Etnaviv NPU update 22: YOLOX support

We have expanded our open-source NPU support for object detection: YOLOX is now running on the Etnaviv driver.

This brings high-performance, open-source AI acceleration to the Vivante VIP line of NPUs, including those found in the NXP i.MX 8M Plus and the Amlogic A311D. Adding YOLOX gives users more options when balancing detection accuracy against available hardware resources.

YOLOX is an open-source object detection model developed by Megvii (Apache 2.0). It is particularly well-suited for edge NPUs, but it is significantly more complex than SSDLite MobileDet (our previously supported model). Getting it running required implementing several new operations in the driver.

As part of this work, we landed support for:

• FullyConnected: A new operation that runs directly on the NN (convolution) cores.
• Reshape, Split, and Concatenate: Handled via metadata changes; these do not execute on the hardware, saving cycles.
• Fused ReLU: Enables activation function hardware on the output.
• Absolute and Logistic: Implemented as lookup table operations on the TP (tensor processing) cores.
• Subtract: Lowered to a convolution, similar to our approach for Add.
• Transpose: Either fused into the next operation or handled as a TP operation.

Additionally, we added support for feature maps in signed 8-bit integers. For certain models, this provides increased accuracy at the exact same computational cost.

This work was performed in partnership with Ideas On Board.

YOLOX is an open-source project developed by Megvii and licensed under the Apache License 2.0.