GPU CPU

Posted on by lechuck park

Traditional Computing (CPU)

  • It presents ‘Multiple threads’, ‘Time-slicing’, and ‘Flattened load’ as its main features.
  • It shows a time-slicing method in the form of bar charts, where multiple threads (Thread 1 to 4) run one by one sequentially by dividing time.
  • The Power Load graph over time remains constant without large fluctuations, and this state is described as ‘Smooth & Predictable’.

AI Computing (GPU)

  • It presents ‘SIMT’, ‘Massive parallel’, and ‘Spiky load’ as its main features.
  • It depicts a massive parallel processing structure where thousands of cores execute the same instruction simultaneously (lock-step), represented by a grid of numerous blue squares.
  • The Power Load graph shows a ‘Spiky’ pattern, with power consumption sharply peaking at specific times because it performs operations at 100% at once.

Summary

A CPU processes multiple tasks sequentially by dividing time, resulting in stable and predictable power consumption. In contrast, a GPU utilizes thousands of cores to process massive calculations in parallel all at once, leading to a structural difference where the power load temporarily spikes.

#CPUvsGPU #AIComputing #ParallelProcessing #TimeSlicing #PowerLoad #HardwareArchitecture

With ChatGPT & Gemini

Knowledge update

Posted on by lechuck park

This image is a workflow diagram illustrating a “Knowledge update” process, demonstrating how artificial intelligence and human collaboration continuously refine a knowledge base.

Image Interpretation:

  • Initial Data and Human Input: The process begins on the far left with a “Change” icon representing data fluctuations. This quantitative data (“number”) flows into the first integration node (+), where a “Human Decision” is applied to formulate the initial block of “Knowledge.”
  • LLM and Knowledge Integration: This foundational knowledge is then passed forward as “Text” to the next processing stage. Here, the workflow incorporates an “LLM Agent” (Large Language Model) alongside multiple existing foundational knowledge sources to enrich and process the information.
  • Final Review and Feedback Loop: The enriched text undergoes a second round of “Human Decision” for final review and validation before being solidified into the final “Knowledge” state. Crucially, a large blue feedback arrow loops from this final “Knowledge” output back to the underlying knowledge sources, illustrating a continuous learning cycle where new updates strengthen the overall system.

Summary

The flowchart maps out a “Human-in-the-loop” AI-driven knowledge management system. It highlights a cyclical process that combines raw data changes, human oversight, and LLM processing capabilities to continuously verify, update, and improve a dynamic knowledge base.

#KnowledgeManagement #ArtificialIntelligence #LLM #Workflow #DataProcessing #AISystems #HumanInTheLoop #KnowledgeUpdate