cv::cudacodec::VideoWriter not working with only NVCUVID

C++
, ,
1

I try to use both cv::cudacodec::VideoReader and cv::cudacodec::VideoWriter in my OpenCV program (a minimally reproducible example here).

Previously, I build OpenCV with NVCUVENC, my cmake output contains something like below:

  NVIDIA CUDA:                   YES (ver 11.8, CUFFT CUBLAS NVCUVID NVCUVENC)
    NVIDIA GPU arch:             35 37 50 52 60 61 70 75 80 86
    NVIDIA PTX archs:

But somehow, if I build latest OpenCV, NVCUVENC is gone, cmake’s output is something like this:

  NVIDIA CUDA:                   YES (ver 12.3, CUFFT CUBLAS NVCUVID)
    NVIDIA GPU arch:             50 52 60 61 70 75 80 86 89 90
    NVIDIA PTX archs:            90

I can still compile my MRE in the above link, but when I try running the program, it complains:

terminate called after throwing an instance of 'cv::Exception'
  what():  OpenCV(4.9.0-pre) /root/repos/opencv/modules/core/include/opencv2/core/private.cuda.hpp:112: error: (-213:The function/feature is not implemented) The called functionality is disabled for current build or platform in function 'throw_no_cuda'

After some investigation, I found this announcement which says that NVCUVENC has reached its EOL in 2021.

So the problem is: is it possible to use cv::cudacodec::VideoWriter with NVCUVID only, without using NVCUVENC?

2

Hi @cudawarped guess you are the best person to take a look at this post, I tried to use the new function you contributed in another(also newer) computer, and I can’t get it work with my GPU. Any thoughts?

3

NCUVENC is just the historical name of the encoding module in OpenCV, if its not present you haven’t compiled against the encoding lib (libnvidia-encode.so) which should be installed when you install the Nvidia driver.

Can you post your CMake output is should have an entry similar to

– Found NVCUVID: /usr/lib/wsl/lib/libnvcuvid.so
– Found NVCUVENC: /usr/lib/wsl/lib/libnvidia-encode.so
– CUDA detected: 12.0

4

The result is a bit different from what you expected. greping rows with CU gives me this:

~/repos/opencv/build# grep CU /tmp/cmake.output 
-- Could NOT find CUDNN (missing: CUDNN_LIBRARY CUDNN_INCLUDE_DIR) (Required is at least version "7.5")
-- CUDA detected: 12.3
-- CUDA: Using CUDA_ARCH_BIN=5.0;5.2;6.0;6.1;7.0;7.5;8.0;8.6;8.9;9.0
-- CUDA NVCC target flags: -gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_52,code=sm_52;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_89,code=sm_89;-gencode;arch=compute_90,code=sm_90;-D_FORCE_INLINES;-gencode;arch=compute_90,code=compute_90
-- Could NOT find Java (missing: Java_JAR_EXECUTABLE Java_JAVAC_EXECUTABLE Java_JAVADOC_EXECUTABLE) (found version "17.0.9")
--   NVIDIA CUDA:                   YES (ver 12.3, CUFFT CUBLAS NVCUVID)

The complete output is as follows:

-- Detected processor: x86_64
-- Looking for ccache - not found
-- Could NOT find OpenJPEG (minimal suitable version: 2.0, recommended version >= 2.3.1). OpenJPEG will be built from sources
-- OpenJPEG: VERSION = 2.5.0, BUILD = opencv-4.9.0-pre-openjp2-2.5.0
-- OpenJPEG libraries will be built from sources: libopenjp2 (version "2.5.0")
-- found Intel IPP (ICV version): 2021.10.0 [2021.10.0]
-- at: /root/repos/opencv/build/3rdparty/ippicv/ippicv_lnx/icv
-- found Intel IPP Integration Wrappers sources: 2021.10.0
-- at: /root/repos/opencv/build/3rdparty/ippicv/ippicv_lnx/iw
-- Could NOT find CUDNN (missing: CUDNN_LIBRARY CUDNN_INCLUDE_DIR) (Required is at least version "7.5")
-- CUDA detected: 12.3
-- CUDA: Using CUDA_ARCH_BIN=5.0;5.2;6.0;6.1;7.0;7.5;8.0;8.6;8.9;9.0
-- CUDA NVCC target flags: -gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_52,code=sm_52;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_89,code=sm_89;-gencode;arch=compute_90,code=sm_90;-D_FORCE_INLINES;-gencode;arch=compute_90,code=compute_90
-- Could not find OpenBLAS include. Turning OpenBLAS_FOUND off
-- Could not find OpenBLAS lib. Turning OpenBLAS_FOUND off
-- Could NOT find Atlas (missing: Atlas_CLAPACK_INCLUDE_DIR Atlas_CBLAS_LIBRARY Atlas_BLAS_LIBRARY) 
-- Could NOT find Java (missing: Java_JAR_EXECUTABLE Java_JAVAC_EXECUTABLE Java_JAVADOC_EXECUTABLE) (found version "17.0.9")
-- Could NOT find JNI (missing: JAVA_INCLUDE_PATH JAVA_INCLUDE_PATH2 AWT) 
-- VTK is not found. Please set -DVTK_DIR in CMake to VTK build directory, or to VTK install subdirectory with VTKConfig.cmake file
-- Checking for module 'gtk+-3.0'
--   Package 'gtk+-3.0', required by 'virtual:world', not found
-- Checking for module 'libavresample'
--   Package 'libavresample', required by 'virtual:world', not found
-- Checking for module 'gstreamer-base-1.0'
--   Package 'gstreamer-base-1.0', required by 'virtual:world', not found
-- Checking for module 'gstreamer-app-1.0'
--   Package 'gstreamer-app-1.0', required by 'virtual:world', not found
-- Checking for module 'gstreamer-riff-1.0'
--   Package 'gstreamer-riff-1.0', required by 'virtual:world', not found
-- Checking for module 'gstreamer-pbutils-1.0'
--   Package 'gstreamer-pbutils-1.0', required by 'virtual:world', not found
-- Checking for module 'gstreamer-video-1.0'
--   Package 'gstreamer-video-1.0', required by 'virtual:world', not found
-- Checking for module 'gstreamer-audio-1.0'
--   Package 'gstreamer-audio-1.0', required by 'virtual:world', not found
-- Checking for module 'libdc1394-2'
--   Package 'libdc1394-2', required by 'virtual:world', not found
-- Module opencv_alphamat disabled because the following dependencies are not found: Eigen
-- freetype2:   YES (ver 24.3.18)
-- harfbuzz:    YES (ver 6.0.0)
-- Julia not found. Not compiling Julia Bindings. 
-- Module opencv_ovis disabled because OGRE3D was not found
-- No preference for use of exported gflags CMake configuration set, and no hints for include/library directories provided. Defaulting to preferring an installed/exported gflags CMake configuration if available.
-- Failed to find installed gflags CMake configuration, searching for gflags build directories exported with CMake.
-- Failed to find gflags - Failed to find an installed/exported CMake configuration for gflags, will perform search for installed gflags components.
-- Failed to find gflags - Could not find gflags include directory, set GFLAGS_INCLUDE_DIR to directory containing gflags/gflags.h
-- Failed to find glog - Could not find glog include directory, set GLOG_INCLUDE_DIR to directory containing glog/logging.h
-- Module opencv_sfm disabled because the following dependencies are not found: Eigen Glog/Gflags
-- Checking for module 'tesseract'
--   Package 'tesseract', required by 'virtual:world', not found
-- Tesseract:   NO
-- Allocator metrics storage type: 'long long'
-- Excluding from source files list: <BUILD>/modules/core/test/test_intrin256.lasx.cpp
-- Excluding from source files list: modules/imgproc/src/imgwarp.lasx.cpp
-- Excluding from source files list: modules/imgproc/src/resize.lasx.cpp
-- Registering hook 'INIT_MODULE_SOURCES_opencv_dnn': /root/repos/opencv/modules/dnn/cmake/hooks/INIT_MODULE_SOURCES_opencv_dnn.cmake
-- opencv_dnn: filter out cuda4dnn source code
-- Excluding from source files list: modules/dnn/src/layers/cpu_kernels/conv_winograd_f63.neon.cpp
-- Excluding from source files list: <BUILD>/modules/dnn/layers/layers_common.rvv.cpp
-- Excluding from source files list: <BUILD>/modules/dnn/layers/layers_common.lasx.cpp
-- Excluding from source files list: <BUILD>/modules/dnn/int8layers/layers_common.lasx.cpp
-- Excluding from source files list: <BUILD>/modules/dnn/layers/cpu_kernels/conv_block.neon.cpp
-- Excluding from source files list: <BUILD>/modules/dnn/layers/cpu_kernels/conv_block.neon_fp16.cpp
-- Excluding from source files list: <BUILD>/modules/dnn/layers/cpu_kernels/conv_depthwise.rvv.cpp
-- Excluding from source files list: <BUILD>/modules/dnn/layers/cpu_kernels/conv_depthwise.lasx.cpp
-- Excluding from source files list: <BUILD>/modules/dnn/layers/cpu_kernels/conv_winograd_f63.neon_fp16.cpp
-- Excluding from source files list: <BUILD>/modules/dnn/layers/cpu_kernels/fast_gemm_kernels.neon.cpp
-- Excluding from source files list: <BUILD>/modules/dnn/layers/cpu_kernels/fast_gemm_kernels.lasx.cpp
-- imgcodecs: OpenEXR codec is disabled in runtime. Details: https://github.com/opencv/opencv/issues/21326
-- highgui: using builtin backend: GTK2
-- rgbd: Eigen support is disabled. Eigen is Required for Posegraph optimization
-- Building with NVIDIA Optical Flow API 2.0
-- Found 'misc' Python modules from /root/repos/opencv/modules/python/package/extra_modules
-- Found 'mat_wrapper;utils' Python modules from /root/repos/opencv/modules/core/misc/python/package
-- Found 'gapi' Python modules from /root/repos/opencv/modules/gapi/misc/python/package
-- Found 'misc' Python modules from /root/repos/opencv/modules/python/package/extra_modules
-- Found 'mat_wrapper;utils' Python modules from /root/repos/opencv/modules/core/misc/python/package
-- Found 'gapi' Python modules from /root/repos/opencv/modules/gapi/misc/python/package
-- 
-- General configuration for OpenCV 4.9.0-pre =====================================
--   Version control:               4.8.0-589-g8c22b4b54b
-- 
--   Extra modules:
--     Location (extra):            /root/repos/opencv_contrib/modules
--     Version control (extra):     4.8.1-51-gab4bfc26-dirty
-- 
--   Platform:
--     Timestamp:                   2023-12-29T17:33:46Z
--     Host:                        Linux 6.1.0-15-amd64 x86_64
--     CMake:                       3.25.1
--     CMake generator:             Unix Makefiles
--     CMake build tool:            /usr/bin/gmake
--     Configuration:               RELEASE
-- 
--   CPU/HW features:
--     Baseline:                    SSE SSE2 SSE3
--       requested:                 SSE3
--     Dispatched code generation:  SSE4_1 SSE4_2 FP16 AVX AVX2 AVX512_SKX
--       requested:                 SSE4_1 SSE4_2 AVX FP16 AVX2 AVX512_SKX
--       SSE4_1 (18 files):         + SSSE3 SSE4_1
--       SSE4_2 (2 files):          + SSSE3 SSE4_1 POPCNT SSE4_2
--       FP16 (1 files):            + SSSE3 SSE4_1 POPCNT SSE4_2 FP16 AVX
--       AVX (9 files):             + SSSE3 SSE4_1 POPCNT SSE4_2 AVX
--       AVX2 (38 files):           + SSSE3 SSE4_1 POPCNT SSE4_2 FP16 FMA3 AVX AVX2
--       AVX512_SKX (8 files):      + SSSE3 SSE4_1 POPCNT SSE4_2 FP16 FMA3 AVX AVX2 AVX_512F AVX512_COMMON AVX512_SKX
-- 
--   C/C++:
--     Built as dynamic libs?:      YES
--     C++ standard:                11
--     C++ Compiler:                /usr/bin/c++  (ver 12.2.0)
--     C++ flags (Release):         -fsigned-char -W -Wall -Wreturn-type -Wnon-virtual-dtor -Waddress -Wsequence-point -Wformat -Wformat-security -Wmissing-declarations -Wundef -Winit-self -Wpointer-arith -Wshadow -Wsign-promo -Wuninitialized -Wsuggest-override -Wno-delete-non-virtual-dtor -Wno-comment -Wimplicit-fallthrough=3 -Wno-strict-overflow -fdiagnostics-show-option -Wno-long-long -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections  -msse -msse2 -msse3 -fvisibility=hidden -fvisibility-inlines-hidden -O3 -DNDEBUG  -DNDEBUG
--     C++ flags (Debug):           -fsigned-char -W -Wall -Wreturn-type -Wnon-virtual-dtor -Waddress -Wsequence-point -Wformat -Wformat-security -Wmissing-declarations -Wundef -Winit-self -Wpointer-arith -Wshadow -Wsign-promo -Wuninitialized -Wsuggest-override -Wno-delete-non-virtual-dtor -Wno-comment -Wimplicit-fallthrough=3 -Wno-strict-overflow -fdiagnostics-show-option -Wno-long-long -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections  -msse -msse2 -msse3 -fvisibility=hidden -fvisibility-inlines-hidden -g  -O0 -DDEBUG -D_DEBUG
--     C Compiler:                  /usr/bin/cc
--     C flags (Release):           -fsigned-char -W -Wall -Wreturn-type -Waddress -Wsequence-point -Wformat -Wformat-security -Wmissing-declarations -Wmissing-prototypes -Wstrict-prototypes -Wundef -Winit-self -Wpointer-arith -Wshadow -Wuninitialized -Wno-comment -Wimplicit-fallthrough=3 -Wno-strict-overflow -fdiagnostics-show-option -Wno-long-long -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections  -msse -msse2 -msse3 -fvisibility=hidden -O3 -DNDEBUG  -DNDEBUG
--     C flags (Debug):             -fsigned-char -W -Wall -Wreturn-type -Waddress -Wsequence-point -Wformat -Wformat-security -Wmissing-declarations -Wmissing-prototypes -Wstrict-prototypes -Wundef -Winit-self -Wpointer-arith -Wshadow -Wuninitialized -Wno-comment -Wimplicit-fallthrough=3 -Wno-strict-overflow -fdiagnostics-show-option -Wno-long-long -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections  -msse -msse2 -msse3 -fvisibility=hidden -g  -O0 -DDEBUG -D_DEBUG
--     Linker flags (Release):      -Wl,--exclude-libs,libippicv.a -Wl,--exclude-libs,libippiw.a   -Wl,--gc-sections -Wl,--as-needed -Wl,--no-undefined  
--     Linker flags (Debug):        -Wl,--exclude-libs,libippicv.a -Wl,--exclude-libs,libippiw.a   -Wl,--gc-sections -Wl,--as-needed -Wl,--no-undefined  
--     ccache:                      NO
--     Precompiled headers:         NO
--     Extra dependencies:          m pthread cudart_static dl rt nppc nppial nppicc nppidei nppif nppig nppim nppist nppisu nppitc npps cublas cufft -L/usr/local/cuda-12.3/lib64 -L/usr/lib/x86_64-linux-gnu
--     3rdparty dependencies:
-- 
--   OpenCV modules:
--     To be built:                 aruco bgsegm bioinspired calib3d ccalib core cudaarithm cudabgsegm cudacodec cudafeatures2d cudafilters cudaimgproc cudalegacy cudaobjdetect cudaoptflow cudastereo cudawarping cudev datasets dnn dnn_objdetect dnn_superres dpm features2d flann freetype fuzzy gapi hdf hfs highgui img_hash imgcodecs imgproc intensity_transform line_descriptor mcc ml objdetect optflow phase_unwrapping photo plot python3 quality rapid reg rgbd saliency shape stereo stitching structured_light superres surface_matching text tracking ts video videoio videostab ximgproc xobjdetect xphoto
--     Disabled:                    world
--     Disabled by dependency:      -
--     Unavailable:                 alphamat cannops cvv java julia matlab ovis python2 sfm viz
--     Applications:                tests perf_tests apps
--     Documentation:               NO
--     Non-free algorithms:         NO
-- 
--   GUI:                           GTK2
--     GTK+:                        YES (ver 2.24.33)
--       GThread :                  YES (ver 2.74.6)
--       GtkGlExt:                  NO
--     VTK support:                 NO
-- 
--   Media I/O: 
--     ZLib:                        /usr/lib/x86_64-linux-gnu/libz.so (ver 1.2.13)
--     JPEG:                        /usr/lib/x86_64-linux-gnu/libjpeg.so (ver 62)
--     WEBP:                        /usr/lib/x86_64-linux-gnu/libwebp.so (ver encoder: 0x020f)
--     PNG:                         /usr/lib/x86_64-linux-gnu/libpng.so (ver 1.6.39)
--     TIFF:                        /usr/lib/x86_64-linux-gnu/libtiff.so (ver 42 / 4.5.0)
--     JPEG 2000:                   build (ver 2.5.0)
--     OpenEXR:                     build (ver 2.3.0)
--     HDR:                         YES
--     SUNRASTER:                   YES
--     PXM:                         YES
--     PFM:                         YES
-- 
--   Video I/O:
--     DC1394:                      NO
--     FFMPEG:                      YES
--       avcodec:                   YES (58.134.100)
--       avformat:                  YES (58.76.100)
--       avutil:                    YES (56.70.100)
--       swscale:                   YES (5.7.100)
--       avresample:                NO
--     GStreamer:                   NO
--     v4l/v4l2:                    YES (linux/videodev2.h)
-- 
--   Parallel framework:            pthreads
-- 
--   Trace:                         YES (with Intel ITT)
-- 
--   Other third-party libraries:
--     Intel IPP:                   2021.10.0 [2021.10.0]
--            at:                   /root/repos/opencv/build/3rdparty/ippicv/ippicv_lnx/icv
--     Intel IPP IW:                sources (2021.10.0)
--               at:                /root/repos/opencv/build/3rdparty/ippicv/ippicv_lnx/iw
--     VA:                          YES
--     Lapack:                      NO
--     Eigen:                       NO
--     Custom HAL:                  NO
--     Protobuf:                    build (3.19.1)
--     Flatbuffers:                 builtin/3rdparty (23.5.9)
-- 
--   NVIDIA CUDA:                   YES (ver 12.3, CUFFT CUBLAS NVCUVID)
--     NVIDIA GPU arch:             50 52 60 61 70 75 80 86 89 90
--     NVIDIA PTX archs:            90
-- 
--   cuDNN:                         NO
-- 
--   OpenCL:                        YES (INTELVA)
--     Include path:                /root/repos/opencv/3rdparty/include/opencl/1.2
--     Link libraries:              Dynamic load
-- 
--   Python 3:
--     Interpreter:                 /usr/bin/python3 (ver 3.11.2)
--     Libraries:                   /usr/lib/x86_64-linux-gnu/libpython3.11.so (ver 3.11.2)
--     numpy:                       /usr/lib/python3/dist-packages/numpy/core/include (ver 1.24.2)
--     install path:                lib/python3.11/dist-packages/cv2/python-3.11
-- 
--   Python (for build):            /usr/bin/python3
-- 
--   Java:                          
--     ant:                         NO
--     Java:                        NO
--     JNI:                         NO
--     Java wrappers:               NO
--     Java tests:                  NO
-- 
--   Install to:                    /usr/local
-- -----------------------------------------------------------------
-- 
-- Configuring done
-- Generating done
-- Build files have been written to: /root/repos/opencv/build

In case you are wondering, my cmake command is this:

cmake \
-D CMAKE_BUILD_TYPE=RELEASE \
-D CMAKE_INSTALL_PREFIX=/usr/local \
-D WITH_CUDA=ON \
-D WITH_NVCUVID=ON \
-D WITH_NVCUVENC=ON \
-D BUILD_opencv_cudacodec=ON \
-D OPENCV_EXTRA_MODULES_PATH=~/repos/opencv_contrib/modules/ \
-D OPENCV_GENERATE_PKGCONFIG=ON \
-D OPENCV_PC_FILE_NAME=opencv.pc \
-D BUILD_EXAMPLES=OFF \
..

Also, tried finding the shared objects you mentioned:

~/repos/opencv/build# find / -name libnvcuvid*.so* 2>/dev/null 
/usr/lib/x86_64-linux-gnu/libnvcuvid.so
/usr/lib/x86_64-linux-gnu/libnvcuvid.so.1
/usr/lib/x86_64-linux-gnu/nvidia/current/libnvcuvid.so.545.23.08
/usr/lib/x86_64-linux-gnu/nvidia/current/libnvcuvid.so
/usr/lib/x86_64-linux-gnu/nvidia/current/libnvcuvid.so.1

~/repos/opencv/build# find / -name libnvidia-encode*.so* 2>/dev/null 
/usr/lib/x86_64-linux-gnu/libnvidia-encode.so.1
/usr/lib/x86_64-linux-gnu/nvidia/current/libnvidia-encode.so.545.23.08
/usr/lib/x86_64-linux-gnu/nvidia/current/libnvidia-encode.so.1
/usr/lib/x86_64-linux-gnu/nvidia/current/libnvidia-encode.so

Any thoughts?

5

Use the latest commits from the 4.x branch. These include the output I showed.

Not sure why its picking up one and not the other, maybe its finding libnvcuvid.so in another location or maybe the headers are missing either way the output from the OpenCV 4.9.0 should shed some light on what is going on.

6

You are correct–I was using the OpenCV’s commit 5 days ago and it doesnt show the info, and I just did another git pull, I can see the output you mentioned now:

-- Found NVCUVID: /usr/lib/x86_64-linux-gnu/libnvcuvid.so
-- NVCUVENC: Library not found, WITH_NVCUVENC requires the Nvidia encoding shared library libnvidia-encode.so from the driver installation or the location of the stub library to be manually set with CUDA_nvidia-encode_LIBRARY i.e. CUDA_nvidia-encode_LIBRARY=/home/user/Video_Codec_SDK_X.X.X/Lib/linux/stubs/x86_64/libnvidia-encode.so
-- CUDA detected: 12.3
-- CUDA: NVCC target flags -gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_52,code=sm_52;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_89,code=sm_89;-gencode;arch=compute_90,code=sm_90;-D_FORCE_INLINES;-gencode;arch=compute_90,code=compute_90

Just added the CUDA_nvidia-encode_LIBRARY as prompted, compiling OpenCV again now. Will come back when the compilation is done.

7

Now I see what’s going on,

is on the search path but

is not.

8

Yes and my compilation is just done–after passing CUDA_nvidia-encode_LIBRARY as suggested, my program works as expected now.

One tiny question though, before I post this question, I was already using the “latest” commit of the 4.x branch, that was the latest commit a few days ago. In that version, I dont have

-- Found NVCUVID: /usr/lib/x86_64-linux-gnu/libnvcuvid.so
-- NVCUVENC: Library not found, WITH_NVCUVENC requires the Nvidia encoding shared library libnvidia-encode.so from the driver installation or the location of the stub library to be manually set with CUDA_nvidia-encode_LIBRARY i.e. CUDA_nvidia-encode_LIBRARY=/home/user/Video_Codec_SDK_X.X.X/Lib/linux/stubs/x86_64/libnvidia-encode.so
-- CUDA detected: 12.3
-- CUDA: NVCC target flags -gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_52,code=sm_52;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_89,code=sm_89;-gencode;arch=compute_90,code=sm_90;-D_FORCE_INLINES;-gencode;arch=compute_90,code=compute_90

yet.

After only a few days, somehow, this useful feature is added to the 4.x branch? Is this just a coincidence?..

9

Honestly yes just a coincidence.