Hardware-Aware Mixed-Precision Quantization
AssigneeMediaTek Singapore Pte. Ltd.
InventorsHantao Huang, Ziang Yang, Jia Yao Christopher Lim, Jung Hau Foo, Chia-Lin Yu
Life of this patent
Estimating the term…
Loading patent…
AssigneeMediaTek Singapore Pte. Ltd.
InventorsHantao Huang, Ziang Yang, Jia Yao Christopher Lim, Jung Hau Foo, Chia-Lin Yu
Estimating the term…
A bit-widths determination method selects bit-widths for mixed-precision neural network computing on a target hardware platform. An activation quantization sensitivity (AQS) value is calculated for each convolution layer in a neural network. The AQS value indicates the sensitivity of convolution output to quantized convolution input. One or more convolution layers are grouped into a quantization group, which is to be executed by a corresponding set of target hardware. A group AQS value is calculated for each quantization group based on the AQS values of the convolution layers in the quantization group. Then bit-widths supported by the target hardware platform are selected for the corresponding quantization groups. The bit-widths are selected to optimize, under a given constraint, a sensitivity metric that is calculated based on each quantization group's group AQS value.
A method for determining bit-widths for mixed-precision neural network computing on a target hardware platform, comprising:
A system operative to determine bit-widths for mixed-precision neural network computing on a target hardware platform, comprising:
Dependencies are inferred from the claim text.