ZSP5000UL is a programmable Vector Digital Signal Processor Core for high performance computer vision and image processing applications. The programmer friendly architecture offers an orthogonal instruction set that greatly simplifies the complex image processing algorithms of programming, as well as control code with a high-performance C/C++ compiler.

 ZSP5000H is a programmable Vector Digital Signal Processor Core targeted for high performance Computer Vision and Image processing applications. The programmer friendly architecture offers an orthogonal instruction set that greatly simplifies programming complex Image processing algorithms as well as control code with a high-performance C/C++ compiler.

 ZSP5000 is a programmable Vector Digital Signal Processor Core for high performance computer vision and image processing applications. The programmer friendly architecture offers an orthogonal instruction set that greatly simplifies complex image processing algorithms of programming, as well as control code with a high-performance C/C++ compiler.

 Hantro VC9000NanoE is a multi-format video encoder supporting H.264, VP8 and JPEG. It is the first HW IP encoder to support VP8 for Google’s WebM and WebRTC. Hantro VC9000NanoE was designed for battery operated devices using state-of-the-art power saving methods leading to unbeatable power consumption.

 Hantro VC9000NanoD is a multi-format video decoder supporting all significant video standards and proprietary video formats. It is the first HW IP decoder to support VP8 for Google’s WebM and WebRTC. Hantro VC9000NanoD was designed for battery operated devices using state-of–the-art power saving methods leading to unbeatable power consumption.  

 Hantro VC9000E enables 8K encoding with a smaller silicon and high video quality single-core solution, or multi-core solution up to 8K@120fps, supporting AV1, HEVC, H.264, VP9 video formats and JPEG.

VeriSilicon's Hantro VC9000E is based on silicon-proven VeriSilicon Hantro technology that has been widely developed in use cases that demand the most performance and quality from data centers to low power AIOT devices, in millions of smartphones, tablets, ARVR, automotive, set-top boxes, DTV’s and video cameras worldwide.
 

Hantro VC9000E provides semiconductor manufacturers a minimum risk solution for integrating high-performance video capability into their chips.

 Hantro VC9000D enables 8K decoding with a smaller silicon single-core solution, or multi-core solution up to 8K@120fps, supporting AV1, HEVC, H.264, AVS3, AVS2, VP9 video formats, JPEG, and legacy formats.

VeriSilicon's Hantro VC9000D is based on silicon-proven VeriSilicon Hantro technology that has been widely developed in use cases that demand the most performance and quality from data centers to low power AIOT devices, in millions of smartphones, tablets, ARVR, automotive, set-top boxes, DTV’s and video cameras worldwide.
 

Hantro VC9000D provides semiconductor manufacturers a minimum risk solution for integrating high-performance video capability into their chips.

芯原Vivante显示处理器IP系列已经经过多种产品验证，具备旋转、数据格式转换、HDR 视频处理和高质量视频缩放等显示处理功能，并可将HDR 层和图形层合成以提供高视觉质量，且显著减少芯片功耗。

Vivante显示处理器IP系列可广泛应用于需要硬件UI显示能力和高质量显示效果的应用，包括可穿戴设备、MCU、MPU、移动、桌面计算机、UHD电视和投影。

 VeriSilicon’s Vivante VIP9400 processor family offers programmable, scalable and extendable solutions for markets that demand real time and powerful AI devices. VIP9400 Series’ patented Neural Network engine and Tensor Processing Fabric deliver superb neural network inference performance with industry-leading power efficiency (TOPS/W) and area efficiency (mm2/W). The VIP9400’s scalable architecture can provide up to more than 300 TOPS computing ability, enables AI for data center and automotive application.

In addition to neural network acceleration, VIP9400 Series are equipped with Parallel Processing Units (PPUs), which provide full programmability along with conformance to OpenCL 1.2 and OpenVX 1.2.

 VeriSilicon’s Vivante VIP9000 processor family offers programmable, scalable and extendable solutions for markets that demand real time and low power AI devices. VIP9000 Series’ patented Neural Network engine and Tensor Processing Fabric deliver superb neural network inference performance with industry-leading power efficiency (TOPS/W) and area efficiency (mm2/W). The VIP9000’s scalable architecture, ranging from 0.5TOPS to 100TOPS, enables AI capability for a wide range of applications, from wearable and IoT devices, IP Cam, surveillance cameras, smart home & appliances, mobile phones and laptops to automotive (ADAS, autonomous driving) and edge servers. In addition to neural network acceleration, VIP9000 Series are equipped with Parallel Processing Units (PPUs), which provide full programmability along with conformance to OpenCL 3.0 and OpenVX 1.2.  

VIP9000 Series IP supports all popular deep learning frameworks (TensorFlow, TensorFlow Lite, PyTorch, Caffe, DarkNet, ONNX, Keras, etc.) and natively accelerates neural network models through optimization techniques such as quantization, pruning, and model compression. AI applications can easily port to VIP9000 platforms through offline conversion by Vivante’s ACUITYTM Tools SDK or through run-time interpretation with Android NN, NNAPI Delegate, ARMNN, or ONNX Runtime.

 VeriSilicon’s Vivante VIP9000Pico processor family offers low power, programmable, scalable and extendable solutions for markets that demand low power AI devices. VIP9000Pico Series’ patented Neural Network engine and Tensor Processing Fabric deliver superb neural network inference performance with industry-leading power efficiency (TOPS/W) and area efficiency (mm2/W). The VIP9000Pico’s scalable architecture enables AI for wearable and IoT market. In addition to neural network acceleration, VIP9000Pico Series are optionally equipped with Parallel Processing Units (PPUs), which provide full programmability along with conformance to OpenCL 3.0 and OpenVX 1.2.  

VIP9000Pico Series IP supports all popular deep learning frameworks (TensorFlow, TensorFlow Lite, PyTorch, Caffe, DarkNet, ONNX, Keras, etc.) and natively accelerates neural network models through optimization techniques such as quantization, pruning, and model compression. AI applications can easily port to VIP9000Pico platforms through offline conversion by Vivante’s ACUITYTM Tools SDK or through run-time interpretation with Android NN, NNAPI Delegate, ARMNN, or ONNX Runtime.

 The new technologies and architecture of VeriSilicon's Vivante 2D composition series enhancements that increase multi-surface composition performance and reduce bandwidth bring new levels of exciting and responsive user experiences to mobile, embedded and consumer devices. These cutting-edge innovations pack more performance per mm² and cut power up to 10X with Vivante’s optimized composition management when paired with Vivante 3D GPUs, and compression/decompression modules.

 VeriSilicon’s Vivante 2.5D GPU series is designed specifically for MCU and MPU applications that require hardware accelerated UI displays and effects. Built upon the mass market proven ScalarMorphic^™ architecture powering some of the leading font rendering engines, HMI interfaces, smartphones, TVs, tablets, automobiles, and embedded devices, the 2.5D GPU series embedded UI architecture brings eye-catching graphics capabilities to MCU/MPU designs.

 VeriSilicon's Vivante 3D GPGPU IP provides computing horsepower, ranging from low-power embedded devices to high-performance servers. Built upon our highly successful GPU/GPGPU computing engine, the CC8000 and CC8X00 Series re-define the computing market with highly scalable IP cores to serve a wide range of computing demands.

 With the latest features and class-leading performance across its entire range of mass market consumer and embedded products, the GC8000Nano series increase performance and GPU computational efficiency and bring new levels of exciting 3D graphics experiences to mobile, embedded, and microcontroller-based devices.