirements and improving overall amplifier efficiency. The product allows for real-time changes, supporting a variety of standard and non-standard communication systems, ensuring a tailored fit for different networking needs. The technologically sophisticated CFR can adjust the Peak to Average Power Ratio (PAPR) to balance spectral emission performance against in-channel outcomes, providing versatile operational benefits. Designed for comprehensive adaptability, FlexCFR is compatible with DPD solutions and envelope tracking, offering robust functionality in diverse network setups. The system is known for its deterministic behavior, facilitating accurate off-line modeling for performance predictions and system optimization. Systems4Silicon offers detailed documentation and ongoing support from experienced engineers to help users harness the full potential of FlexCFR technology.
The D/AVE 2D is a versatile graphics rendering engine designed for high-performance 2D applications. It comes equipped with advanced BLIT functions and vector graphics capabilities, offering an optimal solution for ultra-low power devices and user interfaces in mass-market consumer applications. Available in configurations for both FPGAs and ASICs, it boasts a customizable architecture that ensures adaptability to diverse performance requirements. The D/AVE 2D's strategic design prioritizes low resource consumption, making it suitable for a variety of use cases without compromising on performance.
Himax Technologies provides an extensive range of IC products tailored for monitors, notebooks, and large-sized LCD TVs. This suite includes timing controllers, source drivers, gate drivers, programming gamma/Vcom OP, and OP buffer. Their offerings are designed to cater to the advanced demands of high-resolution display panels, ensuring vibrant visual outputs that are essential for modern consumer electronics. Himax's commitment to innovation ensures these components are optimized for a seamless integration into diverse product lines, maintaining high-quality standards recognized globally.
ELFIS2 is a versatile image sensor designed to cope with challenging environments, with its high reliance on radiation-hardened features. This sensor is characterized by its true high dynamic range (HDR) capabilities, making it optimal for applications requiring accurate light detection across a broad range of intensities. The ELFIS2 features motion artifact-free (MAF) operation, a critical attribute for high-fidelity imaging. Built with a global shutter and back-side illumination (BSI), the sensor ensures all pixels capture light simultaneously, which is vital for sharp images devoid of motion blur. The BSI technology further enhances its sensitivity by allowing more light to reach the photodiode, a crucial feature for low-light conditions or fast imaging demands. With its SEL/SEU radiation-hardened design, the ELFIS2 is tailored for environments exposed to high radiation levels, like space or certain industrial settings. This resiliency, coupled with its innovative design, makes ELFIS2 suitable for complex imaging tasks, capturing high-quality images without compromising performance.
The ATEK552 is a powerful GaN-based power amplifier that supports a wide frequency range from 3 to 17 GHz. It delivers a gain of 21 dB and an impressive output power of 6 watts, powered by a supply voltage of 28 volts and drawing a current of 510 mA. This high-performance amplifier is designed for applications demanding superior amplification capabilities and is available in a die package for advanced integration.
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 direct conversion, this TV tuner supports multiple bands and standards, making it versatile for global broadcast reception. Its architecture allows for seamless integration into various devices, from televisions to set-top boxes, enabling high-quality audio and visual output. The tuner features advanced filtering techniques to minimize interference, ensuring crisp and clear picture and sound regardless of the band or broadcast standard used. Its low power design also makes it suitable for mobile media devices.
Himax develops sophisticated display drivers intended for mobile handset applications. These drivers integrate source driver, gate driver, timing controller, frame buffer, and DC to DC circuits into a singular chip solution. This highly integrated approach allows for enriched image quality and reduced power consumption, addressing the needs of today's compact mobile devices. The flexibility of these drivers ensures compatibility with various panel technologies, delivering exceptional color depth and clarity critical for mobile device displays.