gaffa2002 wrote on 2021-06-15, 13:37:

You know, there is a middle ground between being awfully nice and being a jerk. Your negative feedback towards PCEm could be given in so many better ways if you wanted to.
Plus, what is the point of me showing proof that PCEm runs great on M1? PCEm can be slow AND you can have horrible communication skills, one thing has no relation to the other.

Wouldn't that also due to one's conspiracy theorized delusions for being nice or jerk?
I am fine with your quote and you just proved that it can be done in just 1 minute. I hope the Moderator would do the same since he once said he could do it, too.
It is OK if you do not feel the need to prove anything, you don't have to do it. It is your choice.

I am more than happy to share my technical assessments on how to make PCem great on M1. You don't have to take my words or even believe in what I said. Anyone who has the motivation to revive the project can take note. The M1 is a monster on ST performance and it rarely thermal throttled. If unfairly compared its performance to desktop-class CPUs, then Core i9-9900K or Ryzen 9 5950X, it couldn't win but not very far. For laptops, nothing beats the M1 yet, because almost all Intel/AMD x86 CPUs would thermal throttled. Giving the benefit of doubt to PCem that its ARM64 recompiler is as good as QEMU TCG and with QEMU losing its advantage in virtualization, M1 will be a great CPU for PCem. Unfortunately, if it still insists on software rendered 3D acceleration, then it will never be as good as QEMU at GPU dominant workload, such as 3DMark2000. That is my take.

If someone claimed, just an example, that PCem on Rosetta 2 translation on M1 could beat QEMU native performance, then I would just laugh. For me, it is a joke and I said it. How wrong could that be? Fine, anyone who does not think this is a joke, then just prove it. That's the best way to make anyone swallow one's own joke and be shut up once and for all. It is a fair game, isn't it? Did Intel ever laugh when Apple claimed M1 Rosetta 2 would offer equivalent performance to Intel Macs?

Allow me to quote from PCem forums that I can no longer provide the link as evidence since they are now closed, but anyone frequently visited there could testify if I was making it up. Perhaps if anyone decided to reopen the forums or keep them as read-only, it won't matter to me if it remained or got deleted. "... Any pass-through/virtualization evangelism would be massively missing the point and often introduce variables of stability and bloat that won't hold in the long term (TM) ..." I cordially made up the (TM) in the end 😁.

If this was their joke, then I am fine with it.

Bladeforce wrote on 2021-06-15, 13:30:

If i communicated like this face to face with someone id expect to still be 6 years old. Belittling someones work shows more about the person saying it than the person making the software in their own time. Absolutely ZERO class.
Also publicly doing it this way on a forum just shows how immature your mind set is. What is your endgame? To get a group together and fight the system like children? Grow up

I believe I retaliated Moderator abuse of power in a civil manner. I follow the forums' order and recommendation. I do not resort to personal attacks or harassments.
If he believes that he stands the moral high ground, then just undelete the posts and let 3rd-party review them. Isn't that simple? Then I will bear all the criticisms and disappear for good.

Jo22 wrote on 2021-06-15, 15:11:

People with dementia

There's a couple of people here where I'm pretty sure this plays up regularly.

Oetker wrote on 2021-06-15, 16:53:

Jo22 wrote on 2021-06-15, 15:11:

People with dementia

There's a couple of people here where I'm pretty sure this plays up regularly.

Hah, that would make some posts make a lot more sense.

I don't think you've even clearly stated your case yet. Now it looks like you've just created another topic to rant about PCem.

Hi kjliew 😀. How are you doing today? I hope you are well.

It isn't so much what you say, it's how you say it. Everything in life is. The discussion in the PCem thread you were in was, at that point, about Sarah's decision to leave the project. She was dealing with burnout and a lot of harassment, and it just wasn't the time or place to have a dick measuring contest about performance. Nobody wanted to read about your project or how fast it is on the M1 at that time. It is that simple. Read the room.

In fairness to you, I don't know why your several dedicated threads to your project were closed. I think your project is really interesting and I would like to read about it. But really only in one place.

ZellSF wrote on 2021-06-15, 17:11:

I don't think you've even clearly stated your case yet. Now it looks like you've just created another topic to rant about PCem.

I am sorry if you perceived that I was ranting. I am not, why would I? I am not even an avid PCem user and I don't use it for games.
The case is loud & clear in the 1st post & the title - Moderator abusing of power in violation of Community Standards.
How much more details do you expect? I said I am going to write up the deleted posts but I would rather not as it isn't quite fair for him. I suggested an honored & fair way and it is up to him to take the path.

If I was ranting, then I was ranting that the Moderator deleting my posts based on his conspiracy theorized delusions. I am challenging his judgement in a civil manner.
If you had seen any of the deleted posts, then please bring them up.

cyclone3d wrote on 2021-06-15, 16:55:

Oetker wrote on 2021-06-15, 16:53:

Jo22 wrote on 2021-06-15, 15:11:

People with dementia

There's a couple of people here where I'm pretty sure this plays up regularly.

Hah, that would make some posts make a lot more sense.

That certainly would explain a a lot.

Namrok wrote on 2021-06-15, 16:03:

You know, I wonder if there is some collisions between worlds here. I don't think it's uncommon to use some strong language with hardware/software that's not working out well for you, and frustrating the crap out of you. It's just uncommon to say it in front of the person who made it. And yet here, there is a pretty solid mix of users and creators of hardware/software projects.

Then you get into the egos of certain developers. I've been a developer for almost 20 years. I try to stay humble, and not get too wrapped up in thinking the way I've done things is the absolute best way to do it. But it's a constant struggle. You sink sometimes years of your life into certain projects. Enormous portions of your mental capacity is spent keeping the code alive in your brain. You build a massive castle made of sand with nothing but your brain. And then the users come along like the tide, pointing out bugs, use cases you never thought of, functionality that's non performant to the point of being useless, etc. And your ego wants to viciously defend what you've built from them with every ounce of your being.

If you are on the clock, your boss will tell you to STFU and do it if you want your job. And there is a certain understanding that you are being paid for your time, not your passion. So if you are told to redo it, you redo it, so long as the check cashes. But when it's your side hustle... well... it's a lot easier to let yourself go off the rails.

yes possibly, you make a good point, sometimes we have a bad day and react

From my personal experience, the moderation here is hard but very fair, I have experienced this in some occasions. They are fair and they generally give the chance to explain or justify your case.

The moderators are much, muuuuch, much better than the MacRumors xenophobic moderators, for sure.

I also cannot understand why kjliew has to despise and trash PCem so much. The way he does it gives the moderator a reason to take the actions he chose to.

Yes, his solution for 3Dfx on QEMU are very good, amazing, but is far from being a complete product for everyone to use, like DOSBox, PCem. You can't expect everyone to be able to compile from scratch just to play Need For Speed II SE with 3Dfx. His solution being superior also does not give him the right to bash other solutions or keep bragging about how good his solution is. Just let it (the product) speak by itself, release it as a binary for everyone and let the product do the talking for you. You do not need to talk trash about other solutions.

PCem is not THAT bad at all, and it runs reasonably well here on my old intel mac for most of my games, except some of my preferred ones. It is still far from being the right solution for my gaming emulation needs, but I think its promising and could work for the M1 mac if compiled correctly. @kyro and @almeath are on it for the macOS version.

Currently, vanilla QEMU is what I use on my Mac, while UTM is the choice for my iPad. In a very close second place is DOSBox-X, and it could have surpassed it, if the dynamic core weren't crashing so much on me because the sound emulation cant keep up with the game speed when using Glide passthrough with OpenGlide (example: FIFA 98 RTWC game runs flawlessly without sound, but with sound it crashes right on match kick-off, and it's not a game issue because the same files/game runs fine on VMware, PCem and QEMU).

OP could just do what he was asked to by our colleagues here: provide data, benchmarks, constructive criticism about the emulators instead of bashing them. Then I would totally see no problem in his arguments towards PCem because he would have a point, a constructive debate, instead of insults.

I am not here to defend any emulator of my choice and I do not have a preferred choice anyway. I choose whatever works for me and for my games. I do not care if it is PCem, DOSBox or QEMU + 3Dfx. If these devs could work together and collaborate, all three could benefit so much and the community too. One man can dream.

kjliew wrote on 2021-06-15, 16:30:

Wouldn't that also due to one's conspiracy theorized delusions for being nice or jerk? I am fine with your quote and you just pr […]
Show full quote

Wouldn't that also due to one's conspiracy theorized delusions for being nice or jerk?
I am fine with your quote and you just proved that it can be done in just 1 minute. I hope the Moderator would do the same since he once said he could do it, too.
It is OK if you do not feel the need to prove anything, you don't have to do it. It is your choice.

I am more than happy to share my technical assessments on how to make PCem great on M1. You don't have to take my words or even believe in what I said. Anyone who has the motivation to revive the project can take note. ...

Just to make myself clear, I'm not saying that whoever moderator is right or wrong for deleting your posts (I can't judge that as the posts were deleted). My personal experience is that moderators around here sometimes tend to get too concerned in preventing and hiding "fights". Personally I think some fights may bring interesting discussions (the main challenge being knowing which are useful or not).
My point is more related to your general attitude in your posts. It seems to me that you don't care about being sensitive or polite, you are totally free to do that, but you need to remember this is a community made of people. We people are very complicated beings, so communication should be handled with care (unless you don't care about the hardships it may bring).

As for the technical portion, I read through it, but I couldn't see anything groundbreaking... you said:
1-M1 CPUs are fast in single thread
2-M1 CPUs speed are not much affected by temperature (good for laptops, ok)
3- PCEm is slower because emulation is done by software (ok)
4-PCEm is "bad" because it refuses to use anything other than software for emulation (which I strongly disagree)
5-You made fun of a quote in the (now dead) PCEm forum. (also disagree)

You see, the better application is not just the faster one, to me it seems clear that one of the goals of PCEm was longevity.
In order to achieve longevity in software, you cannot rely too much on hardware specific functionalities, because if for some reason hardware architecture drastically changes (like Apple loves to do) you need a much larger effort just to restore functionality that was already there. Plus it's much easier to port to future architectures as most of the internal workings are part of the software itself.
Maybe QEMU runs "better" today, but this may change in the future once the tradeoff between accuracy and speed becomes smaller, QEMU may even not work anymore depending on what changes.

It reminds me of MAME, nobody used it to play games when it was new as it was too slow, nowadays its the most popular emulator and ported to many other platforms (for the very reason of being software based).

I don't know what PCEm is and what's OP's problem with moderation but I know this: of all the forums I've ever used this is in the top3 when it comes to lax content moderation. A lot of forum mods ban you instantly for even talking back to a mod. That is all.

mothergoose729 wrote on 2021-06-15, 17:20:

Hi kjliew 😀. How are you doing today? I hope you are well.

Thank you, I am good. Hope everyone else the same, safe & healthy. 😁

mothergoose729 wrote on 2021-06-15, 17:20:

It isn't so much what you say, it's how you say it. Everything in life is. The discussion in the PCem thread you were in was, at that point, about Sarah's decision to leave the project. She was dealing with burnout and a lot of harassment, and it just wasn't the time or place to have a dick measuring contest about performance. Nobody wanted to read about your project or how fast it is on the M1 at that time. It is that simple. Read the room.

I understand. Everyone else also faces challenges in real life everyday. Why was she so sensitive about PCem comparison? She could have just taken a break or gone on a vacation, why made everything so personal then? It's just our past time and hobbyist project. How could win or lose ever matter so much? Why couldn't she just have a good laugh? Didn't everyone just build their dreamed retro PCs and posting benchmarks for comparison? Would anyone's feeling got hurt about his 3DMark2000 scores losing or he didn't have a Voodoo5?
At one time, I also joined in the fun and post the Quake2 Timedemo for QEMU VM. Unfortunately, it seemed that I had killed the fun of the thread then. Was my decision to post Quake2 Timedemo benchmark on VMs against retro PCs in any ways provoking? Provoking because of being envious or just having a good laugh, hey that just didn't count. Isn't Facebook and Instagram absolutely provoking this way if anyone couldn't handle the gospel & glory of social media?

I would absolutely love to see others using VMware/VirtualBox/Parallels to play games, besides QEMU. If anyone laughs at QEMU 3Dfx 3D performance compared to VFIO GPU-passthrough, then it is a fair call, one just paid complexity for performance and Linux only. I knew the limits of my creation in term of achievable 3D performance. It's OK to do that anytime. Please post your results at Virtualization showdown.

mothergoose729 wrote on 2021-06-15, 17:20:

In fairness to you, I don't know why your several dedicated threads to your project were closed. I think your project is really interesting and I would like to read about it. But really only in one place.

Well, you might have disclosed the Moderator identity then. Anyway, I can't help but still thank you. He gave his reasons at the last post when they were locked. Were those valid, well then, look like you have your answer.

Wow! I've been here since 2015 and I love this community and I've been a member of a lot of other forums and this one is by far the most laid back. I've never had any issues with any of the mods or members here. This is the only forum I even go to anymore and I truly hope what ever this matter is gets resolved peacefully and we can get back to what we all come here for having fun and learning.

gaffa2002 wrote on 2021-06-15, 18:30:

You see, the better application is not just the faster one, to me it seems clear that one of the goals of PCEm was longevity.
In order to achieve longevity in software, you cannot rely too much on hardware specific functionalities, because if for some reason hardware architecture drastically changes (like Apple loves to do) you need a much larger effort just to restore functionality that was already there. Plus it's much easier to port to future architectures as most of the internal workings are part of the software itself.
Maybe QEMU runs "better" today, but this may change in the future once the tradeoff between accuracy and speed becomes smaller, QEMU may even not work anymore depending on what changes.

While I understand your point, I would like to add that QEMU can use other accelerators, like TCG with JIT when KVM or the hypervisor is not available. It can even use TGI without JIT (slower than TCG) but still fast enough for most stuff, so I think that QEMU's future is pretty much safe for years to come...

Rude, polite or humorous are all up to one's perception. I can't control them.

gaffa2002 wrote on 2021-06-15, 18:30:

4-PCEm is "bad" because it refuses to use anything other than software for emulation (which I strongly disagree)
5-You made fun of a quote in the (now dead) PCEm forum. (also disagree)

For #4, it is not wrong to say "bad in performance (rude?)" or I also said "not very useful (polite) or "just a joke (humorous)". Do you agree?
This was exactly the same conspiracy theorized in the judgement of the Moderator. I pioneered the idea of running legacy Windows games in its released retailed version with only the final official patch (if any) and on the Windows OS the games were designed using Windows VMs without the needs to hunt down unofficial fans' patches on Windows 10 and modern Linux as the efforts to preserve the games. I called that "pristine condition". I never said that it was wrong to create fans' made patches for games or paying for the same games again on GoG/Steam was stupid. I had defended myself in this case against the Moderator's own delusions.

For #5, did you disagree because I made it up or you disagree on the quote itself (which I took it as a joke and had a good laugh)? Or did you disagree my intent in making fun of quotes? Wasn't life a bit bored without an occasional fun?

gaffa2002 wrote on 2021-06-15, 18:30:

You see, the better application is not just the faster one, to me it seems clear that one of the goals of PCEm was longevity.
In order to achieve longevity in software, you cannot rely too much on hardware specific functionalities, because if for some reason hardware architecture drastically changes (like Apple loves to do) you need a much larger effort just to restore functionality that was already there. Plus it's much easier to port to future architectures as most of the internal workings are part of the software itself.
Maybe QEMU runs "better" today, but this may change in the future once the tradeoff between accuracy and speed becomes smaller, QEMU may even not work anymore depending on what changes.

Oh yeah, that is a valid technical discussion. I am always open with such discussion. If a program was written entirely in C, as long as C compiler exists it works. Even better make it ANSI C compliant. If one paid for assembly optimization, then it becomes platform dependent. Being platform independent may pay the price for performance. Basic computer science 101 and typical software design decision. So how could the author of PCem be upset about performance comparison for the design decision that she had committed for her project? In fact, now is the window of opportunity that PCem can be better than QEMU on M1 since QEMU loses its advantage in virtualization. BoxedWine AArch64 dynarec CPU core already outperforms QEMU TCG if sorting out compatibility issues do not incur severe performance hits. Am I envious of BoxedWine achievement outshine my own hobbyist project and call it quit? No, I would congratulate the author, it is a big deal and he has every rights to be proud of. When my prediction of cross architecture virtualization materialized, OK I am trying to be polite, PCem would have no chance at all. Of course, the story will be different if PCem realizes the goodness of virtualization and embraces it, too.

If you aren't very familiar with virtualization, then I would suggest that you read up or Google the topics. It is an interesting study to enrich oneself if one likes Computer Science. And perhaps you could also make a few bucks for petty cash 😁.

kjliew wrote:

So how could the author of PCem be upset about performance comparison for the design decision that she had committed for her project?

Hint: She never was.

Bruninho wrote on 2021-06-15, 19:30:

While I understand your point, I would like to add that QEMU can use other accelerators, like TCG with JIT when KVM or the hypervisor is not available. It can even use TGI without JIT (slower than TCG) but still fast enough for most stuff, so I think that QEMU's future is pretty much safe for years to come...

When I say long term, I mean really long term, decades or so.
Let me put it in another way... every effort you put on a "pure" software emulator will be always relevant on the emulation quality, the only thing that matters for the algorithm is to replicate whatever is being emulated, always using basic computing concepts which will hardly change anytime soon. The only effort which is not technology agnostic are usually the inputs and outputs (the lesser, the better).
Now for an emulator that relies on technology-specific features, there will be always some extra effort once those features are updated or even discontinued. All efforts made on top of something that was deprecated will be lost, requiring extra effort just to restore functionality that was already there.

I believe PCEm (and any other "pure" emulator) is meant for preservation of old technology. And not to provide an efficient way to execute older software like QEMU does.

BTW: Sorry for changing the subject

I don't know if it's because of this drama/critic, but it's highly uncool that a person of our scene was made to feel this way. Bullied out of the scene by over-the-top harassment, it seems.

SMH. Really uncool.

Shreddoc wrote on 2021-06-15, 20:43:

I don't know if it's because of this drama/critic

I have literally no idea who kjliew is.