English
You are here:
Accelerator for Convolutional Neural Networks
Gyrfalcon Technologies(GTI) offers silicon proven, acceleration IP for Convolutional Neural Networks used in image classification, object detection, natural language processing and other artificial intelligence applications. The accelerator utilizes our AI Processing In Memory(APIM) architecture which is specifically designed to address high performance at low power dissipation challenges of the matrix multiplication and memory I/O demands inherent in artificial intelligence tasks. The accelerator IP is available in RTL or hard macros(available in select process geometries). The accelerators are also available in discrete silicon, USB dongles or boards.
Features
- GTI completes the AI solution by offering CNN models optimized for our accelerators. These models include VGG, ResNet, MobileNet, and other custom use cases.
View Accelerator for Convolutional Neural Networks full description to...
- see the entire Accelerator for Convolutional Neural Networks datasheet
- get in contact with Accelerator for Convolutional Neural Networks Supplier
artificial intelligence
- First interconnect solution specifically for artificial Intelligence applications
- FlexNoC AI Package
- Decision tree evaluation core using pipelined architecture
- Decision tree evaluation core using serial architecture
- Area-efficient decision tree ensemble evaluation core based on parallel evaluation of ensemble members
- Behavioral knowledge space combination rule core with serial operation