update log file about the installation of Tesla M2090 in server


Hi,I’ve got Tesla M2090 on my IBM blade,and install the driver version 304.37.I do as the “CUDA Getting Started guide for linux” step by step. check: lspci | grep -i nvidia 8b:00.0 3D controller: nVidia Corporation Device 1091 (rev a1) uname -m && cat /etc/*release: x86_64 SUSE Linux Enterprise Server 11 VERSION = 11 PATCHLEVEL = 1 gcc version:gcc (SUSE Linux) 4.3.4 [gcc-4_3-branch revision 152973]. #sh NVIDIA-Linux-x86_64-304.37.run. I got “Driver file installation is complete.” then generate /dev/nvidia0 and /dev/nvidiacl init 5 when execute nvidia-smi NVIDIA: could not open the device file /dev/nvidia0 (Input/output error). NVIDIA-SMI has failed because it couldn’t communicate with NVIDIA driver. Make sure that latest NVIDIA driver is installed and running. so the device doesn’t work. what’s the problem?I’m eager to receive any reply

Can anyone help me?

Don’t let this problem go please

Hi Tracy2,

This problem looks like it’s likely caused by a bug in the system BIOS that the Linux kernel is detecting:

Can you try putting the card into a different PCIe slot or disabling IOMMU in the system BIOS? Also, please check with your system vendor to see if an updated BIOS is available.

Tracy2, Any updates ? Is your issue resolved ?