y450 archlinux cuda6.5

y450 archlinux cuda6.5

January 28, 2018 4:11 PM

archlinux是最新更新版本，gcc版本到了7.几，太新了。

[qiangge@lqspc ~]$ gcc --version
gcc (GCC) 7.2.1 20180116
Copyright © 2017 Free Software Foundation, Inc.
本程序是自由软件；请参看源代码的版权声明。本软件没有任何担保；
包括没有适销性和某一专用目的下的适用性担保。

这系统对中文翻译的不太习惯哈。

总体步骤

1. 确认安装的archlinux比较新，不想降级gcc等。
2. 确认y450的笔记本显卡型号，g 110M。
3. 确定可以安装的cuda版本。这个地方走过弯路，开始直接pa cuda，结果就给我装了个9.1的版本。反复测试发现安装失败。经过查询显卡型号（上一步）支持的计算能力（compute capability?希望没拼错）只是支持1.2以下，后来安装完发现是1.1.而1.2以下的最多安装cuda-6.5以前的版本。
4. yaourt cuda找到相关版本安装（上一步），安装过程中遇到/tmp不够用，新建个目录挂载到/tmp，冲掉了内存挂载的/tmp，这样可以充分利用硬盘空间来操作。之所以不够用因为内存只有8G，这样默认/tmp就只有4G，废话了。
5. 安装完后测试/opt/cuda/samples的devicequery例子，最好拷贝到自己的/home目录吧。
6. 开始不能编译任何例子，有两个错误。主要参考cuda社区解决。

(1)Here is a patch to /usr/include/bits/floatn.h for avoiding __FLOAT128 only when compiling via NVCC
(2)Here is how to use other GCC compiing via NVCC

1. 第一个错误是floatn.h错误。参考论坛解决，本质上是判断条件里面添加一个条件，就是不编译cuda代码的意思。
2. 第二个错误是默认的gcc版本太新了，cuda65不支持，那就采用5试试看（参考下一步方法），发现这只能编译devicequery。于是经过google，知道必须4.7左右。本机yaourt编译4.7失败，当然依然要/tmp，编译个编译器真的很容易失败，浪费了好几天的电费哈。上海电费蛮贵的，尤其是租房，呜呜。那么总有解决办法吧，参考资料在archlinux的yaourt源里面。作者提到了要动态库加上软连接，

sudo ln -s /usr/lib/libisl.so /usr/lib/libisl.so.10 && sudo ldconfig

不然会失败，当然作为折腾专家，我必须先不加看看效果，果然不行

/usr/lib/gcc/x86_64-unknown-linux-gnu/4.7.4/cc1plus: error while loading shared libraries: libisl.so.10: cannot open shared object file: No such file or directory
make: *** [Makefile:196：bandwidthTest.o] 错误 1

加上还提示另外一个错误，这个是作者没考虑的吧，哈哈

/usr/lib/gcc/x86_64-unknown-linux-gnu/4.7.4/cc1plus: error while loading shared libraries: libmpfr.so.4: cannot open shared object file: No such file or directory

解决办法是相同的思路，相似的代码，读者自行思考哈。

9. 解决gcc问题的方法有两个，本质是一个事情，请看参考1和参考2。最后的效果

[qiangge@lqspc ~]$ ll /opt/cuda/
bin/                          jre/                          libnvvp/                      samples/
doc/                          lib/                          NVIDIA_SLA_cuDNN_Support.txt  share/
extras/                       lib64/                        nvvm/                         src/
include/                      libnsight/                    open64/                       tools/
[qiangge@lqspc ~]$ ll /opt/cuda/bin/gcc/
总用量 8.0K
drwxr-xr-x 2 root 4.0K 1月  28 22:52 .
lrwxrwxrwx 1 root   16 1月  28 22:52 gcc -> /usr/bin/gcc-4.7
lrwxrwxrwx 1 root   16 1月  28 22:52 cpp -> /usr/bin/cpp-4.7
lrwxrwxrwx 1 root   16 1月  28 22:52 g++ -> /usr/bin/g++-4.7
drwxr-xr-x 4 root 4.0K 1月  22 09:45 ..
[qiangge@lqspc ~]$

[qiangge@lqspc 1_Utilities]$ cd bandwidthTest/
[qiangge@lqspc bandwidthTest]$ nvidia-smi
Mon Jan 29 00:01:22 2018
+------------------------------------------------------+
| NVIDIA-SMI 340.106    Driver Version: 340.106        |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|===============================+======================+======================|
|   0  GeForce G 110M      Off  | 0000:01:00.0     N/A |                  N/A |
| N/A   52C   P12    N/A /  N/A |     50MiB /   255MiB |     N/A      Default |
+-------------------------------+----------------------+----------------------+

+-----------------------------------------------------------------------------+
| Compute processes:                                               GPU Memory |
|  GPU       PID  Process name                                     Usage      |
|=============================================================================|
|    0            Not Supported                                               |
+-----------------------------------------------------------------------------+
[qiangge@lqspc bandwidthTest]$

[qiangge@lqspc bandwidthTest]$ ./bandwidthTest
[CUDA Bandwidth Test] - Starting...
Running on...

 Device 0: GeForce G 110M
 Quick Mode

 Host to Device Bandwidth, 1 Device(s)
 PINNED Memory Transfers
   Transfer Size (Bytes)	Bandwidth(MB/s)
   33554432			2551.5

 Device to Host Bandwidth, 1 Device(s)
 PINNED Memory Transfers
   Transfer Size (Bytes)	Bandwidth(MB/s)
   33554432			1675.0

 Device to Device Bandwidth, 1 Device(s)
 PINNED Memory Transfers
   Transfer Size (Bytes)	Bandwidth(MB/s)
   33554432			6319.8

Result = PASS
[qiangge@lqspc bandwidthTest]$

[qiangge@lqspc 1_Utilities]$ cd deviceQuery
[qiangge@lqspc deviceQuery]$ ls
deviceQuery  deviceQuery.cpp  deviceQuery.o  Makefile  NsightEclipse.xml  readme.txt
[qiangge@lqspc deviceQuery]$ ./deviceQuery
./deviceQuery Starting...

 CUDA Device Query (Runtime API) version (CUDART static linking)

Detected 1 CUDA Capable device(s)

Device 0: "GeForce G 110M"
  CUDA Driver Version / Runtime Version          6.5 / 6.5
  CUDA Capability Major/Minor version number:    1.1
  Total amount of global memory:                 256 MBytes (268107776 bytes)
  ( 2) Multiprocessors, (  8) CUDA Cores/MP:     16 CUDA Cores
  GPU Clock rate:                                1000 MHz (1.00 GHz)
  Memory Clock rate:                             700 Mhz
  Memory Bus Width:                              64-bit
  Maximum Texture Dimension Size (x,y,z)         1D=(8192), 2D=(65536, 32768), 3D=(2048, 2048, 2048)
  Maximum Layered 1D Texture Size, (num) layers  1D=(8192), 512 layers
  Maximum Layered 2D Texture Size, (num) layers  2D=(8192, 8192), 512 layers
  Total amount of constant memory:               65536 bytes
  Total amount of shared memory per block:       16384 bytes
  Total number of registers available per block: 8192
  Warp size:                                     32
  Maximum number of threads per multiprocessor:  768
  Maximum number of threads per block:           512
  Max dimension size of a thread block (x,y,z): (512, 512, 64)
  Max dimension size of a grid size    (x,y,z): (65535, 65535, 1)
  Maximum memory pitch:                          2147483647 bytes
  Texture alignment:                             256 bytes
  Concurrent copy and kernel execution:          Yes with 1 copy engine(s)
  Run time limit on kernels:                     Yes
  Integrated GPU sharing Host Memory:            No
  Support host page-locked memory mapping:       Yes
  Alignment requirement for Surfaces:            Yes
  Device has ECC support:                        Disabled
  Device supports Unified Addressing (UVA):      No
  Device PCI Bus ID / PCI location ID:           1 / 0
  Compute Mode:
     < Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >

deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 6.5, CUDA Runtime Version = 6.5, NumDevs = 1, Device0 = GeForce G 110M
Result = PASS
[qiangge@lqspc deviceQuery]$

配置虽然低，学习可能够用吧，不行就去买个新点的台式二手显卡？二手是不是抠门了呢？的确是，但是其实自己不用买，公司有1080TI显卡，可以加班学习用就行了。这里只是想自己安装一次，并且可以简单用来学习、练习和测试。同时帮朋友解决了y550上cuda65，那个显卡是g 240m的样子，最多也是1.2的计算能力。但是他用的Ubuntu。臃肿的Ubuntu还不是我的菜。之后又发现自己硬盘快满了，原来是需要pacman -Sc一下了。回头考虑配置一下自动清除不安装的包吧。