EdgeCortix introduces SAKURA-II, an AI accelerator for the Edge with impressive performance of 60 TOPS (INT8) and a low power consumption of 8 watts. The chip is designed for complex AI tasks, such as processing large language models (LLM), large vision models (LVM), and transformer-based multimodal applications, as well as for applications at the network edge, such as devices IoT and autonomous vehicles.
It allows flexibility in terms of hardware, with the possibility of integrating it into both PCIe expansion cards with one or two SAKURA-II chips, or also in M.2 2280 modules (PCIe x8 or x16 interface) If you prefer. Therefore, powers of up to 120 TOPS can be reached with INT8 or 60 TFLOPS with BF16.
The AI platform also offers a part of cutting-edge software, with a MERA suite for programming and optimization, a heterogeneous compilation platform, advanced quantification techniques, and model calibration capabilities. It also features integration with popular development frameworks such as PyTorch, TensorFlow Lite, and ONNX, as well as access to an extensive library of cutting-edge transformative models and convolutional models.
In addition, the company EdgeCortix has also thought about taking its AI accelerator designs further, being able be integrated into SoCs from other companies, such as AMD.
IA SAKURA-II technical specifications
As for the EdgeCortix SAKURA-II technical specifications, are the following:
- NPU with DNA-II or second-generation Dynamic Neural Accelerator architecture.
- Performance up to 60 TOPS with INT8 or 30 TFLOPS with BF16.
- DRAM memory with dual 64-bit channel type LPDDR4x (8GB, 16GB, 32GB on-board) with bandwidth up to 68 GB/s.
- Integrated 20MB SRAM memory.
- Efficiency of up to 90% utilization, with energy consumption of 8W.
- BGA packaging.
If we refer to SAKURA-II module with M.2 format, we have:
- DRAM memory
- 8GB (2x banks of 4GB LPDDR4)
- 16GB (2x banks of 8GB LPDDR4)
- PCIe Gen 3.0 x4 interface
- Maximum performance of 60 TOPS on INT8, 30 TFLOPS on BF16
- 10W module power
- Dimensions M.2 2280 (22x80mm)
For PCIe expansion card, the specifications are as follows for the AI accelerator:
- PCIe Gen 3.0 x8 interface
- For SAKURA-II single chip model:
- 16GB DRAM memory (2x banks of 8GB LPDDR4)
- Performance of 60 TOPS on INT8, 30 TFLOPS on BF16
- 10W power.
- For the model with two SAKURA-II chips:
- 32GB DRAM memory (2x banks of 16GB LPDDR4)
- Performance of 120 TOPS on INT8, 60 TFLOPS on BF16
- Power of 20W
- 1x Slot
- Includes heatsink
As for the rates, if you are wondering, they will arrive from the second quarter of 2024 with:
- M.2 8GB: $249
- M.2 16GB: $299
- PCIe 1xSAKURA-II: $429
- PCIe 2xSAKURA-II: $749