{"id":21044996,"url":"https://github.com/quansight/scipy_gpu","last_synced_at":"2026-04-14T17:32:31.705Z","repository":{"id":98607976,"uuid":"141304759","full_name":"Quansight/scipy_gpu","owner":"Quansight","description":null,"archived":false,"fork":false,"pushed_at":"2018-08-31T12:06:50.000Z","size":141,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2026-01-19T22:57:22.687Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Quansight.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2018-07-17T14:55:38.000Z","updated_at":"2018-08-31T12:06:51.000Z","dependencies_parsed_at":null,"dependency_job_id":"d146e48a-a844-4272-8d25-8e7e184b7693","html_url":"https://github.com/Quansight/scipy_gpu","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Quansight/scipy_gpu","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Quansight%2Fscipy_gpu","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Quansight%2Fscipy_gpu/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Quansight%2Fscipy_gpu/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Quansight%2Fscipy_gpu/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Quansight","download_url":"https://codeload.github.com/Quansight/scipy_gpu/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Quansight%2Fscipy_gpu/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31808505,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-14T11:13:53.975Z","status":"ssl_error","status_checked_at":"2026-04-14T11:13:53.299Z","response_time":153,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-11-19T14:19:30.692Z","updated_at":"2026-04-14T17:32:31.684Z","avatar_url":"https://github.com/Quansight.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# SciPy-GPU\n\nSciPy-GPU aims at being a drop-in replacement for some SciPy functions that run on the GPU.\n\n## Install\n\nYou will need to have `scipy` and `gfortran` installed. The recommended way is to use `conda`:\n\n```bash\nconda install scipy\nconda install gfortran_linux-64\n```\n\nSet some environment variables:\n\n- `CONDADIR`: path to your Anaconda install, e.g. `/home/david/anaconda3`\n- `GFORTRANDIR`: path to your `gfortran` install, e.g. `$CONDADIR/pkgs/gcc-4.8.5-7`\n- `CUDADIR`: path to your CUDA install, e.g. `/usr/local/cuda-9.2`\n\nAnd change the following paths according to the package versions you have installed:\n\n```bash\n$ export LD_LIBRARY_PATH=$CUDADIR/lib64:$CONDADIR/pkgs/libgcc-ng-7.2.0-hdf63c60_3/lib:$GFORTRANDIR/lib:$CONDADIR/pkgs/cloog-0.18.0-0/lib:$CONDADIR/pkgs/isl-0.12.2-0/lib:$LD_LIBRARY_PATH\n```\n\nYou should create a virtual environment in order to prevent linking with the LAPACK library which may ship with Anaconda's distribution.\n\nThen install with:\n\n```bash\n$ make -C f2py\n```\n\nYou should now have some LAPACK functions executing through the MAGMA library.\n\n```python\nimport numpy as np\nimport _flapack as mm               # MAGMA\nimport scipy.linalg.lapack as lp    # LAPACK\nfrom time import time\n\nm = 8192\nn = 100\na = np.random.uniform(size=m*m).reshape((m, m)).astype(np.float32, order='F')\nb = np.random.uniform(size=m*n).reshape((m, n)).astype(np.float32, order='F')\n\n# sgesv solves a system of linear equations a*x=b\n# see https://docs.scipy.org/doc/scipy/reference/generated/scipy.linalg.lapack.sgesv.html\n\nt0 = time()\nmm.sgesv(a, b)\nt1 = time()\nprint('GPU time:', t1 - t0)\n\nt0 = time()\nlp.sgesv(a, b)\nt1 = time()\nprint('CPU time:', t1 - t0)\n\n# GPU time: 1.9766342639923096\n# CPU time: 5.190711736679077\n```\n\n## Benchmark\n\nThe following benchmark was generated by running `test/test.py` on the following hardware:\n\n- CPU: Intel Broadwell, 1 core at 3 GHz\n- GPU: Quadro P2000, 1024 CUDA cores at 1.48 GHz\n\n![alt text](test/benchmark.png)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fquansight%2Fscipy_gpu","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fquansight%2Fscipy_gpu","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fquansight%2Fscipy_gpu/lists"}