Hardlimit test bank

[cobito]

@krampak What has changed since then is the structure of the database. It invalidates everything because it believes that test 4 is still the one for generic operations when, since version 1.2, test 4 is a memory test (tests 3 and 4 were swapped).

If you are interested in having some kind of statistics or verification of the validations in the style of the raffle page, let me know and I will implement it. From here to a week, I will be back with everything.

[Yorus]

@cobito said in Hardlimit test bench:

@yorus do you have oc on the micro or the memories?

Are you referring to the 4590s from the firm?. It's all in stock, micro at 3Ghz (3,7 with turbo) and memories at 1333.

[cobito]

@yorus OK, I'll take note. It seems like a bug in the validation system. Until a solution is applied, if it happens again you will have to repeat the test because the validation will be registered as "defective" and it will not be possible to send it.

Anyway, if it is what I think it is, the probability of the failure repeating is very, very low.

[Yorus]

I hadn't looked at the data in detail, you mean where it says Reported max frequency: 7000 MHz?

[cobito]

@yorus no, esa información es solo orientativa. Era si habías hecho oc a algún componente.

[Yorus]

As I mentioned through other means, it was a newly installed Dell laptop. Perhaps it was some half-finished update that caused it not to validate correctly until I restarted it.

[cobito]

@yorus Ok, unless the PC has faulty memories, I don't think it's his fault. In a few days I'll take a look at the code to see what could have happened.

The tabs for your i5-3210M and your i7-4600U are already enabled.

Remember that if you pass the benchmark, not only in the default mode but also in mode 0, you will get a more reliable comparison.

[Yorus]

@cobito said in Hardlimit test bench:

@yorus Ok, unless the PC has faulty memories, I don't think it's your fault. In a few days I'll take a look at the code to see what could have happened.

The fiches of your i5-3210M and your i7-4600U are already enabled.

Remember that if you pass the test bench, not only in the default mode but also in mode 0, you will get a more reliable comparison.

Ok, I'll keep that in mind. I'm testing PCs from work that pass through my hands like those two laptops.

[krampak]

@cobito There's no way to pass the Windows offline test, right? (like a pendrive). It would have come in handy now that I was without internet on the terrace

[cobito]

@krampak What you can do in that case is to validate offline, then you will get an error because the browser cannot find the page. Hibernate the computer with the browser open and wake it up connected to the internet. Refreshing the page that had previously given you an error should work.

[Xevipiu]

It would be good to be able to save the log to a file, and from the web to be able to upload the file

I've got myself a few Xeons, let's see what comes out of them

[cobito]

As it seems that new model submissions have stabilized a bit, from now on I will be posting the new micros added to the database and with this, we start with two:

· Core 2 Quad Q8400 by @krampak
· Pentium E5500 by @hAyO

[hAyO]

Maybe I'll send some more in these days, I'll try everything I have at home, old and new.

[cobito]

@Namiga brings us (in all available modes!) a recent micro: the i7-8700 (without k).

It is a CPU with 6 physical cores with 12Mb of L3 cache and a turbo frequency of 4.6GHz, which is 100MHz less than the K variant. The differences in frequencies at different loads mean a reduction in performance of 11-17% with a drop in TDP of 30W (more details).

For single-threaded programs, it performs similarly to the 7700K, which is not bad at all, and for multi-threaded it is quite similar to the Ryzen 1800X when we talk about optimized software, because if we focus on non-optimized software, the AMD micro eats the Intel.

Its price is just under 290€, very close to the Ryzen 1800X and about 40€ cheaper than the i7-8700K.

[Namiga]

And I strongly recommend that you buy another cooler that is not the stock one.
Its performance is not bad, it is worse.
After 5 minutes of video encoding, it was already at 99 degrees.. unacceptable.
In a while I will give you more data in another post

[cobito]

This morning @krampak has completed the benchmark in all modes of the i5-7200U, a mobile micro that came out a year and a half ago and offers performance similar to the previous generation 6500 series. Notably, it offers 90% of the performance of an i7-4790K in single-threaded tasks while running the 7200U at 70% of the desktop chip's frequency.

[cobito]

@Namiga brings us back in all modes a relatively recent micro: the i5-7300U. It is a portable processor with two cores and HT that appeared just over a year ago and that in nomenclature looks quite similar to the 7200U although there are appreciable differences in performance mainly in multi-threaded programs due to a higher frequency. In the rest of the characteristics, both the 7200U and the 7300U are identical

Of the processors of the same generation, the most similar is the i5-7500U that goes practically at the same frequency but comes with an Mb more of L3 cache. To find the most similar in our database you have to go to a higher category of a previous generation: the i5-6560U.

[Mystique]

Hello, I just passed the test on the Mi Notebook 13"

[cobito]

@Namiga is back, this time with an old dog: an Xeon E5645. It's a CPU that came out 8 years ago (Westmere core), you have 6 cores without HT and it runs at 2.8GHz as a maximum.

Coincidentally (I say it because the model has come out several times recently), its performance in multithreading is very similar to the i5-7200U (yes, with only 2 cores) and it is clear that the years have not left it in a good place in single-thread performance.

Apart from that, we do not have in the database a current desktop CPU that resembles it in the slightest; only portable micros like the one mentioned.

[cobito]

This morning @Namiga has once again contributed a couple of CPUs: an i5-4440 and a Celeron N3450.

The first of these is a mid-2013 desktop Haswell with 4 non-HT cores very similar in performance in all aspects to the i7-4720HQ laptop processor. The closest modern micro for which we have data would be the i3-7100 for multi-threaded tasks. For single-threaded tasks as is usually the case, we have to go back to previous generations to find something similar.

The second processor is in my view the most interesting for its low TDP: only 6W. It is the Celeron N3450 which in the case of the results sent by Namiga, is mounted on a CHUWI LapBook, a 14.1" ultrabook and priced at around €450. With that TDP, its 4 cores and 2.2Ghz turbo frequency makes it very difficult to find similar processors apart from the N3540 which as its name suggests, is from the same fifth. And the complication of the comparison comes from the fact that its performance is comparable to CPUs from the Core 2 era but only in FPU processing. As soon as the benchmark for software optimized for SSE3 (the highest set available on this Celeron) is passed, the N3450 eats the veterans LGA775 for breakfast. There are many LGA775 models that are comparable, but each model is in areas that are too specific to be able to choose just a couple of them.