Problems w/ Second GPU on CentOS

Hi. I have a CentoOS machine with 2 GeForce GTX 285s. I am only able to get one of the cards to work. I have swapped cards and the card in the top slot works each time, so I’m pretty sure the cards are okay. I have attached a monitor to both cards, but the second card, again, doesn’t work. Any clues about how I might get the second card going? Are there things I should try? I have read all about getting multiple monitors going with the two cards, but I don’t think I am there yet. Right now I’d just like to be able to run CUDA kernels on both cards. I have the output of deviceQuery below. I also included the output of scanpci.-v.

John McInerney
jmcinerney6@gmail.com


The output of deviceQuery:

There is 1 device supporting CUDA

Device 0: “GeForce GTX 285”
Major revision number: 1
Minor revision number: 3
Total amount of global memory: 2146762752 bytes
Number of multiprocessors: 30
Number of cores: 240
Total amount of constant memory: 65536 bytes
Total amount of shared memory per block: 16384 bytes
Total number of registers available per block: 16384
Warp size: 32
Maximum number of threads per block: 512
Maximum sizes of each dimension of a block: 512 x 512 x 64
Maximum sizes of each dimension of a grid: 65535 x 65535 x 1
Maximum memory pitch: 262144 bytes
Texture alignment: 256 bytes
Clock rate: 1.48 GHz
Concurrent copy and execution: Yes

Test PASSED

The output of scanpci:

pci bus 0x0002 cardnum 0x00 function 0x00: vendor 0x10de device 0x05b1
nVidia Corporation Device unknown
STATUS 0x0010 COMMAND 0x0504
CLASS 0x06 0x04 0x00 REVISION 0xa3
HEADER 0x01 LATENCY 0x00
PRIBUS 0x02 SECBUS 0x03 SUBBUS 0x05
SECLT 0x00 SECSTATUS 0x0000
IOBASE 0x0000f000 IOLIM 0x00000fff
NOPREFETCH_MEMBASE 0xfff00000 MEMLIM 0x000fffff
PREFETCH_MEMBASE 0x00000000fff00000 MEMLIM 0x00000000000fffff
NO_FAST_B2B NO_SEC_BUS_RST NO_M_ABRT NO_VGA_EN NO_ISA_EN SERR_EN PERR_EN

pci bus 0x0003 cardnum 0x00 function 0x00: vendor 0x10de device 0x05b1
nVidia Corporation Device unknown
STATUS 0x0010 COMMAND 0x0504
CLASS 0x06 0x04 0x00 REVISION 0xa3
HEADER 0x01 LATENCY 0x00
PRIBUS 0x03 SECBUS 0x04 SUBBUS 0x04
SECLT 0x00 SECSTATUS 0x0000
IOBASE 0x0000f000 IOLIM 0x00000fff
NOPREFETCH_MEMBASE 0xfff00000 MEMLIM 0x000fffff
PREFETCH_MEMBASE 0x00000000fff00000 MEMLIM 0x00000000000fffff
NO_FAST_B2B NO_SEC_BUS_RST NO_M_ABRT NO_VGA_EN NO_ISA_EN SERR_EN PERR_EN

pci bus 0x0003 cardnum 0x02 function 0x00: vendor 0x10de device 0x05b1
nVidia Corporation Device unknown
STATUS 0x0010 COMMAND 0x0504
CLASS 0x06 0x04 0x00 REVISION 0xa3
HEADER 0x01 LATENCY 0x00
PRIBUS 0x03 SECBUS 0x05 SUBBUS 0x05
SECLT 0x00 SECSTATUS 0x0000
IOBASE 0x0000f000 IOLIM 0x00000fff
NOPREFETCH_MEMBASE 0xfff00000 MEMLIM 0x000fffff
PREFETCH_MEMBASE 0x00000000fff00000 MEMLIM 0x00000000000fffff
NO_FAST_B2B NO_SEC_BUS_RST NO_M_ABRT NO_VGA_EN NO_ISA_EN SERR_EN PERR_EN

pci bus 0x0006 cardnum 0x00 function 0x00: vendor 0x10de device 0x05e3
nVidia Corporation Device unknown
CardVendor 0x3842 card 0x1185 (Card unknown)
STATUS 0x0010 COMMAND 0x0007
CLASS 0x03 0x00 0x00 REVISION 0xa1
BIST 0x00 HEADER 0x00 LATENCY 0x00 CACHE 0x00
BASE0 0xfa000000 addr 0xfa000000 MEM
BASE1 0x00000000d000000c addr 0x00000000d0000000 MEM PREFETCHABLE 64BIT
BASE3 0x00000000f8000004 addr 0x00000000f8000000 MEM 64BIT
BASE5 0x0000ac01 addr 0x0000ac00 I/O
MAX_LAT 0x00 MIN_GNT 0x00 INT_PIN 0x01 INT_LINE 0x0f
BYTE_0 0x42 BYTE_1 0x38 BYTE_2 0x85 BYTE_3 0x11

sounds like a motherboard or power supply problem to me. are you sure both the motherboard and power supply are capable of handling 2 285s?

I just got CentOS 5.3 installed and using the latest beta drivers and Toolkit 2.2 I’m able to see both my Quadro FX 1700 and GeForce 285 GTX. It’s not your exact situation, but pretty close. Therefore, tmurray is probably correct (as usual).

Peter