Low precision deep neural network enabled by compensation instructions

An integrated circuit (IC) comprising:

• a processing element circuit configured to produce a dot product based on a first vector having a set of components and a second vector having a set of corresponding components, wherein a component of the first vector comprises a first quantized value and a first compensation instruction and a corresponding component of the second vector comprises a second quantized value and a second compensation instruction,
• the processing element circuit comprising:
• a computation circuit configured to multiply the first quantized value with the second quantized value to compute a raw product value;
• a compensation circuit configured to compensate the raw product value for a quantization error according to the first and second compensation instructions to produce a compensated product value;
• and
• an accumulation circuit configured to add the compensated product value into an accumulated value for the dot product.

A computer-implemented method for computing a dot-product, comprising:

• receiving a first vector having a set of components and a second vector having a set of corresponding components, wherein a component of the first vector comprises a first quantized value and a first compensation instruction and a corresponding component of the second vector comprises a second quantized value and a second compensation instruction;
• multiplying the first quantized value with the second quantized value to compute a raw product value;
• compensating the raw product value for a quantization error according to the first and second compensation instructions to produce a compensated product value;
• adding the compensated product value into an accumulated value for the dot product;
• and
• converting the accumulated value into an output vector of the dot product, the output vector comprising an output quantized value and an output compensation instruction.