Home
last modified time | relevance | path

Searched refs:CUDA (Results 1 – 25 of 39) sorted by relevance

12

/third_party/vk-gl-cts/external/vulkan-docs/src/chapters/VK_NV_cuda_kernel_launch/
Dmodule.adoc6 == CUDA Modules
10 === Creating a CUDA Module
12 [open,refpage='VkCudaModuleNV',desc='Opaque handle to a CUDA module object',type='handles']
14 CUDA modules must: contain some kernel code and must: expose at least one
17 CUDA modules are represented by sname:VkCudaModuleNV handles:
22 [open,refpage='vkCreateCudaModuleNV',desc='Creates a new CUDA module object',type='protos']
24 To create a CUDA module, call:
34 resulting CUDA module object is returned.
36 Once a CUDA module has been created, the application may: create the
42 [open,refpage='VkCudaModuleCreateInfoNV',desc='Structure specifying the parameters to create a CUDA
[all …]
Ddispatch.adoc6 == Dispatch Command for CUDA PTX Kernels
14 For mode information, please refer to the CUDA toolkit documentation at
17 Prior to using this command, you must: initialize a CUDA module, and create
20 See <<cuda-modules, CUDA Modules>>.
22 The dispatching of a CUDA kernel is recorded into a command buffer, and when
30 To record a CUDA kernel launch, call:
51 [open,refpage='VkCudaLaunchInfoNV',desc='Structure specifying the parameters to launch a CUDA kerne…
54 the CUDA-Driver function
58 Execution Control] of CUDA Driver API.
67 * pname:function is the CUDA-Driver handle to the function being launched.
[all …]
/third_party/skia/third_party/externals/egl-registry/extensions/NV/
DEGL_NV_device_cuda.txt43 EGL and CUDA both have the capability to drive multiple devices,
46 This extension defines a mapping from an EGL device to a CUDA device
67 Add a new section 2.1.3 (CUDA Devices) after 2.1.2 (Devices)
69 "Somewhat analogous to an EGL device, a CUDA device establishes a
70 namespace for CUDA operations. In the CUDA API, such a device is
71 represented by a C int. For more details, see the CUDA
80 success, EGL_TRUE is returned, and a valid CUDA device handle
82 is compatible with CUDA API functions."
DEGL_NV_cuda_event.txt46 This extension allows creating an EGL sync object linked to a CUDA
56 A pointer to type cudaEvent_t, defined in the CUDA header files, may
86 OpenCL object to which the sync object is linked. Likewise, a <CUDA
87 event sync object> reflects the status of a corresponding CUDA
89 results between EGL and the CUDA and OpenCL client APIs (see
93 completion of the corresponding linked CUDA or OpenCL event object."
98 "Section 3.8.1.X Creating CUDA Event Sync Objects
100 If <type> is EGL_SYNC_CUDA_EVENT_NV, a CUDA event sync object is
103 The object must be properly initialized and recorded by the CUDA API
104 (using cudaCreateEvent and cudaEventRecord), and the CUDA device
[all …]
/third_party/EGL/extensions/NV/
DEGL_NV_device_cuda.txt43 EGL and CUDA both have the capability to drive multiple devices,
46 This extension defines a mapping from an EGL device to a CUDA device
67 Add a new section 2.1.3 (CUDA Devices) after 2.1.2 (Devices)
69 "Somewhat analogous to an EGL device, a CUDA device establishes a
70 namespace for CUDA operations. In the CUDA API, such a device is
71 represented by a C int. For more details, see the CUDA
80 success, EGL_TRUE is returned, and a valid CUDA device handle
82 is compatible with CUDA API functions."
DEGL_NV_cuda_event.txt51 This extension allows creating an EGL sync object linked to a CUDA
61 A pointer to type cudaEvent_t, defined in the CUDA header files, may
88 Likewise, a <CUDA event sync object> reflects the status of a
89 corresponding CUDA object. Waiting on this type of sync object is
91 CUDA event object.
96 Section 3.8.1.X Creating and Signaling CUDA Event Sync Objects
98 If <type> is EGL_SYNC_CUDA_EVENT_NV, a CUDA event sync object is
108 must be properly initialized and recorded by the CUDA API (using
109 cudaEventCreate and cudaEventRecord), and the CUDA device
115 CUDA device used to create the CUDA event matches the
[all …]
/third_party/vk-gl-cts/external/vulkan-docs/src/appendices/
DVK_NV_cuda_kernel_launch.adoc18 This extension targets deployment of existing CUDA kernels via Vulkan, with
21 and CUDA contexts.
22 However, we do encourage actual development using the native CUDA runtime
25 The application will first have to create a CUDA module using
26 flink:vkCreateCudaModuleNV then create the CUDA function entry point with
34 the CUDA module handle with flink:vkDestroyCudaFunctionNV and
46 initialization of the CUDA module.
/third_party/ffmpeg/libavcodec/
Dhwconfig.h72 HW_CONFIG_HWACCEL(1, 1, 0, CUDA, CUDA, ff_ ## codec ## _nvdec_hwaccel)
Dnvenc.c69 HW_CONFIG_ENCODER_FRAMES(CUDA, CUDA),
70 HW_CONFIG_ENCODER_DEVICE(NONE, CUDA),
/third_party/skia/third_party/externals/swiftshader/third_party/llvm-10.0/llvm/lib/Target/NVPTX/
DNVPTXLowerArgs.cpp209 if (TM && TM->getDrvInterface() == NVPTX::CUDA) { in runOnKernelFunction()
233 else if (TM && TM->getDrvInterface() == NVPTX::CUDA) in runOnKernelFunction()
DNVPTXSubtarget.cpp58 if (TM.getDrvInterface() == NVPTX::CUDA) in hasImageHandles()
DNVPTX.h54 CUDA enumerator
DNVPTXReplaceImageHandles.cpp148 if (TM.getDrvInterface() == NVPTX::CUDA) { in findIndexForHandle()
DNVPTXTargetMachine.cpp124 drvInterface = NVPTX::CUDA; in NVPTXTargetMachine()
DNVPTXAsmPrinter.h294 NVPTX::CUDA) {} in NVPTXAsmPrinter()
DNVPTXAsmPrinter.cpp966 if (static_cast<NVPTXTargetMachine &>(TM).getDrvInterface() == NVPTX::CUDA) { in emitLinkageDirective()
1494 NVPTX::CUDA) { in emitFunctionParamList()
/third_party/json/tests/cuda_example/
DCMakeLists.txt2 project(json_cuda LANGUAGES CUDA)
/third_party/skia/third_party/externals/egl-registry/extensions/EXT/
DEGL_EXT_sync_reuse.txt308 If EGL_NV_cuda_event is present, then for CUDA event sync objects, the
310 as eglCreateSync. The current CUDA event handle is evaluated at the time
312 the CUDA object with cudaEventRecord has no effect on the sync object
314 unsignaled will cause the CUDA object to be reevaluated.
/third_party/EGL/extensions/EXT/
DEGL_EXT_sync_reuse.txt308 If EGL_NV_cuda_event is present, then for CUDA event sync objects, the
310 as eglCreateSync. The current CUDA event handle is evaluated at the time
312 the CUDA object with cudaEventRecord has no effect on the sync object
314 unsignaled will cause the CUDA object to be reevaluated.
/third_party/skia/third_party/externals/oboe/samples/RhythmGame/third_party/glm/gtx/
Dfast_square_root.inl25 # ifdef __CUDACC__ // Wordaround for a CUDA compiler bug up to CUDA6
/third_party/skia/third_party/externals/swiftshader/third_party/llvm-10.0/llvm/include/llvm/ADT/
DTriple.h181 CUDA, // NVIDIA CUDA enumerator
/third_party/mindspore/
DREADME_CN.md82 | GPU CUDA 10.1 | Ubuntu-x86 | ✔️ |
DREADME.md85 | GPU CUDA 10.1 | Ubuntu-x86 | ✔️ |
/third_party/skia/third_party/externals/swiftshader/third_party/llvm-10.0/llvm/lib/Support/
DTriple.cpp187 case CUDA: return "cuda"; in getOSTypeName()
509 .StartsWith("cuda", Triple::CUDA) in parseOS()
/third_party/ffmpeg/
DChangelog529 - add support for using clang to compile CUDA kernels
641 - scale_cuda CUDA based video scale filter
679 - CUDA thumbnail filter
742 - CUDA CUVID H.263/VP8/VP9/10 bit HEVC (Dithered) Decoding
789 - libnpp/CUDA-accelerated format conversion and scaling
802 - CUDA CUVID H264/HEVC decoder

12