Hardware Metric Predictor for Neural Network Architecture

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for predicting hardware metrics, such as energy consumption and latency, for neural networks on target hardware are impractical due to the need for extensive training data and costly measurement processes, especially when simulators are unavailable or inaccurate.

Innovation Solution

A neural network is trained using a modest set of measurement data to predict hardware metrics for novel hardware targets, employing a transformer architecture and a ground truth set to infer relationships between neural network architectures and their corresponding metrics, allowing for few-shot predictions without requiring extensive data from the target hardware.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a machine learnable model is trained to predict hardware metrics, then prediction accuracy improves, but the amount of training data required increases substantially

Engineering Contradiction:
Improvehardware metric prediction accuracyVSAvoidtraining data volume
Core Design Contradiction:
Measurement precisionVSQuantity of substance

Solution Approach 1:

The system performs preliminary actions by collecting hardware metric measurements from multiple source hardware platforms before training begins. These pre-collected measurements from diverse hardware sources serve as foundational training data, enabling the model to learn hardware-specific patterns without requiring extensive data collection from the target hardware platform itself.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The trained hardware metric predictor is designed to be universally applicable across multiple target hardware platforms. By training on data from various source hardware types, the single model learns transferable patterns that enable accurate predictions on different hardware architectures, reducing the need for platform-specific data collection.

Inventive Principle:
Principle #6Universality (Multi-functionality)

2Measurement precision

If hardware metrics are measured on target hardware, then prediction accuracy improves, but time consumption and cost increase

Engineering Contradiction:
Improvehardware metric measurement accuracyVSAvoidmeasurement cycle time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

Instead of measuring hardware metrics directly on the target hardware, the system creates a predictive model by copying and analyzing measurements from source hardware platforms. The trained model then serves as a virtual copy that can predict target hardware metrics without requiring physical access to or repeated testing on the actual target device, eliminating iterative compile-upload-test cycles.

Inventive Principle:
Principle #26Copying

Solution Approach 2:

Hardware metric measurements from source platforms are collected and processed in advance before the actual prediction is needed. This preliminary data collection and model training enables rapid predictions on target hardware without requiring time-consuming measurement cycles on the target device itself.

Inventive Principle:
Principle #10Preliminary action

3Loss of time

If simulators are used to estimate hardware costs, then measurement time reduces, but accuracy deteriorates

Engineering Contradiction:
Improvehardware metric estimation timeVSAvoidhardware metric estimation accuracy
Core Design Contradiction:
Loss of timeVSMeasurement precision

Solution Approach 1:

The system introduces a trained machine learnable model as an intermediary between hardware architecture descriptions and actual hardware metric values. This model, trained on real measurements from source hardware, acts as a mediator that translates architectural parameters into accurate metric predictions without requiring direct simulation or physical measurement, achieving both speed and accuracy.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP4414895A1Improved method for training a hardware metric predictor
Publication Date: 2024.08.14 ROBERT BOSCH GMBH
  • EP4414895A1 patent drawingFigure 1a~1b
  • EP4414895A1 patent drawingFigure 2a~2b
  • EP4414895A1 patent drawingFigure 2c~3

AI summary

Some embodiments are directed to training a hardware metric predictor. The hardware metric predictor being configured to receive as input a query description of a neural network architecture and to produce as output a predicted hardware metric predicted to be incurred by a neural network corresponding to the query description when run on the target hardware. Method may include giving as training input a number of input/output pairs of a given training function.