Difference between revisions of "RK Platform NPU SDK"
From ESS-WIKI
Yunjin.jiang (talk | contribs) (Created page with "= '''Preface''' = TBD = '''rknpu2''' = TBD = '''rknn-toolkit2''' = TBD") |
Yunjin.jiang (talk | contribs) |
||
| Line 1: | Line 1: | ||
| + | |||
= '''Preface''' = | = '''Preface''' = | ||
| − | + | ||
| + | == NPU Introduce == | ||
| + | |||
| + | === RK3568 === | ||
| + | |||
| + | === RK3588 === | ||
| + | |||
| + | *Neural network acceleration engine with processing performance up to 6 TOPS | ||
| + | *Include triple NPU core, and support triple core co-work, dual core co-work, and work independently | ||
| + | *Support integer 4, integer 8, integer 16, float 16, Bfloat 16 and tf32 operation | ||
| + | *Embedded 384KBx3 internal buffer | ||
| + | *Multi-task, multi-scenario in parallel | ||
| + | *Support deep learning frameworks: TensorFlow, Caffe, Tflite, Pytorch, Onnx NN, Android NN, etc. | ||
| + | *One isolated voltage domain to support DVFS | ||
| + | |||
| + | == RKNN SDK == | ||
= '''rknpu2''' = | = '''rknpu2''' = | ||
Revision as of 04:41, 8 August 2023
Contents
Preface
NPU Introduce
RK3568
RK3588
- Neural network acceleration engine with processing performance up to 6 TOPS
- Include triple NPU core, and support triple core co-work, dual core co-work, and work independently
- Support integer 4, integer 8, integer 16, float 16, Bfloat 16 and tf32 operation
- Embedded 384KBx3 internal buffer
- Multi-task, multi-scenario in parallel
- Support deep learning frameworks: TensorFlow, Caffe, Tflite, Pytorch, Onnx NN, Android NN, etc.
- One isolated voltage domain to support DVFS
RKNN SDK
rknpu2
TBD
rknn-toolkit2
TBD