I mean the Fermi GPU utilization is pretty much CPU speed dependant, and WU type dependant. If these factors won't change for the better in the future, then the ACEMD client will need 8GHz+ CPU cores to feed the new GPUs.

They could always go to larger molecules, increasing the amount of work per teim step for the GPU. But lower end cards would get choked by this.

MrS

---

Scanning for our furry friends since Jan 2002

GPU utilization is 96-98% if using only the GPU and there will be no problem at least for a couple of generations. GPU utilization is low if you don't use SWAN_SYNC or for some workunits which uses a little of CPU. This last case will be less and less important as the new application moved even this tiny bit on GPU.

gdf

It is the case that GPU's are progressing faster than CPU's, so any app that depends partially on a CPU will increasingly hinder the GPU performance, in the long run. However there is a bit more to it that brute force speed. Take for example your 2.8GHz Pent D - this 3 generation old processor is not actually as quick as a 2.4GHz IC2D (E6600). In turn a Wolfdale is about 10 to 15% faster than an equally clocked Conroe. Move on to an i3 and you see another increase in performance, and then again when you move to Sandy Bridge. These 32nm SB processors clocks well and 5GHz is not too hard to reach. By the time we move to 22nm GPU's, it will be old hat for CPU's and 5GHz will be common for high end CPUs. By then I would expect to see many app improvements, but even if there was not it would not be all doom and gloom, so long as you upgrade you CPU when you are upgrading your GPU.

I made a couple of experiments in the weekend, and I've concluded that pairing my GTX580@900MHz with an i3-560@3.33GHz shortens the processing time compared to my overclocked Core2Quad9560@4GHz (no wonder, the i3 has an integrated northbridge), but not as much as the Core2Quad9560 does compared to the Pentium D 820 (no wonder, it's quite old). But I still think the FPU of the Core i3 (i5, i7) is not faster than the FPU of the Core2, but the integrated northbridge boosts the performance (the lower the GPU utilization is, the higher the boost will be). Another side effect of this boost: I had to raise the voltage of the GTX580@900 to 1.083V when it was in the i3 MB, while it runs fine at 1.062V in the Core2Quad MB.
To be on topic: I've overclocked both GPUs of the GTX590 to 700MHz (fan at maximum, 72°C, noise is almost intolerable), and it seems to be running fine (in the Core2Quad MB, so I'm wondering how much overclocking it could take in the i3)

Yes, the FP execution units in 1st generation Core i CPUs are the same as in Core 2 CPUs. But due to numerous tweaks actual hardware utilization is better (depending on load, of course).

The higher voltage using the i3 is intersting. Could be increased GPU temperatures due to the higher GPU utilization, which reduces its maximum frequency at a given voltage slightly, in turn requiring more voltage for the same clock.
Or the PSU could be worse (e.g. stronger ripple).

MrS

---

Scanning for our furry friends since Jan 2002

I'm going on with my experiments in this weekend. This time I'm using a Core i5-2400 (3.1GHz/3.4GHz) in an Intel DH67BL MB. The GPU is a GTX580@900MHz. My experimental host has processed two TONI_AB WUs since I've changed the CPU and the MB, they took about 16.192 sec = 4h30m to finish. Now it's processing an IBUCH_1_mutEGFR, so I'll be able to compare the performance of the i3-560 and the i5-2400, when it'll finish.