pyhpc-benchmarks:一套基准测试,可测试Python最流行的高性能库的顺序CPU和GPU性能

上传者: 42097668 | 上传时间: 2022-05-09 16:03:04 | 文件大小: 236KB | 文件类型: ZIP
适用于Python的HPC基准 这是一组基准测试,用于测试使用Python前端的各种计算后端的顺序CPU和GPU性能。 具体来说,我们想测试哪种高性能后端最适合地球物理(基于有限差分)的模拟。 内容 常问问题 为什么? 科学的Python生态系统正在蓬勃发展,但是Python中的高性能计算还不是真正的事情。 我们尝试来更改此,但是我们应该使用哪个后端进行计算? Python前端到高性能后端的开发需要大量的时间和资源,但是这些通常是为深度学习量身定制的。 我们想了解一下,通过(滥用)这些库进行地球物理建模,我们是否可以从这些进展中获利。 为什么基准看起来如此怪异? 这些或多或少是逐字记录副本(即物理模型的实际部分)。 大多数地球系统和气候模型组件都基于有限差分方案来计算导数。 这可以通过数组的索引移位(例如0.5 * (arr[1:] + arr[:-1]) , arr在每个点的一

文件下载

资源详情

[{"title":"( 46 个子文件 236KB ) pyhpc-benchmarks:一套基准测试,可测试Python最流行的高性能库的顺序CPU和GPU性能","children":[{"title":"pyhpc-benchmarks-master","children":[{"title":"environment-cpu.yml <span style='color:#111;'> 228B </span>","children":null,"spread":false},{"title":"utilities.py <span style='color:#111;'> 4.03KB </span>","children":null,"spread":false},{"title":"backends.py <span style='color:#111;'> 4.44KB </span>","children":null,"spread":false},{"title":"environment-gpu.yml <span style='color:#111;'> 388B </span>","children":null,"spread":false},{"title":"LICENSE <span style='color:#111;'> 1.18KB </span>","children":null,"spread":false},{"title":"benchmarks","children":[{"title":"isoneutral_mixing","children":[{"title":"isoneutral_numba.py <span style='color:#111;'> 7.31KB </span>","children":null,"spread":false},{"title":"isoneutral_numpy.py <span style='color:#111;'> 7.01KB </span>","children":null,"spread":false},{"title":"isoneutral_cupy.py <span style='color:#111;'> 7.22KB </span>","children":null,"spread":false},{"title":"isoneutral_bohrium.py <span style='color:#111;'> 7.23KB </span>","children":null,"spread":false},{"title":"isoneutral_theano.py <span style='color:#111;'> 8.64KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 1.67KB </span>","children":null,"spread":false},{"title":"isoneutral_pytorch.py <span style='color:#111;'> 14.05KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 590B </span>","children":null,"spread":false},{"title":"isoneutral_jax.py <span style='color:#111;'> 8.58KB </span>","children":null,"spread":false}],"spread":true},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"turbulent_kinetic_energy","children":[{"title":"tke_numba.py <span style='color:#111;'> 7.78KB </span>","children":null,"spread":false},{"title":"tke_numpy.py <span style='color:#111;'> 8.31KB </span>","children":null,"spread":false},{"title":"tke_jax.py <span style='color:#111;'> 10.50KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 1.65KB </span>","children":null,"spread":false},{"title":"tke_bohrium.py <span style='color:#111;'> 8.23KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 615B </span>","children":null,"spread":false}],"spread":true},{"title":"equation_of_state","children":[{"title":"eos_numba.py <span style='color:#111;'> 6.82KB </span>","children":null,"spread":false},{"title":"eos_theano.py <span style='color:#111;'> 6.78KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 1.01KB </span>","children":null,"spread":false},{"title":"eos_bohrium.py <span style='color:#111;'> 6.70KB </span>","children":null,"spread":false},{"title":"eos_cupy.py <span style='color:#111;'> 6.68KB </span>","children":null,"spread":false},{"title":"eos_jax.py <span style='color:#111;'> 6.67KB </span>","children":null,"spread":false},{"title":"eos_tensorflow.py <span style='color:#111;'> 6.67KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 352B </span>","children":null,"spread":false},{"title":"eos_pytorch.py <span style='color:#111;'> 6.98KB </span>","children":null,"spread":false},{"title":"eos_numpy.py <span style='color:#111;'> 6.46KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"run.py <span style='color:#111;'> 5.16KB </span>","children":null,"spread":false},{"title":"results","children":[{"title":"pyhpc-benchmarks-colab.ipynb <span style='color:#111;'> 6.47KB </span>","children":null,"spread":false},{"title":"magni.md <span style='color:#111;'> 39.87KB </span>","children":null,"spread":false},{"title":"magni-run-all.sh <span style='color:#111;'> 1.34KB </span>","children":null,"spread":false},{"title":"colab.md <span style='color:#111;'> 32.97KB </span>","children":null,"spread":false},{"title":"magni-plots","children":[{"title":"bench-equation_of_state-CPU.png <span style='color:#111;'> 29.29KB </span>","children":null,"spread":false},{"title":"bench-turbulent_kinetic_energy-CPU.png <span style='color:#111;'> 21.92KB </span>","children":null,"spread":false},{"title":"bench-equation_of_state-GPU.png <span style='color:#111;'> 33.08KB </span>","children":null,"spread":false},{"title":"bench-isoneutral_mixing-CPU.png <span style='color:#111;'> 27.32KB </span>","children":null,"spread":false},{"title":"bench-turbulent_kinetic_energy-GPU.png <span style='color:#111;'> 19.98KB </span>","children":null,"spread":false},{"title":"bench-isoneutral_mixing-GPU.png <span style='color:#111;'> 30.22KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":".gitignore <span style='color:#111;'> 1.23KB </span>","children":null,"spread":false},{"title":"plot.py <span style='color:#111;'> 4.61KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 9.45KB </span>","children":null,"spread":false},{"title":".flake8 <span style='color:#111;'> 158B </span>","children":null,"spread":false}],"spread":false}],"spread":true}]

评论信息

免责申明

【只为小站】的资源来自网友分享,仅供学习研究,请务必在下载后24小时内给予删除,不得用于其他任何用途,否则后果自负。基于互联网的特殊性,【只为小站】 无法对用户传输的作品、信息、内容的权属或合法性、合规性、真实性、科学性、完整权、有效性等进行实质审查;无论 【只为小站】 经营者是否已进行审查,用户均应自行承担因其传输的作品、信息、内容而可能或已经产生的侵权或权属纠纷等法律责任。
本站所有资源不代表本站的观点或立场,基于网友分享,根据中国法律《信息网络传播权保护条例》第二十二条之规定,若资源存在侵权或相关问题请联系本站客服人员,zhiweidada#qq.com,请把#换成@,本站将给予最大的支持与配合,做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明