CUDA v.s. gfxG05

English Install/Boot/Login
#1

Hello,
I’m trying to install CUDA toolkit on my desktop, and I downloaded it from NVIDIA: https://developer.nvidia.com/cuda-downloads?target_os=Linux&target_arch=x86_64&target_distro=OpenSUSE&target_version=150&target_type=rpmlocal
There is one problem with it at the moment. Basically almost all of the cuda pakages 9 and newer have a similar error code when I try to install

Problem: cuda-9-1-9.1.85-1.x86_64 requires cuda-runtime-9-1 >= 9.1.85, but this requirement cannot be provided
  not installable providers: cuda-runtime-9-1-9.1.85-1.x86_64[cuda]
 Solution 1: Following actions will be done:
  deinstallation of nvidia-computeG05-418.56-lp150.9.1.x86_64
  deinstallation of x11-video-nvidiaG05-418.56-lp150.9.1.x86_64
  deinstallation of nvidia-gfxG05-kmp-default-418.56_k4.12.14_lp150.11-lp150.9.1.x86_64
  deinstallation of nvidia-glG05-418.56-lp150.9.1.x86_64
 Solution 2: do not install cuda-9-1-9.1.85-1.x86_64
 Solution 3: break cuda-9-1-9.1.85-1.x86_64 by ignoring some of its dependencies

It seems that nvidi-gfxG05 isn’t happy with the cuda tool-kit.
Could someone help me with this?

#2

Which card?

Maybe try dropping back to G04 driver???

#3

Hi
Install from the cuda run file and use the ignore option and don’t install the driver, else look at using cuda 10?


./cuda_10.0.130_410.48_linux.run --override

I have the 418.56 driver installed (use the hard way) and cuda 10 on Tumbleweed.

#4

Should you be installing toolkit 10.1 instead?
https://developer.nvidia.com/cuda-downloads?target_os=Linux&target_arch=x86_64&target_distro=OpenSUSE&target_version=150&target_type=rpmlocal

https://docs.nvidia.com/cuda/cuda-quick-start-guide/index.html
https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html

TSU

#5

It seems that Gfx04 is happy with cuda 10.1 (nvidia 318.40 driver downgraded from 318.58)

This is strange, I would have thought that cuda nvidia drivers would be more advanced.

#6

Thanks for this, I installed the .run cuda and use 418.56 .run nvidia driver
I did not install the nvidia driver in the cuda .run file.
I followed the post installation instructions then run make for the cuda samples.
Tested it in blender 2.79b and the gpu compute worked.
This is on the latest tumbleweed snapshot.

Result from ./deviceQuery:

/usr/local/cuda-10.1/samples/1_Utilities/deviceQuery> ./deviceQuery
./deviceQuery Starting...

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

Detected 2 CUDA Capable device(s)

Device 0: "GeForce GTX 650 Ti"
  CUDA Driver Version / Runtime Version          10.1 / 10.1
  CUDA Capability Major/Minor version number:    3.0
  Total amount of global memory:                 1992 MBytes (2088632320 bytes)
  ( 4) Multiprocessors, (192) CUDA Cores/MP:     768 CUDA Cores
  GPU Max Clock rate:                            941 MHz (0.94 GHz)
  Memory Clock rate:                             2700 Mhz
  Memory Bus Width:                              128-bit
  L2 Cache Size:                                 262144 bytes
  Maximum Texture Dimension Size (x,y,z)         1D=(65536), 2D=(65536, 65536), 3D=(4096, 4096, 4096)
  Maximum Layered 1D Texture Size, (num) layers  1D=(16384), 2048 layers
  Maximum Layered 2D Texture Size, (num) layers  2D=(16384, 16384), 2048 layers
  Total amount of constant memory:               65536 bytes
  Total amount of shared memory per block:       49152 bytes
  Total number of registers available per block: 65536
  Warp size:                                     32
  Maximum number of threads per multiprocessor:  2048
  Maximum number of threads per block:           1024
  Max dimension size of a thread block (x,y,z): (1024, 1024, 64)
  Max dimension size of a grid size    (x,y,z): (2147483647, 65535, 65535)
  Maximum memory pitch:                          2147483647 bytes
  Texture alignment:                             512 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):      Yes
  Device supports Compute Preemption:            No
  Supports Cooperative Kernel Launch:            No
  Supports MultiDevice Co-op Kernel Launch:      No
  Device PCI Domain ID / Bus ID / location ID:   0 / 1 / 0
  Compute Mode:
     < Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >

Device 1: "GeForce GT 640"
  CUDA Driver Version / Runtime Version          10.1 / 10.1
  CUDA Capability Major/Minor version number:    3.0
  Total amount of global memory:                 2000 MBytes (2097086464 bytes)
  ( 2) Multiprocessors, (192) CUDA Cores/MP:     384 CUDA Cores
  GPU Max Clock rate:                            902 MHz (0.90 GHz)
  Memory Clock rate:                             891 Mhz
  Memory Bus Width:                              128-bit
  L2 Cache Size:                                 262144 bytes
  Maximum Texture Dimension Size (x,y,z)         1D=(65536), 2D=(65536, 65536), 3D=(4096, 4096, 4096)
  Maximum Layered 1D Texture Size, (num) layers  1D=(16384), 2048 layers
  Maximum Layered 2D Texture Size, (num) layers  2D=(16384, 16384), 2048 layers
  Total amount of constant memory:               65536 bytes
  Total amount of shared memory per block:       49152 bytes
  Total number of registers available per block: 65536
  Warp size:                                     32
  Maximum number of threads per multiprocessor:  2048
  Maximum number of threads per block:           1024
  Max dimension size of a thread block (x,y,z): (1024, 1024, 64)
  Max dimension size of a grid size    (x,y,z): (2147483647, 65535, 65535)
  Maximum memory pitch:                          2147483647 bytes
  Texture alignment:                             512 bytes
  Concurrent copy and kernel execution:          Yes with 1 copy engine(s)
  Run time limit on kernels:                     No
  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):      Yes
  Device supports Compute Preemption:            No
  Supports Cooperative Kernel Launch:            No
  Supports MultiDevice Co-op Kernel Launch:      No
  Device PCI Domain ID / Bus ID / location ID:   0 / 3 / 0
  Compute Mode:
     < Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >
> Peer access from GeForce GTX 650 Ti (GPU0) -> GeForce GT 640 (GPU1) : No
> Peer access from GeForce GT 640 (GPU1) -> GeForce GTX 650 Ti (GPU0) : No

deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 10.1, CUDA Runtime Version = 10.1, NumDevs = 2
Result = PASS

Thanks malcolm;)