# cumm
CUda Matrix Multiply library.
[![Build Status](https://github.com/FindDefinition/cumm/workflows/build/badge.svg)](https://github.com/FindDefinition/cumm/actions?query=workflow%3Abuild)
```cumm``` is developed during learning of [CUTLASS](https://github.com/NVIDIA/cutlass), which use too much c++ template and make code unmaintainable. So I develop [pccm](https://github.com/FindDefinition/PCCM), use python as meta programming language, to replace c++ template meta programming.
Now ```pccm``` become a foundational framework of ```cumm``` and my other c++ project such as [spconv](https://github.com/traveller59/spconv).
```cumm``` also contains a python asyncio-based gemm simulator that **share same meta program** with CUDA code, enable gemm visualization and easy debug experience.
## BREAKING CHANGES
* 0.3.1: tv::DType enum value changed, this will affect all binary code of tv::Tensor user. you must recompile all code if upgrade to cumm >= 0.3.1.
## News
* Ampere feature support (by [EvernightAurora](https://github.com/EvernightAurora))
## Install
### Prebuilt
We offer python 3.7-3.11 and cuda 10.2/11.3/11.4/11.7/12.0 prebuilt binaries for linux (manylinux).
We offer python 3.7-3.11 and cuda 10.2/11.3/11.4/11.7/12.0 prebuilt binaries for windows 10/11.
```pip install cumm``` for CPU-only
```pip install cumm-cu102``` for CUDA 10.2
```pip install cumm-cu113``` for CUDA 11.3
```pip install cumm-cu114``` for CUDA 11.4
```pip install cumm-cu117``` for CUDA 11.7
```pip install cumm-cu120``` for CUDA 12.0
### Build from source for development (JIT, recommend for develop)
**WARNING** Use code in [tags](https://github.com/FindDefinition/cumm/releases)!!! code in main branch may contain bugs.
The c++ code will be built automatically when you change c++ code in project.
#### Linux
0. uninstall cumm installed by pip. you must ensure no "cumm" exists in ```pip list | grep cumm```
1. install build-essential, install CUDA
2. ```git clone https://github.com/FindDefinition/cumm```, ```cd ./cumm```, ```git checkout tags/<tag_name>```, ```pip install -e .```
3. in python, ```import cumm``` and wait for build finish.
#### Windows
0. uninstall spconv and cumm installed by pip. you must ensure no "cumm" exists in ```pip list | grep cumm```
1. install visual studio 2019 or newer. make sure C++ development component is installed. install CUDA
2. set [powershell script execution policy](https://docs.microsoft.com/en-us/powershell/module/microsoft.powershell.core/about/about_execution_policies?view=powershell-7.1)
3. start a new powershell, run ```tools/msvc_setup.ps1```
4. ```git clone https://github.com/FindDefinition/cumm```, ```cd ./cumm```, ```git checkout tags/<tag_name>```, ```pip install -e .```
5. in python, ```import cumm``` and wait for build finish.
### Build wheel from source
**WARNING** Use code in [tags](https://github.com/FindDefinition/cumm/releases)!!! code in main branch may contain bugs.
**WARNING**: If ```CUMM_CUDA_VERSION``` is set with a CUDA version, following steps will create a wheel named "cumm-cuxxx", not "cumm", this means you must use ```cumm-cuxxx``` in dependency of your project which depend on cumm, not ```cumm```. If ```CUMM_CUDA_VERSION``` isn't set, ```cumm``` will always built with CUDA, so the CUDA must exists in your system. The wheel name will be ```cumm``` even if it is built with cuda.
#### Linux
It's recommend to build Linux packages in [official build docker](https://github.com/FindDefinition/cumm/blob/main/.github/workflows/build.yaml). Build with CUDA support don't need a real GPU.
##### Build in Official Docker
1. select a cuda version. available: CUDA 11.1, 11.3, 11.4, 11.5, 12.0
2. (Example for CUDA 11.4) ```git clone https://github.com/FindDefinition/cumm```, ```cd ./cumm```, ```docker run --rm -e PLAT=manylinux2014_x86_64 -e CUMM_CUDA_VERSION=114 -v `pwd`:/io scrin/manylinux2014-cuda:cu114-devel-1.0.0 bash -c "source /etc/bashrc && /io/tools/build-wheels.sh"```
##### Build in your environment
1. install build-essential, install CUDA
2. set env for installed cuda version. for example, ```export CUMM_CUDA_VERSION="11.4"```. If you want to build CPU-only, run ```export CUMM_CUDA_VERSION=""```. If ```CUMM_CUDA_VERSION``` isn't set, you need to ensure cuda libraries are inside OS search path, and the built wheel name will be ```cumm```, otherwise ```cumm-cuxxx```
3. run ```export CUMM_DISABLE_JIT="1"```
4. run ```python setup.py bdist_wheel```+```pip install dists/xxx.whl```
#### Windows 10/11
1. install visual studio 2019 or newer. make sure C++ development package is installed. install CUDA
2. set [powershell script execution policy](https://docs.microsoft.com/en-us/powershell/module/microsoft.powershell.core/about/about_execution_policies?view=powershell-7.1)
3. start a new powershell, run ```tools/msvc_setup.ps1```
4. set env for installed cuda version. for example, ```$Env:CUMM_CUDA_VERSION = "11.4"```. If you want to build CPU-only, run ```$Env:CUMM_CUDA_VERSION = ""```. . If ```CUMM_CUDA_VERSION``` isn't set, you need to ensure cuda libraries are inside OS search path, and the built wheel name will be ```cumm```, otherwise ```cumm-cuxxx```
4. run ```$Env:CUMM_DISABLE_JIT = "1"```
5. run ```python setup.py bdist_wheel```+```pip install dists/xxx.whl```
## Contributers
* [EvernightAurora](https://github.com/EvernightAurora): add ampere feature.
## Note
The work is done when the author is an employee at [Tusimple](https://www.tusimple.com/).
## LICENSE
Apache 2.0
Raw data
{
"_id": null,
"home_page": "https://github.com/FindDefinition/cumm",
"name": "cumm-cu113",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.6",
"maintainer_email": "",
"keywords": "",
"author": "Yan Yan",
"author_email": "yanyan.sub@outlook.com",
"download_url": "",
"platform": null,
"description": "\n# cumm\nCUda Matrix Multiply library.\n\n[![Build Status](https://github.com/FindDefinition/cumm/workflows/build/badge.svg)](https://github.com/FindDefinition/cumm/actions?query=workflow%3Abuild)\n\n```cumm``` is developed during learning of [CUTLASS](https://github.com/NVIDIA/cutlass), which use too much c++ template and make code unmaintainable. So I develop [pccm](https://github.com/FindDefinition/PCCM), use python as meta programming language, to replace c++ template meta programming. \nNow ```pccm``` become a foundational framework of ```cumm``` and my other c++ project such as [spconv](https://github.com/traveller59/spconv). \n```cumm``` also contains a python asyncio-based gemm simulator that **share same meta program** with CUDA code, enable gemm visualization and easy debug experience.\n\n## BREAKING CHANGES\n\n* 0.3.1: tv::DType enum value changed, this will affect all binary code of tv::Tensor user. you must recompile all code if upgrade to cumm >= 0.3.1.\n\n## News\n\n* Ampere feature support (by [EvernightAurora](https://github.com/EvernightAurora))\n\n## Install\n\n### Prebuilt\n\nWe offer python 3.7-3.11 and cuda 10.2/11.3/11.4/11.7/12.0 prebuilt binaries for linux (manylinux).\n\nWe offer python 3.7-3.11 and cuda 10.2/11.3/11.4/11.7/12.0 prebuilt binaries for windows 10/11.\n\n```pip install cumm``` for CPU-only\n\n```pip install cumm-cu102``` for CUDA 10.2\n\n```pip install cumm-cu113``` for CUDA 11.3\n\n```pip install cumm-cu114``` for CUDA 11.4\n\n```pip install cumm-cu117``` for CUDA 11.7\n\n```pip install cumm-cu120``` for CUDA 12.0\n\n### Build from source for development (JIT, recommend for develop)\n\n**WARNING** Use code in [tags](https://github.com/FindDefinition/cumm/releases)!!! code in main branch may contain bugs.\n\nThe c++ code will be built automatically when you change c++ code in project.\n\n#### Linux\n\n0. uninstall cumm installed by pip. you must ensure no \"cumm\" exists in ```pip list | grep cumm```\n1. install build-essential, install CUDA\n2. ```git clone https://github.com/FindDefinition/cumm```, ```cd ./cumm```, ```git checkout tags/<tag_name>```, ```pip install -e .```\n3. in python, ```import cumm``` and wait for build finish.\n\n#### Windows\n0. uninstall spconv and cumm installed by pip. you must ensure no \"cumm\" exists in ```pip list | grep cumm```\n1. install visual studio 2019 or newer. make sure C++ development component is installed. install CUDA\n2. set [powershell script execution policy](https://docs.microsoft.com/en-us/powershell/module/microsoft.powershell.core/about/about_execution_policies?view=powershell-7.1)\n3. start a new powershell, run ```tools/msvc_setup.ps1```\n4. ```git clone https://github.com/FindDefinition/cumm```, ```cd ./cumm```, ```git checkout tags/<tag_name>```, ```pip install -e .```\n5. in python, ```import cumm``` and wait for build finish.\n\n### Build wheel from source \n\n**WARNING** Use code in [tags](https://github.com/FindDefinition/cumm/releases)!!! code in main branch may contain bugs.\n\n**WARNING**: If ```CUMM_CUDA_VERSION``` is set with a CUDA version, following steps will create a wheel named \"cumm-cuxxx\", not \"cumm\", this means you must use ```cumm-cuxxx``` in dependency of your project which depend on cumm, not ```cumm```. If ```CUMM_CUDA_VERSION``` isn't set, ```cumm``` will always built with CUDA, so the CUDA must exists in your system. The wheel name will be ```cumm``` even if it is built with cuda.\n\n#### Linux\n\nIt's recommend to build Linux packages in [official build docker](https://github.com/FindDefinition/cumm/blob/main/.github/workflows/build.yaml). Build with CUDA support don't need a real GPU.\n\n##### Build in Official Docker\n\n1. select a cuda version. available: CUDA 11.1, 11.3, 11.4, 11.5, 12.0\n2. (Example for CUDA 11.4) ```git clone https://github.com/FindDefinition/cumm```, ```cd ./cumm```, ```docker run --rm -e PLAT=manylinux2014_x86_64 -e CUMM_CUDA_VERSION=114 -v `pwd`:/io scrin/manylinux2014-cuda:cu114-devel-1.0.0 bash -c \"source /etc/bashrc && /io/tools/build-wheels.sh\"```\n\n##### Build in your environment\n\n1. install build-essential, install CUDA\n2. set env for installed cuda version. for example, ```export CUMM_CUDA_VERSION=\"11.4\"```. If you want to build CPU-only, run ```export CUMM_CUDA_VERSION=\"\"```. If ```CUMM_CUDA_VERSION``` isn't set, you need to ensure cuda libraries are inside OS search path, and the built wheel name will be ```cumm```, otherwise ```cumm-cuxxx```\n3. run ```export CUMM_DISABLE_JIT=\"1\"```\n4. run ```python setup.py bdist_wheel```+```pip install dists/xxx.whl```\n\n#### Windows 10/11\n\n1. install visual studio 2019 or newer. make sure C++ development package is installed. install CUDA\n2. set [powershell script execution policy](https://docs.microsoft.com/en-us/powershell/module/microsoft.powershell.core/about/about_execution_policies?view=powershell-7.1)\n3. start a new powershell, run ```tools/msvc_setup.ps1```\n4. set env for installed cuda version. for example, ```$Env:CUMM_CUDA_VERSION = \"11.4\"```. If you want to build CPU-only, run ```$Env:CUMM_CUDA_VERSION = \"\"```. . If ```CUMM_CUDA_VERSION``` isn't set, you need to ensure cuda libraries are inside OS search path, and the built wheel name will be ```cumm```, otherwise ```cumm-cuxxx```\n4. run ```$Env:CUMM_DISABLE_JIT = \"1\"```\n5. run ```python setup.py bdist_wheel```+```pip install dists/xxx.whl```\n\n## Contributers\n\n* [EvernightAurora](https://github.com/EvernightAurora): add ampere feature.\n\n## Note\nThe work is done when the author is an employee at [Tusimple](https://www.tusimple.com/).\n\n## LICENSE\n\nApache 2.0\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "CUda Matrix Multiply library",
"version": "0.5.1",
"project_urls": {
"Homepage": "https://github.com/FindDefinition/cumm"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "08c650557a08c11983a32c632c20ad5a7762349a8a99256e2f6bb0223e004386",
"md5": "5899ce961ead6f658fd7094c886c176a",
"sha256": "8ffd29666421ef01b669e4261e1ec046f8462ba43548af4186818cab284a3cf1"
},
"downloads": -1,
"filename": "cumm_cu113-0.5.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl",
"has_sig": false,
"md5_digest": "5899ce961ead6f658fd7094c886c176a",
"packagetype": "bdist_wheel",
"python_version": "cp310",
"requires_python": ">=3.6",
"size": 22601319,
"upload_time": "2023-12-26T04:25:54",
"upload_time_iso_8601": "2023-12-26T04:25:54.404615Z",
"url": "https://files.pythonhosted.org/packages/08/c6/50557a08c11983a32c632c20ad5a7762349a8a99256e2f6bb0223e004386/cumm_cu113-0.5.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "e8700df677f45f0af309678cf3a918f8d0cb37790601fbc63e0b2dd6bcf9ae6c",
"md5": "f45298d72a8df562bbfee1761a3c44ad",
"sha256": "7caee91e25081341c9766530519d4e43f133bca1763989d0a561995df82eff36"
},
"downloads": -1,
"filename": "cumm_cu113-0.5.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl",
"has_sig": false,
"md5_digest": "f45298d72a8df562bbfee1761a3c44ad",
"packagetype": "bdist_wheel",
"python_version": "cp311",
"requires_python": ">=3.6",
"size": 22604049,
"upload_time": "2023-12-26T04:25:59",
"upload_time_iso_8601": "2023-12-26T04:25:59.788046Z",
"url": "https://files.pythonhosted.org/packages/e8/70/0df677f45f0af309678cf3a918f8d0cb37790601fbc63e0b2dd6bcf9ae6c/cumm_cu113-0.5.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "fac4aa48bf0a9f5299376165b1894a313d4a483b5ef6ff96f8382e384dd671c8",
"md5": "1a6ea8faae1bd14b34da85aa119c927d",
"sha256": "15bc6f9f97c2923c99f36ba154e01bd23358c12074046dd23a220a238ba500cf"
},
"downloads": -1,
"filename": "cumm_cu113-0.5.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl",
"has_sig": false,
"md5_digest": "1a6ea8faae1bd14b34da85aa119c927d",
"packagetype": "bdist_wheel",
"python_version": "cp37",
"requires_python": ">=3.6",
"size": 22592644,
"upload_time": "2023-12-26T04:26:06",
"upload_time_iso_8601": "2023-12-26T04:26:06.258077Z",
"url": "https://files.pythonhosted.org/packages/fa/c4/aa48bf0a9f5299376165b1894a313d4a483b5ef6ff96f8382e384dd671c8/cumm_cu113-0.5.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "d4787d80f25d79262dffd7ac5fc3185c1c2d9b721319b518e2f1fd0d75f89f4d",
"md5": "ab16a5e666ab3179be2e7fe1875f7026",
"sha256": "71240db42efca7ed4cd74fea8f73be96b4ed76dd1600bea3dad2c536b570fe30"
},
"downloads": -1,
"filename": "cumm_cu113-0.5.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl",
"has_sig": false,
"md5_digest": "ab16a5e666ab3179be2e7fe1875f7026",
"packagetype": "bdist_wheel",
"python_version": "cp38",
"requires_python": ">=3.6",
"size": 22600077,
"upload_time": "2023-12-26T04:26:12",
"upload_time_iso_8601": "2023-12-26T04:26:12.318844Z",
"url": "https://files.pythonhosted.org/packages/d4/78/7d80f25d79262dffd7ac5fc3185c1c2d9b721319b518e2f1fd0d75f89f4d/cumm_cu113-0.5.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "1f42bf835580e7693e46c02b9dd63c643de396c772c941cb9d915269faaf449f",
"md5": "7eebcc156e4afd30c6b167f0324d9e9e",
"sha256": "457dc89931c18e45a58ee0039204005df82f39ed25685c7bea90b097244f4bf1"
},
"downloads": -1,
"filename": "cumm_cu113-0.5.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl",
"has_sig": false,
"md5_digest": "7eebcc156e4afd30c6b167f0324d9e9e",
"packagetype": "bdist_wheel",
"python_version": "cp39",
"requires_python": ">=3.6",
"size": 22599670,
"upload_time": "2023-12-26T04:26:20",
"upload_time_iso_8601": "2023-12-26T04:26:20.758766Z",
"url": "https://files.pythonhosted.org/packages/1f/42/bf835580e7693e46c02b9dd63c643de396c772c941cb9d915269faaf449f/cumm_cu113-0.5.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-12-26 04:25:54",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "FindDefinition",
"github_project": "cumm",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "cumm-cu113"
}