Hardlimit test bank

[whoololon]

Let me see if I understand it correctly: the program executed by default shows reliable results, but when adjusting the parameter of how many threads we want it to use, it is prone to showing "unusual" results...

If that is the case, personally I would only let the results obtained by default be validated, at least until the incident is resolved... we just needed an army of pollagorders cheating at solitaire and, by the way, falsifying the ranking (this is the most serious thing for me, after all, I think what is intended is for the table to be reliable).

The option to choose the number of threads can be maintained, warning that it may give erroneous results and that they are not "official", for those who like tinkering.

[cobito]

Surely, by tomorrow or the day after (from there, depending on how long it takes Microsoft to certify it), version 1.4 will be ready, which will come with the issue of falsified scores fixed, among other changes.

If any of you have a current and powerful processor, I could use a screenshot of the CPU tab to put on the Store page, since I only have a few older PCs around here.

[whoololon]

This is the most powerful thing I have in my house, I don't know if it's what you're looking for.

[cobito]

@whoololon Thanks for the image. In the end I didn't put it because it seems to be very compressed and doesn't look good in the Store.

Regarding the program, version 1.4 is already available. You can find the details in the first message of this thread. In essence, among other things, the issue of falsified punctuation has been corrected and some changes have been made to the interface.

For now, you can still choose twice the number of threads of the maximum processor only in models without HT/SMT.

[krampak]

Very cool the latest version!! it looks more professional and you can tell a lot about the reduced loading time.

[whoololon]

And to celebrate, we inaugurate it with a radiant i3-3120M. Edit: By the way, Smart Screen is still popping up, at least on W8.1.

[cobito]

@krampak said in Hardlimit Test Bench:

Very cool the latest version!! It looks more professional and the reduced load time is noticeable.

Thanks. I'm glad you can see the difference in the boot time.

@whoololon said in Hardlimit Test Bench:

And to celebrate, we inaugurate it with a radiant i3-3120M.

Edit: By the way, Smart Screen is still popping up, at least on W8.1.

Perfect, it's been a while since anything new came in.

Smart Screen is still happening on Windows 10 as well. To be honest, it's taking longer than I've read around. Maybe it hasn't been downloaded enough times yet, or maybe it really is important to download it from Internet Explorer or Edge. I hope it disappears in the next few days.

[Xevipiu]

New micro

[url=https://bm.hardlimit.com/result.php?bm=0f38c8bc44c5faeaa7a1f2038f2a2b492134] [img]https://bm.hardlimit.com/screenshot.php?bm=0f38c8bc44c5faeaa7a1f2038f2a2b492134&style=1[/img] [/url]

https://bm.hardlimit.com/screenshot.php?bm=0f38c8bc44c5faeaa7a1f2038f2a2b492134

[cobito]

@Xevipiu Is it a sample of engineering? Perhaps of a Core i9-9900K/S?

[Xevipiu]

@cobito said in Hardlimit test bench:

@Xevipiu Is it a sample of engineering? Maybe of a Core i9-9900K/S?

No, it's from a 10th Gen series, an i9 10980HK, throttled, but it holds its own

[cobito]

@Xevipiu said in Hardlimit test bench:

@cobito said in Hardlimit test bench:

@Xevipiu Is this a sample of engineering? Maybe from a Core i9-9900K/S?

No, it's from a 10th Gen series, an i9 10980HK, capped, but it holds its own

Ok, I was confused by the signature because yours returns 906ED of which all are Coffee Lakes.

Actually it makes sense according to the results because it pulls 15-20% ahead of the Core i9-9900K in multi-thread.

It remains in a very good position in single-thread. If you remove the memory test (where Zen 2 usually does well) it would be first in the single-thread ranking.

[Xevipiu]

@cobito said in Hardlimit Test Bench:

@Xevipiu said in Hardlimit Test Bench:

@cobito said in Hardlimit Test Bench:

@Xevipiu Is this a sample of engineering? Maybe from a Core i9-9900K/S?

No, it's from a 10th Gen series, an i9 10980HK, capped, but it holds its own

Ok, I was distracted by the signature because yours returns 906ED of which all are Coffee Lakes.

Actually it makes sense according to the results because it beats the Core i9-9900K by 15-20% in multi-thread.

It remains in a very good position in single-thread. If you remove the memory test (where Zen 2 usually does well) it would be first in the single-thread ranking.

Think that the memory issue is capped at 2140 or 2400mhz, it's a big handicap, the ZEN or the same 9900k beat me

Here you have the family of micro-code's of processors "ES", for your database

[cobito]

The version 1.5.0 of the program has just been released the program version that mainly comes with changes on the information related to the memory:

· Now it detects "form factor" of integrated memory in processor encapsulation (SoC).
· Now it detects memory types HBM, HBM2, DDR5 and LPDDR5.
· A bug has been fixed that made that under certain memory configurations, the information of the memory type, form factor or frequency was not shown in the program.
· Now the brand and part number of the memory is shown in the program.
· *Also the brand and part number of the RAM memory is sent in the validation process.
· *In addition, the available instruction repertoire is also sent in the validation along with the detection of hypervisor (execution on virtual machine).

*The information related to the memory and the available instruction repertoire will be shown in the central soon. This will also give rise to the creation of a database of memories along with the results of the memory test. Regarding the detection of hypervisor use, soon the results sent from a virtual machine will be discarded for the calculation of statistics.

For the moment the executable is available and in the next few hours it will be possible to download/update it from the Microsoft Store.

As usual, if you see something strange, do not hesitate to comment on it.

[cobito]

It seems that we have been for over a month with the test bank database blocked and, therefore, without receiving validations during this period. Since yesterday, the validation system is operational again.

[cobito]

Histograms have been added to the validated results page. Now, when you validate your result, if there are more than 5 validations in the mode in question, a histogram per test will appear where you can see the frequency in which the scores are repeated in a series of ranges. It also indicates in which range your result is located. Example. They take a little while to load and there are still a couple of things to fix, but for most cases, they work correctly.

In addition, Zen 3, Tiger Lake and Rocket Lake are added to the list of architectures, so it is now possible to see the rankings of the CPUs that we have received from said architectures.

[cobito]

The central extends its tentacles to the world of motherboards. The menu now includes a list of motherboards sorted by socket. Within the list, they are classified by chipset. In addition, in the tab of each processor, a list of motherboards where the micro has been tested is shown.

[cobito]

The motherboard database has been completed (a few of the validations made in recent days are still pending). Example: LGA 1700 motherboard list.

A database of PCs and laptops has also been created, which can be accessed from the "Computers" menu. They are classified by architecture and brand. Many are still missing from this (I am at 15% of all those we have). It will be completed little by little. Example: list of Skylake PCs and laptops.

Finally, extra information about the processor has been added to the validation result, paving the way for adding extra information about the motherboard and memory. Example: this validation.

The motherboard and computer databases are still very basic. Extra information such as type of memory, type and number of connectors and other typical characteristics of these gadgets still need to be added.

[cobito]

Finally, the database of motherboards and computers has been completed. In total, we have 540 different models.

In addition, the datasheet for each processor now shows the list of computers where the CPU has been tested alongside the list of motherboards. Example.

The type of memory and form factor are also shown in the datasheet for each motherboard and each computer. Example.

Finally, the validation results now show more precise and detailed information about the motherboard or computer. Example with computer.
Example with motherboard.

Next stop: memories.

P.S.: I wanted to thank everyone who has sent validations and those who continue to do so, because the central would be nothing without your contributions.

[cobito]

To compensate for the lack of news on the front page last week, we present version 3.11 for Group Work of the central that is more tocha than usual.

We have added the database of RAM memories that are sorted by type of memory. This now allows us to show the relationships between motherboards, memories and processors in each tab (what has been tested with what). We have a total of 300 memory models.

The new memory database along with the motherboard database that debuted in the previous version, has served to show all the available information at the time of validation. With this, the user obtains a detailed report of their hardware every time they validate a result (as long as their hardware is in our database). Example.

Similar computers are also shown in the tab of each computer. Similar computers are considered those that mount the same motherboard.

Another pending change was the list of architectures, which has been updated. The last one added has been Alder Lake that debuted in 2021. At the moment we have 9 cpus of this hybrid architecture of Intel.

A small change: the "Architectures" menu is now the "Processors" menu, since the computers are also ordered by architecture.

To finish, the front page of the central now shows the latest validations of processors, motherboards, computers and RAM memories. This change has also been applied to the general front page, where the latest videos have also been moved to second position and validations have been left for the end.

The details are in the first post of this thread and in the first post of the front page thread.

As usual, any report of any failure will be welcome.

[jordiqui]

In the next version, there might be the possibility of having the MPi cluster option for windows, MPHI for linux. Just out of curiosity, I think we could do a test by connecting nodes between a few.