The present disclosure provides a computation device. The computation device is configured to perform a machine learning computation, and includes an operation unit, a controller unit, and a conversion unit. The storage unit is configured to obtain input data and a computation instruction. The controller unit is configured to extract and parse the computation instruction from the storage unit to obtain one or more operation instructions, and to send the one or more operation instructions and the input data to the operation unit. The operation unit is configured to perform operations on the input data according to one or more operation instructions to obtain a computation result of the computation instruction. In the examples of the present disclosure, the input data involved in machine learning computations is represented by fixed-point data, thereby improving the processing speed and efficiency of training operations.

The present disclosure provides a computation device. The computation device is configured to perform a machine learning computation, and includes an operation unit, a controller unit, and a conversion unit. The storage unit is configured to obtain input data and a computation instruction. The controller unit is configured to extract and parse the computation instruction from the storage unit to obtain one or more operation instructions, and to send the one or more operation instructions and the input data to the operation unit. The operation unit is configured to perform operations on the input data according to one or more operation instructions to obtain a computation result of the computation instruction. In the examples of the present disclosure, the input data involved in machine learning computations is represented by fixed-point data, thereby improving the processing speed and efficiency of training operations.

The present disclosure provides a computation device. The computation device is configured to perform a machine learning computation, and includes an operation unit, a controller unit, and a conversion unit. The storage unit is configured to obtain input data and a computation instruction. The controller unit is configured to extract and parse the computation instruction from the storage unit to obtain one or more operation instructions, and to send the one or more operation instructions and the input data to the operation unit. The operation unit is configured to perform operations on the input data according to one or more operation instructions to obtain a computation result of the computation instruction. In the examples of the present disclosure, the input data involved in machine learning computations is represented by fixed-point data, thereby improving the processing speed and efficiency of training operations.

A system for block floating point computation in a neural network receives a plurality of floating point numbers. An exponent value for an exponent portion of each floating point number of the plurality of floating point numbers is identified and mantissa portions of the floating point numbers are grouped. A shared exponent value of the grouped mantissa portions is selected according to the identified exponent values and then removed from the grouped mantissa portions to define multi-tiered shared exponent block floating point numbers. One or more dot product operations are performed on the grouped mantissa portions of the multi-tiered shared exponent block floating point numbers to obtain individual results. The individual results are shifted to generate a final dot product value, which is used to implement the neural network. The shared exponent block floating point computations reduce processing time with less reduction in system accuracy.

A method to produce a final product from a multiplicand and a multiplier is provided. The method is executed by a parallel decimal multiplication hardware architecture, which includes a 3 generator, at least one additional generator, a multiplier recoder, a partial product tree, and a decimal adder. The 3 generator, the at least one additional generator, and the multiplier recoder generate decimal partial products from the multiplicand and the multiplier. The partial product tree executes a reduction of the decimal partial products to produce two corresponding partial product accumulations. The decimal adder adds the two corresponding partial product accumulations of the decimal partial products to produce the final product.

A round-for-reround mode (preferably in a BID encoded Decimal format) of a floating point instruction prepares a result for later rounding to a variable number of digits by detecting that the least significant digit may be a 0, and if so changing it to 1 when the trailing digits are not all 0. A subsequent reround instruction is then able to round the result to any number of digits at least 2 fewer than the number of digits of the result. An optional embodiment saves a tag indicating the fact that the low order digit of the result is 0 or 5 if the trailing bits are non-zero in a tag field rather than modify the result. Another optional embodiment also saves a half-way-and-above indicator when the trailing digits represent a decimal with a most significant digit having a value of 5. An optional subsequent reround instruction is able to round the result to any number of digits fewer or equal to the number of digits of the result using the saved tags.

A round-for-reround mode (preferably in a BID encoded Decimal format) of a floating point instruction prepares a result for later rounding to a variable number of digits by detecting that the least significant digit may be a 0, and if so changing it to 1 when the trailing digits are not all 0. A subsequent reround instruction is then able to round the result to any number of digits at least 2 fewer than the number of digits of the result. An optional embodiment saves a tag indicating the fact that the low order digit of the result is 0 or 5 if the trailing bits are non-zero in a tag field rather than modify the result. Another optional embodiment also saves a half-way-and-above indicator when the trailing digits represent a decimal with a most significant digit having a value of 5. An optional subsequent reround instruction is able to round the result to any number of digits fewer or equal to the number of digits of the result using the saved tags.

A method may include generating, from an expression, an expression tree including an arithmetic operation and conversion operations each converting an operand of the arithmetic operation from an initial decimal format to an optimized decimal format. The initial decimal format may include a shape. The method may further include at runtime, evaluating the arithmetic operation with initial operands represented in the initial decimal format, and specializing one of the conversion operations according to the shape of the corresponding initial operand.

A method may include generating, from an expression, an expression tree including an arithmetic operation and conversion operations each converting an operand of the arithmetic operation from an initial decimal format to an optimized decimal format. The initial decimal format may include a shape. The method may further include at runtime, evaluating the arithmetic operation with initial operands represented in the initial decimal format, and specializing one of the conversion operations according to the shape of the corresponding initial operand.

A system for block floating point computation in a neural network receives a plurality of floating point numbers. An exponent value for an exponent portion of each floating point number of the plurality of floating point numbers is identified and mantissa portions of the floating point numbers are grouped. A shared exponent value of the grouped mantissa portions is selected according to the identified exponent values and then removed from the grouped mantissa portions to define multi-tiered shared exponent block floating point numbers. One or more dot product operations are performed on the grouped mantissa portions of the multi-tiered shared exponent block floating point numbers to obtain individual results. The individual results are shifted to generate a final dot product value, which is used to implement the neural network. The shared exponent block floating point computations reduce processing time with less reduction in system accuracy.