Neural Processing Element With N+1-Bit Operand Extension

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing general-purpose processors, such as GPUs, are unsuitable for long-duration DNN operations in low-power devices due to high computational complexity and power consumption, and existing ASICs do not adequately address the need for reduced power consumption and improved performance in DNN processing.

Innovation Solution

A neural processing element with increased precision calculations is implemented, using hardware AND gates and concatenation circuits to extend operands from N bits to N+1 bits, particularly for operands from DNN layers like ReLU, enabling higher precision computations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If general-purpose processors like GPUs are used for DNN operations, then computational performance is improved, but power consumption increases

Engineering Contradiction:
Improvecomputational performanceVSAvoidpower consumption
Core Design Contradiction:
ProductivityVSUse of energy by moving object

Solution Approach 1:

The processor is divided into multiple processing elements (PEs), each specialized for specific DNN operations. Each PE contains dedicated multiply-accumulate units and activation function units, segmenting the computational tasks to improve efficiency while reducing overall power consumption through targeted optimization.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The processor dynamically adjusts operational parameters including precision settings (16-bit, 32-bit, 64-bit floating point), activation function selection, and precision control based on input characteristics. This allows the system to optimize the balance between computational performance and power consumption by selecting appropriate precision levels for different DNN layers and operations.

Inventive Principle:
Principle #35Parameter changes

2Measurement precision

If standard precision N-bit operations are used, then device complexity is reduced, but measurement precision deteriorates

Engineering Contradiction:
Improvecomputational precisionVSAvoidarchitecture complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The processor implements dynamic precision control where the precision level (N-bit, N+1-bit, or extended precision) is adjusted based on the specific DNN layer and operation type. The system can switch between different precision modes including 16-bit, 32-bit, and 64-bit floating point operations, allowing high precision where needed while maintaining lower complexity elsewhere in the network.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system changes the precision parameter dynamically based on input characteristics and layer requirements. For ReLU layers, the system can utilize all N bits of the operand for increased precision, while for other layers it may use standard N-bit operations, thereby adapting the computational precision to the specific requirements of each operation.

Inventive Principle:
Principle #35Parameter changes

3Measurement precision

If N-bit operations are used for ReLU layer outputs, then device complexity is reduced, but measurement precision deteriorates

Engineering Contradiction:
Improveoperand precisionVSAvoidprocessing complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The processor applies different precision handling strategies to different parts of the computation pipeline. For ReLU layer outputs, the system locally increases precision by utilizing all N bits of the operand in subsequent operations, while maintaining standard precision handling for other operations. This localized precision enhancement improves overall DNN accuracy without requiring increased precision throughout the entire system.

Inventive Principle:
Principle #3Local quality

Data Source

PatentEP3991023B1Increased precision neural processing element
Publication Date: 2025.09.17 MICROSOFT TECHNOLOGY LICENSING LLC
  • EP3991023B1 patent drawingFigure 1
  • EP3991023B1 patent drawingFigure 2
  • EP3991023B1 patent drawingFigure 3A

AI summary

Neural processing elements are configured with a hardware AND gate configured to perform a logical AND operation between a sign extend signal and a most significant bit ("MSB") of an operand. The state of the sign extend signal can be based upon a type of a layer of a deep neural network ("DNN") that generate the operand. If the sign extend signal is logical FALSE, no sign extension is performed. If the sign extend signal is logical TRUE, a concatenator concatenates the output of the hardware AND gate and the operand, thereby extending the operand from an N-bit unsigned binary value to an N+1 bit signed binary value. The neural processing element can also include another hardware AND gate and another concatenator for processing another operand similarly. The outputs of the concatenators for both operands are provided to a hardware binary multiplier.