Hi all, I’m working on a cuda project and got arround 20x optimization. But I still want to get more benefit from cuda :rolleyes: Currently, my H->D bandwidth is only 1.9G (pinned). So I want to buy a better hardware to speed up it. I ever read a topic in this forum: someone get 5.7G (pinned) H->D…

As NV employee, do you know NV has any plan to solve this bottleneck? A new MB chip for cuda? I think million people as me are looking forward this External Media

Because the overhead of pageable memory is mostly DRAM → DRAM copies, so when those copies are very fast compared to PCI-E v2 speeds, the gain of pinned memory is decreasing.

Thanks, BTW do you think x58 + 9800GX2 is the best solution currently?

No. If you want to go X2 (ie, do the work of managing 2 GPUs) then just wait for the GTX295 X2. It’ll be out in a month.

Thanks, I know GTX295 is the best solution. But my bottleneck is switching from calculating to Disk/Memory IO. So, I can’t get big improvement on GTX295. BTW, if my boss don’t care the budget, I will buy one. External Media

It should be a $450, which is less than you’ll pay for the i7+x58+DDR3 setup. What do you mean that disk IO is your bottleneck? And why get 9800GX2 instead of GTX260?

$450? Sound great, I have discussed with my boss, he preferred more powerful GPU. So maybe GTX295(s) will go on its way :rolleyes: In my project, disk IO occupied more than 40%, GPU calculating occupied arround 10% and rest of them are hard to tune. Why I preferred duo GPU than more powerfull sin…

Using dual GPUs will only double performance if you are almost completely compute bound with very little I/O. My program, for instance, which otherwise is capable of running the entire calculation on the GPU requires a lot of communication between the two GPUS in a dual-GPU mode. Because of the extr…

Memory bandwidth bound kernels (that are nive and parallel) should benefit too in my imagination (as in, have not started to do multi-GPU yet, that will come next year)

Best solution for maximizing bandwidth? More then 5.7G H->D bandwidth except Tesla

Accelerated Computing CUDA CUDA Programming and Performance

nightingx9 December 21, 2008, 3:21am 6

Yes, someone in this forum got >5GB/s (pagable) on X58, but he get only arround 5.7GB/s for pinned memory. Why?

In fact, my MB is a very old version of Dell, 2GB/s is already a surprise to me. That’s why I need to buy a new one. Seems X58 is the best choice. What do you think?

Topic		Replies	Views
The fastest platform of GPU computing CUDA Programming and Performance	38	40809	January 19, 2010
Strange bandwidthTest results with new hardware Lower, and asymetric H->D, D->H CUDA Programming and Performance	18	26441	February 8, 2010
Memory bandwidth CUDA Programming and Performance	31	38795	October 5, 2007
Question about PCI-E transfer throughput CUDA Programming and Performance	13	420	April 5, 2025
Slow memcpy performance in dual-CPU, 10 GPU system CUDA Programming and Performance cuda , nsight , gpu	24	2653	January 18, 2023
Device Memory Bandwidth CUDA Programming and Performance	17	8685	January 17, 2018
Is this PCIe 2.0 bandwidth low? 3.1 GB/s pinned CUDA Programming and Performance	45	20498	December 28, 2008
concurrent D2H+H2D transfers? CUDA Programming and Performance	5	2593	May 10, 2016
Concurrent bandwidth test CUDA Programming and Performance	30	46636	April 27, 2012
PCI Express x16 bandwidth - host<->device transfer Bandwidth is much lower than should be CUDA Programming and Performance	38	68503	April 18, 2008

Best solution for maximizing bandwidth? More then 5.7G H->D bandwidth except Tesla

Related topics