MCPcopy Create free account

hub / github.com/NVIDIA/cuda-samples / functions

Functions2,694 in github.com/NVIDIA/cuda-samples

↓ 1 callersFunctioncomputeGold
/////////////////////////////////////////////////////////////////////////// Compute reference data set C = A * B @param C reference data, com
cpp/0_Introduction/matrixMulDynlinkJIT/matrixMul_gold.cpp:42
↓ 1 callersFunctioncompute_local_gradients
Compute a local "gradient" vector on the current GPU. For demo purposes, we initialize: grad[i] = rank + 0.001 * i Parameters
python/4_DistributedComputing/multiGPUGradientAverage/multiGPUGradientAverage.py:165
↓ 1 callersFunctionconstantInit
cpp/0_Introduction/matrixMulDrv/matrixMulDrv.cpp:92
↓ 1 callersFunctionconvert_sm_ver_to_cores
Maps SM version to the number of CUDA cores per SM. Information taken from: https://github.com/NVIDIA/cuda-samples/blob/master/Common/he
python/1_GettingStarted/deviceQuery/deviceQuery.py:80
↓ 1 callersFunctionconvolutionColumnCPU
cpp/2_Concepts_and_Techniques/convolutionSeparable/convolutionSeparable_gold.cpp:53
↓ 1 callersFunctionconvolutionColumnsCPU
cpp/2_Concepts_and_Techniques/convolutionTexture/convolutionTexture_gold.cpp:58
↓ 1 callersFunctionconvolutionRowCPU
cpp/2_Concepts_and_Techniques/convolutionSeparable/convolutionSeparable_gold.cpp:33
↓ 1 callersFunctionconvolutionRowsCPU
cpp/2_Concepts_and_Techniques/convolutionTexture/convolutionTexture_gold.cpp:33
↓ 1 callersMethodcopyCudaArrayToYUV
Copy Cuda Array in YUV 420 format to a file
cpp/8_Platform_Specific/Tegra/cudaNvSciBufMultiplanar/cudaNvSciBufMultiplanar.cpp:390
↓ 1 callersMethodcopyExtMemToMultiPlanarArrays
Map NvSciBufObj to cudaMipmappedArray
cpp/8_Platform_Specific/Tegra/cudaNvSciBufMultiplanar/cudaNvSciBufMultiplanar.cpp:231
↓ 1 callersFunctioncopyFilePath
cpp/9_CUDA_Tile/tileMatmulAutotuner/backend_common.h:197
↓ 1 callersMethodcopyYUVToCudaArrayAndFlipBits
YUV 420 image is flipped and copied to cuda Array which is mapped to nvsciBuf
cpp/8_Platform_Specific/Tegra/cudaNvSciBufMultiplanar/cudaNvSciBufMultiplanar.cpp:303
↓ 1 callersFunctioncopy_image_from_gpu_cuda_core
Copy image from GPU memory back to CPU memory. This function reverses the GPU-to-CPU transfer process: 1. Allocate pinned CPU memory for
python/1_GettingStarted/copyImageArraytoGPU/copyImageArraytoGPU.py:123
↓ 1 callersFunctioncopy_image_to_gpu_cuda_core
Copy image from CPU memory to GPU memory using optimal transfer method. This function demonstrates the recommended approach: 1. Use pinn
python/1_GettingStarted/copyImageArraytoGPU/copyImageArraytoGPU.py:75
↓ 1 callersFunctioncreateAndSetAttrList
cpp/8_Platform_Specific/Tegra/cuDLALayerwiseStatsStandalone/main.cpp:391
↓ 1 callersFunctioncreateAndSetAttrList
cpp/8_Platform_Specific/Tegra/cuDLAStandaloneMode/main.cpp:279
↓ 1 callersFunctioncreateAxes
cpp/4_CUDA_Libraries/randomFog/randomFog.cpp:194
↓ 1 callersFunctioncreateDepthBuffer
/////////////////////////////////////////////////////////////////////////// /////////////////////////////////////////////////////////////////////////
cpp/5_Domain_Specific/postProcessGL/main.cpp:654
↓ 1 callersFunctioncreateFramebuffer
/////////////////////////////////////////////////////////////////////////// /////////////////////////////////////////////////////////////////////////
cpp/5_Domain_Specific/postProcessGL/main.cpp:706
↓ 1 callersFunctioncreateGaussianMap
cpp/5_Domain_Specific/nbody/render_particles.cpp:337
↓ 1 callersFunctioncreateGaussianMap
cpp/8_Platform_Specific/Tegra/nbody_opengles/render_particles.cpp:338
↓ 1 callersFunctioncreateImage
cpp/5_Domain_Specific/simpleVulkan/VulkanBaseApp.cpp:780
↓ 1 callersFunctioncreateImage
cpp/5_Domain_Specific/simpleVulkanMMAP/VulkanBaseApp.cpp:773
↓ 1 callersFunctioncreateLinearSystem
cpp/3_CUDA_Features/jacobiCudaGraphs/main.cpp:190
↓ 1 callersFunctioncreateMeshIndexBuffer
create index buffer for rendering quad mesh
cpp/4_CUDA_Libraries/oceanFFT/oceanFFT.cpp:768
↓ 1 callersFunctioncreateMeshPositionVBO
create fixed vertex buffer to store mesh vertices
cpp/4_CUDA_Libraries/oceanFFT/oceanFFT.cpp:800
↓ 1 callersFunctioncreatePBO
/////////////////////////////////////////////////////////////////////////// Create PBO ///////////////////////////////////////////////////////////////
cpp/0_Introduction/simpleCUDA2GL/main.cpp:156
↓ 1 callersFunctioncreatePBO
/////////////////////////////////////////////////////////////////////////// Create PBO ///////////////////////////////////////////////////////////////
cpp/5_Domain_Specific/postProcessGL/main.cpp:250
↓ 1 callersFunctioncreateShaderModule
cpp/5_Domain_Specific/simpleVulkan/VulkanBaseApp.cpp:917
↓ 1 callersFunctioncreateShaderModule
cpp/5_Domain_Specific/simpleVulkanMMAP/VulkanBaseApp.cpp:914
↓ 1 callersFunctioncreateSurfaceNonNvSCI
Create NvMediaImage surface based on the input attributes. * Returns NVMEDIA_STATUS_OK on success */
cpp/8_Platform_Specific/Tegra/cudaNvSciNvMedia/nvmedia_producer.cpp:157
↓ 1 callersFunctioncreateTextureDst
/////////////////////////////////////////////////////////////////////////// /////////////////////////////////////////////////////////////////////////
cpp/0_Introduction/simpleCUDA2GL/main.cpp:424
↓ 1 callersFunctioncreateTextureDst
/////////////////////////////////////////////////////////////////////////// /////////////////////////////////////////////////////////////////////////
cpp/5_Domain_Specific/postProcessGL/main.cpp:616
↓ 1 callersFunctioncreateTextureSrc
/////////////////////////////////////////////////////////////////////////// /////////////////////////////////////////////////////////////////////////
cpp/5_Domain_Specific/postProcessGL/main.cpp:587
↓ 1 callersFunctioncreateVBO
/////////////////////////////////////////////////////////////////////////// Create VBO ///////////////////////////////////////////////////////////////
cpp/5_Domain_Specific/marchingCubes/marchingCubes.cpp:835
↓ 1 callersFunctioncross
cpp/8_Platform_Specific/Tegra/nbody_opengles/bodysystem.h:122
↓ 1 callersFunctioncross
Common/helper_math.h:1442
↓ 1 callersFunctioncudaConsumerAcquireFrame
cpp/2_Concepts_and_Techniques/EGLStream_CUDA_CrossGPU/cuda_consumer.cpp:90
↓ 1 callersFunctioncudaConsumerReleaseFrame
cpp/2_Concepts_and_Techniques/EGLStream_CUDA_CrossGPU/cuda_consumer.cpp:160
↓ 1 callersFunctioncudaConsumerTest
cpp/2_Concepts_and_Techniques/EGLStream_CUDA_Interop/cuda_consumer.cpp:44
↓ 1 callersFunctioncudaDeviceCreateConsumer
cpp/2_Concepts_and_Techniques/EGLStream_CUDA_Interop/cuda_consumer.cpp:285
↓ 1 callersFunctioncudaDeviceCreateConsumer
cpp/2_Concepts_and_Techniques/EGLStream_CUDA_CrossGPU/cuda_consumer.cpp:191
↓ 1 callersFunctioncudaDeviceCreateProducer
cpp/2_Concepts_and_Techniques/EGLStream_CUDA_Interop/cuda_producer.cpp:293
↓ 1 callersFunctioncudaDeviceCreateProducer
cpp/2_Concepts_and_Techniques/EGLStream_CUDA_CrossGPU/cuda_producer.cpp:183
↓ 1 callersFunctioncudaDeviceInit
Return a CUDA capable device or exit if one cannot be found.
cpp/7_libNVVM/simple/simple.c:56
↓ 1 callersFunctioncudaDeviceInit
Return the device compute capability in major and minor.
cpp/7_libNVVM/uvmlite/uvmlite.c:151
↓ 1 callersFunctioncudaDeviceInit
Return the device compute capability in major and minor.
cpp/7_libNVVM/device-side-launch/dsl.c:160
↓ 1 callersMethodcudaImportNvSciImage
cpp/4_CUDA_Libraries/cudaNvSci/cudaNvSci.cpp:264
↓ 1 callersMethodcudaImportNvSciRawBuf
cpp/4_CUDA_Libraries/cudaNvSci/cudaNvSci.cpp:484
↓ 1 callersMethodcudaImportNvSciSemaphore
cpp/4_CUDA_Libraries/cudaNvSci/cudaNvSci.cpp:457
↓ 1 callersFunctioncudaProducerDeinit
cpp/2_Concepts_and_Techniques/EGLStream_CUDA_Interop/cuda_producer.cpp:404
↓ 1 callersFunctioncudaProducerDeinit
cpp/2_Concepts_and_Techniques/EGLStream_CUDA_CrossGPU/cuda_producer.cpp:285
↓ 1 callersFunctioncudaProducerInit
cpp/2_Concepts_and_Techniques/EGLStream_CUDA_Interop/cuda_producer.cpp:388
↓ 1 callersFunctioncudaProducerInit
cpp/2_Concepts_and_Techniques/EGLStream_CUDA_CrossGPU/cuda_producer.cpp:227
↓ 1 callersFunctioncudaProducerPrepareFrame
cpp/2_Concepts_and_Techniques/EGLStream_CUDA_CrossGPU/cuda_producer.cpp:54
↓ 1 callersFunctioncudaProducerPresentFrame
cpp/2_Concepts_and_Techniques/EGLStream_CUDA_CrossGPU/cuda_producer.cpp:111
↓ 1 callersFunctioncudaProducerReadARGBFrame
cpp/2_Concepts_and_Techniques/EGLStream_CUDA_Interop/cuda_producer.cpp:102
↓ 1 callersFunctioncudaProducerReadYUVFrame
cpp/2_Concepts_and_Techniques/EGLStream_CUDA_Interop/cuda_producer.cpp:43
↓ 1 callersFunctioncudaProducerReturnFrame
cpp/2_Concepts_and_Techniques/EGLStream_CUDA_CrossGPU/cuda_producer.cpp:142
↓ 1 callersFunctioncudaProducerTest
cpp/2_Concepts_and_Techniques/EGLStream_CUDA_Interop/cuda_producer.cpp:133
↓ 1 callersFunctioncuda_consumer_Deinit
cpp/2_Concepts_and_Techniques/EGLStream_CUDA_CrossGPU/cuda_consumer.cpp:259
↓ 1 callersFunctioncuda_consumer_deinit
cpp/2_Concepts_and_Techniques/EGLStream_CUDA_Interop/cuda_consumer.cpp:326
↓ 1 callersFunctioncuda_consumer_init
cpp/2_Concepts_and_Techniques/EGLStream_CUDA_Interop/cuda_consumer.cpp:314
↓ 1 callersFunctioncuda_consumer_init
cpp/2_Concepts_and_Techniques/EGLStream_CUDA_CrossGPU/cuda_consumer.cpp:234
↓ 1 callersFunctioncustom_relu
Custom ReLU operation using cuda.core. This function provides a TensorFlow-native interface to custom CUDA kernels compiled with cuda.co
python/3_FrameworkInterop/customTensorFlowKernel/customTensorFlowKernel.py:231
↓ 1 callersFunctioncutEndThread
Wait for thread to finish
cpp/5_Domain_Specific/MonteCarloMultiGPU/multithreading.cpp:38
↓ 1 callersFunctioncutEndThread
Wait for thread to finish
Common/multithreading.cpp:37
↓ 1 callersFunctioncutStartThread
Create thread
cpp/5_Domain_Specific/MonteCarloMultiGPU/multithreading.cpp:32
↓ 1 callersFunctioncutWaitForThreads
Wait for multiple threads
cpp/5_Domain_Specific/MonteCarloMultiGPU/multithreading.cpp:45
↓ 1 callersMethoddebugVectors
render vectors to screen for debugging
cpp/5_Domain_Specific/smokeParticles/SmokeRenderer.cpp:571
↓ 1 callersMethoddeinit
cpp/8_Platform_Specific/Tegra/cudaNvSciBufMultiplanar/cudaNvSciBufMultiplanar.cpp:91
↓ 1 callersFunctiondeleteDepthBuffer
/////////////////////////////////////////////////////////////////////////// /////////////////////////////////////////////////////////////////////////
cpp/5_Domain_Specific/postProcessGL/main.cpp:695
↓ 1 callersFunctiondeleteFramebuffer
/////////////////////////////////////////////////////////////////////////// /////////////////////////////////////////////////////////////////////////
cpp/5_Domain_Specific/postProcessGL/main.cpp:727
↓ 1 callersFunctiondeletePBO
cpp/0_Introduction/simpleCUDA2GL/main.cpp:178
↓ 1 callersFunctiondeletePBO
cpp/5_Domain_Specific/postProcessGL/main.cpp:272
↓ 1 callersFunctiondeleteVBO
/////////////////////////////////////////////////////////////////////////// Delete VBO ///////////////////////////////////////////////////////////////
cpp/4_CUDA_Libraries/oceanFFT/oceanFFT.cpp:761
↓ 1 callersFunctiondeleteVBO
/////////////////////////////////////////////////////////////////////////// Delete VBO ///////////////////////////////////////////////////////////////
cpp/5_Domain_Specific/marchingCubes/marchingCubes.cpp:851
↓ 1 callersFunctiondemo_device_and_pinned
Use pinned host memory as a staging area for a device-side kernel. Canonical H2D / compute / D2H pattern: host (pinned) -> device -> launch
python/2_CoreConcepts/memoryResources/memoryResources.py:85
↓ 1 callersFunctiondemo_explicit_device_pool
Allocate from a user-created DeviceMemoryResource with default options.
python/2_CoreConcepts/memoryResources/memoryResources.py:176
↓ 1 callersFunctiondemo_managed
Allocate a managed (unified) buffer; kernel writes are visible on host.
python/2_CoreConcepts/memoryResources/memoryResources.py:139
↓ 1 callersFunctiondemo_reduce_lambda
reduce_into driven by a lambda.
python/2_CoreConcepts/cudaComputeLambdas/cudaComputeLambdas.py:64
↓ 1 callersFunctiondemo_reduction_tuning
Demonstrate launch config tuning for reduction (shared memory).
python/2_CoreConcepts/launchConfigTuning/launchConfigTuning.py:265
↓ 1 callersFunctiondemo_scan_custom_op
inclusive_scan with a Python function that sums only even values. This shows the same pattern that also works for reduce/transform: the Pytho
python/2_CoreConcepts/cudaComputeLambdas/cudaComputeLambdas.py:112
↓ 1 callersFunctiondemo_unary_transform_lambda
unary_transform driven by a lambda: y = x*x + 1.
python/2_CoreConcepts/cudaComputeLambdas/cudaComputeLambdas.py:89
↓ 1 callersFunctiondemo_vector_add_tuning
Demonstrate launch configuration tuning for vector addition.
python/2_CoreConcepts/launchConfigTuning/launchConfigTuning.py:194
↓ 1 callersMethoddepthSort
depth sort the particles
cpp/5_Domain_Specific/smokeParticles/ParticleSystem.cpp:133
↓ 1 callersFunctiondestroySurface
cpp/8_Platform_Specific/Tegra/cudaNvSciNvMedia/nvmedia_producer.cpp:183
↓ 1 callersFunctiondisplay
cpp/5_Domain_Specific/nbody/nbody.cpp:648
↓ 1 callersFunctiondisplay
cpp/5_Domain_Specific/fluidsGL/fluidsGL.cpp:127
↓ 1 callersMethoddisplay
cpp/2_Concepts_and_Techniques/particles/render_particles.cpp:102
↓ 1 callersFunctiondisplayImage
display image to the screen as textured quad
cpp/0_Introduction/simpleCUDA2GL/main.cpp:280
↓ 1 callersFunctiondisplayImage
display image to the screen as textured quad
cpp/5_Domain_Specific/postProcessGL/main.cpp:392
↓ 1 callersFunctiondisplayNBodySystem
cpp/5_Domain_Specific/nbody/nbody.cpp:638
↓ 1 callersFunctiondisplayNBodySystem
cpp/8_Platform_Specific/Tegra/nbody_opengles/nbody_opengles.cpp:642
↓ 1 callersFunctiondiv_zero
cpp/2_Concepts_and_Techniques/interval/boost/numeric/interval/detail/division.hpp:131
↓ 1 callersFunctiondot
cpp/8_Platform_Specific/Tegra/nbody_opengles/bodysystem.h:120
↓ 1 callersFunctiondot
Common/nvVector.h:973
↓ 1 callersMethoddownward
cpp/2_Concepts_and_Techniques/interval/boost/numeric/interval/rounding.hpp:27
↓ 1 callersFunctiondrawText
cpp/4_CUDA_Libraries/randomFog/randomFog.cpp:248
↓ 1 callersFunctiondumpBuffer
cpp/5_Domain_Specific/marchingCubes/marchingCubes.cpp:337
← previousnext →601–700 of 2,694, ranked by callers