Comments (1)
Hi.
We're sorry for our late reply.
The NPB default mode collects parameters from the file npbparams.hpp, which is generated when you compile a benchmark (it is located in the directory of the benchmark, for instance, in the BT directory). This is the correct way of using the NPB right now.
The other mode is when you read an input file, for example, as you mentioned, inputbt.data. In this case, instead of reading data from the file npbparams.hpp, the benchmark will read the inputs of inputbt.data. However, this breaks the code execution unless the values from the file inputbt.data are equal to the ones in the file npbparams.hpp.
We ported the NPB from Fortran to C++ trying to make it as similar as possible. In the original version, the parameters from inputbt.data are not treated too, which breaks the code. Thus, we will remove this alternative mode from the code soon. We did not realize that this mode was not treated. So, thank you for commenting about this.
In addition, I will answer your question about where we should place these files.data, it should go into the directory named CUDA (it is the root directory of an NPB version). That is the directory where you can put the file timer.flag too.
from npb-gpu.
Related Issues (9)
- IS updates HOT 9
- Lack of atomic operations for old GPUs
- Lack of information about the GPU compute capability in the read-me HOT 1
- collect2: error: ld returned 1 exit status HOT 9
- FT running problem on classD HOT 1
- All workloads failed in verification with CUDA 12.3 HOT 1
- Verification Problem HOT 7
- choosing GPU_DEVICE from gpu.config doesn't work HOT 2
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 npb-gpu.