Cuda未知错误（ErrNo：30）on cudaMalloc（） [英] Cuda Unknown Error(ErrNo: 30) on cudaMalloc()
问题描述
我搜索了原因，但没有运气。它在这样一个简单的程序失败：
#include< iostream&
using namespace std;
int main（）{
int * n;
cout<< cudaMallocManaged（& n，4 * sizeof（int））<< endl;
return 0;
}
返回代码为30，未知错误。 cudaMalloc 也会失败，并显示相同的代码。
这是我的硬件：
$ lspci | grep NV
01：00.0 3D控制器：NVIDIA公司GF117M [GeForce 610M / 710M / 820M / GT 620M / 625M / 630M / 720M]（rev a1）
$ nvidia-smi
Sat Mar 7 14:02:04 2015
+ ---------------------------------- -------------------- +
| NVIDIA-SMI 331.113驱动程序版本：331.113 |
| ------------------------------- + ------------- --------- + ---------------------- +
| GPU名称Persistence-M | Bus-Id Disp.A |挥发性。 ECC |
| Fan Temp Perf Pwr：Usage / Cap |内存使用| GPU-Util Compute M. |
| ============================= + ============= ========= + ======================
| 0 NVS 5200M Off | 0000：01：00.0 N / A | N / A |
| N / A 53℃N / A N / A / N / A | 279MiB / 1023MiB |不适用默认|
+ ------------------------------- + ------------- --------- + ---------------------- +
+ -------- -------------------------------------------------- ------------------- +
|计算进程：GPU Memory |
| GPU PID进程名称用法|
| ========================================= ==============================
| 0不支持|
+ --------------------------------------------- -------------------------------- +
我使用的是Ubuntu 14.10，使用官方软件库中的CUDA 6.0（希望如果Ubuntu不会搞乱它）。
这是一个联想T430s labtop，该卡在Optimus上，以便可能会导致一些问题。
$ b
更新1
> OK， nvidia_uvm 未加载... $ lsmod | grep nv
nvidia 10744914 65
nvram 14362 1 thinkpad_acpi
drm 310919 6 i915，drm_kms_helper，nvidia
$ sudo modprobe nvidia_uvm
modprobe ：错误：../libkmod/libkmod-module.c:816 kmod_module_insert_module（）无法找到模块by name ='nvidia_331_updates_uvm'
modprobe：错误：无法插入'nvidia_331_updates_uvm'：功能未实现
更新2
，我重新安装了nvidia-331-updates-uvm并且模块已加载。
$ lsmod | grep nv
nvidia_uvm 34855 0
nvidia 10744914 66 nvidia_uvm
nvram 14362 1 thinkpad_acpi
drm 310919 6 i915，drm_kms_helper，nvidia
$ b更新3
/ p>
经过一些更多的测试（主要是尝试以root身份运行），现在我得到错误71：操作不支持。但是，如果我只是使用
cudaMalloc成功。我还将检查我的设备是否支持统一内存寻址。
更新4
OK，我的卡只支持SM 2.1，因此不支持统一内存。
解决方案AFAIK
nvidia_uvm内核模块是CUDA工作所必需的。
您需要安装包含该内核模块的软件包，例如
nvidia-331-uvm和
通过安装nvidia-modprobe软件包启用自动加载：sudo apt-get install nvidia-modprobe nvidia-331-uvm
如果在安装
nvidia-modprobe后不想重新启动，可以尝试以root身份运行程序sudo ./a.out） - 应在以root身份运行时加载模块。I have searched for the reason but no luck. It fails on such a simple program:
#include <iostream> using namespace std; int main() { int* n; cout << cudaMallocManaged(&n, 4 * sizeof(int)) << endl; return 0; }The return code is 30, unknown error.
cudaMallocalso fails with same code.This is my hardware:
$ lspci | grep NV 01:00.0 3D controller: NVIDIA Corporation GF117M [GeForce 610M/710M/820M / GT 620M/625M/630M/720M] (rev a1) $ nvidia-smi Sat Mar 7 14:02:04 2015 +------------------------------------------------------+ | NVIDIA-SMI 331.113 Driver Version: 331.113 | |-------------------------------+----------------------+----------------------+ | GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. | |===============================+======================+======================| | 0 NVS 5200M Off | 0000:01:00.0 N/A | N/A | | N/A 53C N/A N/A / N/A | 279MiB / 1023MiB | N/A Default | +-------------------------------+----------------------+----------------------+ +-----------------------------------------------------------------------------+ | Compute processes: GPU Memory | | GPU PID Process name Usage | |=============================================================================| | 0 Not Supported | +-----------------------------------------------------------------------------+I am using Ubuntu 14.10, with CUDA 6.0 from official repository(hopefully, if Ubuntu does not mess it up).
It is a Lenovo T430s labtop, the card is on Optimus so that might cause some problem. I have tested on another machine and the same code works.
Update 1
OK,
nvidia_uvmis not loaded...$ lsmod |grep nv nvidia 10744914 65 nvram 14362 1 thinkpad_acpi drm 310919 6 i915,drm_kms_helper,nvidia $ sudo modprobe nvidia_uvm modprobe: ERROR: ../libkmod/libkmod-module.c:816 kmod_module_insert_module() could not find module by name='nvidia_331_updates_uvm' modprobe: ERROR: could not insert 'nvidia_331_updates_uvm': Function not implementedUpdate 2
OK, I reinstalled nvidia-331-updates-uvm and the module was loaded.
$ lsmod | grep nv nvidia_uvm 34855 0 nvidia 10744914 66 nvidia_uvm nvram 14362 1 thinkpad_acpi drm 310919 6 i915,drm_kms_helper,nvidiaHowever, the code still returns error 30.
Update 3
After some more testing (mainly tried running as root), now I get error 71: operation not supported. However, if I am just using
cudaMallocit succeeded. I will also check whether my device support unified memory addressing.Update 4
OK, my card only supports SM 2.1, so it does not support Unified Memory.
解决方案AFAIK
nvidia_uvmkernel module is required for CUDA to work.You need to install package with that kernel module, e.g.
nvidia-331-uvmand enable it's autoloading by installingnvidia-modprobepackage:sudo apt-get install nvidia-modprobe nvidia-331-uvmIf you don't want to reboot after installing
nvidia-modprobe, you can try to run your program as root (e.g.sudo ./a.out) — module should be loaded during run as root.这篇关于Cuda未知错误（ErrNo：30）on cudaMalloc（）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！
