Primeiro, eu não consegui instalar o driver nvidia do ppa, já que isso me levou ao loop de login. Eu tive que usar o arquivo .run com a opção --no-opengl *, usando a seguinte linha de comando no modo TTY:
$ sudo ./cuda_9.2.148_396.37_linux.run --no-opengl-libs
Isto parece instalar corretamente o driver nvidia. Quando eu uso um dos códigos de exemplo instalados pelo arquivo de execução, recebo:
sudo ./bandwidthTest
[CUDA Bandwidth Test] - Starting...
Running on...
Device 0: GeForce GTX 1080 Ti
Quick Mode
Host to Device Bandwidth, 1 Device(s)
PINNED Memory Transfers
Transfer Size (Bytes) Bandwidth(MB/s)
33554432 12040.7
Device to Host Bandwidth, 1 Device(s)
PINNED Memory Transfers
Transfer Size (Bytes) Bandwidth(MB/s)
33554432 12875.9
Device to Device Bandwidth, 1 Device(s)
PINNED Memory Transfers
Transfer Size (Bytes) Bandwidth(MB/s)
33554432 347433.7
Result = PASS
NOTE: The CUDA Samples are not meant for performance measurements. Results may vary when GPU Boost is enabled.
Aqui estão as informações sobre as duas GPUs instaladas na minha máquina
$ sudo lshw -C display
*-display UNCLAIMED
description: VGA compatible controller
product: ASPEED Graphics Family
vendor: ASPEED Technology, Inc.
physical id: 0
bus info: pci@0000:07:00.0
version: 41
width: 32 bits
clock: 33MHz
capabilities: pm msi vga_controller bus_master cap_list
configuration: latency=0
resources: memory:90000000-90ffffff memory:91000000-9101ffff ioport:2000(size=128) memory:c0000-dffff
*-display
description: VGA compatible controller
product: NVIDIA Corporation
vendor: NVIDIA Corporation
physical id: 0
bus info: pci@0000:65:00.0
version: a1
width: 64 bits
clock: 33MHz
capabilities: pm msi pciexpress vga_controller bus_master cap_list rom
configuration: driver=nvidia latency=0
resources: irq:69 memory:df000000-dfffffff memory:c0000000-cfffffff memory:d0000000-d1ffffff ioport:b000(size=128) memory:e0000000-e007ffff
No entanto, tenho uma resolução muito ruim, embora tenha tentado "reproduzir" no arquivo xorg.conf que postei abaixo
Section "ServerLayout"
Identifier "Layout0"
#Screen 0 "Screen0"
Screen 1 "intel"
Screen 0 "nvidia"
InputDevice "Keyboard0" "CoreKeyboard"
InputDevice "Mouse0" "CorePointer"
EndSection
Section "Files"
EndSection
Section "InputDevice"
# generated from default
Identifier "Mouse0"
Driver "mouse"
Option "Protocol" "auto"
Option "Device" "/dev/psaux"
Option "Emulate3Buttons" "no"
Option "ZAxisMapping" "4 5"
EndSection
Section "InputDevice"
# generated from default
Identifier "Keyboard0"
Driver "kbd"
EndSection
Section "Monitor"
Identifier "Monitor0"
VendorName "Unknown"
ModelName "Unknown"
HorizSync 60.0 - 100.0
VertRefresh 60.0 - 100.0
Option "DPMS"
EndSection
Section "Device"
Identifier "nvidia"
Driver "nvidia"
BusID "PCI:65:0:0" # "PCI:0@0000:65:00.0" ##
VendorName "NVIDIA Corporation"
EndSection
Section "Device"
Identifier "intel"
Driver "intel"
BusID "PCI:7:0:0" # "PCI:0@0000:07:00.0"
Option "AccelMethod" "SNA"
EndSection
Section "Screen"
Identifier "nvidia"
Device "nvidia"
Monitor "Monitor0"
DefaultDepth 24
Option "UseDisplayDevice" "DFP" ## from another link
Option "AllowEmptyInitialConfiguration" "on"
Option "IgnoreDisplayDevices" "CRT"
SubSection "Display"
Depth 24
Modes "nvidia-auto-select"
EndSubSection
EndSection
Section "Screen"
Identifier "intel"
Device "intel"
Monitor "Monitor0"
EndSection
Além disso, recebo
$ inxi -G
Graphics: Card-1: ASPEED ASPEED Graphics Family
Card-2: NVIDIA Device 1b06
Display Server: X.Org 1.19.6 drivers: fbdev,nouveau (unloaded: vesa,intel) FAILED: nvidia
Resolution: [email protected]
GLX Renderer: llvmpipe (LLVM 6.0, 256 bits) GLX Version: 3.0 Mesa 18.0.5
Alguma ideia sobre o problema? Estou usando um busID errado no arquivo acima?