惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
酷 壳 – CoolShell
酷 壳 – CoolShell
博客园_首页
Engineering at Meta
Engineering at Meta
量子位
A
About on SuperTechFans
阮一峰的网络日志
阮一峰的网络日志
Recent Announcements
Recent Announcements
博客园 - 司徒正美
V
Visual Studio Blog
H
Hackread – Cybersecurity News, Data Breaches, AI and More
The GitHub Blog
The GitHub Blog
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
F
Fortinet All Blogs
Martin Fowler
Martin Fowler
腾讯CDC
Jina AI
Jina AI
C
Check Point Blog
H
Help Net Security
罗磊的独立博客
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
V
V2EX
爱范儿
爱范儿
I
InfoQ

Primate Labs: FAQs

Geekbench Valid and Invalid Tags / Geekbench / Knowledge Base Geekbench Valid and Invalid Tags / Geekbench / Knowledge Base Geekbench AI Command Line Tool / Geekbench AI / Knowledge Base Geekbench AI Command Line Tool / Geekbench AI / Knowledge Base Geekbench AI Standalone Mode / Geekbench AI / Knowledge Base Geekbench AI Standalone Mode / Geekbench AI / Knowledge Base Geekbench 6 Command Line Tool / Geekbench / Knowledge Base Geekbench 6 Command Line Tool / Geekbench / Knowledge Base Geekbench 6 Pro Standalone Mode / Geekbench / Knowledge Base Geekbench 6 Pro Standalone Mode / Geekbench / Knowledge Base Geekbench 5 Pro Standalone Mode / Geekbench / Knowledge Base Geekbench 5 Pro Standalone Mode / Geekbench / Knowledge Base Interpreting Geekbench 5 Scores / Geekbench / Knowledge Base Interpreting Geekbench 5 Scores / Geekbench / Knowledge Base Installing Geekbench 5 on Linux / Geekbench / Knowledge Base Installing Geekbench 5 on Linux / Geekbench / Knowledge Base Geekbench 5 Pro Command Line Tool / Geekbench / Knowledge Base Geekbench 5 Pro Command Line Tool / Geekbench / Knowledge Base Geekbench 4 Pro Command Line Tool / Geekbench / Knowledge Base Geekbench 4 Pro Command Line Tool / Geekbench / Knowledge Base Installing Geekbench 4 on Linux / Geekbench / Knowledge Base Installing Geekbench 4 on Linux / Geekbench / Knowledge Base Frequently Asked Questions / Geekbench / Knowledge Base Frequently Asked Questions / Geekbench / Knowledge Base Interpreting Geekbench 4 Scores / Geekbench / Knowledge Base Interpreting Geekbench 4 Scores / Geekbench / Knowledge Base Geekbench 4 Pro Standalone Mode / Geekbench / Knowledge Base Geekbench 4 Pro Standalone Mode / Geekbench / Knowledge Base Geekbench 3 Command Line Workload Codes / Geekbench / Knowledge Base Geekbench 3 Command Line Workload Codes / Geekbench / Knowledge Base
Interpreting Geekbench 2 Scores / Geekbench / Knowledge Base
John · 2011-02-01 · via Primate Labs: FAQs

Summary

Geekbench 2 scores are calibrated using the 2003 entry-level Power Mac G5 as a baseline with a score of 1,000 points. Higher scores are better, with double the score indicating double the performance.

Geekbench 2 Workloads

Geekbench 2 uses a number of different tests, or workloads, to measure performance. The workloads are divided into four different sections:

  • Integer performance: Integer workloads measure the integer instruction performance of your computer by performing processor-intensive tasks that make heavy use of integer instructions. All software makes heavy use of integer instructions, meaning a high integer scores indicates good overall performance.

  • Floating point performance: Floating point workloads measure floating point performance by performing a variety of processor-intensive tasks that make heavy use of floating-point operations. While almost all software makes use of floating point instructions, floating point performance is especially important in video games, digital content creation, and high-performance computing applications.

  • Memory performance: Memory workloads measure the performance of the memory hardware (which includes the motherboard and the chipset along with the memory itself). Memory workloads also measure the performance of the memory management functions provided by the operating system.

  • Stream performance: Stream workloads measure memory bandwidth. Geekbench 2 uses tests based on the STREAM benchmarks developed John D. McCalpin. Software working with large amounts of data (e.g., digital content creation) relies on good memory bandwidth performance to keep the processor busy.

A complete description of the individual Geekbench workloads can be found on the Primate Labs website.

Geekbench 2 Scores

Each workload's performance is compared against a baseline to determine a score. These scores are averaged together to determine an overall, or Geekbench, score for the system.

Geekbench uses the 2003 entry-level Power Mac G5 as the baseline with a score of 1,000 points. Higher scores are better, with double the score indicating double the performance.

Geekbench provides three different kinds of scores:

  • Workload Scores Each time a workload is executed Geekbench calculates a score based on the computer's performance compared to the baseline performance. There can be multiple workload scores for the same workload as Geekbench can execute each workload multiple times with different settings. For example, the "Dot Product" workload is executed four times (single-threaded scalar code, multi-threaded scalar code, single-threaded vector code, and multi-threaded vector code) producing four "Dot Product" scores.

  • Section Scores A section score is the average of all the workload scores for workloads that are part of the section. These scores are useful for determining the performance of the computer in a particular area. See the section descriptions above for a summary on what each section measures.

  • Geekbench Score The Geekbench score is the weighted average of the four section scores. The Geekbench score provides a way to quickly compare performance across different computers and different platforms without getting bogged down in details

When comparing scores, remember that higher scores are better, and double the score indicates double the performance. For example, if a MacBook Pro has a score of 3,000 points, then the MacBook Pro is three times faster than the Power Mac G5. If a Dell Precision workstation has a score of 6,000 points, then the Dell is twice as fast as the MacBook Pro, and six times as fast as the Power Mac G5.