github-starred/cs249r_book
2
0
Fork 0
mirror of https://github.com/harvard-edge/cs249r_book.git synced 2026-03-12 02:06:14 -05:00
Code Issues Packages Projects Releases Wiki Activity

Update benchmarking.qmd

Browse Source
This commit is contained in:
Vijay Janapa Reddi
2023-09-21 14:05:04 -04:00
parent 26d7780726
commit 44a604b6e1
1 changed files with 6 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
benchmarking.qmd
View File

@@ -2,14 +2,14 @@
## Introduction
Explanation: Introducing the concept and importance of benchmarking sets the stage for the reader to understand why it is crucial in the evaluation and optimization of AI systems, especially in resource-constrained embedded environments.
Explanation: Introducing the concept and importance of benchmarking sets the stage for the reader to understand why it is crucial in the evaluation and optimization of AI systems, especially in resource-constrained embedded environments where it is even more important!
- Importance of benchmarking in AI
- Objectives of benchmarking
## Types of Benchmarks
Explanation: Understanding the different types of benchmarks helps readers tailor their benchmarking activities to specific needs, whether they are evaluating low-level operations or entire application performance.
Explanation: Understanding the different types of benchmarks will help our readers tailor their performance evaluation activities to specific needs, whether they are evaluating low-level operations or entire application performance.
- Micro-benchmarks
- Macro-benchmarks
@@ -24,6 +24,7 @@ Explanation: Metrics are the yardsticks used to measure performance. This sectio
- Throughput
- Power Consumption
- Memory Footprint
- End to end Metrics (User vs. System)
## Benchmarking Tools
@@ -34,13 +35,13 @@ Explanation: Tools are the practical means to carry out benchmarking. Discussing
## Benchmarking Process
Explanation: Outlining the step-by-step process of benchmarking provides a structured approach for readers, ensuring that they can conduct benchmarks in a systematic and repeatable manner.
Explanation: Outlining the step-by-step process of benchmarking provides a structured approach for readers, ensuring that they can conduct benchmarks in a systematic and repeatable manner.e
- Data Preparation
- Dataset Limitation/Sources
- Model Selection
- Test Environment Setup
- Running the Benchmarks
- Data Collection
- Run Rules
## Interpreting Results