p60975123
/
mindspore
forked from mindspore-Ecosystem/mindspore
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

!15205 fix sponge readme 

From: @jiahongqian
Reviewed-by: @ljl0711,@wang_zi_dong
Signed-off-by: @wang_zi_dong
This commit is contained in:
mindspore-ci-bot 2021-04-17 15:35:28 +08:00 committed by Gitee
parent 4bf4aa0b7f 3f0c1a8f94
commit 2fefa6679a
1 changed files with 19 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
model_zoo/research/hpc/sponge/README.md
View File

@ -14,33 +14,33 @@
## Description ## Description
SPONGE in MindSpore is a high-performance and modularized molecular dynamics simulation library developed by `Yiqin Gao` group (`Peking University` and `Shenzhen Bay Laboratory`) and `MindSpore` team at `Huawei` Company. It can efficiently simulate traditional molecular dynamics tasks based on the “graph-kernel-fusion” and “automatic parallelization” features of MindSpore. In the meanwhile, it utilizes the automatic differentiation feature of MindSpore, and introduces machine learning methods, such as neural network, into traditional molecular simulation, achieving methodological inventions. SPONGE in MindSpore is a molecular dynamics simulation library, featuring high performance and modularization. It is developed by the `Yiqin Gao` group (`Peking University` and `Shenzhen Bay Laboratory`) and `Huawei MindSpore` team. It can efficiently simulate traditional molecular dynamics tasks based on the "graph-kernel-fusion" and "automatic parallelization" features of MindSpore. In addition, it utilizes the automatic differentiation feature of MindSpore, and introduces machine learning methods, such as neural network, into traditional molecular simulation, achieving methodological inventions.
This example demonstrates how to perform high-performance molecular dynamics simulations with the built-in SPONGE module of MindSpore on `GPU`. The following example demonstrates how to perform high-performance molecular dynamics simulations with the built-in MindSpore SPONGE module on a `GPU`.
## Dataset ## Dataset
There are three inputs for the example, property file `NVT_290_10ns.in`, topology file `WATER_ALA.parm7` and coordinates file `WATER_ALA_350_cool_290.rst7`, respectivelly. There are three inputs in the example, the property file `NVT_290_10ns.in`, the topology file `WATER_ALA.parm7` and the coordinates file `WATER_ALA_350_cool_290.rst7`, respectivelly.
![ALA Aqueous System](https://images.gitee.com/uploads/images/2021/0323/184453_4bd9b1a6_8142020.png "图片1.png") ![ALA Aqueous System](https://images.gitee.com/uploads/images/2021/0323/184453_4bd9b1a6_8142020.png "图片1.png")
Topology file and coordinates file can be generated by `tleap` in `AmberTools` ([link](<http://ambermd.org/GetAmber.php>)). For more details, please refer to: The topology file and coordinates file can be generated by `tleap` in `AmberTools` ([link](<http://ambermd.org/GetAmber.php>)). For more details, please refer to:
- [SPONGE Tutorial](https://gitee.com/mindspore/docs/blob/master/tutorials/training/source_zh_cn/advanced_use/hpc_sponge.md) - [SPONGE Tutorial](https://gitee.com/mindspore/docs/blob/master/tutorials/training/source_zh_cn/advanced_use/hpc_sponge.md)
## Environment Requirements ## Environment Requirements
- Hardware: `GPU` - Hardware: `GPU`
- Prepare hardware environment with `GPU` processor. - Prepare a hardware environment with `GPU`.
- Framework - Framework
- [MindSpore](https://www.mindspore.cn/install/en) - [MindSpore](https://www.mindspore.cn/install/en)
- For more information, please check the resources below: - For more information, visit the resources below:
- [MindSpore Tutorials](https://www.mindspore.cn/tutorial/training/en/master/index.html) - [MindSpore Tutorials](https://www.mindspore.cn/tutorial/training/en/master/index.html)
- [MindSpore Python API](https://www.mindspore.cn/doc/api_python/en/master/index.html) - [MindSpore Python API](https://www.mindspore.cn/doc/api_python/en/master/index.html)
## Quick Start ## Quick Start
After installing MindSpore via the official website, you can start running as follows: After installing MindSpore, run the following command:
```shell ```shell
python main.py --i /path/NVT_290_10ns.in \ python main.py --i /path/NVT_290_10ns.in \
@ -81,11 +81,11 @@ python main.py --i /path/NVT_290_10ns.in \
--o /path/ala_NVT_290_10ns.out --o /path/ala_NVT_290_10ns.out
``` ```
Training result will be stored in the specified file, which ends with ".out". Training result will be stored in the specified .out file.
## Result ## Result
After training，the results in `ala_NVT_290_10ns.out` are： After training, the following results are stored in `ala_NVT_290_10ns.out`:
```text ```text
_steps_ _TEMP_ _TOT_POT_ENE_ _BOND_ENE_ _ANGLE_ENE_ _DIHEDRAL_ENE_ _14LJ_ENE_ _14CF_ENE_ _LJ_ENE_ _CF_PME_ENE_ _steps_ _TEMP_ _TOT_POT_ENE_ _BOND_ENE_ _ANGLE_ENE_ _DIHEDRAL_ENE_ _14LJ_ENE_ _14CF_ENE_ _LJ_ENE_ _CF_PME_ENE_
@ -93,23 +93,23 @@ _steps_ _TEMP_ _TOT_POT_ENE_ _BOND_ENE_ _ANGLE_ENE_ _DIHEDRAL_ENE_ _14LJ_ENE_ _1
... ...
``` ```
There are sorts of energy in the output, steps (_steps_), temperature (_TEMP_), total energy (_TOT_POT_E_), bond energy (_BOND_ENE_), angle energy (_ANGLE_ENE_), dihedral energy (_DIHEDRAL_ENE_), non bond enrgy, includes Coulomb force (_14CF_ENE_) and Leonard-Jones energy (_14LJ_ENE_), Van der Waals energy (_LJ_ENE_) and Coulomb force in PME (_CF_PME_ENE_). There are sorts of energy in the output, steps (_steps_), temperature (_TEMP_), total energy (_TOT_POT_E_), bond energy (_BOND_ENE_), angle energy (_ANGLE_ENE_), dihedral energy (_DIHEDRAL_ENE_), non-bond energy, includes Coulomb force (_14CF_ENE_) and Lennard-Jones energy (_14LJ_ENE_), Van der Waals energy (_LJ_ENE_) and Coulomb force in PME (_CF_PME_ENE_).
## Model Description ## Model Description
### Evaluation Performance ### Evaluation Performance
| Parameters | GPU | | Parameter | GPU |
| -------------------------- |---------------------------------- | | -------------------------- |---------------------------------- |
| Resource | GPU(Tesla V100 SXM2), Memory 16G | Resource | GPU (Tesla V100 SXM2); memory 16 GB
| uploaded Date | | Upload date |
| MindSpore Version | 1.2 | MindSpore version | 1.2
| Training Parameters | step=1 | Training parameter | step=1
| Outputs | numpy file | Output | numpy file
| Speed | 16.7 ms/step | Speed | 16.7 ms/step
| Total time | 10.7 s | Total time | 10.7 s
| Scripts | [Link](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/research/hpc/sponge) | Script | [Link](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/research/hpc/sponge)
## ModelZoo HomePage ## ModelZoo Homepage
Please check the official [homepage](https://gitee.com/mindspore/mindspore/tree/master/model_zoo). Visit [ModelZoo](https://gitee.com/mindspore/mindspore/tree/master/model_zoo).