在当前不可调试的 GPU 上创建了 CUDA 上下文 [英] A CUDA context was created on a GPU that is not currently debuggable
本文介绍了在当前不可调试的 GPU 上创建了 CUDA 上下文的处理方法，对大家解决问题具有一定的参考价值，需要的朋友们下面随着小编来一起学习吧！
问题描述
当我开始 cuda 调试时，Nsight 返回这个错误:
<块引用>在当前不可调试的 GPU 上创建了 CUDA 上下文.断点将被禁用.
适配器:GeForce GT 720M
这是我的系统和 CUDA 信息.
请注意，已安装最新版本的 CUDA 和 Nsight.
我搜索了这个问题，但找不到我的答案.非常感谢.
<块引用>报告信息UnixTime 生成 1490538033操作系统信息计算机名称 DESKTOP-OLFM6NTNetBIOS 名称 DESKTOP-OLFM6NT操作系统名称 Windows 10 ProGetVersionExdwMajor 版本 10dwMinorVersion 0dwBuildNumber 14393dwPlatformId 2wServicePackMajor 0wServicePackMinor 0wSuiteMask 256wProductType 工作站获取产品信息 48获取本机系统信息wProcessorArchitecture x64dwPageSize 4096lpMinimumApplicationAddress 65536lpMaximumApplicationAddress 140737488289791dwActiveProcessorMask 15dwNumberOfProcessors 4dwAllocationGranularity 65536wProcessorLevel 6wProcessorRevision 17665枚举显示设备显示装置设备名称 \.DISPLAY1DeviceString 英特尔(R) 高清显卡系列州旗 5设备ID PCIVEN_8086&DEV_0A16&SUBSYS_397817AA&REV_09DeviceKey RegistryMachineSystemCurrentControlSetControlVideo{A9611CC2-95E1-4DAE-9937-60210AFEDCE0} 000监视器设备名称 \.DISPLAY1Monitor0DeviceString 通用 PnP 监视器州旗 3设备 ID 监视器CMN15B6{4d36e96e-e325-11ce-bfc1-08002be10318} 003DeviceKey RegistryMachineSystemCurrentControlSetControlClass{4d36e96e-e325-11ce-bfc1-08002be10318} 003显示装置设备名称 \.DISPLAY2DeviceString 英特尔(R) 高清显卡系列状态标志 1设备ID PCIVEN_8086&DEV_0A16&SUBSYS_397817AA&REV_09DeviceKey RegistryMachineSystemCurrentControlSetControlVideo{A9611CC2-95E1-4DAE-9937-60210AFEDCE0} 001监视器设备名称 \.DISPLAY2Monitor0DeviceString 通用 PnP 监视器州旗 3设备 ID MONITORSAM04FD{4d36e96e-e325-11ce-bfc1-08002be10318} 004DeviceKey RegistryMachineSystemCurrentControlSetControlClass{4d36e96e-e325-11ce-bfc1-08002be10318} 004显示装置设备名称 \.DISPLAY3DeviceString 英特尔(R) 高清显卡系列状态标志 0设备ID PCIVEN_8086&DEV_0A16&SUBSYS_397817AA&REV_09DeviceKey RegistryMachineSystemCurrentControlSetControlVideo{A9611CC2-95E1-4DAE-9937-60210AFEDCE0} 002GlobalMemoryStatusExdwMemoryLoad 34ullTotalPhys 8486227968ullAvailPhys 5588660224ullTotalPageFile 13854937088ullAvailPageFile 10756182016ullTotalVirtual 140737488224256ullAvailVirtual 140737442308096处理器信息0名称 Intel(R) Core(TM) i7-4500U CPU @ 1.80GHz时钟速度 (MHz) 23941名称 Intel(R) Core(TM) i7-4500U CPU @ 1.80GHz时钟速度 (MHz) 23942名称 Intel(R) Core(TM) i7-4500U CPU @ 1.80GHz时钟速度 (MHz) 23943名称 Intel(R) Core(TM) i7-4500U CPU @ 1.80GHz时钟速度 (MHz) 2394NvAPIIsMSHybridGraphics 真显示驱动程序版本驱动程序版本 37609变更清单 0BuildBranchString r376_06默认 AdapterString GeForce GT 720MDisplayDriverCompileType 发布NvDebugApiWDDM 设备图形处理器名称 GeForce GT 720M建筑费米架构编号 208架构实现 7架构修订版 162GPC 数量 1TPC 数量 2SM 数量 2每 SM 48 的经纱每经线的车道数 32注册文件大小 32768每个 SM 8 的最大 CTA每个 CTA 的最大共享内存大小(字节)49152SM 修订版 131073FB PA 数量 6每个 LTC 的 LT 数量 2RMGpuId 1024RM 设备CUDACUDA 设备名称 GeForce GT 720M驱动器 WDDM设备索引 0GPU 家族 GF117RMGpuId 1024计算专业 2计算辅修 1MAX_THREADS_PER_BLOCK 1024MAX_BLOCK_DIM_X 1024MAX_BLOCK_DIM_Y 1024MAX_BLOCK_DIM_Z 64MAX_GRID_DIM_X 65535MAX_GRID_DIM_Y 65535MAX_GRID_DIM_Z 65535MAX_SHARED_MEMORY_PER_BLOCK 49152TOTAL_CONSTANT_MEMORY 65536WARP_SIZE 32MAX_PITCH 2147483647MAX_REGISTERS_PER_BLOCK 32768CLOCK_RATE 1550000TEXTURE_ALIGNMENT 512GPU_OVERLAP 1MULTIPROCESSOR_COUNT 2KERNEL_EXEC_TIMEOUT 0综合 0CAN_MAP_HOST_MEMORY 1计算模式 0MAXIMUM_TEXTURE1D_WIDTH 65536MAXIMUM_TEXTURE2D_WIDTH 65536MAXIMUM_TEXTURE2D_HEIGHT 65535MAXIMUM_TEXTURE3D_WIDTH 2048MAXIMUM_TEXTURE3D_HEIGHT 2048MAXIMUM_TEXTURE3D_DEPTH 2048MAXIMUM_TEXTURE2D_LAYERED_WIDTH 16384MAXIMUM_TEXTURE2D_LAYERED_HEIGHT 16384MAXIMUM_TEXTURE2D_LAYERED_LAYERS 2048SURFACE_ALIGNMENT 512CONCURRENT_KERNELS 1ECC_ENABLED 0PCI_BUS_ID 4PCI_DEVICE_ID 0TCC_DRIVER 0MEMORY_CLOCK_RATE 900000GLOBAL_MEMORY_BUS_WIDTH 64L2_CACHE_SIZE 131072MAX_THREADS_PER_MULTIPROCESSOR 1536ASYNC_ENGINE_COUNT 1UNIFIED_ADDRESSING 1MAXIMUM_TEXTURE1D_LAYERED_WIDTH 16384MAXIMUM_TEXTURE1D_LAYERED_LAYERS 2048CAN_TEX2D_GATHER 1MAXIMUM_TEXTURE2D_GATHER_WIDTH 16384MAXIMUM_TEXTURE2D_GATHER_HEIGHT 16384MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE 0MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE 0MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE 0PCI_DOMAIN_ID 0TEXTURE_PITCH_ALIGNMENT 32MAXIMUM_TEXTURECUBEMAP_WIDTH 16384MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH 16384MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS 2046MAXIMUM_SURFACE1D_WIDTH 65536MAXIMUM_SURFACE2D_WIDTH 65536MAXIMUM_SURFACE2D_HEIGHT 32768MAXIMUM_SURFACE3D_WIDTH 65536MAXIMUM_SURFACE3D_HEIGHT 32768MAXIMUM_SURFACE3D_DEPTH 2048MAXIMUM_SURFACE1D_LAYERED_WIDTH 65536MAXIMUM_SURFACE1D_LAYERED_LAYERS 2048MAXIMUM_SURFACE2D_LAYERED_WIDTH 65536MAXIMUM_SURFACE2D_LAYERED_HEIGHT 32768MAXIMUM_SURFACE2D_LAYERED_LAYERS 2048MAXIMUM_SURFACECUBEMAP_WIDTH 32768MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH 32768MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS 2046MAXIMUM_TEXTURE1D_LINEAR_WIDTH 134217728MAXIMUM_TEXTURE2D_LINEAR_WIDTH 65000MAXIMUM_TEXTURE2D_LINEAR_HEIGHT 65000MAXIMUM_TEXTURE2D_LINEAR_PITCH 1048544MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH 16384MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT 16384MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH 16384STREAM_PRIORITIES_SUPPORTED 0GLOBAL_L1_CACHE_SUPPORTED 1LOCAL_L1_CACHE_SUPPORTED 1MAX_SHARED_MEMORY_PER_MULTIPROCESSOR 49152MAX_REGISTERS_PER_MULTIPROCESSOR 32768MANAGED_MEMORY 0MULTI_GPU_BOARD 0MULTI_GPU_BOARD_GROUP_ID 0HOST_NATIVE_ATOMIC_SUPPORTED 0SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO 12PAGEABLE_MEMORY_ACCESS 0并发_管理_访问 0COMPUTE_PREEMPTION_SUPPORTED 0CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM 0DISPLAY_NAME GeForce GT 720MCOMPUTE_CAPABILITY_MAJOR 2COMPUTE_CAPABILITY_MINOR 1TOTAL_MEMORY 2147483648RAM_TYPE 7RAM_LOCATION 1GPU_PCI_DEVICE_ID 289411294GPU_PCI_SUB_SYSTEM_ID 939530154GPU_PCI_REVISION_ID 161GPU_PCI_EXT_DEVICE_ID 4416GPU_PCI_EXT_GEN 1GPU_PCI_EXT_GPU_GEN 1GPU_PCI_EXT_GPU_LINK_RATE 5000GPU_PCI_EXT_GPU_LINK_WIDTH 8GPU_PCI_EXT_DOWNSTREAM_LINK_RATE 5000GPU_PCI_EXT_DOWNSTREAM_LINK_WIDTH 4 解决方案
您的 GT 720m 是计算能力 2.1 设备(请参阅 这里).
尝试在同时支持(托管)显示器的 GPU 上调试 CUDA 代码(例如设置断点)需要计算能力 3.5 或更高版本的设备，以支持抢占.
您的设备不符合该要求，因此由于您的 GPU 托管您的笔记本电脑显示器，因此它不能用于在 CUDA 代码中设置断点.
另请注意，最新版本的 Nsight VSE(目前为 5.2)具有 正式放弃对 Fermi GPU 的支持(您的是 Fermi GPU):
<块引用>注意:Nsight™ Visual Studio Edition 5.2 或更高版本不再支持 Fermi 系列 GPU 和旧系列.
When i start cuda debugging, Nsight return this error:
A CUDA context was created on a GPU that is not currently debuggable. Breakpoints will be disabled.
Adapter: GeForce GT 720M
This is my system and CUDA information.
Please note that last version of CUDA and Nsight are installed.
I searched this issue and could not find my answer. Thank you so much.
Report Information UnixTime Generated 1490538033 OS Information Computer Name DESKTOP-OLFM6NT NetBIOS Name DESKTOP-OLFM6NT OS Name Windows 10 Pro GetVersionEx dwMajorVersion 10 dwMinorVersion 0 dwBuildNumber 14393 dwPlatformId 2 wServicePackMajor 0 wServicePackMinor 0 wSuiteMask 256 wProductType Workstation GetProductInfo 48 GetNativeSystemInfo wProcessorArchitecture x64 dwPageSize 4096 lpMinimumApplicationAddress 65536 lpMaximumApplicationAddress 140737488289791 dwActiveProcessorMask 15 dwNumberOfProcessors 4 dwAllocationGranularity 65536 wProcessorLevel 6 wProcessorRevision 17665 EnumDisplayDevices Display Device DeviceName \.DISPLAY1 DeviceString Intel(R) HD Graphics Family StateFlags 5 DeviceID PCIVEN_8086&DEV_0A16&SUBSYS_397817AA&REV_09 DeviceKey RegistryMachineSystemCurrentControlSetControlVideo{A9611CC2-95E1-4DAE-9937-60210AFEDCE0} 000 Monitor DeviceName \.DISPLAY1Monitor0 DeviceString Generic PnP Monitor StateFlags 3 DeviceID MONITORCMN15B6{4d36e96e-e325-11ce-bfc1-08002be10318} 003 DeviceKey RegistryMachineSystemCurrentControlSetControlClass{4d36e96e-e325-11ce-bfc1-08002be10318} 003 Display Device DeviceName \.DISPLAY2 DeviceString Intel(R) HD Graphics Family StateFlags 1 DeviceID PCIVEN_8086&DEV_0A16&SUBSYS_397817AA&REV_09 DeviceKey RegistryMachineSystemCurrentControlSetControlVideo{A9611CC2-95E1-4DAE-9937-60210AFEDCE0} 001 Monitor DeviceName \.DISPLAY2Monitor0 DeviceString Generic PnP Monitor StateFlags 3 DeviceID MONITORSAM04FD{4d36e96e-e325-11ce-bfc1-08002be10318} 004 DeviceKey RegistryMachineSystemCurrentControlSetControlClass{4d36e96e-e325-11ce-bfc1-08002be10318} 004 Display Device DeviceName \.DISPLAY3 DeviceString Intel(R) HD Graphics Family StateFlags 0 DeviceID PCIVEN_8086&DEV_0A16&SUBSYS_397817AA&REV_09 DeviceKey RegistryMachineSystemCurrentControlSetControlVideo{A9611CC2-95E1-4DAE-9937-60210AFEDCE0} 002 GlobalMemoryStatusEx dwMemoryLoad 34 ullTotalPhys 8486227968 ullAvailPhys 5588660224 ullTotalPageFile 13854937088 ullAvailPageFile 10756182016 ullTotalVirtual 140737488224256 ullAvailVirtual 140737442308096 Processor Information 0 Name Intel(R) Core(TM) i7-4500U CPU @ 1.80GHz Clock speed (MHz) 2394 1 Name Intel(R) Core(TM) i7-4500U CPU @ 1.80GHz Clock speed (MHz) 2394 2 Name Intel(R) Core(TM) i7-4500U CPU @ 1.80GHz Clock speed (MHz) 2394 3 Name Intel(R) Core(TM) i7-4500U CPU @ 1.80GHz Clock speed (MHz) 2394 NvAPI IsMSHybridGraphics True DisplayDriverVersion Driver Version 37609 Changelist 0 BuildBranchString r376_06 Default AdapterString GeForce GT 720M DisplayDriverCompileType Release NvDebugApi WDDM Devices GPU Name GeForce GT 720M Architecture Fermi Architecture Number 208 Architecture Implementation 7 Architecture Revision 162 Number of GPCs 1 Number of TPCs 2 Number of SMs 2 Warps per SM 48 Lanes per warp 32 Register file size 32768 Max CTAs per SM 8 Max size of shared memory per CTA (bytes) 49152 SM Revision 131073 Number of FB PAs 6 Number of LTs per LTC 2 RmGpuId 1024 RM Devices CUDA CUDA Device Name GeForce GT 720M Driver WDDM DeviceIndex 0 GPU Family GF117 RmGpuId 1024 Compute Major 2 Compute Minor 1 MAX_THREADS_PER_BLOCK 1024 MAX_BLOCK_DIM_X 1024 MAX_BLOCK_DIM_Y 1024 MAX_BLOCK_DIM_Z 64 MAX_GRID_DIM_X 65535 MAX_GRID_DIM_Y 65535 MAX_GRID_DIM_Z 65535 MAX_SHARED_MEMORY_PER_BLOCK 49152 TOTAL_CONSTANT_MEMORY 65536 WARP_SIZE 32 MAX_PITCH 2147483647 MAX_REGISTERS_PER_BLOCK 32768 CLOCK_RATE 1550000 TEXTURE_ALIGNMENT 512 GPU_OVERLAP 1 MULTIPROCESSOR_COUNT 2 KERNEL_EXEC_TIMEOUT 0 INTEGRATED 0 CAN_MAP_HOST_MEMORY 1 COMPUTE_MODE 0 MAXIMUM_TEXTURE1D_WIDTH 65536 MAXIMUM_TEXTURE2D_WIDTH 65536 MAXIMUM_TEXTURE2D_HEIGHT 65535 MAXIMUM_TEXTURE3D_WIDTH 2048 MAXIMUM_TEXTURE3D_HEIGHT 2048 MAXIMUM_TEXTURE3D_DEPTH 2048 MAXIMUM_TEXTURE2D_LAYERED_WIDTH 16384 MAXIMUM_TEXTURE2D_LAYERED_HEIGHT 16384 MAXIMUM_TEXTURE2D_LAYERED_LAYERS 2048 SURFACE_ALIGNMENT 512 CONCURRENT_KERNELS 1 ECC_ENABLED 0 PCI_BUS_ID 4 PCI_DEVICE_ID 0 TCC_DRIVER 0 MEMORY_CLOCK_RATE 900000 GLOBAL_MEMORY_BUS_WIDTH 64 L2_CACHE_SIZE 131072 MAX_THREADS_PER_MULTIPROCESSOR 1536 ASYNC_ENGINE_COUNT 1 UNIFIED_ADDRESSING 1 MAXIMUM_TEXTURE1D_LAYERED_WIDTH 16384 MAXIMUM_TEXTURE1D_LAYERED_LAYERS 2048 CAN_TEX2D_GATHER 1 MAXIMUM_TEXTURE2D_GATHER_WIDTH 16384 MAXIMUM_TEXTURE2D_GATHER_HEIGHT 16384 MAXIMUM_TEXTURE3D_WIDTH_ALTERNATE 0 MAXIMUM_TEXTURE3D_HEIGHT_ALTERNATE 0 MAXIMUM_TEXTURE3D_DEPTH_ALTERNATE 0 PCI_DOMAIN_ID 0 TEXTURE_PITCH_ALIGNMENT 32 MAXIMUM_TEXTURECUBEMAP_WIDTH 16384 MAXIMUM_TEXTURECUBEMAP_LAYERED_WIDTH 16384 MAXIMUM_TEXTURECUBEMAP_LAYERED_LAYERS 2046 MAXIMUM_SURFACE1D_WIDTH 65536 MAXIMUM_SURFACE2D_WIDTH 65536 MAXIMUM_SURFACE2D_HEIGHT 32768 MAXIMUM_SURFACE3D_WIDTH 65536 MAXIMUM_SURFACE3D_HEIGHT 32768 MAXIMUM_SURFACE3D_DEPTH 2048 MAXIMUM_SURFACE1D_LAYERED_WIDTH 65536 MAXIMUM_SURFACE1D_LAYERED_LAYERS 2048 MAXIMUM_SURFACE2D_LAYERED_WIDTH 65536 MAXIMUM_SURFACE2D_LAYERED_HEIGHT 32768 MAXIMUM_SURFACE2D_LAYERED_LAYERS 2048 MAXIMUM_SURFACECUBEMAP_WIDTH 32768 MAXIMUM_SURFACECUBEMAP_LAYERED_WIDTH 32768 MAXIMUM_SURFACECUBEMAP_LAYERED_LAYERS 2046 MAXIMUM_TEXTURE1D_LINEAR_WIDTH 134217728 MAXIMUM_TEXTURE2D_LINEAR_WIDTH 65000 MAXIMUM_TEXTURE2D_LINEAR_HEIGHT 65000 MAXIMUM_TEXTURE2D_LINEAR_PITCH 1048544 MAXIMUM_TEXTURE2D_MIPMAPPED_WIDTH 16384 MAXIMUM_TEXTURE2D_MIPMAPPED_HEIGHT 16384 MAXIMUM_TEXTURE1D_MIPMAPPED_WIDTH 16384 STREAM_PRIORITIES_SUPPORTED 0 GLOBAL_L1_CACHE_SUPPORTED 1 LOCAL_L1_CACHE_SUPPORTED 1 MAX_SHARED_MEMORY_PER_MULTIPROCESSOR 49152 MAX_REGISTERS_PER_MULTIPROCESSOR 32768 MANAGED_MEMORY 0 MULTI_GPU_BOARD 0 MULTI_GPU_BOARD_GROUP_ID 0 HOST_NATIVE_ATOMIC_SUPPORTED 0 SINGLE_TO_DOUBLE_PRECISION_PERF_RATIO 12 PAGEABLE_MEMORY_ACCESS 0 CONCURRENT_MANAGED_ACCESS 0 COMPUTE_PREEMPTION_SUPPORTED 0 CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM 0 DISPLAY_NAME GeForce GT 720M COMPUTE_CAPABILITY_MAJOR 2 COMPUTE_CAPABILITY_MINOR 1 TOTAL_MEMORY 2147483648 RAM_TYPE 7 RAM_LOCATION 1 GPU_PCI_DEVICE_ID 289411294 GPU_PCI_SUB_SYSTEM_ID 939530154 GPU_PCI_REVISION_ID 161 GPU_PCI_EXT_DEVICE_ID 4416 GPU_PCI_EXT_GEN 1 GPU_PCI_EXT_GPU_GEN 1 GPU_PCI_EXT_GPU_LINK_RATE 5000 GPU_PCI_EXT_GPU_LINK_WIDTH 8 GPU_PCI_EXT_DOWNSTREAM_LINK_RATE 5000 GPU_PCI_EXT_DOWNSTREAM_LINK_WIDTH 4
解决方案
Your GT 720m is a compute capability 2.1 device (see here).
Attempting to debug CUDA code (e.g. set breakpoints) on a GPU that is also supporting (hosting) a display requires a compute capability 3.5 or higher device, to support preemption.
Your device does not meet that requirement, so because your GPU is hosting your laptop display, it cannot be used to set breakpoints in CUDA code.
Also note that the latest version of Nsight VSE (5.2 at this time) has officially dropped support for Fermi GPUs (yours is a Fermi GPU):
Note: Fermi family GPUs, and older families, are no longer supported with Nsight™ Visual Studio Edition 5.2 or better.
这篇关于在当前不可调试的 GPU 上创建了 CUDA 上下文的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！
查看全文
