Comments (2)
Usually this is due to multiple calls to the marker API
in your measured code.
Without an code example it is difficult for me to help.
It is important that you install likwid-pin to work correctly with make install.
You execute the program serial above. If it is a threaded program you have to
measure the same number of threads you intrumented.
Find attached two examples for usage. One is serial (dofp.c) and one OpenMP
parallel (openMP.c). If it works please let me know what part in the
documentation maybe was not clear enough.
Original comment by [email protected]
on 21 Jul 2010 at 10:17
Attachments:
from likwid.
As I got no further answer I regard this issue as solved.
You might reopen it if there is still a problem.
Original comment by [email protected]
on 3 Aug 2010 at 8:46
- Changed state: Fixed
from likwid.
Related Issues (20)
- Implement multiplexing support for using more events than physical counters in groups HOT 4
- Allow scatter policy in thread list expressions HOT 1
- Extend thread list syntax to allows for strides HOT 1
- Replace fixed time duration in timeline mode with measured time HOT 3
- likwid-pin should work on unknown processor with physical core ids HOT 1
- Only measure necessary counters in Marker API HOT 3
- Honor proposed Intel Hardware performance counter usage policy HOT 8
- Add support for Atom HOT 3
- Add Overflow treatment HOT 2
- Restrict Initialization to required counters only HOT 3
- Provide an extended Version of likwid-perfscope script (timeline mode) HOT 2
- Make PCI Uncore interface on SandyBridge more robust HOT 1
- Output for CPI and runtime missing for custom event set HOT 2
- Can't link MIC benchmark objects to likwid-bench HOT 1
- Bad link in the wiki introduction HOT 1
- Add support for round robin thread placement in likwid-pin HOT 3
- Counting AVX HOT 1
- L3 bandwidth is wrong on SandyBridge for certain data access patterns HOT 1
- Register check in accessDaemon does not support all architectures HOT 2
- Events reported with "-H -g" switches not correct for L3CACHE group on AMD Interlagos HOT 1
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 likwid.