Comments (3)
If you look at the make flow, you will see that it calls a PERL script to compute the scores from the log files.
Please refer to these lines of code:
'CoreMark-PRO' => {
'factor' => 1000,
'geomean' => {
'cjpeg-rose7-preset' => (1 / 40.3438),
'linear_alg-mid-100x100-sp' => (1 / 38.5624),
'loops-all-mid-10k-sp' => (1 / 0.87959),
'nnet_test' => (1 / 1.45853 ),
'parser-125k' => (1 / 4.81116),
'radix2-big-64k' => (1 / 99.6587),
'sha-test' => (1 / 48.5201),
'zip-test' => (1 / 21.3618),
'core' => (10000 / 2855)
}
},
These reference scores were selected from an internal platform when the benchmark was written.
All scores, single and multi are computed by this script. The scaling is simply the ratio of the two scores.
Does this answer your question?
from coremark-pro.
I have attached log reports for cjpeg-rose7-preset.exe can you show me how we can calculate it,i understood for geomean and factor you are going fo follow pearl script.i want to understand the complete calculation for one binary because due to some issue i am simply running binaries on my target but not pearl script.
Thanks
from coremark-pro.
The result is the geomean of each score times the weights I provided above.
from coremark-pro.
Related Issues (20)
- steps to build with msvc HOT 1
- Compiling without Make HOT 3
- Is it normal for parser-125k Multicore score lower than Singlecore score? HOT 4
- How to run workloads in bare-metal with multicore? HOT 2
- Cannot find -lrt and -lpthread during make build with "gcc-arm-none-eabi-10.3-2021.10" HOT 4
- Can I ask where does the number '1000' come from? Thanks! HOT 3
- regarding the benchmark run option HOT 5
- GLIBC_2.27' not found required by arm-linux-gnueabihf HOT 1
- ARM cortex-M4 compiler option for coremark-pro benchmark HOT 1
- Running `loops-all-mid-10k-sp.exe` on PPC64 (e6500) causes illegal instruction
- Incorrect Coremark-Pro score calculation HOT 1
- Shell script for running HOT 1
- which Tool I have to use to run coremark-pro on NXP imx rt1170
- make TARGET=linux certify-all not computing results
- for baremetal run, cjpeg macro variable SELECT_PRESET_ID is wrong HOT 2
- how to run one of the nine tests individually? HOT 1
- Question about the iteration count in the kernel of "cjpeg-rose7-preset" HOT 3
- Unable to build the benchmark for ARM AARCH64 HOT 4
- Race condition in Makefile ? HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from coremark-pro.