MCPcopy Create free account

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

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

↓ 1 callersMethod_selectDemo
cpp/5_Domain_Specific/nbody/nbody.cpp:392
↓ 1 callersMethod_selectDemo
cpp/8_Platform_Specific/Tegra/nbody_opengles/nbody_opengles.cpp:365
↓ 1 callersFunction_time_call
(fn, *args, **kwargs)
python/2_CoreConcepts/processCheckpoint/processCheckpoint.py:120
↓ 1 callersFunction_validate_threads_arg
(threads)
python/2_CoreConcepts/reductionMultiBlockCG/reductionMultiBlockCG.py:78
↓ 1 callersFunction_validate_threads_per_block
(threads_per_block)
python/2_CoreConcepts/reduction/reduction.py:207
↓ 1 callersFunctionadd4
cpp/5_Domain_Specific/bilateralFilter/bilateralFilter_cpu.cpp:97
↓ 1 callersFunctionaddFileToProgram
cpp/7_libNVVM/ptxgen/ptxgen.c:80
↓ 1 callersMethodadd_down
cpp/2_Concepts_and_Techniques/interval/cuda_interval_rounded_arith.h:61
↓ 1 callersMethodadd_up
cpp/2_Concepts_and_Techniques/interval/cuda_interval_rounded_arith.h:63
↓ 1 callersFunctionadjustGridSize
cpp/5_Domain_Specific/MonteCarloMultiGPU/MonteCarloMultiGPU.cpp:82
↓ 1 callersFunctionadjustProblemSize
Utility function to tweak problem size for small GPUs
cpp/5_Domain_Specific/MonteCarloMultiGPU/MonteCarloMultiGPU.cpp:64
↓ 1 callersMethodalloc
cpp/5_Domain_Specific/smokeParticles/GpuArray.h:117
↓ 1 callersFunctionasin
cpp/2_Concepts_and_Techniques/interval/boost/numeric/interval/transc.hpp:108
↓ 1 callersFunctionattachShader
Attach shader to a program
cpp/4_CUDA_Libraries/oceanFFT/oceanFFT.cpp:827
↓ 1 callersFunctionautoTest
cpp/5_Domain_Specific/fluidsGL/fluidsGL.cpp:175
↓ 1 callersFunctionautoTest
cpp/8_Platform_Specific/Tegra/fluidsGLES/fluidsGLES.cpp:409
↓ 1 callersFunctionautotuner
cpp/9_CUDA_Tile/tileMatmulAutotuner/matmul_autotuner.cpp:170
↓ 1 callersFunctionaverage_gradients
Average gradients across all MPI ranks using host-staging Allreduce. Steps: 1. Copy local gradients from GPU to CPU (NumPy). 2. Perf
python/4_DistributedComputing/multiGPUGradientAverage/multiGPUGradientAverage.py:211
↓ 1 callersMethodbackward
Backward pass: compute gradient. For y = x², the derivative is dy/dx = 2x Therefore: grad_x = grad_output * 2x Para
python/3_FrameworkInterop/customPyTorchKernel/customPyTorchKernel.py:191
↓ 1 callersFunctionbaseNameWithoutExtension
cpp/9_CUDA_Tile/tileMatmulAutotuner/backend_common.h:161
↓ 1 callersMethodbeginSceneRender
render scene depth to texture (this is to ensure that particle are correctly occluded in the low-resolution render buffer)
cpp/5_Domain_Specific/smokeParticles/SmokeRenderer.cpp:412
↓ 1 callersMethodbeginSingleTimeCommands
cpp/5_Domain_Specific/simpleVulkan/VulkanBaseApp.cpp:195
↓ 1 callersMethodbeginSingleTimeCommands
cpp/5_Domain_Specific/simpleVulkanMMAP/VulkanBaseApp.cpp:189
↓ 1 callersFunctionbench_iters
cpp/9_CUDA_Tile/Benchmark_Common/benchmark.h:57
↓ 1 callersFunctionbenchmark
cpp/5_Domain_Specific/recursiveGaussian/recursiveGaussian.cpp:353
↓ 1 callersFunctionbenchmarkReduce
cpp/2_Concepts_and_Techniques/reduction/reduction.cpp:247
↓ 1 callersFunctionbenchmark_cuda_compute
Benchmark cuda.compute.reduce_into() using cuda.core events.
python/2_CoreConcepts/parallelReduction/parallelReduction.py:246
↓ 1 callersFunctionbenchmark_custom
Benchmark custom reduction kernel using cuda.core events.
python/2_CoreConcepts/parallelReduction/parallelReduction.py:204
↓ 1 callersFunctionbinomialOptionsCPU
cpp/5_Domain_Specific/binomialOptions/binomialOptions_gold.cpp:85
↓ 1 callersFunctionblit2DImage
cpp/8_Platform_Specific/Tegra/cudaNvSciNvMedia/nvmedia_producer.cpp:185
↓ 1 callersFunctionblit2DImageNonNvSCI
cpp/8_Platform_Specific/Tegra/cudaNvSciNvMedia/nvmedia_producer.cpp:265
↓ 1 callersFunctionblur_image_unified_memory
Blur image on GPU using unified memory with cuda.core. This function demonstrates: 1. Allocate managed memory using ManagedMemoryResourc
python/1_GettingStarted/blurImageUnifiedMemory/blurImageUnifiedMemory.py:115
↓ 1 callersFunctionbuffer_to_numpy
Create numpy view of cuda.core Buffer via DLPack.
python/2_CoreConcepts/streamingCopyComputeOverlap/streamingCopyComputeOverlap.py:82
↓ 1 callersFunctionbuildKernel
cpp/7_libNVVM/uvmlite/uvmlite.c:200
↓ 1 callersFunctionbuildKernel
cpp/7_libNVVM/device-side-launch/dsl.c:191
↓ 1 callersFunctionbuild_graph
Capture the 3-stage pipeline into a CUDA graph and return it.
python/2_CoreConcepts/cudaGraphs/cudaGraphs.py:109
↓ 1 callersFunctionbuild_kernel_source
Generate a specialized matmul + epilogue CUDA kernel.
python/2_CoreConcepts/persistentProgramCache/persistentProgramCache.py:143
↓ 1 callersFunctioncache_clear
(cache_dir: Path)
python/2_CoreConcepts/persistentProgramCache/persistentProgramCache.py:152
↓ 1 callersMethodcalcVectors
calculate vectors for half-angle slice rendering
cpp/5_Domain_Specific/smokeParticles/SmokeRenderer.cpp:174
↓ 1 callersFunctioncalculateAverageAndStdDev
cpp/6_Performance/UnifiedMemoryPerf/helperFunctions.cpp:165
↓ 1 callersFunctioncalculateStdDevBandwidth
cpp/6_Performance/UnifiedMemoryPerf/helperFunctions.cpp:183
↓ 1 callersFunctionceilDiv
cpp/9_CUDA_Tile/tileMatmulAutotuner/backend_common.h:78
↓ 1 callersFunctioncheckCudaCapabilities
General check for CUDA GPU SM Capabilities
Common/helper_cuda.h:964
↓ 1 callersFunctioncheckGLErrors
check for OpenGL errors
cpp/5_Domain_Specific/nbody/nbody.cpp:545
↓ 1 callersFunctioncheck_ipc_support
Return True if this device/platform supports CUDA IPC memory pools.
python/4_DistributedComputing/ipcMemoryPool/ipcMemoryPool.py:81
↓ 1 callersFunctioncheckbuf
cpp/2_Concepts_and_Techniques/EGLStream_CUDA_Interop/cuda_consumer.cpp:256
↓ 1 callersFunctionchildProcess
cpp/3_CUDA_Features/memMapIPCDrv/memMapIpc.cpp:306
↓ 1 callersFunctionchooseSwapExtent
cpp/5_Domain_Specific/simpleVulkan/VulkanBaseApp.cpp:673
↓ 1 callersFunctionchooseSwapExtent
cpp/5_Domain_Specific/simpleVulkanMMAP/VulkanBaseApp.cpp:666
↓ 1 callersFunctionchooseSwapPresentMode
cpp/5_Domain_Specific/simpleVulkan/VulkanBaseApp.cpp:657
↓ 1 callersFunctionchooseSwapPresentMode
cpp/5_Domain_Specific/simpleVulkanMMAP/VulkanBaseApp.cpp:650
↓ 1 callersFunctionchooseSwapSurfaceFormat
cpp/5_Domain_Specific/simpleVulkan/VulkanBaseApp.cpp:641
↓ 1 callersFunctionchooseSwapSurfaceFormat
cpp/5_Domain_Specific/simpleVulkanMMAP/VulkanBaseApp.cpp:634
↓ 1 callersFunctioncleanUp
cpp/8_Platform_Specific/Tegra/cuDLALayerwiseStatsStandalone/main.cpp:110
↓ 1 callersFunctioncleanUp
cpp/8_Platform_Specific/Tegra/cuDLAStandaloneMode/main.cpp:108
↓ 1 callersFunctioncleanup
cpp/5_Domain_Specific/volumeFiltering/volumeFiltering.cpp:518
↓ 1 callersFunctioncleanup
cpp/5_Domain_Specific/smokeParticles/particleDemo.cpp:170
↓ 1 callersFunctioncleanup
cpp/5_Domain_Specific/volumeRender/volumeRender.cpp:390
↓ 1 callersFunctioncleanup
cpp/5_Domain_Specific/recursiveGaussian/recursiveGaussian.cpp:202
↓ 1 callersFunctioncleanup
cpp/5_Domain_Specific/marchingCubes/marchingCubes.cpp:524
↓ 1 callersFunctioncleanup
cpp/5_Domain_Specific/fluidsGL/fluidsGL.cpp:340
↓ 1 callersFunctioncleanup
cpp/8_Platform_Specific/Tegra/cudaNvSciNvMedia/main.cpp:63
↓ 1 callersFunctioncleanupNvMedia
cpp/8_Platform_Specific/Tegra/cudaNvSciNvMedia/nvmedia_producer.cpp:333
↓ 1 callersFunctioncleanupNvSciBuf
cpp/8_Platform_Specific/Tegra/cudaNvSciNvMedia/nvsci_setup.cpp:142
↓ 1 callersFunctioncleanupNvSciSync
cpp/8_Platform_Specific/Tegra/cudaNvSciNvMedia/nvsci_setup.cpp:149
↓ 1 callersFunctioncolorRamp
create a color ramp
cpp/2_Concepts_and_Techniques/particles/particleSystem.cpp:101
↓ 1 callersMethodcompareBin2BinFloat
Common/rendercheck_gl.h:424
↓ 1 callersFunctioncompareFiles
Compare input and generated image files
cpp/8_Platform_Specific/Tegra/cudaNvSciBufMultiplanar/cudaNvSciBufMultiplanar.cpp:41
↓ 1 callersFunctioncompileASMShader
cpp/2_Concepts_and_Techniques/boxFilter/boxFilter.cpp:340
↓ 1 callersFunctioncompileASMShader
cpp/2_Concepts_and_Techniques/imageDenoising/imageDenoisingGL.cpp:347
↓ 1 callersFunctioncompileASMShader
cpp/5_Domain_Specific/bicubicTexture/bicubicTexture.cpp:579
↓ 1 callersFunctioncompileASMShader
cpp/5_Domain_Specific/bilateralFilter/bilateralFilter.cpp:373
↓ 1 callersFunctioncompileFile
cpp/9_CUDA_Tile/tileMatmulAutotuner/matmul_autotuner.cpp:129
↓ 1 callersFunctioncompileFileToCUBIN
Common/nvrtc_helper.h:50
↓ 1 callersFunctioncompileFileWithNVCC
cpp/9_CUDA_Tile/tileMatmulAutotuner/backend_nvcc.h:40
↓ 1 callersFunctioncompileFileWithNVRTC
cpp/9_CUDA_Tile/tileMatmulAutotuner/backend_nvrtc.h:115
↓ 1 callersFunctioncompileGLSLprogram
/////////////////////////////////////////////////////////////////////////// /////////////////////////////////////////////////////////////////////////
cpp/0_Introduction/simpleCUDA2GL/main.cpp:541
↓ 1 callersFunctioncompileGLSLprogram
/////////////////////////////////////////////////////////////////////////// /////////////////////////////////////////////////////////////////////////
cpp/5_Domain_Specific/postProcessGL/main.cpp:824
↓ 1 callersFunctioncompileTileIRToCubin
cpp/9_CUDA_Tile/tileMatmulAutotuner/backend_nvrtc.h:51
↓ 1 callersFunctioncompile_fill_kernel
(device: Device)
python/2_CoreConcepts/processCheckpoint/processCheckpoint.py:102
↓ 1 callersFunctioncompile_kernel
Compile the reduction kernel for the given device.
python/2_CoreConcepts/parallelReduction/parallelReduction.py:114
↓ 1 callersFunctioncompile_kernel
Compile a CUDA kernel using cuda.core.Program.
python/2_CoreConcepts/launchConfigTuning/launchConfigTuning.py:115
↓ 1 callersFunctioncompile_kernels
(device: Device)
python/2_CoreConcepts/greenContext/greenContext.py:320
↓ 1 callersFunctioncompile_or_load_kernel
Compile the generated kernel or load its CUBIN bytes from cache.
python/2_CoreConcepts/persistentProgramCache/persistentProgramCache.py:157
↓ 1 callersFunctioncompilerBackendName
cpp/9_CUDA_Tile/tileMatmulAutotuner/backend_common.h:74
↓ 1 callersFunctioncomputeArch
The libNVVM architecture string for a compute capability, e.g. 10.0 becomes "compute_100".
cpp/7_libNVVM/cuda-c-linking/cuda-c-linking.cpp:91
↓ 1 callersFunctioncomputeFPS
Calculate the Frames per second and print in the title bar
cpp/2_Concepts_and_Techniques/boxFilter/boxFilter.cpp:144
↓ 1 callersFunctioncomputeFPS
cpp/2_Concepts_and_Techniques/particles/particles.cpp:233
↓ 1 callersFunctioncomputeFPS
cpp/2_Concepts_and_Techniques/imageDenoising/imageDenoisingGL.cpp:117
↓ 1 callersFunctioncomputeFPS
cpp/2_Concepts_and_Techniques/FunctionPointers/FunctionPointers.cpp:108
↓ 1 callersFunctioncomputeFPS
cpp/0_Introduction/simpleTexture3D/simpleTexture3D.cpp:112
↓ 1 callersFunctioncomputeFPS
cpp/3_CUDA_Features/bindlessTexture/bindlessTexture.cpp:104
↓ 1 callersFunctioncomputeFPS
cpp/5_Domain_Specific/volumeFiltering/volumeFiltering.cpp:115
↓ 1 callersFunctioncomputeFPS
cpp/5_Domain_Specific/Mandelbrot/Mandelbrot.cpp:186
↓ 1 callersFunctioncomputeFPS
cpp/5_Domain_Specific/volumeRender/volumeRender.cpp:142
↓ 1 callersFunctioncomputeFPS
cpp/5_Domain_Specific/bicubicTexture/bicubicTexture.cpp:176
↓ 1 callersFunctioncomputeFPS
cpp/5_Domain_Specific/recursiveGaussian/recursiveGaussian.cpp:135
↓ 1 callersFunctioncomputeFPS
cpp/5_Domain_Specific/bilateralFilter/bilateralFilter.cpp:144
↓ 1 callersFunctioncomputeFPS
cpp/5_Domain_Specific/SobelFilter/SobelFilter.cpp:110
↓ 1 callersFunctioncomputeFPS
cpp/5_Domain_Specific/marchingCubes/marchingCubes.cpp:290
← previousnext →501–600 of 2,694, ranked by callers