{"id":1677,"date":"2025-05-22T23:58:05","date_gmt":"2025-05-22T14:58:05","guid":{"rendered":"https:\/\/www.dogrow.net\/nnet\/?p=1677"},"modified":"2025-05-23T16:25:47","modified_gmt":"2025-05-23T07:25:47","slug":"blog47-rtx-5070ti%e3%81%a7-devicequery%e3%82%92%e5%ae%9f%e8%a1%8c%e3%81%97%e3%81%a6%e3%81%bf%e3%82%8b%e3%80%82","status":"publish","type":"post","link":"https:\/\/www.dogrow.net\/nnet\/blog47-rtx-5070ti%e3%81%a7-devicequery%e3%82%92%e5%ae%9f%e8%a1%8c%e3%81%97%e3%81%a6%e3%81%bf%e3%82%8b%e3%80%82\/","title":{"rendered":"(47) RTX 5070ti\u3067 deviceQuery\u3092\u5b9f\u884c\u3057\u3066\u307f\u308b\u3002"},"content":{"rendered":"

\u30101\u3011\u3084\u308a\u305f\u3044\u3053\u3068<\/h1>\n

Ubuntu24.04\u306b CUDA 12.8\u3092\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u3057\u305f\u306e\u3067\u3001\u3053\u308c\u3092\u4f7f\u3063\u3066\u30d1\u30bd\u30b3\u30f3\u306b\u642d\u8f09\u3057\u3066\u3044\u308b GPU\u306e\u60c5\u5831\u3092\u8868\u793a\u3057\u3066\u307f\u305f\u3044\u3002<\/p>\n

\u4f7f\u7528\u3059\u308b\u30d7\u30ed\u30b0\u30e9\u30e0\u306f\u6bce\u5ea6\u304a\u306a\u3058\u307f\u306e deviceQuery<\/span>
\nNVIDIA\u516c\u5f0f\u306e CUDA\u30b5\u30f3\u30d7\u30eb\u30d7\u30ed\u30b0\u30e9\u30e0\u306e\u4e00\u3064\u3060\u3002<\/p>\n

\u30102\u3011\u3084\u3063\u3066\u307f\u308b<\/h1>\n

Step 1\/3: CUDA\u30b5\u30f3\u30d7\u30eb\u3092\u5165\u624b\uff06\u5c55\u958b\u3059\u308b\u3002<\/h3>\n

\u4e0b\u8a18\u306e\u30b5\u30a4\u30c8\u304b\u3089 zip\u30d5\u30a1\u30a4\u30eb\u3092\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9\u3059\u308b\u3002<\/p>\n

https:\/\/github.com\/nvidia\/cuda-samples
\n\"\"<\/a><\/p>\n

\u3042\u3089\u304b\u3058\u3081\u5c55\u958b\u5148\u306e\u30c7\u30a3\u30ec\u30af\u30c8\u30ea\u3092\u4f5c\u308a\u3001\u305d\u3053\u3078\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9\u3059\u308b\u3068\u697d\u3060\u3002
\n\u4ee5\u4e0b\u306f\u3001 \/home\/{user}\/cuda-samples<\/span> \u306b\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u3057\u305f\u4f8b\u3060\u3002<\/p>\n

\r\n$ mkdir -p ~\/cuda-samples<\/span>\r\n$ cd ~\/cuda-samples<\/span>\r\n$ wget https:\/\/github.com\/NVIDIA\/cuda-samples\/archive\/refs\/heads\/master.zip<\/span>\r\n<\/pre>\n
\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9\u3057\u305f\u30d5\u30a1\u30a4\u30eb\u3092\u89e3\u51cd\u3059\u308b\u3002<\/p>\n
\r\n$ unzip master.zip<\/span>\r\n$ ls -l<\/span>\r\ndrwxrwxr-x 6 hoge hoge      4096 May 23 03:43 cuda-samples-master\/\r\n<\/pre>\n
cuda-samples-master<\/span> \u306a\u308b\u30c7\u30a3\u30ec\u30af\u30c8\u30ea\u304c\u51fa\u73fe\u3057\u305f\u3002\u3053\u306e\u4e2d\u306b\u8272\u3005\u3068\u5165\u3063\u3066\u3044\u308b\u3002<\/p>\n
Step 2\/3: deviceQuery\u30d7\u30ed\u30b0\u30e9\u30e0\u3092\u4f5c\u308b\u3002<\/h3>\n
ZIP\u30d5\u30a1\u30a4\u30eb\u3092\u5c55\u958b\u3057\u305f\u3060\u3051\u3067\u306f\u3001deviceQuery\u30d7\u30ed\u30b0\u30e9\u30e0\u306f\u4f7f\u3048\u306a\u3044\u3002<\/p>\n
\u30d7\u30ed\u30b0\u30e9\u30e0\u30bd\u30fc\u30b9\u30b3\u30fc\u30c9\u304c\u63d0\u4f9b\u3055\u308c\u305f\u3060\u3051\u306a\u306e\u3067\u3001
\n\u3053\u308c\u3092\u81ea\u5206\u306e\u74b0\u5883\u3067\u30b3\u30f3\u30d1\u30a4\u30eb\u3001\u30ea\u30f3\u30af\u3057\u3001deviceQuery\u30d7\u30ed\u30b0\u30e9\u30e0\u3092\u4f5c\u308b\u5fc5\u8981\u304c\u3042\u308b\u3002<\/p>\n
\u4ee5\u4e0b\u3001\u4e00\u3064\u305a\u3064\u305d\u308c\u3092\u5b9f\u884c\u3057\u3066\u3044\u304f\u3002<\/p>\n
\u307e\u305a\u306f Samples\u30c7\u30a3\u30ec\u30af\u30c8\u30ea\u3078\u79fb\u52d5\u3057\u3001\u4e2d\u8eab\u3092\u898b\u3066\u307f\u308b\u3002<\/p>\n
\r\n$ cd cuda-samples-master\/Samples\/<\/span>\r\n$ ls -l<\/span>\r\ntotal 48\r\ndrwxrwxr-x 11 hoge hoge 4096 May 23 03:43 .\/\r\ndrwxrwxr-x  6 hoge hoge 4096 May 23 03:43 ..\/\r\ndrwxrwxr-x 48 hoge hoge 4096 May 23 03:43 0_Introduction\/\r\ndrwxrwxr-x  5 hoge hoge 4096 May 23 03:43 1_Utilities\/\r\ndrwxrwxr-x 34 hoge hoge 4096 May 23 03:43 2_Concepts_and_Techniques\/\r\ndrwxrwxr-x 26 hoge hoge 4096 May 23 03:43 3_CUDA_Features\/\r\ndrwxrwxr-x 36 hoge hoge 4096 May 23 03:43 4_CUDA_Libraries\/\r\ndrwxrwxr-x 38 hoge hoge 4096 May 23 03:43 5_Domain_Specific\/\r\ndrwxrwxr-x  7 hoge hoge 4096 May 23 03:43 6_Performance\/\r\ndrwxrwxr-x 11 hoge hoge 4096 May 23 03:43 7_libNVVM\/\r\ndrwxrwxr-x  3 hoge hoge 4096 May 23 03:43 8_Platform_Specific\/\r\n-rw-rw-r--  1 hoge hoge  867 May 23 03:43 CMakeLists.txt\r\n<\/pre>\n
\u30ab\u30c6\u30b4\u30ea\u3054\u3068\u306b\u8272\u3005\u3068\u5165\u3063\u3066\u3044\u308b\u3002
\ndeviceQuery\u304c\u3069\u3053\u306b\u5165\u3063\u3066\u3044\u308b\u306e\u304b\u63a2\u3057\u3066\u307f\u308b\u3002<\/p>\n
\r\n$ find . -type d -name deviceQuery<\/span>\r\n.\/1_Utilities\/deviceQuery\r\n<\/pre>\n
\u30c7\u30a3\u30ec\u30af\u30c8\u30ea 1_Utilities\/deviceQuery<\/span> \u306e\u4e2d\u306b\u3044\u308b\u306e\u3067\u3001\u3053\u3053\u3078\u79fb\u52d5\u3059\u308b\u3002<\/p>\n
\r\n$ cd 1_Utilities\/deviceQuery<\/span>\r\n$ ls -l\r\ntotal 36\r\ndrwxrwxr-x 3 hoge hoge  4096 May 23 03:43 .\/\r\ndrwxrwxr-x 5 hoge hoge  4096 May 23 03:43 ..\/\r\n-rw-rw-r-- 1 hoge hoge  1239 May 23 03:43 CMakeLists.txt\r\n-rw-rw-r-- 1 hoge hoge 14774 May 23 03:43 deviceQuery.cpp\r\n-rw-rw-r-- 1 hoge hoge  1503 May 23 03:43 README.md\r\ndrwxrwxr-x 2 hoge hoge  4096 May 23 03:43 .vscode\/\r\n<\/pre>\n
CMake\u3067\u30d3\u30eb\u30c9\u3059\u308b\u3088\u3046\u306b\u63d0\u4f9b\u3055\u308c\u3066\u3044\u308b\u306e\u3067\u3001\u307e\u305a\u306f\u30d3\u30eb\u30c9\u30c4\u30fc\u30eb\u985e\u3092\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u3059\u308b\u3002<\/p>\n
\r\n$ sudo apt update<\/span>\r\n$ sudo apt install build-essential<\/span>\r\n$ sudo apt install cmake<\/span>\r\n<\/pre>\n
CMake\u3067\u306f\u30d3\u30eb\u30c9\u30c7\u30a3\u30ec\u30af\u30c8\u30ea\u3092\u5206\u3051\u3066\u304a\u304f\u306e\u304c\u304a\u4f5c\u6cd5\u306a\u306e\u3067\uff08\uff1d\u5143\u30c7\u30a3\u30ec\u30af\u30c8\u30ea\u3092\u6c5a\u3055\u306a\u3044\u305f\u3081\uff09\u3001
\n\u76f4\u4e0b\u306b build\u30c7\u30a3\u30ec\u30af\u30c8\u30ea\u3092\u4f5c\u3063\u3066\u3001\u305d\u3053\u3078\u79fb\u52d5\u3057\u3066\u4f5c\u696d\u3059\u308b\u3002<\/p>\n
\r\n$ mkdir build<\/span>\r\n$ cd build<\/span>\r\n$ cmake ..<\/span>\r\n-- The C compiler identification is GNU 13.3.0\r\n-- The CXX compiler identification is GNU 13.3.0\r\n-- The CUDA compiler identification is NVIDIA 12.8.93\r\n-- Detecting C compiler ABI info\r\n-- Detecting C compiler ABI info - done\r\n-- Check for working C compiler: \/usr\/bin\/cc - skipped\r\n-- Detecting C compile features\r\n-- Detecting C compile features - done\r\n-- Detecting CXX compiler ABI info\r\n-- Detecting CXX compiler ABI info - done\r\n-- Check for working CXX compiler: \/usr\/bin\/c++ - skipped\r\n-- Detecting CXX compile features\r\n-- Detecting CXX compile features - done\r\n-- Detecting CUDA compiler ABI info\r\n-- Detecting CUDA compiler ABI info - done\r\n-- Check for working CUDA compiler: \/usr\/local\/cuda-12.8\/bin\/nvcc - skipped\r\n-- Detecting CUDA compile features\r\n-- Detecting CUDA compile features - done\r\n-- Found CUDAToolkit: \/usr\/local\/cuda-12.8\/targets\/x86_64-linux\/include (found version \"12.8.93\")\r\n-- Performing Test CMAKE_HAVE_LIBC_PTHREAD\r\n-- Performing Test CMAKE_HAVE_LIBC_PTHREAD - Success\r\n-- Found Threads: TRUE\r\n-- Configuring done (1.9s)\r\n-- Generating done (0.0s)\r\n-- Build files have been written to: \/home\/hoge\/cuda-samples\/cuda-samples-master\/Samples\/1_Utilities\/deviceQuery\/build\r\n<\/pre>\n
cmake\u3092\u5b9f\u884c\u3057\u3001\u30d3\u30eb\u30c9\u74b0\u5883\u304c\u751f\u6210\u3055\u308c\u305f\u3002
\n\u3044\u3088\u3044\u3088\u672c\u756a\u3060\u3001make\u3059\u308b\u3002<\/p>\n
\r\n$ make<\/span>\r\n[ 50%] Building CXX object CMakeFiles\/deviceQuery.dir\/deviceQuery.cpp.o\r\n[100%] Linking CXX executable deviceQuery\r\n[100%] Built target deviceQuery\r\n$\r\n$ ls -l<\/span>\r\ntotal 88\r\ndrwxrwxr-x 3 hoge hoge  4096 May 23 06:23 .\/\r\ndrwxrwxr-x 4 hoge hoge  4096 May 23 06:19 ..\/\r\n-rw-rw-r-- 1 hoge hoge 32119 May 23 06:19 CMakeCache.txt\r\ndrwxrwxr-x 6 hoge hoge  4096 May 23 06:23 CMakeFiles\/\r\n-rw-rw-r-- 1 hoge hoge  1754 May 23 06:19 cmake_install.cmake\r\n-rwxrwxr-x 1 hoge hoge 32616 May 23 06:23 deviceQuery*<\/span>\r\n-rw-rw-r-- 1 hoge hoge  5654 May 23 06:19 Makefile\r\n<\/pre>\n
deviceQuery\u304c\u51fa\u529b\u3055\u308c\u305f\u3002<\/span><\/p>\n
Step 3\/3: deviceQuery\u3092\u5b9f\u884c\u3059\u308b\u3002<\/h3>\n
\u4e0a\u8a18\u306e Step2 \u3067\u4f5c\u3063\u305f deviceQuery\u30d7\u30ed\u30b0\u30e9\u30e0\u3092\u5b9f\u884c\u3059\u308b\u3060\u3051\u3060\u3002<\/p>\n
\r\n$ .\/deviceQuery<\/span>\r\n.\/deviceQuery Starting...\r\n\r\nCUDA Device Query (Runtime API) version (CUDART static linking)\r\n\r\nDetected 1 CUDA Capable device(s)\r\n\r\nDevice 0: \"NVIDIA GeForce RTX 5070 Ti\"\r\n  CUDA Driver Version \/ Runtime Version          12.8 \/ 12.8\r\n  CUDA Capability Major\/Minor version number:    12.0\r\n  Total amount of global memory:                 15842 MBytes (16611999744 bytes)\r\n  (070) Multiprocessors, (128) CUDA Cores\/MP:    8960 CUDA Cores\r\n  GPU Max Clock rate:                            2482 MHz (2.48 GHz)\r\n  Memory Clock rate:                             14001 Mhz\r\n  Memory Bus Width:                              256-bit\r\n  L2 Cache Size:                                 50331648 bytes\r\n  Maximum Texture Dimension Size (x,y,z)         1D=(131072), 2D=(131072, 65536), 3D=(16384, 16384, 16384)\r\n  Maximum Layered 1D Texture Size, (num) layers  1D=(32768), 2048 layers\r\n  Maximum Layered 2D Texture Size, (num) layers  2D=(32768, 32768), 2048 layers\r\n  Total amount of constant memory:               65536 bytes\r\n  Total amount of shared memory per block:       49152 bytes\r\n  Total shared memory per multiprocessor:        102400 bytes\r\n  Total number of registers available per block: 65536\r\n  Warp size:                                     32\r\n  Maximum number of threads per multiprocessor:  1536\r\n  Maximum number of threads per block:           1024\r\n  Max dimension size of a thread block (x,y,z): (1024, 1024, 64)\r\n  Max dimension size of a grid size    (x,y,z): (2147483647, 65535, 65535)\r\n  Maximum memory pitch:                          2147483647 bytes\r\n  Texture alignment:                             512 bytes\r\n  Concurrent copy and kernel execution:          Yes with 2 copy engine(s)\r\n  Run time limit on kernels:                     Yes\r\n  Integrated GPU sharing Host Memory:            No\r\n  Support host page-locked memory mapping:       Yes\r\n  Alignment requirement for Surfaces:            Yes\r\n  Device has ECC support:                        Disabled\r\n  Device supports Unified Addressing (UVA):      Yes\r\n  Device supports Managed Memory:                Yes\r\n  Device supports Compute Preemption:            Yes\r\n  Supports Cooperative Kernel Launch:            Yes\r\n  Supports MultiDevice Co-op Kernel Launch:      Yes\r\n  Device PCI Domain ID \/ Bus ID \/ location ID:   0 \/ 2 \/ 0\r\n  Compute Mode:\r\n     < Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >\r\n\r\ndeviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 12.8, CUDA Runtime Version = 12.8, NumDevs = 1\r\nResult = PASS\r\n<\/pre>\n
\u6211\u304c\u5bb6\u306e GeForce RTX 5070ti<\/a> \u306e\u60c5\u5831\u304c\u8868\u793a\u3055\u308c\u305f\u3002
\n\n
CUDA Capability<\/td>12.0<\/td><\/tr>
Total amount of global memory<\/td>15842 MBytes<\/td><\/tr>
CUDA Cores<\/td>8960 CUDA Cores<\/td><\/tr>
GPU Max Clock rate<\/td>2482 MHz (2.48 GHz)<\/td><\/tr>\n<\/table><\/p>\n
\u306a\u3069\u306a\u3069\u3002<\/p>\n
11\u5e74\u524d\u306e\u904e\u53bb\u8a18\u4e8b (22) cuda-convnet2\u306f\u3084\u3063\u3066\u307f\u308c\u306a\u3044<\/a> \u3067\u306f
\nCUDA Compute Capability\u304c 3.5\u306b\u6e80\u305f\u306a\u3044\u305f\u3081\u306b\u3001\u52d5\u304b\u3057\u305f\u3044\u30d7\u30ed\u30b0\u30e9\u30e0\u3092\u52d5\u304b\u305b\u306a\u304b\u3063\u305f\u82e6\u3005\u3057\u3044\u8a18\u61b6\u304c\u3042\u308b\u3002<\/p>\n
\u3042\u306e\u9803\u306f GTX 780 \u304c\u9ad8\u5dba\u306e\u82b1\u3060\u3063\u305f\u3002
\n\u4eca\u306f Compute Capability\u304c 12.0 \u306a\u306e\u304b…<\/p>\n
\u6642\u4ee3\u306e\u6d41\u308c\u3092\u5f37\u304f\u611f\u3058\u308b\u4eca\u65e5\u3053\u306e\u9803\u3067\u3059\u3002\u3002\u3002<\/p>\n
\u30103\u3011\u4ed6\u306e\u30b5\u30f3\u30d7\u30eb\u3082\u3084\u3063\u3066\u307f\u308b<\/h1>\n
1) Mandelbrot<\/h2>\n
\u30d5\u30e9\u30af\u30bf\u30eb\u56f3\u5f62\u300c\u30de\u30f3\u30c7\u30eb\u30d6\u30ed\u96c6\u5408\u300d\u3092 CUDA \u3067\u9ad8\u901f\u63cf\u753b\u3059\u308b\u30b5\u30f3\u30d7\u30eb\u3060\u3002
\nZoom in\u3057\u3066\u3069\u3053\u307e\u3067\u3082\u7121\u9650\u306b\u7d9a\u304f\u5e7e\u4f55\u5b66\u6a21\u69d8\u3092\u697d\u3057\u3081\u308b\u3002<\/span>
\n\"\"<\/p>\n
\u56f3\u5f62\u3092 Zoom in\u3059\u308b\u3068\u3001\u30ea\u30a2\u30eb\u30bf\u30a4\u30e0\u3067\u518d\u8a08\u7b97\u3057\u3066\u63cf\u753b\u66f4\u65b0\u3057\u3066\u304f\u308c\u308b\u3002
\n\u4e00\u77ac\u3067\u6f14\u7b97\uff06\u63cf\u753b\u3067\u304d\u3066\u3057\u307e\u3046\u901f\u5ea6\u6027\u80fd\u306f\u3001\u3055\u3059\u304c\u306f\u4e26\u5217\u8a08\u7b97\u304c\u5f97\u610f\u306a GPU\u3060\u3002<\/p>\n
\u5b9f\u884c\u307e\u3067\u306e\u624b\u9806\u306f\u4ee5\u4e0b\u306e\u901a\u308a\u3002<\/p>\n
OpenGL + GLUT \u958b\u767a\u7528\u30e9\u30a4\u30d6\u30e9\u30ea\u304c\u7121\u3051\u308c\u3070\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u3057\u3066\u304a\u304f\u3002<\/p>\n
\r\n$ sudo apt update<\/span>\r\n$ sudo apt install libgl1-mesa-dev freeglut3-dev<\/span>\r\n<\/pre>\n
\u5148\u307b\u3069\u306e deviceQuery\u3068\u540c\u69d8\u306b\u3001cmake<\/span> \u2192 make<\/span> \u3092\u5b9f\u884c\u3059\u308b\u3002<\/p>\n
\r\n$ cd ~\/cuda-samples\/cuda-samples-master\/Samples\/5_Domain_Specific\/Mandelbrot<\/span>\r\n$ mkdir build<\/span>\r\n$ cd build<\/span>\r\n$ cmake ..<\/span>\r\n$ make<\/span>\r\n<\/pre>\n
\u5b9f\u884c\u4f53 Mandelbrot \u304c\u51fa\u6765\u4e0a\u304c\u3063\u3066\u3044\u308b\u3002<\/p>\n
\r\n$ ls -l<\/span>\r\ntotal 4492\r\ndrwxrwxr-x 4 hoge hoge    4096 May 23 07:55 .\/\r\ndrwxrwxr-x 6 hoge hoge    4096 May 23 07:51 ..\/\r\n-rw-rw-r-- 1 hoge hoge   37568 May 23 07:55 CMakeCache.txt\r\ndrwxrwxr-x 5 hoge hoge    4096 May 23 07:55 CMakeFiles\/\r\n-rw-rw-r-- 1 hoge hoge    1764 May 23 07:51 cmake_install.cmake\r\ndrwxrwxr-x 2 hoge hoge    4096 May 23 07:55 data\/\r\n-rw-rw-r-- 1 hoge hoge    7449 May 23 07:55 Makefile\r\n-rwxrwxr-x 1 hoge hoge 4526328 May 23 07:55 Mandelbrot*<\/span>\r\n<\/pre>\n
\u5b9f\u884c\uff01<\/p>\n
\r\n$ .\/Mandelbrot<\/span>\r\n<\/pre>\n
\u4e00\u77ac\u30010.1\u79d2\u3082\u7d4c\u305f\u305a\u306b\u3053\u3093\u306a\u753b\u50cf\u304c\u8868\u793a\u3055\u308c\u305f\u3002
\n\"\"<\/p>\n
\u62e1\u5927\u3059\u308b\u3002\uff08\u753b\u50cf\u4e0a\u3067\u30de\u30a6\u30b9\u30db\u30a4\u30fc\u30eb\u3092\u62bc\u3057\u306a\u304c\u3089\u4e0a\u65b9\u5411\u79fb\u52d5\uff09
\n\"\"<\/p>\n
\u66f4\u306b\u62e1\u5927\u3059\u308b\u3002
\n\"\"<\/p>\n
Zoom in\u3057\u3066\u3069\u3053\u307e\u3067\u3082\u7121\u9650\u306b\u7d9a\u304f\u5e7e\u4f55\u5b66\u6a21\u69d8\u3092\u697d\u3057\u3081\u308b\u3002<\/span><\/p>\n
\u3067\u3082…
\n3D\u30b0\u30ea\u30f3\u30b0\u30ea\u30f3\u306a\u30b2\u30fc\u30e0\u306b\u65e5\u3054\u308d\u304b\u3089\u63a5\u3057\u3066\u3044\u308b\u306e\u3067\u3001\u5168\u7136\u9a5a\u304b\u306a\u3044…<\/p>\n
\u6163\u308c\u308b\u3063\u3066\u6016\u3044\u306a\u3002
\n\u523a\u6fc0\u306b\u6c17\u3065\u304b\u306a\u304f\u306a\u3063\u3066\u3057\u307e\u3046\u3002<\/p>\n
\n","protected":false},"excerpt":{"rendered":"
\u30101\u3011\u3084\u308a\u305f\u3044\u3053\u3068 Ubuntu24.04\u306b CUDA 12.8\u3092\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u3057\u305f\u306e\u3067\u3001\u3053\u308c\u3092\u4f7f\u3063\u3066\u30d1\u30bd\u30b3\u30f3\u306b\u642d\u8f09\u3057\u3066\u3044\u308b GPU\u306e\u60c5\u5831\u3092\u8868\u793a\u3057\u3066\u307f\u305f\u3044\u3002 \u4f7f\u7528\u3059\u308b\u30d7\u30ed\u30b0\u30e9\u30e0\u306f\u6bce\u5ea6\u304a\u306a\u3058\u307f\u306e deviceQuery NV\u2026 \u7d9a\u304d\u3092\u8aad\u3080 »<\/a><\/span><\/p>\n","protected":false},"author":1,"featured_media":1705,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[8],"tags":[],"class_list":["post-1677","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-cuda"],"views":1064,"amp_enabled":true,"_links":{"self":[{"href":"https:\/\/www.dogrow.net\/nnet\/wp-json\/wp\/v2\/posts\/1677","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.dogrow.net\/nnet\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.dogrow.net\/nnet\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.dogrow.net\/nnet\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.dogrow.net\/nnet\/wp-json\/wp\/v2\/comments?post=1677"}],"version-history":[{"count":37,"href":"https:\/\/www.dogrow.net\/nnet\/wp-json\/wp\/v2\/posts\/1677\/revisions"}],"predecessor-version":[{"id":1720,"href":"https:\/\/www.dogrow.net\/nnet\/wp-json\/wp\/v2\/posts\/1677\/revisions\/1720"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.dogrow.net\/nnet\/wp-json\/wp\/v2\/media\/1705"}],"wp:attachment":[{"href":"https:\/\/www.dogrow.net\/nnet\/wp-json\/wp\/v2\/media?parent=1677"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.dogrow.net\/nnet\/wp-json\/wp\/v2\/categories?post=1677"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.dogrow.net\/nnet\/wp-json\/wp\/v2\/tags?post=1677"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}