aiWare specifications
Key features
| Performance | 1-24 TOPS per core @ 1.5GHz |
| MAC/Cycle (8x8) | 512-4096 INT8 (32-bit internal) |
| Utilization | Up to 98% for NNs such as vgg16 or Yolo >85% for many automotive CNNs |
| NN Convolution | Up to 100% efficiency achievable. MAC arrays optimized for 2D and 3D convolution and deconvolution. Matrix multipliers not used - no need for Winograd or other transforms |
| Support functions | Wide range of Activation, Pooling, Unary, Binary, Tensor Introduction/Shaping and Linear operations to ensure 100% CNN execution within aiWare core with no host CPU intervention |
| Configurability | Wide range of workload optimizations possible without compromising flexibility |
| NN capability | Any INT8 CNN (no depth limit) |
| Data types | INT8 Native 32-bit internal precision and dynamic per-layer scaling |
| Sparsity | Not needed for well-optimized NNs |
| Multicore capability | No limit |
| Safety | Designed to be part of an ASIL-B and higher certified subsystem full safety manual |
Memory
| Embedded SRAM | 10-200 Mbits per core |
| External Memory | Dedicated off-chip DRAM or shared SOC memory |
| Bandwidth reduction | On-chip compression |
| Main interface | AXI4 to LPDDR AXI4 to host |
Neural Network Development Frameworks
| Frameworks supported | Caffe/Caffe2, TensorFlow, PyTorch, ONNX, Khronos NNEF |
| Inference deployment | Binary compiled using aiWare Studio or command line tools offline Single binary contains one or multiple NNs, weights and all scheduling info |
| Software runtime | Minimal host CPU management required during execution. Simple generic portable runtime API runs on any RTOS or HLOS; wrappers to popular APIs available on request |
| Development Tools | aiWare Studio provides comprehensive tools to import, analyse and optimize any NN with easy to use interactive UI |
| Evaluation Tools | aiWare Studio features offline performance estimator accurate to within 5% of final silicon FPGA implementations also available |
Target applications
| Automotive Inference for automated driving | |
| High performance automotive multi-camera perception | |
| Large camera NN processing (no upper limit on input resolution) | |
| High data rate heterogeneous multi-sensor fusion |
Interested in aiWare's hardware innovations?
Contact Us
Get in touch with us
Our team is always ready to work with exciting and ambitious clients. If you're ready to start your partnership with us, get in touch.
