AMD Ryzen 7 5700G Linux Performance

[ddriver]

Please show me where I can buy one. They've been out of stock forever. Preferably a 5600U.

The Asus PN51 is decent, and seems to available in stock here and there. It sold out quickly from all the big stores, understandably, but you may be able to find one in some smaller local retailer that got stock.

I also presume they did not end production, but are merely scheduling another batch. Poor availability shouldn't be unexpected in this market climate.

Lastly, do not ignore the 4000 series U barebones, they are still way, way faster than what you are replacing. They actually offer better bang for the buck, even if 10-15% slower.

[CaptainLugnuts]

I can't find any GE CPUs in prebuilt systems in Canada. I do prefer to build my own so I can make it silent and as efficient as possible.
I have probably put more into electricity over the last decade for the HT box than it cost to build. All of the prebuilt boxes use shit parts on low-end machines.

[domih]

Set the power profile to energy saver or whatever and you are there even with a 5000 G.

Yes. A "ge" is basically a "g" with a lower base clock, but I guess AMD also saves power elsewhere in the CPU at the performance expense obviously.

Another way to buy a "ge" if it is absolutely what you want, go buy an OEM PC with a "ge", replace the "ge" with another compatible CPU, put the "ge" in your system and finally sell the OEM PC used "like new" not a scratch on eBay signaling you put a faster CPU :-)

Or directly buy a used "ge" from eBay (search for "AMD ge" for instance). Issues: scalper prices on the recent ones, ES (?), genuine offer (?). This should not stop you though, before the pandemic back in 2019 I bought a used TR 2950X well below MSRP and I never had any problem with it and it is still running. Have I ever been burned on eBay? Sure I bought 4 used HGST He 6TB, 3 were good, 1 had probably visited a country at war and had unrecoverable errors. But given the price, it was still a good deal. The trick is to be patient for the "good" deals and do your home work to avoid the "too good" deals.

Or get a 5000 U series barebone, those are 15-20 watts, and will run circles around your 35 watt 2100T.

Mmm... Is not AMD 5000U series FC-BGA? Not AM4?

---

On my side a 4750g idle with Ubuntu Mate burns ~26W at the wall, climbs max to ~78W during boot, 80W running a Phoronix Test Suite with one exception: climbed to 139.3 W (!) during the Video Encoding Test Suite.

In comparison an ASRock 4x4 4800U box idle with Windows 10 desktop between 8.5 and 14W(*) at the wall, climbs max to 54W during boot. Note: this box gets hot like crazy as soon as the CPU actually do something significant and let's say the fan is not silent which means it could be an issue during an HTPC viewing. I would advise to rather use a much bigger box with plenty of ventilation holes (mesh) and use a bigger heat sink with a 90 or 120mm fan (e.g. Noctua) so noise is not an issue. On the other hand, these boxes are great to fix between a monitor to save room on the desk. You can't always get it all :-)

I'm pretty sure the 4750g looks at the 4800U in its rear mirror during benchmarks (I have not merge the results to see).

(*) It seems that Windows 10 always finds something to do to keep busy and burn calories to stay in shape I guess.

[CaptainLugnuts]

Or get a 5000 U series barebone, those are 15-20 watts, and will run circles around your 35 watt 2100T.

Please show me where I can buy one. They've been out of stock forever. Preferably a 5600U.

[ddriver]

You and me both.
I've been waiting well over a year for a low power solution to replace my ancient Sandybridge 2100T home theater box.
C'mon AMD, get it together and release these things already!

Set the power profile to energy saver or whatever and you are there even with a 5000 G.

Or get a 5000 U series barebone, those are 15-20 watts, and will run circles around your 35 watt 2100T.

[CaptainLugnuts]

what happen to GE variants of 5000 series?
will they only be available for OEM builds?

You and me both.
I've been waiting well over a year for a low power solution to replace my ancient Sandybridge 2100T home theater box.
C'mon AMD, get it together and release these things already!

[ddriver]

Please be careful, there has been bad information circulated regarding ECC support on APUs. In the past, people have posted that it works because their system operates with ECC UDIMMs installed, not realizing the RAM was operating in non-ECC mode. I myself bought a Ryzen 2400G and ECC RAM but dmidecode showed it running as non-ECC.

It is very possible AMD has fixed this issue but I recommend waiting for a dmidecode screenshot to be posted before making purchasing decisions.

In order to get ecc running you need cpu support and motherboard support, for starters the mobo has to have the extra traces, which many don't, and also firmware support.

Asrock have always explicitly stated that ecc is not supported on NON PRO APUs. So it is no surprise that the 2400g didn't. They are my goto for ecc systems, almost all of their boards support it.

They have updated their info to:

For Ryzen Series APUs (Picasso and Renoir), ECC is only supported with PRO CPUs.

This no longer puts apus under the same umbrella, leading me to presume that the 5000 series cezanne apus indeed support it.

Also, Wendel from L1T claims it will be supported this time.

[Paradigm Shifter]

I'd like to see a performance comparison between 2133/2666/3200/4000, as the overclocking forums I'm active on swear by 4000MHz RAM, but I'm still chugging along with 3200MHz on one system (it originally had 2666 and I noticed basically no difference in performance in my daily workload) and even 2133MHz in one box! But my daily workload is a mix of CPU, RAM, GPU and I/O load (not all maximum at the same time, but each will be fully loaded at some point during a normal workload) so there are many factors which come into play. Faster RAM is nice, but frankly more cores and faster I/O will give me larger gains than faster RAM.

It basically boils down to buy the fastest stuff you can afford at the capacity you require. If the price difference between 2666/2933 and 3200 is minimal (it was when I upgraded from 64GB 2666 to 128GB 3200) then why not go faster? But with 3600/4000/4400 RAM the prices go crazy pretty quickly.

edit: ...and I forgot to comment on the CPU.

I've been able to find them in stock here (finally) so am weighing up buying one to replace the Ryzen 1700 in my home PC. A 65w TDP is perfect as it's the same as the 1700, but should be a big jump in CPU work. Only problem is do I try to update the BIOS of my current board (if it will support it) or just replace that too? And suddenly what wasn't so expensive gets that way quickly. Bah.

[willupowers]

Is the CPU package power reporting ok? It seems there might be something weird going on since the 11600K is trending higher than the 11900K on the light load/idle states. Any possibility of some power test results at the wall or at the PSU out for idle and non-idle?

[domih]

The 3200 and 3600 exchanged barbs in both directions in all the testing suites and mostly within margin of error.

This kind of situation always make me think about what a great new feature the Phoronix Test Suite could implement:

Add 3 columns to the Test Results graphs:
- %: the difference expressed in percentage. Personally anything under 5% is not worth $$$.
- Comparison: based on the estimated margin of error: Significant, Borderline or Non-Significant difference.
- Who will notice: Anybody, Power User, Professional, Expert

I'm not a gamer, so I do not know how one feels about Frame Rates. But for a beginner gamer, is there really a difference of user experience between 125 and 150 FPS? or 60 and 90? I don't know. What I do know is that even for a 3 FPS difference while we are in the stratospheric 100 or above FPS there are Volga-river-long online discussion threads about which hardware is the "best of the best" based on the result. Really?

Not talking about Phoronix here but how many times one can see online stuff like "hardware A" rates at 2387, while "hardware B" rates at 2490 and therefore B is so mucho much better, while in fact the difference is 4.3% and a lambda user will probably never see the difference.

I don't even want to talk about charts where the origin is not zero in order to "highlight" the difference.

Phoronix could show the way to the pseudo-science statisticians from a few major tech news sites (I'm not giving names) and restore some sanity (...)