Quadro FX 1800 computing capability?

What is the Quadro FX 1800 computing capability?
I cannot find any info because it is a new card.

@NVIDIA: Could you put Computing Capability on the Specification page of your GPUs, please?

I am pretty sure it is G94 based (like the 9600GT), so 1.1 capability

Amen. We shouldn’t have to wait until the next CUDA programming guide comes out to get a definitive reference.

yeah, agreed. let me poke people

I just installed the card in place the old Quadro FX 3400 on
ell Precision 670, Intel Xeon 3.00Ghz, RAM 2GB, 64-bit, Windows 7

Here is what deviceQuery.exe generated:

==============
CUDA Device Query (Runtime API) version (CUDART static linking)
There is 1 device supporting CUDA

Device 0: “Quadro FX 1800”
CUDA Capability Major revision number: 1
CUDA Capability Minor revision number: 1
Total amount of global memory: 805306368 bytes
Number of multiprocessors: 8
Number of cores: 64
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 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: 1.38 GHz
Concurrent copy and execution: Yes
Run time limit on kernels: No
Integrated: No
Support host page-locked memory mapping: No
Compute mode: Default (multiple host threads can use this device simultaneously)

==============

Here is what bandwidthtest generated:

==============

Running on…
device 0:Quadro FX 1800
Quick Mode
Host to Device Bandwidth for Pageable memory
.
Transfer Size (Bytes) Bandwidth(MB/s)
33554432 1031.3

Quick Mode
Device to Host Bandwidth for Pageable memory
.
Transfer Size (Bytes) Bandwidth(MB/s)
33554432 779.6

Quick Mode
Device to Device Bandwidth
.
Transfer Size (Bytes) Bandwidth(MB/s)
33554432 31702.4

============================================================

can you also run bandwidthTest --memory=pinned? That will come closer to theoretical PCI-Express maximum.

here is what I got. What do you think for these results up to now?

Running on…

  device 0:Quadro FX 1800

Quick Mode

Host to Device Bandwidth for Pinned memory

.

Transfer Size (Bytes) Bandwidth(MB/s)

33554432 2427.4

Quick Mode

Device to Host Bandwidth for Pinned memory

.

Transfer Size (Bytes) Bandwidth(MB/s)

33554432 2691.6

Quick Mode

Device to Device Bandwidth

.

Transfer Size (Bytes) Bandwidth(MB/s)

33554432 31720.7

This is definitely below average for a PCI-Express 1.0 connection, but motherboards with different chipsets show a surprising range of bandwidths in this test.

What is your theoretical maximum for PCIe 1.0?

I’ve lost access to my PCI-Express 1.0 motherboard (finally died last week). My 8800 GTX in a Phenom II system (a PCI-e 1.0 card in a high-end PCI-e 2.0 motherboard) gets 2.6 GB/sec Host-to-Device and 3.1 GB/sec Device-to-Host. Other systems I’ve seen reported in the forums get > 3 GB/sec in both directions. (4 is the theoretical max, but I don’t think I’ve ever seen anyone get higher than 3.5 in practice.)

For comparison, a PCI-e 2.0 card in an Phenom system (PCI-e 2.0 motherboard) gets 5.3 H->D and 5.0 D->H, and in a Core i7 system (also PCI-e 2.0 motherboard) gets 5.8 and 5.6 GB/sec.

Here are some results for a pretty poor performing PCI-e 1.0 system (my development machine which is a Shuttle Flex-ATX G31 chipset board with a Core 2 Quad Q6600, 2Gb of DDR2-667 ram and a GF9500GT) which gives some idea of what below average looks like…
htod.png
dtoh.png

A multiple clock frequencies that can be quoted for any card: core clock, shader clock, and memory clock.

Which one the deviceProp.clockRate is returning?

should be shader clock.