High throughput coding of neural network parameters
AssigneeQUALCOMM Incorporated
InventorAmir Said
Life of this patent
Estimating the term…
Abstract
Certain aspects of the disclosure provide for encoding quantized data including neural network weights. Encoding can include determining bits of quantized data that are compressible and non-compressible based on one or more properties of the quantized data and performing a byte-aligned rearrangement of the bits of the quantized data. Subsequently, a compression technique can be selectively applied to at least one compressible bit, and at least one non-compressible bit can be copied. Further, the data can be decoded by identifying a compressed byte in a stream of bytes, decompressing the compressed byte, and extracting bits from the stream of bytes that encode quantized data.
Claims20
A method of encoding data, comprising:
- determining bits of quantized data that are compressible and non-compressible based on one or more properties of the quantized data;
- performing a byte-aligned rearrangement of the bits of the quantized data;
- applying a compression technique to at least one compressible bit;
- and
- copying at least one non-compressible bit.
An apparatus configured to encode data, the apparatus comprising:
- one or more memories;
- processing circuitry in communication with the one or more memories, the processing circuitry configured to:
- determine bits of quantized data that are compressible and non-compressible based on one or more properties of the quantized data;
- perform a byte-aligned rearrangement of the bits of the quantized data;
- apply a compression technique at least one compressible bit;
- and
- copy at least one non-compressible bit.
A method of decoding coded data, comprising:
- receiving a stream of bytes that represent quantized data;
- identifying at least one compressed byte in the stream of bytes;
- decompressing the at least one compressed byte;
- and
- extracting bits from the stream of bytes that encode the quantized data.
Dependencies are inferred from the claim text.