CUDA 12.6.2 windows build (#2023)

* cuda 126 windows build and driver update

* refactor code

* unblock the pipeline

* correct syntax

* test overwrite:true

Co-authored-by: Andrey Talman <[email protected]>

---------

Co-authored-by: Andrey Talman <[email protected]>

Author: tinglvv

.github/workflows/build-magma-windows.yml

@@ -17,7 +17,7 @@ jobs:
     runs-on: windows-2019
     strategy:
       matrix:
-        cuda_version: ["124", "121", "118"]
+        cuda_version: ["126", "124", "118"]
         config: ["Release", "Debug"]
     env:
       CUDA_VERSION: ${{ matrix.cuda_version }}
@@ -32,9 +32,10 @@ jobs:
       - name: Build MAGMA and push to S3
         run: windows/internal/build_magma.bat
       - name: Save as artifact
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v4
         with:
           path: magma_*_cuda*_*.7z
+          overwrite: true
   push-windows-magma:
     if: ${{ github.event_name == 'push' && github.ref == 'refs/heads/main' }}
     environment: magma

conda/pytorch-nightly/bld.bat

@@ -25,10 +25,7 @@ if "%desired_cuda%" == "11.8" (
     set TORCH_CUDA_ARCH_LIST=%TORCH_CUDA_ARCH_LIST%;3.7+PTX
     set TORCH_NVCC_FLAGS=-Xfatbin -compress-all --threads 2
 )
-if "%desired_cuda%" == "12.1" (
-    set TORCH_NVCC_FLAGS=-Xfatbin -compress-all --threads 2
-)
-if "%desired_cuda%" == "12.4" (
+if "%desired_cuda:~0,3%" == "12." (
     set TORCH_NVCC_FLAGS=-Xfatbin -compress-all --threads 2
 )
 

windows/cuda126.bat

@@ -0,0 +1,58 @@
+@echo off
+
+set MODULE_NAME=pytorch
+
+IF NOT EXIST "setup.py" IF NOT EXIST "%MODULE_NAME%" (
+    call internal\clone.bat
+    cd ..
+) ELSE (
+    call internal\clean.bat
+)
+IF ERRORLEVEL 1 goto :eof
+
+call internal\check_deps.bat
+IF ERRORLEVEL 1 goto :eof
+
+REM Check for optional components
+
+set USE_CUDA=
+set CMAKE_GENERATOR=Visual Studio 15 2017 Win64
+
+IF "%NVTOOLSEXT_PATH%"=="" (
+    IF EXIST "C:\Program Files\NVIDIA Corporation\NvToolsExt\lib\x64\nvToolsExt64_1.lib"  (
+        set NVTOOLSEXT_PATH=C:\Program Files\NVIDIA Corporation\NvToolsExt
+    ) ELSE (
+        echo NVTX ^(Visual Studio Extension ^for CUDA^) ^not installed, failing
+        exit /b 1
+    )
+)
+
+IF "%CUDA_PATH_V124%"=="" (
+    IF EXIST "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.6\bin\nvcc.exe" (
+        set "CUDA_PATH_V124=C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.6"
+    ) ELSE (
+        echo CUDA 12.6 not found, failing
+        exit /b 1
+    )
+)
+
+IF "%BUILD_VISION%" == "" (
+    set TORCH_CUDA_ARCH_LIST=5.0;6.0;6.1;7.0;7.5;8.0;8.6;9.0
+    set TORCH_NVCC_FLAGS=-Xfatbin -compress-all
+) ELSE (
+    set NVCC_FLAGS=-D__CUDA_NO_HALF_OPERATORS__ --expt-relaxed-constexpr -gencode=arch=compute_50,code=sm_50 -gencode=arch=compute_60,code=sm_60 -gencode=arch=compute_70,code=sm_70 -gencode=arch=compute_75,code=sm_75 -gencode=arch=compute_80,code=compute_80 -gencode=arch=compute_86,code=compute_86 -gencode=arch=compute_90,code=compute_90
+)
+
+set "CUDA_PATH=%CUDA_PATH_V126%"
+set "PATH=%CUDA_PATH_V126%\bin;%PATH%"
+
+:optcheck
+
+call internal\check_opts.bat
+IF ERRORLEVEL 1 goto :eof
+
+call internal\copy.bat
+IF ERRORLEVEL 1 goto :eof
+
+call internal\setup.bat
+IF ERRORLEVEL 1 goto :eof

windows/internal/build_magma.bat

@@ -35,10 +35,7 @@ cd magma
 mkdir build && cd build
 
 set GPU_TARGET=All
-if "%CUVER_NODOT%" == "124" (
-  set CUDA_ARCH_LIST=-gencode arch=compute_50,code=sm_50 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=sm_80 -gencode arch=compute_86,code=sm_86 -gencode arch=compute_90,code=sm_90
-)
-if "%CUVER_NODOT%" == "121" (
+if "%CUVER_NODOT:~0,2%" == "12" (
   set CUDA_ARCH_LIST=-gencode arch=compute_50,code=sm_50 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_80,code=sm_80 -gencode arch=compute_86,code=sm_86 -gencode arch=compute_90,code=sm_90
 )
 if "%CUVER_NODOT%" == "118" (

windows/internal/cuda_install.bat

@@ -26,6 +26,7 @@ if exist "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v%CUDA_VERSION_STR%
 if %CUDA_VER% EQU 118 goto cuda118
 if %CUDA_VER% EQU 121 goto cuda121
 if %CUDA_VER% EQU 124 goto cuda124
+if %CUDA_VER% EQU 126 goto cuda126
 
 echo CUDA %CUDA_VERSION_STR% is not supported
 exit /b 1
@@ -111,6 +112,33 @@ xcopy /Y "%SRC_DIR%\temp_build\zlib\dll_x64\*.dll" "C:\Windows\System32"
 
 goto cuda_common
 
+:cuda126
+
+set CUDA_INSTALL_EXE=cuda_12.6.2_560.94_windows.exe
+if not exist "%SRC_DIR%\temp_build\%CUDA_INSTALL_EXE%" (
+    curl -k -L "https://ossci-windows.s3.amazonaws.com/%CUDA_INSTALL_EXE%" --output "%SRC_DIR%\temp_build\%CUDA_INSTALL_EXE%"
+    if errorlevel 1 exit /b 1
+    set "CUDA_SETUP_FILE=%SRC_DIR%\temp_build\%CUDA_INSTALL_EXE%"
+    set "ARGS=cuda_profiler_api_12.6 thrust_12.6 nvcc_12.6 cuobjdump_12.6 nvprune_12.6 nvprof_12.6 cupti_12.6 cublas_12.6 cublas_dev_12.6 cudart_12.6 cufft_12.6 cufft_dev_12.6 curand_12.6 curand_dev_12.6 cusolver_12.6 cusolver_dev_12.6 cusparse_12.6 cusparse_dev_12.6 npp_12.6 npp_dev_12.6 nvrtc_12.6 nvrtc_dev_12.6 nvml_dev_12.6 nvjitlink_12.6 nvtx_12.6"
+)
+
+set CUDNN_FOLDER=cudnn-windows-x86_64-9.5.0.50_cuda12-archive
+set CUDNN_LIB_FOLDER="lib"
+set "CUDNN_INSTALL_ZIP=%CUDNN_FOLDER%.zip"
+if not exist "%SRC_DIR%\temp_build\%CUDNN_INSTALL_ZIP%" (
+    curl -k -L "http://s3.amazonaws.com/ossci-windows/%CUDNN_INSTALL_ZIP%" --output "%SRC_DIR%\temp_build\%CUDNN_INSTALL_ZIP%"
+    if errorlevel 1 exit /b 1
+    set "CUDNN_SETUP_FILE=%SRC_DIR%\temp_build\%CUDNN_INSTALL_ZIP%"
+)
+
+@REM cuDNN 8.3+ required zlib to be installed on the path
+echo Installing ZLIB dlls
+curl -k -L "http://s3.amazonaws.com/ossci-windows/zlib123dllx64.zip" --output "%SRC_DIR%\temp_build\zlib123dllx64.zip"
+7z x "%SRC_DIR%\temp_build\zlib123dllx64.zip" -o"%SRC_DIR%\temp_build\zlib"
+xcopy /Y "%SRC_DIR%\temp_build\zlib\dll_x64\*.dll" "C:\Windows\System32"
+
+goto cuda_common
+
 :cuda_common
 :: NOTE: We only install CUDA if we don't have it installed already.
 :: With GHA runners these should be pre-installed as part of our AMI process

windows/internal/driver_update.bat

@@ -1,8 +1,9 @@
-set "DRIVER_DOWNLOAD_LINK=https://ossci-windows.s3.amazonaws.com/528.89-data-center-tesla-desktop-winserver-2016-2019-2022-dch-international.exe"
-curl --retry 3 -kL %DRIVER_DOWNLOAD_LINK% --output 528.89-data-center-tesla-desktop-winserver-2016-2019-2022-dch-international.exe
+set WIN_DRIVER_VN=528.89
+set "DRIVER_DOWNLOAD_LINK=https://ossci-windows.s3.amazonaws.com/%WIN_DRIVER_VN%-data-center-tesla-desktop-winserver-2016-2019-2022-dch-international.exe"
+curl --retry 3 -kL %DRIVER_DOWNLOAD_LINK% --output %WIN_DRIVER_VN%-data-center-tesla-desktop-winserver-2016-2019-2022-dch-international.exe
 if errorlevel 1 exit /b 1
 
-start /wait 528.89-data-center-tesla-desktop-winserver-2016-2019-2022-dch-international.exe -s -noreboot
+start /wait %WIN_DRIVER_VN%-data-center-tesla-desktop-winserver-2016-2019-2022-dch-international.exe -s -noreboot
 if errorlevel 1 exit /b 1
 
-del 528.89-data-center-tesla-desktop-winserver-2016-2019-2022-dch-international.exe || ver > NUL
+del %WIN_DRIVER_VN%-data-center-tesla-desktop-winserver-2016-2019-2022-dch-international.exe || ver > NUL

windows/internal/smoke_test.bat

@@ -91,6 +91,9 @@ if "%CUDA_VERSION%" == "121" (
 if "%CUDA_VERSION%" == "124" (
     set "CONDA_EXTRA_ARGS=pytorch-cuda=12.4 -c nvidia -c pytorch-nightly"
 )
+if "%CUDA_VERSION%" == "126" (
+    set "CONDA_EXTRA_ARGS=pytorch-cuda=12.6 -c nvidia -c pytorch-nightly"
+)
 
 rmdir /s /q conda
 del miniconda.exe