All IPs > Processor > DSP Core
In the realm of semiconductor IP, DSP Cores play a pivotal role in enabling efficient digital signal processing capabilities across a wide range of applications. Short for Digital Signal Processor Cores, these semiconductor IPs are engineered to handle complex mathematical calculations swiftly and accurately, making them ideal for integration into devices requiring intensive signal processing tasks.
DSP Core semiconductor IPs are widely implemented in industries like telecommunications, where they are crucial for modulating and encoding signals in mobile phones and other communication devices. They empower these devices to perform multiple operations simultaneously, including compressing audio, optimizing bandwidth usage, and enhancing data packets for better transmission quality. Additionally, in consumer electronics, DSP Cores are fundamental in audio and video equipment, improving the clarity and quality of sound and visuals users experience.
Moreover, DSP Cores are a linchpin in the design of advanced automotive systems and industrial equipment. In automotive applications, they assist in radar and lidar systems, crucial for autonomous driving features by processing the data needed for real-time environmental assessment. In industrial settings, DSP Cores amplify the performance of control systems by providing precise feedback loops and enhancing overall process automation and efficiency.
Silicon Hub's category for DSP Core semiconductor IPs includes a comprehensive collection of advanced designs tailored to various processing needs. These IPs are designed to integrate seamlessly into a multitude of hardware architectures, offering designers and engineers the flexibility and performance necessary to push the boundaries of technology in their respective fields. Whether for enhancing consumer experiences or driving innovation in industrial and automotive sectors, our DSP Core IPs bring unparalleled processing power to the forefront of digital innovations.
The 1G to 224G SerDes technology by Alphawave Semi is a robust connectivity solution designed for high-speed data transmission. It integrates seamlessly into various applications including Ethernet, PCI Express, and die-to-die connections, enabling fast and reliable data transfer. This technology supports a broad spectrum of signaling schemes such as PAM2, PAM4, PAM6, and PAM8, ensuring compatibility with over 30 different industry protocols and standards. As the demand for high-performance data centers and networking solutions increases, the 1G to 224G SerDes proves indispensable, delivering the speed and bandwidth required by modern systems. Alphawave Semi's SerDes supports data rates from as low as 1Gbps to a staggering 224Gbps, making it highly versatile for a multitude of configurations. Its application extends beyond traditional data centers, also covering areas like AI and 5G communication networks where latency and data throughput are critical. This flexibility is further enhanced by its low power consumption, which is essential for efficient data processing in today's power-conscious technological environment. Incorporating the 1G to 224G SerDes into your chip designs guarantees reduced latency and increased data throughput, which is vital for applications that demand real-time data processing. By ensuring high data integrity and reducing signal degradation, this SerDes solution aids in maintaining steadfast connectivity, even under heavy data loads, promising a future-ready component in the evolving tech landscape.
The Veyron V2 CPU represents Ventana's second-generation RISC-V high-performance processor, designed for cloud, data center, edge, and automotive applications. This processor offers outstanding compute capabilities with its server-class architecture, optimized for handling complex, virtualized, and cloud-native workloads efficiently. The Veyron V2 is available as both IP for custom SoCs and as a complete silicon platform, ensuring flexibility for integration into various technological infrastructures. Emphasizing a modern architectural design, it includes full compliance with RISC-V RVA23 specifications, showcasing features like high Instruction Per Clock (IPC) and power-efficient architectures. Comprising of multiple core clusters, this CPU is capable of delivering superior AI and machine learning performance, significantly boosting throughput and energy efficiency. The Veyron V2's advanced fabric interconnects and extensive cache architecture provide the necessary infrastructure for high-performance applications, ensuring broad market adoption and versatile deployment options.
Leveraging a high-performance RISC architecture, the eSi-3250 32-bit core efficiently integrates instruction and data caches. This makes it compatible with designs utilizing slower on-chip memories such as eFlash. The core not only supports MMU for address translation but also allows for user-defined custom instructions, greatly enhancing its flexibility for specialized and high-performance applications.
Chimera GPNPU is engineered to revolutionize AI/ML computational capabilities on single-core architectures. It efficiently handles matrix, vector, and scalar code, unifying AI inference and traditional C++ processing under one roof. By alleviating the need for partitioning AI workloads between different processors, it streamlines software development and drastically speeds up AI model adaptation and integration. Ideal for SoC designs, the Chimera GPNPU champions an architecture that is both versatile and powerful, handling complex parallel workloads with a single unified binary. This configuration not only boosts software developer productivity but also ensures an enduring flexibility capable of accommodating novel AI model architectures on the horizon. The architectural fabric of the Chimera GPNPU seamlessly blends the high matrix performance of NPUs with C++ programmability found in traditional processors. This core is delivered in a synthesizable RTL form, with scalability options ranging from a single-core to multi-cluster designs to meet various performance benchmarks. As a testament to its adaptability, the Chimera GPNPU can run any AI/ML graph from numerous high-demand application areas such as automotive, mobile, and home digital appliances. Developers seeking optimization in inference performance will find the Chimera GPNPU a pivotal tool in maintaining cutting-edge product offerings. With its focus on simplifying hardware design, optimizing power consumption, and enhancing programmer ease, this processor ensures a sustainable and efficient path for future AI/ML developments.
The Jotunn8 AI Accelerator is engineered for lightning-fast AI inference at unprecedented scale. It is designed to meet the demands of modern data centers by providing exceptional throughput, low latency, and optimized energy efficiency. The Jotunn8 outperforms traditional setups by allowing large-scale deployment of trained models, ensuring robust performance while reducing operational costs. Its capabilities make it ideal for real-time applications such as chatbots, fraud detection, and advanced search algorithms. What sets the Jotunn8 apart is its adaptability to various AI algorithms, including reasoning and generative models, alongside agentic AI frameworks. This seamless integration achieves near-theoretical performance, allowing the chip to excel in applications that require logical rigor and creative processing. With a focus on minimizing carbon footprint, the Jotunn8 is meticulously designed to enhance both performance per watt and overall sustainability. The Jotunn8 supports massive memory handling with HBM capability, promoting incredibly high data throughput that aligns with the needs of demanding AI processes. Its architecture is purpose-built for speed, efficiency, and the ability to scale with technological advances, providing a solid foundation for AI infrastructure looking to keep pace with evolving computational demands.
xcore.ai is XMOS Semiconductor's innovative programmable chip designed for advanced AI, DSP, and I/O applications. It enables developers to create highly efficient systems without the complexity typical of multi-chip solutions, offering capabilities that integrate AI inference, DSP tasks, and I/O control seamlessly. The chip architecture boasts parallel processing and ultra-low latency, making it ideal for demanding tasks in robotics, automotive systems, and smart consumer devices. It provides the toolset to deploy complex algorithms efficiently while maintaining robust real-time performance. With xcore.ai, system designers can leverage a flexible platform that supports the rapid prototyping and development of intelligent applications. Its performance allows for seamless execution of tasks such as voice recognition and processing, industrial automation, and sensor data integration. The adaptable nature of xcore.ai makes it a versatile solution for managing various inputs and outputs simultaneously, while maintaining high levels of precision and reliability. In automotive and industrial applications, xcore.ai supports real-time control and monitoring tasks, contributing to smarter, safer systems. For consumer electronics, it enhances user experience by enabling responsive voice interfaces and high-definition audio processing. The chip's architecture reduces the need for exterior components, thus simplifying design and reducing overall costs, paving the way for innovative solutions where technology meets efficiency and scalability.
The **Ceva-SensPro DSP family** unites scalar processing units and vector processing units under an 8-way VLIW architecture. The family incorporates advanced control features such as a branch target buffer and a loop buffer to speed up execution and reduce power. There are six family members, each with a different array of MACs, targeted at different application areas and performance points. These range from the Ceva-SP100, providing 128 8-bit integer or 32 16-bit integer MACs at 0.2 TOPS performance for compact applications such as vision processing in wearables and mobile devices; to the Ceva-SP1000, with 1024 8-bit or 256 16-bit MACs reaching 2 TOPS for demanding applications such as automotive, robotics, and surveillance. Two of the family members, the Ceva-SPF2 and Ceva-SPF4, employ 32 or 64 32-bit floating-point MACs, respectively, for applications in electric-vehicle power-train control and battery management. These two members are supported by libraries for Eigen Linear Algebra, MATLAB vector operations, and the TVM graph compiler. Highly configurable, the vector processing units in all family members can add domain-specific instructions for such areas as vision processing, Radar, or simultaneous localization and mapping (SLAM) for robotics. Integer family members can also add optional floating-point capabilities. All family members have independent instruction and data memory subsystems and a Ceva-Connect queue manager for AXI-attached accelerators or coprocessors. The Ceva-SensPro2 family is programmable in C/C++ as well as in Halide and Open MP, and supported by an Eclipse-based development environment, extensive libraries spanning a wide range of applications, and the Ceva-NeuPro Studio AI development environment. [**Learn more about Ceva-SensPro2 solution>**](https://www.ceva-ip.com/product/ceva-senspro2/?utm_source=silicon_hub&utm_medium=ip_listing&utm_campaign=ceva_senspro2_page)
Designed for efficient processing, the SCR3 microcontroller core offers a versatile solution for embedded environments. It comes equipped with a 5-stage in-order pipeline and supports both 32-bit and 64-bit symmetric multiprocessing (SMP) configurations, facilitating advanced applications. The core integrates privilege modes and includes memory protection units (MPUs), along with L1 and L2 caches, ensuring data integrity and performance. Its efficient architecture is optimized for energy-conscious applications, making it ideal for industrial, automotive, and IoT applications.
The Codasip RISC-V BK Core Series offers versatile, low-power, and high-performance solutions tailored for various embedded applications. These cores ensure efficiency and reliability by incorporating RISC-V compliance and are verified through advanced methodologies. Known for their adaptability, these cores can cater to applications needing robust performance while maintaining stringent power and area requirements.
The Digital Radio (GDR) from GIRD Systems is an advanced software-defined radio (SDR) platform that offers extensive flexibility and adaptability. It is characterized by its multi-channel capabilities and high-speed signal processing resources, allowing it to meet a diverse range of system requirements. Built on a core single board module, this radio can be configured for both embedded and standalone operations, supporting a wide frequency range. The GDR can operate with either one or two independent transceivers, with options for full or half duplex configurations. It supports single channel setups as well as multiple-input multiple-output (MIMO) configurations, providing significant adaptability in communication scenarios. This flexibility makes it an ideal choice for systems that require rapid reconfiguration or scalability. Known for its robust construction, the GDR is designed to address challenging signal processing needs in congested environments, making it suitable for a variety of applications. Whether used in defense, communications, or electronic warfare, the GDR's ability to seamlessly switch configurations ensures it meets the evolving demands of modern communications technology.
The Spiking Neural Processor T1 is an ultra-low power processor developed specifically for enhancing sensor capabilities at the edge. By leveraging advanced Spiking Neural Networks (SNNs), the T1 efficiently deciphers patterns in sensor data with minimal latency and power usage. This processor is especially beneficial in real-time applications, such as audio recognition, where it can discern speech from audio inputs with sub-millisecond latency and within a strict power budget, typically under 1mW. Its mixed-signal neuromorphic architecture ensures that pattern recognition functions can be continually executed without draining resources. In terms of processing capabilities, the T1 resembles a dedicated engine for sensor tasks, offering functionalities like signal conditioning, filtering, and classification independent of the main application processor. This means tasks traditionally handled by general-purpose processors can now be offloaded to the T1, conserving energy and enhancing performance in always-on scenarios. Such functionality is crucial for pervasive sensing tasks across a range of industries. With an architecture that balances power and performance impeccably, the T1 is prepared for diverse applications spanning from audio interfaces to the rapid deployment of radar-based touch-free interactions. Moreover, it supports presence detection systems, activity recognition in wearables, and on-device ECG processing, showcasing its versatility across various technological landscapes.
The Tyr AI Processor Family revolutionizes edge AI by executing data processing directly where data is generated, instead of relying on cloud solutions. This empowers industries with real-time decision-making capabilities by bringing intelligence closer to devices, machines, and sensors. The Tyr processors integrate cutting-edge AI capabilities into compact, efficient designs, achieving high performance akin to data center class levels with much lower power needs. The edge processors from the Tyr line ensure reduced latency and enhanced privacy, making them suitable for autonomous vehicles, smart factories, and other real-time applications demanding immediate, secure insights. They feature robust local data processing options, ensuring minimal reliance on cloud services, which contributes to lower costs and improved compliance with privacy standards. With a focus on multi-modal input handling and sustainability, the Tyr processors provide balanced compute power, memory utilization, and intelligent features that align with the needs of highly dynamic and bandwidth-restricted environments. Using RISC-V cores, they facilitate versatile AI model deployment across edge devices, ensuring high adaptability to the latest technological advances and market demands.
The Codasip L-Series DSP Core is designed to handle demanding signal processing tasks, offering an exemplary balance of computational power and energy efficiency. This DSP core is particularly suitable for applications involving audio processing and sensor data fusion, where performance is paramount. Codasip enriches this product with their extensive experience in RISC-V architectures, ensuring robust and optimized performance.
The eSi-3200, a 32-bit cacheless core, is tailored for embedded control with its expansive and configurable instruction set. Its capabilities, such as 64-bit multiply-accumulate operations and fixed-point complex multiplications, cater effectively to signal processing tasks like FFTs and FIRs. Additionally, it supports SIMD and single-precision floating point operations, coupled with efficient power management features, enhancing its utility for diverse embedded applications.
The ISPido on VIP Board is tailored specifically for Lattice Semiconductor's Video Interface Platform (VIP) and is designed to achieve clear and balanced real-time imaging. This ISPido variant supports automatic configuration options to provide optimal settings the moment the board is powered on. Alternatively, users can customize their settings through a menu interface, allowing for adjustments such as gamma table selection and convolutional filtering. Equipped with the CrossLink VIP Input Bridge, the board features dual Sony IMX 214 image sensors and an ECP5 VIP Processor. The ECP5-85 FPGA ensures reliable processing power while potential outputs include HDMI in YCrCb 4:2:2 format. This flexibility ensures users have a complete, integrated solution that supports runtime calibration and serial port menu configuration, making it an extremely practical choice for real-time applications. The ISPido on VIP Board is built to facilitate seamless integration and high interoperability, making it a suitable choice for those engaged in designing complex imaging solutions. Its adaptability and high-definition support make it particularly advantageous for users seeking to implement sophisticated vision technologies in a variety of industrial applications.
The iCan PicoPop® is a highly compact System on Module (SOM) based on the Zynq UltraScale+ MPSoC from Xilinx, suited for high-performance embedded applications in aerospace. Known for its advanced signal processing capabilities, it is particularly effective in video processing contexts, offering efficient data handling and throughput. Its compact size and performance make it ideal for integration into sophisticated systems where space and performance are critical.
The Prodigy Universal Processor by Tachyum is a groundbreaking innovation in the realm of computing, marked as the world's first processor that merges General Purpose Computing, High-Performance Computing, Artificial Intelligence, and various other AI disciplines into a single compact chip. This processor promises to revolutionize hyperscale data centers with its unprecedented processing capabilities and efficiency, pushing the boundaries of current computational power. With its superior performance per watt, Prodigy minimizes energy consumption while maximizing data processing abilities. Offering up to 21 times higher performance compared to its contemporaries, Prodigy stands out by providing a coherent multiprocessor architecture that simplifies the programming environment. It aims to overcome challenges like high power use and server underutilization, which have long plagued modern data centers. By addressing these core issues, it allows enterprises to manage workloads more effectively and sustainably. Furthermore, Prodigy's emulation platform broadens the scope of testing and evaluation, enabling developers to optimize their applications for better performance and low power consumption. With native support for the Prodigy instruction set architecture, the processor seamlessly integrates existing software packages, promising a smooth transition and robust application support. Through the integration of this versatile processor, Tachyum is leading the charge toward a sustainable technological future.
The Universal DSP Library is designed to simplify digital signal processing tasks within FPGA systems. This extensive collection of DSP algorithms and functions allows for efficient development and deployment of signal processing applications. Users can leverage this library to handle complex computations swiftly, making it perfect for industries requiring real-time processing power. It streamlines development by offering pre-tested routines that developers can integrate into their systems without extensive customization.
TUNGA is an advanced System on Chip (SoC) leveraging the strengths of Posit arithmetic for accelerated High-Performance Computing (HPC) and Artificial Intelligence (AI) tasks. The TUNGA SoC integrates multiple CRISP-cores, employing Posit as a core technology for real-number calculations. This multi-core RISC-V SoC is uniquely equipped with a fixed-point accumulator known as QUIRE, which allows for extremely precise computations across vectors as long as 2 billion entries. The TUNGA SoC includes programmable FPGA gates for enhancing field-critical functions. These gates are instrumental in speeding up data center services, offloading tasks from the CPU, and advancing AI training and inference efficiency using non-standard data types. TUNGA's architecture is tailored for applications demanding high precision, including cryptography and variable precision computing tasks, facilitating the transition towards next-generation arithmetic. In the computational ecology, TUNGA stands out by offering customizable features and rapid processing capabilities, making it suitable not only for typical data center functions but also for complex, precision-demanding workloads. By capitalizing on Posit arithmetic, TUNGA aims to deliver more efficient and powerful computational performance, reflecting a strategic advancement in handling complex data-oriented processes.
The Trifecta-GPU offers cutting-edge graphics processing capabilities designed for high-efficiency computing needs. This PXIe/CPCIe module excels in handling intensive tasks across various applications, including signal processing, modular test and measurement, and electronic warfare systems. Built to deliver robust performance, it incorporates advanced GPU technology to ensure rapid data throughput and high computational capability. With a focus on versatility, the Trifecta-GPU seamlessly integrates with existing hardware setups, aiding in the enhancement of system performance through its powerful data handling skills. It is particularly well-suited for environments that demand precise data analysis and execution speed, such as AI and machine learning inference tasks. Its inclusion in RADX's product lineup signifies its importance in providing comprehensive solutions tailored for demanding industrial and research applications. Moreover, this module supports various applications, empowered by its substantial memory bandwidth, and possesses innovative architecture designed to optimize processing power. The Trifecta-GPU is an integral component within RADX’s lineup designed to offer flexibility and power efficiency in equal measure, making it well-suited for future-tech applications that necessitate high-performance standards.
The Veyron V1 is a high-performance RISC-V CPU designed to meet the rigorous demands of modern data centers and compute-intensive applications. This processor is tailored for cloud environments requiring extensive compute capabilities, offering substantial power efficiency while optimizing processing workloads. It provides comprehensive architectural support for virtualization and efficient task management with its robust feature set. Incorporating advanced RISC-V standards, the Veyron V1 ensures compatibility and scalability across a wide range of industries, from enterprise servers to high-performance embedded systems. Its architecture is engineered to offer seamless integration, providing an excellent foundation for robust, scalable computing designs. Equipped with state-of-the-art processing cores and enhanced vector acceleration, the Veyron V1 delivers unmatched throughput and performance management, making it suitable for use in diverse computing environments.
The RFicient chip is a cutting-edge technology designed to optimize power usage in IoT applications. This ultra-low-power receiver is ideal for environments requiring long-term battery operation, such as remote sensors in industrial IoT setups. With its efficient energy harvesting capabilities, the RFicient chip is pivotal in advancing sustainable technology solutions, reducing power consumption within the Internet of Things (IoT) framework.
The xcore-200 chip from XMOS is a pivotal component for audio processing, delivering unrivaled performance for real-time, multichannel streaming applications. Tailored for professional and high-resolution consumer audio markets, xcore-200 facilitates complex audio processing with unparalleled precision and flexibility. This chip hosts XMOS's adept capabilities in deterministic and parallel processing, crucial for achieving zero-latency outputs in applications such as voice amplification systems, high-definition audio playback, and multipoint conferencing. Its architecture supports complex I/O operations, ensuring that all audio inputs and outputs are managed efficiently without sacrificing audio quality. The xcore-200 is crafted to handle large volumes of data effortlessly while maintaining the highest levels of integrity and clarity in audio outputs. It provides superior processing power to execute intensive tasks such as audio mixing, effects processing, and real-time equalization, crucial for both consumer electronics and professional audio gear. Moreover, xcore-200 supports a flexible integration into various systems, enhancing the functionality of audio interfaces, smart soundbars, and personalized audio solutions. It also sustains the robust performance demands needed in embedded AI implementations, thereby extending its utility beyond traditional audio systems. The xcore-200 is a testament to XMOS's dedication to pushing the boundaries of what's possible in audio engineering, blending high-end audio performance with cutting-edge processing power.
The NX Class RISC-V CPU IP by Nuclei is characterized by its 64-bit architecture, making it a robust choice for storage, AR/VR, and AI applications. This processing unit is designed to accommodate high data throughput and demanding computational tasks. By leveraging advanced capabilities, such as virtual memory and enhanced processing power, the NX Class facilitates cutting-edge technological applications and is adaptable for integration into a vast array of high-performance systems.
ISPido is a powerful and flexible image signal processing pipeline tailored for high-resolution image processing and tuning. It supports a comprehensive pipeline of image enhancement features such as defect correction, color filter array interpolation, and various color space conversions, all configurable via the AXI4-LITE protocol. Designed to handle input depths of 8, 10, or 12 bits, ISPido excels in processing high-definition resolutions up to 7680x7680 pixels, making it highly suitable for a variety of advanced vision applications. The architecture of ISPido is built to be highly compatible with AMBA AXI4 standards, ensuring that it can be seamlessly integrated into existing systems. Each module in the pipeline is individually configurable, allowing for extensive customization to optimize performance. Features such as auto-white balance, gamma correction, and HDR chroma resampling empower developers to produce precise and visually accurate outputs in complex environments. ISPido's modular and versatile design makes it an ideal choice for deploying in heterogeneous processing environments, ranging from low-power battery-operated devices to sophisticated vision systems capable of handling resolutions higher than 8K. This adaptability makes it a prime solution for developers working across various sectors demanding high-quality image processing.
The SCR4 microcontroller core enhances embedded processing with robust features tailored for demanding applications. This core is designed with a 5-stage in-order pipeline, privilege modes, and advanced support for floating-point units (FPUs). Accompanied by MPUs and comprehensive cache infrastructures, including L1 and L2 caches, it ensures high efficiency and performance. Its ability to handle both 32-bit and 64-bit SMP setups makes it versatile for various industries such as industrial control, IoT, and embedded network devices.
Microdul's temperature sensor for IoT applications is engineered for ultra-low-power operation, an essential feature for extending battery life in portable devices. These sensors provide accurate temperature readings with minimal energy consumption, making them ideal for IoT and energy harvesting systems. Featuring a compact design, the temperature sensor is easy to integrate into diverse hardware environments. Its ability to deliver precise measurements, even in fluctuating conditions, ensures reliability across a broad range of applications from wearable technology to smart home devices. This sensor supports efficient power management by activating only when necessary, thus optimizing the device's overall energy use. Its application in IoT emphasizes its design for longevity and consistent performance in networked devices that require continuous data monitoring and processing over extended periods.
SiFive Performance family processors are specifically engineered to deliver outstanding performance and efficiency across a wide range of applications. These processors cater to diverse market demands, including data centers, consumer electronics, and AI-driven workloads. They feature high-performance, 64-bit out-of-order cores with optional vector engines, making them ideal for heavy-duty tasks requiring maximum throughput and scalability. The series incorporates a variety of architectural features that optimize performance and energy efficiency. It includes cores scalable from three-wide to six-wide, supporting up to 256-bit vector operations, which are particularly advantageous for AI and multimedia processing applications. This optimal balance ensures that each core offers superior compute density and power efficiency. Additionally, the SiFive Performance series emphasizes flexibility, allowing users to mix and match cores to achieve the desired balance between performance and power consumption. This makes the series a perfect fit for both performance-intensive and power-sensitive applications, enabling developers to create customized solutions tailored to their specific needs.
TimeServo is a sophisticated System Timer IP Core for FPGAs, providing high-resolution timing essential for line-rate independent packet timestamping. Its architecture allows seamless operation without the need for associated host processor interaction, leveraging a flexible PI-DPLL which utilizes an external 1 PPS signal, ensuring time precision and stability across applications. Besides functioning as a standalone timing solution within an FPGA, TimeServo offers multi-output capabilities with up to 32 independent time domains. Each time output can be individually configured, supporting multiple timing formats, including Binary 48.32 and IEEE standards, which offer great flexibility for timing-sensitive applications. TimeServo uniquely combines software control via an AXI interface with an internal, logically-heavy phase accumulator and Digital Phase Locked Loop mechanisms, achieving impressive jitter performance. Consequently, TimeServo serves as an unparalleled solution for network operators and developers requiring precise timing and synchronization in their systems.
The AON1020 belongs to the sophisticated AONSens™ Neural Network Series, cementing its role in both audio and multifunctional sensor applications. The core is delivered in a Verilog RTL format, allowing flexibility for ASIC or FPGA synthesis. Designed for efficient energy usage, the AON1020 is ideal for persistent voice command recognition, offering its capabilities with negligible power draw for always-on operations. Capable of beyond-the-basics voice control, this IP comprehensively tackles real-time responses to acoustic events and environmental cues. It seamlessly integrates with sensor systems for detecting human activities, making it suitable for contexts requiring sensors for activity updates, such as fitness monitoring or interactive toys. Maintaining pin-point accuracy under challenging sound conditions or user unpredictability, AON1020 is perfect for high-responsiveness scenarios. It supports the company's data-centric approach, embedding functions necessary for context detection and acoustic events, thus providing a holistic suite for user interaction and functional triggers in connected ecosystems.
The eSi-3264 stands out with its support for both 32/64-bit operations, including 64-bit fixed and floating-point SIMD (Single Instruction Multiple Data) DSP extensions. Engineered for applications mandating DSP functionality, it does so with minimal silicon footprint. Its comprehensive instruction set includes specialized commands for various tasks, bolstering its practicality across multiple sectors.
The ARC Processor by Synopsys offers a versatile and scalable processing solution that caters to diverse applications, from consumer electronics to high-end autonomous systems. Renowned for its customizable architecture, the ARC Processor allows developers to tailor features to meet specific application needs, optimizing both performance and power consumption. This processor IP is designed with a focus on high efficiency and flexibility, offering a rich set of features that enable seamless integration into complex SoCs. It supports a wide variety of processing tasks, including complex computational algorithms, real-time processing, and power-sensitive tasks. This scalability makes the ARC Processor suitable for a broad spectrum of markets, including automotive, mobile, and internet of things (IoT) applications. With its advanced design, the ARC Processor provides exceptional processing capabilities while maintaining low power requirements, making it ideal for battery-operated devices. By delivering efficient execution and high processing throughput, this processor empowers designers to create innovative solutions that meet demanding performance criteria.
The Neural Network Accelerator from Gyrus AI is designed to enhance edge computing capabilities through native graph processing. This innovative solution offers up to 30 TOPs/W, making it highly efficient by achieving 10-30 times lower clock-cycles than conventional processors. Its design supports low memory usage configurations, significantly reducing power consumption and enabling up to 20 times lower energy requirements. Designed for seamless integration, it supports diverse neural network models with superior utilization of over 80%, leading to enhanced performance and reduced die area by 10 to 8 times smaller than traditional designs.
Tensix Neo represents a groundbreaking leap in AI processing, purpose-built to optimize specific AI workloads with outstanding performance-per-watt efficiency. The platform delivers adaptable solutions to AI developers, facilitating rapid acceleration of AI networks and applications. Designed with a sophisticated Network-on-Chip (NoC), Tensix Neo ensures comprehensive connectivity and scalability to accommodate an expanding array of AI models, allowing developers to match pace with swift industry changes. It supports diverse precision formats and is engineered for seamless interaction with emerging technologies, maintaining flexibility to cater to AI-driven advancements.
AON1000 is a robust AI solution that elevates voice and sound recognition capabilities for IoT devices, wearables, and smart home applications. Designed to operate with ultra-low power, the AON1000 demonstrates exceptional accuracy within acoustically challenging environments. This advanced product supports multi-wake-word detection and always-listening voice-enabled applications. Its inherent capability for adaptive voice activity detection and extensive acoustic event monitoring distinguishes it in the audio processing domain. The AON1000 harnesses the power of proprietary neural network architecture, optimized for deep neural network inferencing directly at the edge. This allows for unique efficiency in processing voice commands, detecting speakers, and handling various sensor inputs concurrently. The design philosophy incorporates real-world noise conditions, offering top-tier accuracy per microwatt consumed. This AI engine can either function independently or integrate with existing hardware, such as microphones, thus minimizing the need for an auxiliary application processor during continuous monitoring phases. This solution also supports seamless integration with software algorithms that can be ported to alternative DSPs for less power-sensitive applications. Its comprehensive package covers data augmentation during training, thus facilitating high-end accuracy even in variable use-case scenarios, making it a leading choice for developers aiming to optimize consumer electronics and smart devices.
The Cottonpicken DSP Engine is a powerful micro-coded digital signal processing unit developed by Section5, designed to support a wide range of applications in signal processing. It's equipped to handle complex operations like Bayer pattern decoding and YUV conversion, making it essential for tasks involving various imaging formats. With support for RGB and additional programmable delays, it offers remarkable versatility in handling image data especially suitable for high-speed environments. The architecture supports YCrCb, YCoCg formats and can perform specific matrix operations that are fully cascadeable, making it an ideal solution for advanced signal processing needs. Capable of operating up to a pixel clock of 150 MHz, the engine ensures efficient processing speeds that can be tailored to specific performance requirements. Despite its robust capabilities, the Cottonpicken DSP Engine maintains a low resource footprint, only available as a netlist object within a development package. This makes it particularly attractive for developers seeking comprehensive DSP functions without extensive hardware integration challenges, streamlining the development process for custom projects.
The TSP1 Neural Network Accelerator by Applied Brain Research is a groundbreaking AI chip engineered to enhance processing power and efficiency for time series data. Utilizing state-of-the-art neural network capabilities, it facilitates natural voice interfaces and advanced bio-signal classification within compact battery-powered devices. The TSP1 ensures fully self-contained processing across multiple network setups, handling diverse voice and sensor signal applications with low power consumption. This chip is revolutionary in its ability to perform high-efficiency neural network operations while sustaining ultra-low energy usage. The integrated DC-DC supply supports a range of power options, ensuring adaptability across various applications like wearables and smart home technologies. Moreover, its architecture offers robust AI inference with minimal latency, making it a prime choice for those aiming to incorporate efficient AI processing into edge devices. Technically, the TSP1 supports up to four stereo audio inputs and features secure on-chip storage, empowering devices to execute complex AI functions with great fidelity. Its compact packaging options make it suitable for a host of applications, ensuring seamless integration in environments where space and power efficiency are critical. This AI chip stands out in the market for its ability to offer comprehensive AI capabilities while remaining highly efficient and low-cost, promising transformative impacts across multiple sectors.
The TimbreAI T3 is meticulously designed to cater to ultra-low-power AI applications, notably in audio devices like headsets. Providing optimal noise reduction capabilities, the T3 performs efficient AI inference while utilizing minimal power, making it ideal for power-constrained environments. This AI engine achieves superior audio processing through 3.2 billion operations per second, while consuming less than 300 microWatts of power. The TimbreAI T3 supports full deployment across leading silicon processes, delivering seamless integration as soft IP to enhance audio experiences without extensive power requirements. With its focus on minimal footprint and maximized efficiency, the TimbreAI T3 allows developers to deploy neural networks without altering trained models, ensuring high accuracy and performance in tiny devices. Its flexibility and proven field deployment further solidify its credentials as a leading solution for the mobile audio market.
The Secure Protocol Engines by Secure-IC are designed to offload and enhance network and security processing tasks within an SoC environment. These high-performance IP blocks ensure efficient management of cryptographic operations and facilitate secure data exchanges across networks. By integrating these engines, developers can achieve improved throughput and reduced latency in their security implementations, which is critical for maintaining the performance and safety of connected devices. These engines support standard protocols, ensuring compatibility with a wide range of applications.
Targeting high-performance demands, the Origin E8 is built for sectors requiring robust AI capabilities, such as data centers and autonomous driving. It accommodates demanding applications for real-time processing tasks, offering up to 128 TOPS in a single core configuration. The E8 expedites complex AI workloads with its advanced packet-based architecture that enhances efficiency through concurrent multi-layer execution. The scalable design of the Origin E8 enables its use in diverse contexts, managing multiple AI networks simultaneously with minimal latency. Expedera's solution addresses the architectural needs of sectors where performance, area, and power efficiency are paramount, providing competitive advantages through optimal configuration. Including a comprehensive suite of development tools like a compiler, scheduler, and quantizer, the Origin E8 facilitates straightforward integration and adaptation to various AI models, thereby ensuring it can meet a broad range of application scenarios.
UltraRISC's UR-E Processor Core series is targeted towards enhanced edge computing applications, offering high efficiency in processing tasks that require quick, reliable execution at the data source. Built on the robust RISC-V architecture, the UR-E core excels in meeting the needs of dynamic workloads at the edge, providing the flexibility needed to adapt to varying processing demands. The UR-E core design focuses on optimized performance with low power consumption, making it an excellent solution for environments where energy efficiency is critical. This processor core integrates advanced low-power technologies, ensuring that energy use is minimized without affecting performance. This balance is crucial for a range of applications, including IoT devices, and industrial automation, where energy constraints are a constant concern. The UR-E Core provides a flexible framework for developers to implement custom instructions to address specific needs beyond the standard RISC-V instruction set. This adaptability, combined with UltraRISC's expertise in processor core design, allows the UR-E series to cater to various application domains such as edge devices and industrial processing, enabling significant advancements in these fields.
The iniDSP core is a powerful 16-bit digital signal processor designed for enhancing signal processing tasks effectively. It is particularly suited for applications demanding intensive arithmetic processing such as audio processing, telecommunications, and radar systems. By offering flexible design integration and high-performance capabilities, iniDSP manages complex calculations with impressive efficiency. The processor's architecture is constructed to support and simplify the implementation of complex signal algorithms, enabling seamless integration into a range of electronic systems. With its proven application across various sectors, iniDSP provides a robust solution for engineers aiming to optimize digital signal processing.
The Blazar Bandwidth Accelerator Engine brings in-memory computing directly to FPGA configurations. It provides a blend of high-capacity, low-latency memory aligned with extensive compute power to tackle bandwidth-intensive applications. With a throughput capacity of up to 640 Gbps and the potential for integration of up to 32 RISC cores, it supports high-performance applications such as SmartNIC and SmartSwitches. The device reduces data transport delays by implementing operations within the memory environment, significantly enhancing system responsiveness.
Catalyst-GPU is a robust graphics processing unit tailored for environments requiring high-performance computation and data visualization. This PXIe module stands at the core of RADX’s high-tech solutions, engineered for the streamlined execution of intensive tasks associated with modern computing needs, including AI, DSP, and EW applications. By leveraging cutting-edge GPU technology, the Catalyst-GPU raises the bar in computational speed and efficiency, accommodating the increasing data demands of contemporary applications. Its architecture supports seamless integration, allowing for straightforward upgrades and enhancements to existing systems, ensuring minimal disruption and maximum throughput. With a primary focus on delivering rapid processing power, the Catalyst-GPU is crafted to meet the evolving challenges in data-driven markets. Whether in research or industrial settings, its capability to handle large datasets swiftly and accurately makes it indispensable for modern computing tasks that demand high fidelity and real-time processing.
The Floating Point Library IP delivers precise and flexible floating-point arithmetic operations suitable for various applications requiring high accuracy. Following IEEE 754 standards, it supports customizable precision levels to match specific computational needs. This IP core efficiently balances logic usage with performance, providing hardware-accelerated floating-point operations suited for complex calculations in both FPGA and ASIC deployments. It offers adaptive solutions, from simple arithmetic tasks to extensive data processing challenges.
The Origin E2 NPU is engineered for power-sensitive devices requiring on-device AI processing. Suitable for smartphones and edge nodes, it supports various AI models and balances performance with low power consumption. By utilizing Expedera's packet-based architecture, the E2 achieves high efficiency and effective resource utilization, facilitating parallel execution across multiple layers to enhance computational throughput. The E2 is highly adaptable, supporting a broad performance range from 1 to 20 TOPS, making it well-suited for running neural networks like RNN, LSTM, CNN, and DNN without the need for hardware-specific modifications. This ensures seamless integration for customers looking to leverage their existing trained models. Equipped with a full TVM-based software stack, the Origin E2 simplifies network deployment while offering excellent customization capabilities to meet specific application requirements. Its design emphasizes field-proven reliability with its inclusion in over 10 million consumer devices globally.
AON1010 forms an integral component of the AONVoice™ Neural Network Series, specifically tailored for voice and audio recognition tasks. It efficiently processes microphone inputs for a plethora of applications including sound analysis and voice command execution. The hardware is available as AI processing engine in Verilog RTL, making it compatible for ASIC and FPGA configurations. With its built-in AI-driven software, AON1010 excels in managing always-on functionality. It offers multi-wake-word detection, enabling voice command recognition directly on the device, without sacrificing power efficiency. The architecture is particularly strong in adapting to dynamic audio environments, maintaining high accuracy even amidst background noise or sound reverbs. Providing seamless speaker identification and context-sensitive responses, the AON1010 adapts to changes within the user demographic and environmental variabilities. Moreover, it demonstrates scalability by handling simultaneous command detections, making it versatile for diverse deployments. This technology is critical in advancing efficient voice-activated systems for consumer electronics and enterprise solutions.
The v-MP6000UDX Visual Processing Unit is a powerhouse of the Videantis portfolio, offering extensive capabilities for handling deep learning, computer vision, and video coding across a singular architecture. This unit brings prowess in processing tasks that require real-time performance and energy efficiency, making it pivotal for next-generation intelligent devices. Designed to support multiple computational requirements, the v-MP6000UDX processes deep learning models efficiently, acting as a unified platform that negates the need for disparate hardware accelerators. This processor's architecture is optimized for running complete neural networks swiftly and at low power, facilitating applications that demand rapid computing power with minimal energy constraints. Boasting a sophisticated memory hierarchy and high-bandwidth interfaces, the processor ensures efficient data handling and processing. Its enhanced memory architecture paired with a network-on-chip design fosters an environment where high-performance computations are achieved seamlessly. This makes the v-MP6000UDX suitable for deployment in complex systems such as autonomous vehicles, mobile technology, and industrial automation, where proficient data processing and precision are critical. Incorporating the latest design principles, the v-MP6000UDX unit integrates seamlessly into devices that require extensive video processing capabilities, benefiting from a vast library of codecs and support for emerging standards in video compression. This processing unit is indispensable for businesses aiming to enhance their product offerings with cutting-edge technology.
Specialty Microcontrollers from Advanced Silicon are architected on the contemporary RISC-V platforms, integrating sophisticated coprocessing units for advanced image processing tasks. These microcontrollers are crucial for applications demanding high-performance algorithm execution, notably in touch screen and interactive display technologies. Leveraging the CoolTouch® technology, the microcontrollers provide enhanced touch interface solutions with built-in machine learning for gesture recognition and command interaction. The systems are developed to excel in varied environments, maintaining reliability under challenging conditions such as EMI interference or with tactile accessories like gloves.
Designed for edge inference applications, the Origin E6 NPU offers a state-of-the-art solution supporting both traditional and generative AI models. With performance scaling from 16 to 32 TOPS, the E6 is tailored to meet the sophisticated demands of next-gen smartphones, AR/VR devices, and automotive applications. Expedera's packet-based architecture facilitates parallel operations, ensuring efficient resource use and reducing latency. The E6 is highly customizable, supporting a wide range of AI models and enabling seamless deployments across diverse hardware environments without the need for extensive hardware-specific tuning. Expedera offers the Origin E6 with a complete software stack that promotes ease of integration and supports advanced features like multiple job APIs and quantization options. By achieving up to 90% processor utilization, the E6 maximizes performance while minimizing dark silicon waste, positioning it as a leading choice for AI chip architects seeking power efficiency and scalability in their designs.
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!
No credit card or payment details required.
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!