For the Folding@Home single precision benchmark the 2070 FE matched the results from the 1080Ti FE card.

Yeah, depending on the benchmark it looks like it bounces between the GTX 1080 to GTX 1080Ti performance levels. But given current pricing, you'd be better off with a new GTX 1080.

Having said that, Phoronix have released the Linux benchmarks for the RTX 2070, that is compute benchmarks.
For Linux compute work it generally matches, or beats, the GTX 1080Ti, and it's performance per dollar actually puts it in front of most of the other video cards (RTX and 900 & 1000 series).

While it might be a humho card for gaming, it looks like it could be an excellent computing performer.
It will be interesting to see how it does perform for Seti crunching.

---

Grant
Darwin NT

We should know shortly how well a 2080Ti does with the CUDA10 app when Vyper gets his card this week.

Aaand it's here..

At first glance it seems like Titan V is still the king ofcourse. Will let it run with a small cache because this is not the right computer it should be in. So this is just temporary.
Feel free to check and comment. http://setiathome.berkeley.edu/show_host_detail.php?hostid=8598043

Pics or it didn't happen :)

https://drive.google.com/file/d/1YbAemMGzfmx5U3g2h9HFbhkvSV984LGP
https://drive.google.com/file/d/1pjIK3jQ4IcCd8rayEcWGo5hP7mECTIfb

---

_________________________________________________________________________
Addicted to SETI crunching!
Founder of GPU Users Group

A quick look and Juan's 1080Ti seems to be around 80s for the BLC22 tasks in your video showing 55-57s.
So roughly a 30% gain.

sweet performance. that thing sure is power hungry though. using nearly 250W continuously.

---

Seti@Home classic workunits: 29,492 CPU time: 134,419 hours

If Gtx's are "dead" I wish their prices would go down so I could afford some 1080Ti's :)

---

A proud member of the OFA (Old Farts Association).

If Gtx's are "dead" I wish their prices would go down so I could afford some 1080Ti's :)

they are definitely down. in the last 3 months or so i've purchased like 8 or 9 1080tis. all for around $500 including shipping.

---

Seti@Home classic workunits: 29,492 CPU time: 134,419 hours

..... See if it's any better on the higher end cards.
It has sm_75 code, so it's a little bigger. It will work with the 750Ti & higher in 14.04.1 and higher.
It still uses API 7.11.0 and S_LIMIT 127. You need the driver from here, https://www.nvidia.com/Download/driverResults.aspx/138279/en-us
It's here, http://www.arkayn.us/lunatics/setiathome_x41p_V0.97b2_x86_64-pc-linux-gnu_cuda100.7z

Here's a New build you can try on the 2000 series. It's basically the same as the b2 version, but, it's the earlier 0.97 version. It uses the older API 7.5.0, if you have an API line in your app_info.xml. Otherwise it's the same as b2, works with 14.04.1, CC=5.0 and higher, uses S_Limit 127.
On my machine it's a couple of seconds faster than the b2 CUDA 10 app; http://www.arkayn.us/lunatics/setiathome_x41p_V0.97_x86_64-pc-linux-gnu_cuda100.7z

We should know shortly how well a 2080Ti does with the CUDA10 app when Vyper gets his card this week.

Aaand it's here..

At first glance it seems like Titan V is still the king of course. Will let it run with a small cache because this is not the right computer it should be in. So this is just temporary.
Feel free to check and comment. http://setiathome.berkeley.edu/show_host_detail.php?hostid=8598043

Pics or it didn't happen :)

https://drive.google.com/file/d/1YbAemMGzfmx5U3g2h9HFbhkvSV984LGP
https://drive.google.com/file/d/1pjIK3jQ4IcCd8rayEcWGo5hP7mECTIfb

Congratz Vyper. Yes the Titan V is still king with 80 SM's versus the 68 of the 2080Ti and the fact it has 1/2 FP32 compute to boot.

Looks like about 5 seconds slower than Petri's Titan V. Was a little surprised at the power usage myself. That is a lot more than the Titan V pulls from Petri's posts.

---

Seti@Home classic workunits:20,676 CPU time:74,226 hours

A proud member of the OFA (Old Farts Association)

Thanks Keith..

It seems like it benefits with the -nobs parameter (three seconds) TBar. Otherwise it was roughly the same 57-56 seconds runtime. With -nobs it went down to 53 seconds.
Gonna try Petris with Nobs now.

---

_________________________________________________________________________
Addicted to SETI crunching!
Founder of GPU Users Group

You might try adding the -pfb 32 command line option too. Petri runs with it.

---

Seti@Home classic workunits:20,676 CPU time:74,226 hours

A proud member of the OFA (Old Farts Association)

So i'm curious. I just run a Nvidia Geforce Gt 730 in the system here. It does one unit every two hours or so.

What would one of these expensive cards do? Do they have more cores and such? How much faster would they turn units back in?

So i'm curious. I just run a Nvidia Geforce Gt 730 in the system here. It does one unit every two hours or so.

What would one of these expensive cards do? Do they have more cores and such? How much faster would they turn units back in?

Yes.
My AMD R9 380 returns a unit every 8 to 10 minutes.
A Nvidia 1080TI in less than 5 minutes.
On Linux with the special app 2 minutes.

---

With each crime and every kindness we birth our future.

So i'm curious. I just run a Nvidia Geforce Gt 730 in the system here. It does one unit every two hours or so.

What would one of these expensive cards do? Do they have more cores and such? How much faster would they turn units back in?

Yes.
My AMD R9 380 returns a unit every 8 to 10 minutes.
A Nvidia 1080TI in less than 5 minutes.
On Linux with the special app 2 minutes.

A gtx 1060 3GB running about $150 on eBay will run a SOG gpu task in about 7-8 minutes under Windows 10 and about 3-4 minutes under Linux/Cuda91 (Linux/special app).

Tom

---

A proud member of the OFA (Old Farts Association).

Hot dang! and here I was impressed with a two hour turn around on the units my system sends. Compared to 5-10+ hours back in 2005 and before.

Trying to remember what I was using when Art bell got me into it. At that point in time a 300 mhz pentium II system was still kicking around the house along with a 2.4 ghz Pentium 4 with HT courtesy of a gateway store closing and dumping it in the trash


Can't imagine doing units that quick. Turning in 5 every 2ish hours isn't bad though (4 cpu and 1 gpu)

My GTX 1080 alone will do about ~880wu per day with average time of ~1:38 per task (around 37wu per hour) running the linux special app with the current..
I wonder how much faster my 6700K/1080 is VS my first computer running SETI (pentium 150mhz). Did the workunit size changed since the early days?

---

I thought the reason primarily for the move to boinc and away from the seti@home classic client was more computation and such? Much of it is over my head due to the math load involved so others may know more. Even if it's the same size, probably more "work" is being done to find the signals?

---

Historian for the Defunct Riviera Hotel and Casino, Former Classic Seti@home user for Team Art Bell. Greetings from the High Desert!

That and the ability to bring gpus into the crunching fold. To get caught back up on the technical aspects of the analysis of signals, you might want to browse read through the Technical News forum.
If you really want to know what is going on with the science apps, search for the posts by our two volunteer app developers, Raistmer for the stock OpenCL apps and petri33 for the beta CUDA apps.

We have continuously improved the search algos in the science apps since the move from Classic to BOINC infrastructure.

---

Seti@Home classic workunits:20,676 CPU time:74,226 hours

A proud member of the OFA (Old Farts Association)

Thanks, I'll go take a look at that forum later. I miss the classic seti app, but understand the move. Just always looked cool and "techie" when it was running, even though it was wasting cpu cycles for the graphics. Newer one just doesn't have the draw for me like the older one

---

Historian for the Defunct Riviera Hotel and Casino, Former Classic Seti@home user for Team Art Bell. Greetings from the High Desert!

Thanks, I'll go take a look at that forum later. I miss the classic seti app, but understand the move. Just always looked cool and "techie" when it was running, even though it was wasting cpu cycles for the graphics. Newer one just doesn't have the draw for me like the older one

I still get the "cool" graphics when I am running standard CPU seti tasks under Windows. I even get things when I am running the non-Seti BOINC cpu tasks.

Tom

---

A proud member of the OFA (Old Farts Association).

For the Folding@Home single precision benchmark the 2070 FE matched the results from the 1080Ti FE card.

Yeah, depending on the benchmark it looks like it bounces between the GTX 1080 to GTX 1080Ti performance levels. But given current pricing, you'd be better off with a new GTX 1080.

Having said that, Phoronix have released the Linux benchmarks for the RTX 2070, that is compute benchmarks.
For Linux compute work it generally matches, or beats, the GTX 1080Ti, and it's performance per dollar actually puts it in front of most of the other video cards (RTX and 900 & 1000 series).

While it might be a humho card for gaming, it looks like it could be an excellent computing performer.
It will be interesting to see how it does perform for Seti crunching.

Nice going! Try keepp2 and clock the memory to what it is in p0. Also set power limit to 300w.

---

To overcome Heisenbergs:
"You can't always get what you want / but if you try sometimes you just might find / you get what you need." -- Rolling Stones