Logging Unit Timestamp Precision via LSB Segmentation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

In computer systems, especially those with high-frequency event occurrence like signal processing units, there is a trade-off between timestamp precision and payload information due to limited trace log storage capacity, leading to ambiguous timestamps and loss of time flow if more bits are allocated for timestamps, reducing the available bits for event data.

Innovation Solution

The solution involves increasing the number of bits in the timestamp by storing only the least significant bits in each entry and adding additional entries when these bits wrap, allowing for an N-bit timestamp without increasing the entry size, thereby maintaining timestamp precision and payload information.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If the number of timestamp bits is increased to extend wraparound time, then timestamp precision is improved, but payload information capacity deteriorates due to limited entry size

Engineering Contradiction:
Improvetimestamp precisionVSAvoidpayload information capacity
Core Design Contradiction:
Measurement precisionVSLoss of information

Solution Approach 1:

The timestamp is segmented into two parts: the least significant bits (LSBs) are stored in the timestamp field of each entry, while the most significant bits (MSBs) are stored in a separate counter register. This segmentation allows the system to achieve high timestamp precision (by using more total bits) without reducing the payload capacity of individual log entries, as only the LSBs need to be stored with each event.

Inventive Principle:
Principle #1Segmentation

2Reliability

If the number of timestamp bits is increased to reduce wraparound frequency, then time flow accuracy is improved, but the available bits for payload are reduced

Engineering Contradiction:
Improvetime flow accuracyVSAvoidentry structure complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

A separate counter register acts as an intermediary to store the MSBs of the timestamp. This intermediary structure allows the system to maintain high time flow accuracy over extended periods without increasing the complexity of individual log entry structures, as the MSBs are stored externally to the event entries.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Measurement precision

If more bits are allocated to timestamp in each entry, then timestamp precision is improved, but payload information capacity deteriorates

Engineering Contradiction:
Improvetimestamp resolutionVSAvoidpayload data capacity
Core Design Contradiction:
Measurement precisionVSQuantity of substance

Solution Approach 1:

The solution moves part of the timestamp storage to another dimension - a separate counter register rather than the log entry structure. This dimensional separation allows the timestamp to use more total bits (improving resolution) while keeping the payload capacity of each entry unchanged, as the MSBs are stored in a different storage dimension (the counter register) rather than consuming payload space.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Data Source

PatentEP3098733B1Logging events with timestamps
Publication Date: 2020.01.15 IMAGINATION TECH LTD
  • EP3098733B1 patent drawingFigure 1~2
  • EP3098733B1 patent drawingFigure 3
  • EP3098733B1 patent drawingFigure 4~5

AI summary

A logging unit is used to log entries for events in a computer system. Each entry includes an n-bit timestamp field and a payload. The payload includes information about the event and the timestamp field includes the n least significant bits of an N-bit timestamp for the event, where N > n. If the n least significant bits of the timestamp have wrapped compared to the corresponding n bits of the timestamp of the preceding entry then a timing entry is logged which includes other bits of the timestamp. Therefore, an N-bit timestamp can be determined for an event, but only the n least significant bits of the timestamp are stored in the timestamp field of an entry for the event. Therefore, the time flow of events in the store is better maintained (by having a larger timestamp) without increasing the number of bits (n) in the timestamp field of each entry.