ARITHMETIC PROCESSING DEVICE AND CONTROL METHOD OF THE ARITHMETIC PROCESSING DEVICE

• US 20180181406A1
• Filed: 10/13/2017
• Published: 06/28/2018
• Est. Priority Date: 12/27/2016
• Status: Active Grant

• Current Assignee: Fujitsu Limited
• Original Assignee: Fujitsu Limited
• Inventors: Kuramoto, Masahiro
• Granted Patent: US 10,642,622 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 15/8015 One dimensional arrays, e.g. rings, linear arrays, buses
• CPC Class Codes: G06F 17/15 Correlation function computation including computation of convolution operations arithmetic circuits for sum of products per se, e.g. multiply-accumulators G06F7/5443; digital filters, e.g. FIR, IIR, adaptive filters H03H17/00
• CPC Class Codes: G06F 17/16 Matrix or vector computation , e.g. matrix-matrix or matrix-vector multiplication, matrix factorization matrix transposition G06F7/78
• CPC Class Codes: G06F 7/5443 Sum of products for applications thereof, see the relevant places, e.g. G06F17/10, H03H17/00
• CPC Class Codes: G06F 9/3001 Arithmetic instructions
• CPC Class Codes: G06F 9/30032 Movement instructions, e.g. MOVE, SHIFT, ROTATE, SHUFFLE
• CPC Class Codes: G06F 9/30036 Instructions to perform operations on packed data, e.g. vector, tile or matrix operations
• CPC Class Codes: G06F 9/3887 controlled by a single instruction for multiple data lanes [SIMD]
• CPC Class Codes: G06F 9/3895 for complex operations, e.g. multidimensional or interleaved address generators, macros
• CPC Class Codes: G06N 3/04 Architecture, e.g. interconnection topology
• CPC Class Codes: G06N 3/06 Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
• CPC Class Codes: G06N 3/063 using electronic means
• CPC Class Codes: G06N 3/084 Backpropagation, e.g. using gradient descent

Abstract

Each of product-sum arithmetic units 501 to 503 acquires, from a register file 410, different pieces of first element data included in a first predetermined row of first data that forms a matrix; acquires, from a register file 420, same pieces of second element data included in a second predetermined row of second data that forms a matrix; performs a row portion operation that is an operation performed on the first data by an amount corresponding to a single row by performing a process of performing an operation using the acquired first element data and the second element data; and performs an operation by using the first data and the second data based on the result of the row portion operation.

Claims

1. An arithmetic processing device comprising:

a data storage unit that stores first data and second data each of which has pieces of element data included in a matrix;

a plurality of arithmetic units;

a first storage unit that is arranged for each of the arithmetic units and that stores a first predetermined row of the first data that is stored in the data storage unit;

a second storage unit that is arranged for each of the arithmetic units and that stores a second predetermined row of the second data that is stored in the data storage unit; and

product-sum arithmetic units, which are arranged in each of the arithmetic units, each of which acquires different pieces of first element data included in the first predetermined row from the first storage unit, each of which acquires same pieces of second element data included in the second predetermined row from the second storage unit, and each of which performs, by performing a process of an operation using the acquired first element data and the acquired second element data a predetermined number of times, an operation by using the first data and the second data based on results of a row portion operation that is an operation performed on the first data corresponding to a single row.

2. The arithmetic processing device according to claim 1, wherein each of the plurality of arithmetic units determines, based on the size of the first data or the second data, the number of the arithmetic units that are used to perform the operation and determines the number of second arithmetic units included in the arithmetic units based on the size of one of the first data and the second data and based on an amount of movement of the second data.

3. The arithmetic processing device according to claim 1, each of the product-sum arithmetic units acquires the first element data that is moved forward by an amount corresponding to the number of strides for each operation starting from the first element data, as the top position, having a number incremented by 1 from the top in the first predetermined row, sequentially acquires, in numerical order for each operation, the second element data arrayed with consecutive numbers included in the second predetermined row, and performs the row portion operation by repeating an operation of adding a value obtained by multiplying the acquired first element data by the second element data to the last operation result.

4. The arithmetic processing device according to claim 1, wherein each of the product-sum arithmetic units acquires, from among the pieces of the first element data arrayed with consecutive numbers included in the first predetermined row, the different pieces of the first element data in numerical order, acquires, for each operation in numerical order, the second element data arrayed with consecutive numbers included in the second predetermined row, and performs the row portion operation by repeating an operation of adding a value obtained by multiplying the acquired first element data by the second element data to the operation result that is calculated in the last operation by the product-sum arithmetic unit located at the position ahead by an amount corresponding to the number of strides.

5. A control method of an arithmetic processing device connected to a storage device that stores first data and second data each of which has pieces of element data that form a matrix, the control method comprising:

storing, in a first storage device that is arranged for each computing unit having a plurality of product-sum computing units, a first predetermined row of the first data stored in the storage device;

storing, in a second storage device that is arranged for each computing unit, a second predetermined row of the second data stored in the storage device;

acquiring different pieces of first element data included in the first predetermined row from the first storage device, acquiring same pieces of second element data included in the second predetermined row from the second storage device, and allowing each of the product-sum computing units to perform an arithmetic operation of performing an operation by using the acquired first element data and the acquired second element data;

allowing each of the product-sum computing units to perform, by performing the arithmetic operation process a predetermined number of times, a row portion operation that is an operation performed on the first data corresponding to a single row; and

allowing each of the product-sum computing units to perform an operation by using the first data and the second data based on results of the row portion operation.