The following occurs to me: the 960 (Maxwell) should be better than the 780 (Kepler) on a computation basis, much like successive generations of CPUs are better than the previous. Given that the limit for cards seems to be about 3 WUs at a time, shouldn't the 960 be better than the 780 for SETI?

Yes, I know the 780 has more computation units (whatever they are called), but are the SETI apps written to use more if available? And, if not, then a 960 should beat a 780 (or 780Ti) because of the much higher GPU clock, right?

Please help me understand, as I would like to replace my two 780s with 960s (if my analysis is correct). This should be for free or even better, as the 780s are still better for gaming because of the larger (if slower) chips, and can be sold to buy the 960s and (maybe) have some cash left over... Which would be a win-win.

---

I`m certainly no nvidia person but i dont think a 960 can beat a 780 or 780TI.
Frequency is not everything in case of processing speed.

I`m sure Jason can explain that much better.

---

With each crime and every kindness we birth our future.

The numbers that stand out to me are single precision processing power and the same number divided by watts. It would appear that a 780 has big edge in the former while the 960 has a slight edge in the latter.

Generally speaking (there are a lot of variables to look at, as Mike suggested), The benefit of the Maxwell architecture is performance per Watt. Looking at market segmentation of the models, with a 960, which is a midrange card, you could expect somewhere around the performance of the prior generation ( + say 20-30% ) in the similar class, but using less power. That should place performance above a 760 overall, but quieter and more refined.

With the 780 comparison, the chip was a different breed (GK110) which is a monster. Once you get above a certain amount of raw compute horsepower, the limitations become largely related to memory bandwidth, and how smoothly you can 'feed' the GPU work (which includes all kindos of other system issues).

So in short, there are ways you can ensure you're getting the most out of your cards, though going from 780s to 960s might not be a straightforward comparison, depending on if you have considerations like power and heat. Directly, with current applications ( MB, AP and other ) limitations are more likely not with the compute cores themselves.

---

"Living by the wisdom of computer science doesn't sound so bad after all. And unlike most advice, it's backed up by proofs." -- Algorithms to live by: The computer science of human decisions.

also, check this:
http://gpuboss.com/gpus/GeForce-GTX-960-vs-GeForce-GTX-780
;)

---

non-profit org. Play4Life in Zagreb, Croatia, EU

I understand what you guys are saying, but the "way faster" stuff is in terms of GAMING, not running apps, and especially SETI apps. The latter is what I was referring to. The 780 is better for gaming because it has lots more computation streams, and is built primarily for gaming, not computation, as, of course, also is the 960.

To the extent it is designed that way, I agree, it is faster, overall, as GPU boss says. But are the SETI apps designed differently, and therefore have different characteristics than games? And, if so, does the relative performance of SETI on the 960 vs. 780 differ from games? That's the question I was trying to get at.

---

There is some difference because science apps use cuda and opencl and games are using directx. Games can use more memory which is related to display resolution and detail levels.

If you lazy math and multiply cuda cores times gpu clock you will get much higher numbers for a 780 than compared to a 960/760. And I'm not even mentioning memory bandwidth which can come into play when you run multiple simultaneous WUs. As much as I would like to believe that something that costs $200-250 now will destroy something from the previous generation that cost $650, I don't think that the comparison is fair.

Yes relative performance for different software ( either games or apps ) will vary considerably depending on how those apps/games are written. older games will tend to run at very high frames per second, and newer texture heavy ones become more framebuffer dependant, depending on the settings and resolution driven.

For non-graphics compute applications, you will have similar considerations, but with different balance and bottleneck. There is so much (theoretical) compute horsepower in either GPU, that for 'our' purposes, on these high performance GPUs, the limiting factor is the VRAM, driver latency, and system overheads dictated by the aging application designs.

I mention the aging application designs, not to denigrate their effectiveness etc, but to point out that underlying Cuda is DirectX, and for NV's OpenCL implementation similar calls.

The DirectX implementation API level under the 780 is 11.2, while the 960 is DirectX12, which is not released formally until Windows 10.

The difficulty that presents, is that there are shifting goalposts in terms of the underlying infrastructure, right up through OS and drivers and the applications. Apples to Apples comparisons therefore become difficult to find, and depend on your precise conditions & requirements.

More detail on your needs in the change would help the comparison, as there are just too many variables to make firm assertions about what you would likely achieve (other than reduced power and heat). Boinc RAC, for example, has something like a +/- 37% variance under stable running conditions, so would be a bad comparison to make. Number of workunits in a specific angle range controlled situation might be workable, if power was measured and factored in.

If the comparison had been between 780 & 970 or 980, then it might be a bit easier to draw conclusions (but not much if not concerned about power/heat).

My usual tactic when things are that hard to call, is to sit tight as is, and wait for the next gen where the jump is clearer.

---

"Living by the wisdom of computer science doesn't sound so bad after all. And unlike most advice, it's backed up by proofs." -- Algorithms to live by: The computer science of human decisions.

Jason - on a one for one basis, are Maxwell cores more powerful computationally than Kepler? (Like Haswell > Ivy Bridge > Sandy Bridge) That's the core (pun intended) of my question.

---

Jason - on a one for one basis, are Maxwell cores more powerful computationally than Kepler? (Like Haswell > Ivy Bridge > Sandy Bridge) That's the core (pun intended) of my question.

Yes, provided 'One for One' means 1 Watt to 1 Watt (the only fixed reference I can really compare). There is both more computation per Watt 'possible', and better facilities to hide latencies/overheads such that higher efficiency is extracted.

---

"Living by the wisdom of computer science doesn't sound so bad after all. And unlike most advice, it's backed up by proofs." -- Algorithms to live by: The computer science of human decisions.

Actually the 960 would be just short of a 770 in performance while using around 55% of the power of a 770.

Cheers.

Actually the 960 would be just short of a 770 in performance while using around 55% of the power of a 770.

Cheers.

sounds about right to me (with healthy doses of your mileage may vary)

---

"Living by the wisdom of computer science doesn't sound so bad after all. And unlike most advice, it's backed up by proofs." -- Algorithms to live by: The computer science of human decisions.