Correct memory bandwidths for the Tesla 870?

I have a Tesla C870 card installed on Fedora Core 7 x86_64 using the driver NVIDIA-Linux-x86_64-169.07-pkg2.run. When I run the CUDA SDK bandwidthTest i get the following numbers:

Host to Device 975.4
Device to Host 798.8
Device to Device 63923.3

Does this seem correct? Am I using the right version of the driver? I saw in other posts on these forums that the 169.09 version had issues causing slow memory, which is why I have installed the .07 version. Hopefully I will soon have time to plug our S870 in to see how it looks too. ;)

On a somewhat unrelated note, do the CUBLAS functions block until the result is computed on the board? In other words, if I call gettimeofday() immediately before and after a call to cublasSgbmv(), will the difference give me the execution time of that function?

Thanks for any help!!
-Jonathan

The results of bandwidthTest depend on the motherboard/CPU that you’re using. Also, are you posting the pinned or pagable numbers?

The numbers are very low.

Yes I guess that would make sense… Those results were for pagable memory, for pinned memory I see:

Host to Device Bandwidth for Pinned memory 2316.4
Device to Host Bandwidth for Pinned memory 2186.6
Device to Device Bandwidth 63904.1

My processor is a dual core Intel® Xeon® CPU 5120 @ 1.86GHz I have a Dell Precision Workstation 690.