There are some Xeons running these batches. I can have a look through the logs and report back what runtimes they give, if that would help?

I do not want to divert you from your much more important work to do. Perhaps such stats could be exported at the CPDN site (bit more useful than https://www.cpdn.org/cpu_list.php), rather than digging manually via logs (as most of us do when looking for sec/TS figures). There is the WUProp@Home project that does collect some metrics from BOINC machines and allows comparison between different hardware, but haven't check it recently and not sure how many CPDN users are on it.

I was going to write a web-scrapper of the cpdn logs anyway because I wanted to collect stats on the types of fails we've seen - I can pull out the runtimes/cpu types/etc at the same time. I'd be interested myself.

I realise there is no easy answer on what hardware to use for CPDN, so all the contributions so far are very useful. Thanks

Comes down to cost as well of course. Saying that I've just found a HP Z440 Workstation - Intel Xeon E5 V3 3rd Gen / 16GB RAM / 1TB HDD going for £20 on ebay! (working order apparently, some case damage). I'd want to check the max RAM I could put in first though. And the cases are big.

So the RYZEN 5950X may not be as powerful as the new models but for energy efficiency hard to beat.

If you care about energy efficiency, you should use ECO mode on AMD and limit PL1 and especially PL2 for Intel. You lose less than 10% of performance if you limit 7950X to 105W and cutting power limit by half should have similar story for Intel. That's also good for thermal. (https://www.youtube.com/watch?v=W6aKQ-eBFk0)

That's just unfortunately how scaling works. Both vendors pushed their top processor out of efficient range in the default configuration due to the competition for top performance, but their architecture is still highly efficient, more efficient than previous generation so long as you dial them back into the right range.

Some might, if you swapped to a business account, and paid them business-class money.

My current supplier who piggy backs off the BT infrastructure don't have anything faster in my street anyway however much i am willing to pay.

Mine also piggybacks off BT, and they lowered my download speed from 54 (line limit, actually "up to 80") to 32, claiming the area was overused so BT had removed the option for full speed. I don't believe them, I smell a rat. But I did manage to get £10 a month off the bill.

I cannot leave side off. The case is interlocked with the power supply so the power supply instantly shuts off if you even move the lever that opens it.

Then disconnect the interlock. By any chance is it a Dell computer? They do stupid things like that. Why on earth would it shut off when you open it? It's not like it's got live parts at 50,000 volts, or huge spinning belts like a car engine in there. And my car engine keeps running when I open the bonnet.

And I doubt that would help all that much.

These are temperatures right now with about half the cores idle (no WCG, no Rosetta, only two instead of five CPDN).
Room temperature 75°F. When room temperature is twenty degrees hotter in six or seven months from now the box will also be that much hotter. And when the cores get to 88.0°C, I must cut the cores running Boinc from 12 to 8 or even 6 or 7.

coretemp-isa-0000
Adapter: ISA adapter
Package id 0:  +65.0°C  (high = +88.0°C, crit = +98.0°C)
Core 1:        +65.0°C  (high = +88.0°C, crit = +98.0°C)
Core 2:        +62.0°C  (high = +88.0°C, crit = +98.0°C)
Core 3:        +61.0°C  (high = +88.0°C, crit = +98.0°C)
Core 5:        +60.0°C  (high = +88.0°C, crit = +98.0°C)
Core 8:        +59.0°C  (high = +88.0°C, crit = +98.0°C)
Core 9:        +64.0°C  (high = +88.0°C, crit = +98.0°C)
Core 11:       +61.0°C  (high = +88.0°C, crit = +98.0°C)
Core 12:       +61.0°C  (high = +88.0°C, crit = +98.0°C)

amdgpu-pci-6500
Adapter: PCI adapter
vddgfx:       +0.96 V
fan1:        2055 RPM  (min = 1800 RPM, max = 6000 RPM)
edge:         +44.0°C  (crit = +97.0°C, hyst = -273.1°C)
power1:        9.15 W  (cap =  25.00 W)

dell_smm-virtual-0
Adapter: Virtual device
fan1:        4273 RPM
fan2:        1126 RPM
fan3:        3920 RPM

Sounds like Dell or whoever made it designed the PC very badly. You need to find out where the bottleneck in removing the temperature is. What is the temperature of the CPU compared to the temperature of the top of the heatsink (test with your own thermometer, preferably an IR one). If the heatsink is hot to the touch, you need more fan. If the whole heatsink isn't that hot but the CPU is, better heatsink transfer compound could help. If the heatsink is hotter at the bottom than the top, you need a better one with heatpipes.

AMD Ryzen 7 3700X is what I have, currently with 32GB RAM.

Same choice that I took some years ago for one of my machines.
Nice and solid.

Got myself a new machine last week and chose the Ryzen 7 5700X and dropped 64GB RAM into the board.
Could add another 64GB.
As I'm supporting a lot of Boinc projects I went for a reasonable energy footprint (CPU has 65W TDP), as much threads as possible (sixteen), a processor with decent L3 cache (32MB) and enough RAM (chose a board that supports up to 128GB). Also added a GTX 1660 with six gigs of VRAM to crunch on it.
I put all that into an ITX case

There's your problem, too small. It can't breathe in there.

and had to take the CPU frequency down to 2.2GHz due to cooling reasons. Will soon enhance this situation with another cooler, but not running at full specs doesn't really bother me, as it also reduces energy consumption and is still way more power than I need for my everyday stuff.

There's your problem, too small. It can't breathe in there.

There's no problem.
I got what I wanted, and there are means for taking the temperature lower.
Just set the cooler to run more aggressive which took some temps away.
The next one is called Noctua and hopefully will arrive soon.

I had for some time thought about a Ryzen 7 4800U in a tiny box, and this one additionally has a decent GPU.
And if I really want to give it full power I have other cases in which I can put everything.
All's fine for me.

---

- - - - - - - - - -
Greetings, Jens

LOVE Noctua coolers. 5700x is a very underrated chip.. overclocks like a boss if you decide to go the other way and run it hot :)
ITX seems entirely appropriate for chips under 100w.. I love/hate em for assembly. Seems like mATX is getting less common though.

LOVE Noctua coolers. 5700x is a very underrated chip.. overclocks like a boss if you decide to go the other way and run it hot :)

I use the Zalman CNPS20X, second choice is Noctua NH-D15.

ITX seems entirely appropriate for chips under 100w.. I love/hate em for assembly. Seems like mATX is getting less common though.

Unless you live in a very small house, always buy a huge case. Much easier to work inside and much more airflow.

LOVE Noctua coolers. 5700x is a very underrated chip.. overclocks like a boss if you decide to go the other way and run it hot :)
ITX seems entirely appropriate for chips under 100w.. I love/hate em for assembly. Seems like mATX is getting less common though.

I've been looking at ITX cases, some of them are rather nice, but I agree with Peter, airflow can be a serious issue if not careful.

Out of interest - which case(s) did you use or prefer?

but I agree with Peter, airflow can be a serious issue if not careful.

I have a big case and liquid cooling. Not so much because air cooling isn't good enough but the liquid cooler is a lot quieter.

If the heatsink is hotter at the bottom than the top, you need a better one with heatpipes.

My heat sink has heatpipes.

---

but I agree with Peter, airflow can be a serious issue if not careful.

I have a big case and liquid cooling. Not so much because air cooling isn't good enough but the liquid cooler is a lot quieter.

Ah, sorry, I was asking just about ITX cases to TR UNESCO..

But yes, for Intel chips I'd always use a AIO because of the core placement on the die, for AMD a good air cooler is fine (though personally I dislike the enormous size of the things even if they are generally cheaper and last longer).

I've been looking at ITX cases, some of them are rather nice, but I agree with Peter, airflow can be a serious issue if not careful.
Out of interest - which case(s) did you use or prefer?

I have this one.
Barebone to which I added the CPU, CPU cooler, SSD, RAM and GPU.
The PSU is rated at 500 Watts, so I couldn't get the Palit GeForce RTX 3060 StormX (which wants a PSU with 550 Watts), but took the Palit GeForce GTX 1660 StormX.
The mainboard supports up to 128GB of RAM in four slots, and the it can handle Ryzen G processors, so a discrete GPU isn't needed.
A serious fan and cooler is absolutely needed! No AMD Wraith Stealth for this box, please!

---

- - - - - - - - - -
Greetings, Jens

I cannot leave side off. The case is interlocked with the power supply so the power supply instantly shuts off if you even move the lever that opens it. And I doubt that would help all that much.

These are temperatures right now with about half the cores idle (no WCG, no Rosetta, only two instead of five CPDN).
Room temperature 75°F. When room temperature is twenty degrees hotter in six or seven months from now the box will also be that much hotter. And when the cores get to 88.0°C, I must cut the cores running Boinc from 12 to 8 or even 6 or 7.

You could try disabling turbo boost in the bios. It should run cooler and draw less power from the wall. It's definitely a good summer time option in my experience.

[You could try disabling turbo boost in the bios. It should run cooler and draw less power from the wall. It's definitely a good summer time option in my experience.

I'm doing this all year long.
The machines run more smooth that way, and Turbo doesn't have that high a benefit.
Also, it's less stress for the machine.

---

- - - - - - - - - -
Greetings, Jens

but I agree with Peter, airflow can be a serious issue if not careful.

I have a big case and liquid cooling. Not so much because air cooling isn't good enough but the liquid cooler is a lot quieter.

Too expensive, especially for 8 computers with 15 GPUs! I just put them in the furthest away room from me and control them from here. Is using a grid of 0 guage wire, a 130Ah leisure battery, and three 1kW 12V lighting supplies unusual?

For AMD a good air cooler is fine (though personally I dislike the enormous size of the things even if they are generally cheaper and last longer).

But the water cooler has pipes and a radiator, you're just moving the size.

I have this one.

I don't understand, that says "168 (W) x 219.3 (D) x 218.3(H) mm" - how do you fit anything in there? How does even the motherboard get in? A motherboard is 300x300mm minimum. And every GPU I've owned is 300mm long. Perhaps I'm misunderstanding - is that a box for your Raspberry PI?

I cannot leave side off. The case is interlocked with the power supply so the power supply instantly shuts off if you even move the lever that opens it. And I doubt that would help all that much.

These are temperatures right now with about half the cores idle (no WCG, no Rosetta, only two instead of five CPDN).
Room temperature 75°F. When room temperature is twenty degrees hotter in six or seven months from now the box will also be that much hotter. And when the cores get to 88.0°C, I must cut the cores running Boinc from 12 to 8 or even 6 or 7.

You could try disabling turbo boost in the bios. It should run cooler and draw less power from the wall. It's definitely a good summer time option in my experience.

Most CPUs will take up to 100C, and they all slow down themselves if they were to get any hotter.

[You could try disabling turbo boost in the bios. It should run cooler and draw less power from the wall. It's definitely a good summer time option in my experience.

I'm doing this all year long.
The machines run more smooth that way, and Turbo doesn't have that high a benefit.
Also, it's less stress for the machine.

I leave it on the default which is automatic turbo (the one that comes with the CPU, not the overclock stuff which causes instability). CPUs never ever wear out.