The official BenchMate support thread

[cbjaust]

I like the adjustabilty of the Super Pi Window at the end of the run and the message in the dialogue box is a nice touch, but can you put in a carriage return and make the box narrower? 

[keeph8n]

Just want to put out a huge thank you to @_mat_

He worked his magic from across the world and fixed a couple of issues on the fly to make sure I could bench. Absolutely awesome! Above and beyond my man. Thank you again!

[bigblock990]

2 hours ago, macsbeach98 said:

W7 works off the RTC regardless of platform why do we need Benchslow for W7.

I vote for W8/10 only for it

Irregardless of your opinion, name calling is 100% unnecessary. Really surprised to see this comment coming from you.

Mat is trying to implement change that improves hwbot. If you have a problem with this, try and provide some constructive criticism. Look at @Mr.Scott concern of XP/legacy hardware support for example.

[_mat_]

BenchMate 0.8.1

 

Small Bundle: https://bit.ly/2Y2hDW2 (15 MB, GPUPI 3.2 + 3.3, SuperPi, CPU-Z, GPU-Z)

Big Bundle: https://bit.ly/2Gf6uHd (385 MB, + GeekBench 3+4, all CBs)

 

Note: These are now self-extracting executables, they should work everywhere!

 

Changelog

• Activated another protection against DLL injection attacks
• Improved font sizes on result dialog, changed font to Calibri
• Bugfix for 2920X/2950X and invalid processor groups
• Bugfix for error dialog, parent window wasn't responding
• Unified DPI scaling for error dialog
• Fixed a bug with Geekbench 3.4.2
• Performance improvement for file hashing of benchmark files
• Smaller SuperPi result message box reminder

 

Upgrading

• You can move your result directory and your config.json into the new installation at any time. They will be recognized on the next launch of BenchMate.
• Please close all benchmarks that were guarded by an old BenchMate version. If you don't want to bother, just reboot!

Known bugs

• Result capturing fails with Geekbench 3.1.5 (use latest version of Geekbench for now)
• SuperPi might not start on some Windows 7 versions ("Failed to guard application")

Special thanks to @keeph8n for letting me into his troubled Threadripper sys!

Edited July 15, 2019 by _mat_

[Rauf]

I think we need to be realistic, hwbot is a dead end when it comes to change. 95% of the value of hwbot is the database of old scores and the ability to compete and rank your scores against the same hw. Most of the database consist of scores on old Windows versions and/or old and unsecure benchmarks.

You can never force benchmate on the ones benching for hw-points without resetting all the scores. I don't see that ever happening.

As you said, implementing benchmate on hwbot in a proper way would also require alot of work from hwbot's side. I don't see that happening either.

The way benchmate can be used is for new hw and world records (globals). This can be reset in a day as there is no database to speak of. But there is still the part of getting proper integration with hwbot. Good luck with that! My suggestion to mat is if you ever want to see your great softare get any proper use you will have to do everything yourself and most likely set up your own site.

[Lucky_n00b]

Agree on @Rauf about benchmate being used to new hw points and globals.

Aside from the Benchmate competition to test things, what if hwbot start by giving points with benchmark that are completely new, that MUST be benched and submitted with Benchmate? This will test the integration and speed up things generally.

(If I have to select new benchmark, I'm suggesting Cinebench R20 for BOTH ST and MT as starters, it's easy to run, and the ST part will give more single-threaded CPU benchmark in HWBOT database, so far only SuperPi 32M and GB4 SC there. ,The minus side being there's already Cinebench R15 already getting points for the Multi-core part)

 

 

[Leeghoofd]

12 hours ago, _mat_ said:

 

Have you tested it? Isn't it great to upload a result in a matter of seconds not having to bother about screenshots or entering numbers manually into a form?

Works like a charm, fast and furious at its best!

@Rauf Rome wasn't build in a day, we have some foundations to start from however some are still solid, some have cracks, some are just missing :p  As long as we progress into the right direction and users are happy I'm happy... but one can't please everybody right?...  A clean slate would be fab, but too much data would get lost and not everybody benches the latest and greatest as you do.

@_mat_ Devroush has asked after the benchmate implementation, I'll tell him to contact you as you have the knowledge of the hows and whats

 

1 hour ago, Lucky_n00b said:

(If I have to select new benchmark, I'm suggesting Cinebench R20 for BOTH ST and MT as starters, it's easy to run, and the ST part will give more single-threaded CPU benchmark in HWBOT database, so far only SuperPi 32M and GB4 SC there. ,The minus side being there's already Cinebench R15 already getting points for the Multi-core part)

I got almost shot down when I made the suggestion to get CB R20 into the mix Alva, Maybe I need to smile more and people will accept it :p

Edited July 15, 2019 by Leeghoofd

[GeorgeStorm]

We don't need another cinebench surely yeesh.

And if people want to start over with the rankings they may as well do it elsewhere, rather than get rid of everything hwbot already has?

Have some permanent separate rankings for benchmate for people to try it out etc sure why not. I just don't see the point in pushing it for being necessary when the xp and dropping benchmarks issues remain.

[Leeghoofd]

@_mat_ Possible to minimize the font of the Cinebenches and reduce the name to eg something in the screenie. Can that result score screen also be moved around and/or partly covered?(read so not always on top) 

We have to think if all info is required to be shown in the score screen, for me the total score and green approval of Benchmate of the checked run is sufficient

Sorry for my crap Paint skilzzzz :p

 

Edited July 15, 2019 by Leeghoofd

[macsbeach98]

I am not criticising Mat I think he is doing a fantastic job with it it is definitely needed for W8/10 I just dont see why its needed for W7 or XP when there is no problem with the RTC.

Calling it Benchslow was just in jest it wasnt meant to offend sorry it has.

[Leeghoofd]

29 minutes ago, macsbeach98 said:

I am not criticising Mat I think he is doing a fantastic job with it it is definitely needed for W8/10 I just dont see why its needed for W7 or XP when there is no problem with the RTC.

Calling it Benchslow was just in jest it wasnt meant to offend sorry it has.

The benchmate is not only for RTC bug detection, it has more potential to secure ( critical bechmarks ), easy screenshotting and submitting….  but one step at a time

No harm done I guess, _Mat_ is still here: p

Edited July 15, 2019 by Leeghoofd

[Splave]

2 hours ago, GeorgeStorm said:

We don't need another cinebench surely yeesh.

And if people want to start over with the rankings they may as well do it elsewhere, rather than get rid of everything hwbot already has?

Have some permanent separate rankings for benchmate for people to try it out etc sure why not. I just don't see the point in pushing it for being necessary when the xp and dropping benchmarks issues remain.

think the idea of not pushing it to be necessary is a kind way of saying thanks but no thanks  Amirite?

 

SImple fixes:

Delete warp9's team boom no longer need old hw to work kidding kidding  

HW that cant run on windows 7 allow on XP (Derp) that was hard? 

[GeorgeStorm]

I'm all for it allowing new AMD to run on w10 etc.

So if stuff can technically run w7 but is way slower, benchmate has to be used, making old records even more difficult to beat?

[Guest Digg_de]

I have a problem with GB4.. showing no Pts after run. Ill try 0.8.1

edit: same with 0.8.1

Edited July 15, 2019 by Digg_de

[noizemaker]

i guess only with a valid licence gb3 & gb4 score gets regocnized

[MrGenius]

If that's how it is...that sucks. I'm having the same problem with it BTW. Might just have to slap on the eye patch and go rogue. Because I ain't payin' for that shit. Not even remotely worth it.

EDIT: Sure enough. That appears to be exactly how it is. I just ran it with a "licensed" version of GB4 and it recognized the score. Ummmm...that's BULLSHIT! NO PTP!!! ?

About that "Benchslow" comment(which I know was a joke)...so far I'm finding it to be the opposite. With all the Cinebench versions it supports, they're all scoring slightly higher for me with it and W7. Which I assume is because it's forcing HPET. Which I don't do for Cinebench. Since that's not under the allowed optimisations for it. But I'm sure everybody probably does anyway...

Edited July 15, 2019 by MrGenius

[_mat_]

I have to check about the GB 4 and licensing, seems like there are some differences I have not anticipated.

Cinebench uses timeGetTime() which is RTC. By enabling HPET in the OS (useplatformclock) you will only activate it for the timer facility called QPC (QueryPerformanceCounter). All other timing functions stay exactly the same, so there is no HPET for Cinebench. The benchmark itself has to take care of timer reliability and Cinebench doesn't care at all.

The reason that Cinebench might be faster is that BenchMate injects the faster and more precise TSC timer into it. The score should also be more stable, RTC is horrible for measuring time periods.

[_mat_]

20 hours ago, Leeghoofd said:

@_mat_ Possible to minimize the font of the Cinebenches and reduce the name to eg something in the screenie. Can that result score screen also be moved around and/or partly covered?(read so not always on top) 

We have to think if all info is required to be shown in the score screen, for me the total score and green approval of Benchmate of the checked run is sufficient

Sorry for my crap Paint skilzzzz :p

 

You really need to think different here. One of the main goals of BenchMate is to be able to make bench life easier by unwinding the rules and removing everything that is no longer necessary. That's easily possible in this case.

So the important questions here are:

Do we need to see the Cinebench rendering?

No, we actually don't and this shouldn't be the way to moderate Cinebench anyways! There are multiple ways to show a fullscreen image instead of the real benchmark window and desktop. This could be an application that does this or just a desktop wallpaper to trick the screenshot. It's impossible to verify such a cheat and even if I would try, it would turn into a cat and mouse game.

But we don't have to go down that road because there are other, much better solutions to check that everything has been rendered correctly. We can check the file hashes of the textures and even better every other file that CB uses for the run. Additionally we can upload a second screenshot that shows the window buffer of the CB window. That's also not the prefered method because it's easy to write into that buffer at any time, but that won't be as easy as a fake wallpaper and if used additionally to the file hash check it adds protection and a nice way (for fellow benchers as well) to inspect only the benchmark window if it's overlapped by anything.
This would completely remove the many problems we have with overlapped benchmark windows. We would end up with less rules for the screenshot, less to moderate and more valid results.

Do we need the CPU-Z windows?

As you can see for yourself on this screen they have to be placed very carefully so they don't overlap anything important. You have to play around with the window's order to get it right. Not to mention that it takes time to open two to three CPU-Z windows and fiddle around. I think this was fine when we had no alternative, but we have the possibility to improve the process right now, so why don't we use it?

So the question to ask here is, what information do those CPU-Z windows offer that BenchMate doesn't have already.
First of all the information on CPU-Z is captured at the time the screenshot was made and not during the benchmark run itself. The CPU can be downclocked manually after the run or as it often happens with air and water results it has to downclock because either the CPU gets too hot there was an AVX negative ratio applied and the benchmark used AVX. Same goes for voltages of course, they can differ greatly due to loadline calibration settings, dynamic voltage options and the likes. So the information is outdated and not very reliable.
But there are also things it does offer, that are not implemented in BenchMate. Three things actually:

• Bus frequency and ratio (can be added easily to BenchMate)
• A second level of CPU name detection by checking the CPUID family, model and stepping ID (can be done as well in BenchMate, but will take more time)
• The memory's Command Rate (currently not part of the HWiNFO SDK, but I'm sure it can be enabled)

These are the things that need to be discussed here to make our lifes better. Shrinking the BenchMate window to a stoplight is definitely not what I had in mind for creating a new standard of benchmark validation and that's why I'm not going to do that, especially for wrong reasons.

Edited July 16, 2019 by _mat_

[cbjaust]

12 hours ago, Digg_de said:

I have a problem with GB4.. showing no Pts after run. Ill try 0.8.1

edit: same with 0.8.1

https://community.hwbot.org/uploads/monthly_2019_07/snaphsot0009.png.b5b3f3ce37fc6ac39f25650c77d2b0ae.png

 

12 hours ago, noizemaker said:

i guess only with a valid licence gb3 & gb4 score gets regocnized

I had the same issue with the GB4 Tryout (I already have a GB3 licence). USD$9.99 later and problem solved. @_mat_ should set up affiliate links if that is possible with primate labs

[Leeghoofd]

File hashing is the only way to go if we don't want to use the full rendered screen. This might imply we have a a simplified rules set for benchmate subs and one for those that might not use it  (eg. on other unsupported benchmate Osses) We have to be ready for any upcoming challenges whenever a new benchmark pops up and it will take time for you to analyze the new benchmark, so we might trail the release.

I just look at the current things and not looking too far into the future, one step at a time Matt. Not everything is yet covered/implemented by Benchmate, so we need to have a workaround, which currently still is the full rendered screen and the CPU-Zs tabs. Like I mentioned wheneverf benchmate approves/validates the run and that is well clear in the screenshot than its fine for me.

Could it be possible to have the additonal info like eg (I know its a bad example) XTU, where you have a tab in the submission to open the required info?

Keep it up

Edited July 16, 2019 by Leeghoofd

[cbjaust]

I try to include CPU, Memory, Mainboard and SPD tabs from CPU-Z and also GPU-Z in my screenshots for both 2D and 3D just so I have some reference for future research into previous scores.

Do the files saved (.json and .hwbot) include all the info that is saved by a CPU-Z dump?

Edited July 16, 2019 by cbjaust

[GeorgeStorm]

I would want to avoid having more different rulesets depending on os, hw used etc than we already have.

 

Having benchmate subs have different rules to others doesn't sound like a good idea to me

[Leeghoofd]

With Benchmate it will become easier George, just give it time to mature.

[_mat_]

BenchMate shouldn't have a different rule set, I agree. It's here to make life easier for everybody (except me). That's why it should need NO rules at all. Just run your benchmarks with it and you are fine. That's by the way exactly what you always wanted, Leeghoofd ... "Just click the damn run button!"
The question is what do we need to do to get there in the eyes of the HWBOT moderation team.

@Leeghoofd I will add texture file hashing for CB in the next minor version, 0.8.2.

When a new benchmark pops up, it should never be added without knowing what it does, which vulnerabilities it has and how reliable it is. Otherwise things can go south quickly, results have to be removed, maybe the whole benchmark. I've seen this happening too often and it leads to a lot of bad blood. So we should work together on ensuring to avoid that at any cost.
When adding new benchmarks to BenchMate I ensure that they are in fact validatable. If they are not, we can contact the author and talk about the necessary changes. That's an important communication and verification process that HWBOT misses right now.

Also important to note here is what happens when a benchmark is added to BenchMate. As soon as it's in a lot of well-known vulnerabilities are already handled. Timer troubles are gone instantely and results can be submitted to HWBOT without any additional work for integration.
Do you see how easy things could be?

About XTU, please post a screen to clarify this.

@cbjaust I guess you are talking about all the information that's shown on results like this: https://valid.x86.fr/2xfi08
BenchMate is currently designed to detect everything that's necessary for benchmarking. Complete system analysis will be added further down the road by adding more and more information as needed.

Edited July 16, 2019 by _mat_

[cbjaust]

@_mat_ yeah pretty much that however I was thinking of the report function:

and I think @Leeghoofd was referring to XTU profiles: