Mips Vs Arm

[skeezix]

Your post and not the reply? I Don't see another post of yours above, so perhaps another thread? I only saw: "The PSP is clocked at 222Mhz, saying it isn't just noncence, its like saying the GP32 is 200Mhz. I'm not arguing with anyone. I don't know any sony engineers" -- clearly incorrect. I think the debate was about pound-for-pound MHz comparisons, and thus I'm dispelling some of the silly notions.

As to battery life.. all batteries are too short (I have an Axim X50v, I know about pathetic battery life .. still, it matters not to me; I've only got a few mins here or there to fiddle, so any battery is good enough for me

jeff

 

[junker]

"The PSP is clocked at 222Mhz, saying it isn't just noncence, its like saying the GP32 is 200Mhz".
you didn't use the word overclock, eh?

anyway, we're not talking about PDA's. that PDA benchmark graph was brought up in the search for a good comparison between Arm/Mips, and to see whether Arm cpus, mhz for mhz, are more powerful than Mips cpus, which is what we're originally talking about here, not whether overall the gp2x's mmsp2 is better than the psp's 333mhz cpu.

no one also made any serious claims from these charts, and on one can, given all the factors involved. just speculation and guesses.

and no, all those threads about DS vs PSP don't count as good Arm/Mips comparisons.

back on topic, i don't think this discussion will go anywhere so we'll just have to wait and see. shouldn't be too far off

 

[Goity]

Your post and not the reply? I Don't see another post of yours above, so perhaps another thread? I only saw: "The PSP is clocked at 222Mhz, saying it isn't just noncence, its like saying the GP32 is 200Mhz. I'm not arguing with anyone. I don't know any sony engineers" -- clearly incorrect. I think the debate was about pound-for-pound MHz comparisons, and thus I'm dispelling some of the silly notions.

As to battery life.. all batteries are too short (I have an Axim X50v, I know about pathetic battery life .. still, it matters not to me; I've only got a few mins here or there to fiddle, so any battery is good enough for me

jeff

​

Which Is why I want one of those Asus Mypal A620bts.... Mmmmmmmm 17 hour battery life.....

 

[Cyclops]

Your post and not the reply? I Don't see another post of yours above, so perhaps another thread? I only saw: "The PSP is clocked at 222Mhz, saying it isn't just noncence, its like saying the GP32 is 200Mhz. I'm not arguing with anyone. I don't know any sony engineers" -- clearly incorrect. I think the debate was about pound-for-pound MHz comparisons, and thus I'm dispelling some of the silly notions.

As to battery life.. all batteries are too short (I have an Axim X50v, I know about pathetic battery life .. still, it matters not to me; I've only got a few mins here or there to fiddle, so any battery is good enough for me

jeff

​

I'll make it clear that I could be talking compleatly out of my ass, but my understand was/is regardless of core speed. That commercial games (regardless of homebrew) run at core speed of 222mHz, and they do so with good reason. Am I not 100% correct.

I also suspect that I am 100% correct in my assumption that developers would love to utilise the extra power much in the same way that homebrew does.

I also assume that the rules that apply with good reason also apply to homebrew. Although people will use that extra power where processer power is needed.

There are tens of thousands of web pages discussing the missing 111Mhz; tools to utilse the full core; hidden features inside games to make it possible to run the games utilising its full speed; Wild speculation of why Sony would do this.

You can clock the PSP at a variaty of speeds, yet sony chose 222Mhz for the very reasons you discuss as silly notions - battery life. I fail to see what I said wrong. I understand more why you are saying I'm clearly incorrect with your views on battery life in a portable device. I suspect that most people(I would have said all before seeing your reply), want a portable(well anything) handheld gaming device to have as long a battery life as possible. Hence 222Mhz.

"The PSP is clocked at 222Mhz, saying it isn't just noncence, its like saying the GP32 is 200Mhz".
you didn't use the word overclock, eh?

anyway, we're not talking about PDA's. that PDA benchmark graph was brought up in the search for a good comparison between Arm/Mips, and to see whether Arm cpus, mhz for mhz, are more powerful than Mips cpus, which is what we're originally talking about here, not whether overall the gp2x's mmsp2 is better than the psp's 333mhz cpu.

no one also made any serious claims from these charts, and on one can, given all the factors involved. just speculation and guesses.

and no, all those threads about DS vs PSP don't count as good Arm/Mips comparisons.

back on topic, i don't think this discussion will go anywhere so we'll just have to wait and see. shouldn't be too far off

​

No I didn't use the word overclock lol

really seriously no use of the word overclock. In fact I correctly use the term clocked at, becuase it is. Seriously you need to try harder looking for your quotes . I 've said all kinds of stupid stuff.

If your trying to convince me that this discussion is not completely GP2X vs PSP. It is veryone knows it its in the GP2X forums and every post mentions the PSP

 

[declaration]

Your post and not the reply? I Don't see another post of yours above, so perhaps another thread? I only saw: "The PSP is clocked at 222Mhz, saying it isn't just noncence, its like saying the GP32 is 200Mhz. I'm not arguing with anyone. I don't know any sony engineers" -- clearly incorrect. I think the debate was about pound-for-pound MHz comparisons, and thus I'm dispelling some of the silly notions.

As to battery life.. all batteries are too short (I have an Axim X50v, I know about pathetic battery life .. still, it matters not to me; I've only got a few mins here or there to fiddle, so any battery is good enough for me

jeff

​

I'll make it clear that I could be talking compleatly out of my ass, but my understand was/is regardless of core speed. That commercial games (regardless of homebrew) run at core speed of 222mHz, and they do so with good reason. Am I not 100% correct.

I also suspect that I am 100% correct in my assumption that developers would love to utilise the extra power much in the same way that homebrew does.

I also assume that the rules that apply with good reason also apply to homebrew. Although people will use that extra power if it is needed where processer power is needed.

There are tens of thousands of web pages discussing the missing 111Mhz; tools to utilse the full core; hidden features inside games to make it possible to run the games utilising its full speed; Wild speculation of why Sony would do this.

You can clock the PSP at a variaty of speeds, yet sony chose 222Mhz for the very reasons you discuss as silly notions - battery life. I fail to see what I said wrong. I understand more why you are saying I'm clearly incorrect with your views on battery life in a portable device. I suspect that most people(I would have said all before seeing your reply), want a portable(well anything) handheld gaming device to have as long a battery life as possible. Hence 222Mhz

​

Lots of GP32 software is clocked lower than 133mhz to preserve battery life. In fact, I think no commercial game goes as high as 133.

That doesnt mean it would be accurate to say the GP32 only runs at say 60mhz, would it? Criticise the PSP based on having shit battery life, but don't try to claim it only runs upto 222mhz without overclocking.

one other thing to remember- we don't yet know the GP2X's overclocking potentials.

 

[whiskthecat]

"one other thing to remember- we don't yet know the GP2X's overclocking potentials."


That right there is more than enuff said.

 

[DijiTao]

I’m pretty sure it’s impossible to mention 333Mhz on the PSP with out starting a flame war.

My whole point is looking at what emulators are capable of running at full speed on the psp (at 333Mhz) could gives us a little insight into what to expect out of the GP2X *if* we knew how a 333Mhz MIPS processor compared to a 200Mhz ARM processor. Since I can’t find much of anything on that other then the admittedly lame PDA benchmarks I linked to in the first post, I was hoping somebody with a dev board, or practical experience in dealing with MIPS & ARM could give me some insight into the subject. As of right now with what I’m seeing here it sounds like we can expect a 200Mhz ARM processor to perform like a 250Mhz MIPS processor.

Geez… chill people..

 

[Cyclops]

Lots of GP32 software is clocked lower than 133mhz to preserve battery life. In fact, I think no commercial game goes as high as 133.

That doesnt mean it would be accurate to say the GP32 only runs at say 60mhz, would it? Criticise the PSP based on having shit battery life, but don't try to claim it only runs upto 222mhz without overclocking.

one other thing to remember- we don't yet know the GP2X's overclocking potentials.

​

Its not simple; its about the PSP to be a viable competitor to the DS. They chose a clock speed of 222Mhz. Its a win-win situation for them. They get extended battery life which they need in a handheld, and they can claim their chip is faster than the PS2. Its nothing to do with the GP32/GP2X.

So that leaves homebrew; clock speeds up to 333Mhz but you lose the battery life. That is the price, a price sony are unwilling to pay,but its needed for high-end emulation, so the figure becomes important. If I have to plug my PSP into the wall to emulate the SNES for any length of time I would rather use my computer. It stops being portable, and becomes a brick.

Can't we just see how well it does at stock speeds??

 

[Cyclops]

I’m pretty sure it’s impossible to mention 333Mhz on the PSP with out starting a flame war.

My whole point is looking at what emulators are capable of running at full speed on the psp (at 333Mhz) could gives us a little insight into what to expect out of the GP2X *if* we knew how a 333Mhz MIPS processor compared to a 200Mhz ARM processor. Since I can’t find much of anything on that other then the admittedly lame PDA benchmarks I linked to in the first post, I was hoping somebody with a dev board, or practical experience in dealing with MIPS & ARM could give me some insight into the subject. As of right now with what I’m seeing here it sounds like we can expect a 200Mhz ARM processor to perform like a 250Mhz MIPS processor.

Geez… chill people..

​

Look at that graph and tell me what can be achived from 206Mhz ARM chip

E-2000 (ARM 206MHz) 427

Simpad_SL4 (ARM 206MHz) 340

What I'm seeing is massive differences from chips of the same Mhz of the same type. Greater if choose to move a couple of Mhz either way. So when I say a figure pulled from the ass I mean it.

CASSIOPEIA E-750 (MIPS 200MHz) 330

is that the about the same less.

 

[Eolair]

Is the battery situation really that bad for homebrew on the PSP? Someone told me that the battery lasts around 5-6 hours if you play SNES @ 333MHz. Doesn't exactly sound like the "brick in the wall" situation that you're describing? :unsure:

 

[PSyMastR]

BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH BAH
ARGH! Its become a flame war between the PSP and GP32/GP2X!!! GIVE IT A REST GUYS!!!!

 

[Cyclops]

Is the battery situation really that bad for homebrew on the PSP? Someone told me that the battery lasts around 5-6 hours if you play SNES @ 333MHz. Doesn't exactly sound like the "brick in the wall" situation that you're describing? :unsure:

​

http://psp.ign.com/articles/574/574557p1.htmlmakes for interesting reading esp considering ridge racer isn't using the full 333Mhz

Sony games head Ken Kutaragi has admitted that the PSP's quoted battery life of four to six hours for games is not entirely accurate

I dont think there is anything wrong with 5-6 hours, but I'm tempted to call that a outright lie.

Its a brick.

 

[skeezix]

Really, graphs and stats are mostly meaningless unless from a trusted source who knows what they're doing. (Note that most trusted sources still have no idea what they're doing

ie: I've seen real reputable companies doing things like battery duration tests.. but plugging one device into speakers, while another into headphones, and not mentioning it (or mentioning it in small print.) (Note that speakers are heavier draw on the battery)

Now, when you meaqsure two Pocket PC devices, performance and battery life can very wildly, even with nothing running on the devices.. one VAR might include different features in the OS, and different screen technology (with different draws).. or even different brightness levels 'at default'.. certainly different video chipsets and such alter things significantly..

So its no value to compare PDA to PDA across chip families.

We're all dieing to know, but we'll have to see. The Zodiac (PAlm OS) at 200MHz flew past other Palm OS devices at 230MHz, due to snappier bus and supporting chipsets.

jeff

 

[Hooka]

All I gotta say is take the NES emulator for PSX for example... sure it's not quite as fully featured as some other emulators but because it was specifically designed to work on the PSX, it proves to be an excellent emulator! If anything I'm hope you understand that it doesn't necessarily always depend on the hardware but sometimes on the code/coder... so sit back, relax, wait for hardware to get released then enjoy yourself trying to force it to do whatever you want to the full potential if the system if you can, if not do the same and hope that somebody who knows what their doing is nice to you

 

[Radek]

What a nice discussion is this topic getting.

Myself I tried to make an one important (imho) point about the GP2x (but will repeat).
These 2x200MHz Arm9 cores are just an one aspects of this machine. There are far more in the MMSP2 than just those dual cpu cores. It's the GPH's fault that they didn't show the GP2x better. Yes, I know that raw CPU power is a very important factor for emulators however there are other helpers and certainly developers will find ways to utilise them.

So... PSP's cpu can run at 333MHz but is clocked typically at 222MHz for obvious reasons. Do you know then the GP2x's chipset also has different "power modes" and do you know (according to the officials docs) at what freqency it can be clocked? It's hard to say without having actually a GP2x (it might has a limitation of some sort) but docs say 266MHz for the dual arm9 cores in the MMSP2 and this isn't an overclock.

And when returning to the whole debate it must be repeated "there is far more to a perfomance than just this damn cpu's clock". This is true especially for a machine like the GP2x. And I'm sure (but perhaps I'm dumb? :lol: ) when developers will learn to utilise GP2x's hardware properly you will be amazed.

 

[Blah]

Hey, settle down everybody. Its not lorded over by Sony, and its atleast 4x the machine the GP32 is, and thats all that matters.

 

[EvilDragon]

... and don't forget one thing:
Optimization!

I've never seen as optimized emulators as on the GP32, to be honest (I've never seen that many great coders on any other homebrew system, to be honest!)

Most PSP emulators are simple C-Ports.

On GP32, a lot of emulators run at a fantastic speed because they use assembler cores. And as we still have ARM processors, most these emulators can be ported pretty fast onto the gp2x.

MHz is not everything! Optimization can make programs 10 times faster!

 

[codeninja]

... and don't forget one thing:
Most PSP emulators are simple C-Ports.

On GP32, a lot of emulators run at a fantastic speed because they use assembler cores. And as we still have ARM processors, most these emulators can be ported pretty fast onto the gp2x.

​

Being a fan of ARM assembly myself, that aspect alone is good enough for me to choose ARM over MIPS processor any day of the week. MIPS4x00 is an ancient architecture that Columbus used to go across the Altantic ocean back in the days, and no wonder he found America instead of India that he intended.

 

[pepone]

If anything I'm hope you understand that it doesn't necessarily always depend on the hardware but sometimes on the code/coder... so sit back, relax, wait for hardware to get released then enjoy yourself trying to force it to do whatever you want to the full potential if the system if you can, if not do the same and hope that somebody who knows what their doing is nice to you

​

Amen!

 

[Undefined Error]

MIPS4x00 is an ancient architecture that Columbus used to go across the Altantic ocean back in the days, and no wonder he found America instead of India that he intended.

​

Having been forced to take a class in MIPS assembler, I can safely say this is the most intelligent thing I've heard in this entire thread. :lol:

If anything I'm hope you understand that it doesn't necessarily always depend on the hardware but sometimes on the code/coder...

​

This is a close second. Really, the ingenuity of the coders and developers will almost always find new ways to overreach any limitation that it's believed a hardware imposes. I know a lot of people are always concerned at any new system's launch about what it "can" do, but in my experience, most systems never get their power fully tapped before they are replaced by a successor anyway. Sure, games get better as the platform matures (read: coders become familiar with it) but just look at some of the recent homebrew for "dead" consoles that completely outstrips anything developers did for those systems when they were alive and kicking. Those still writing for these systems have the advantage of both 20/20 hindsight on what their predecessors on the system did right and wrong as well as years more time to learn every minute detail about the system's quirks, not to mention the simple advancement of basic algorithms and computer science theory in that time. Frankly, even if someone one day said "I truly believe there is nothing more the GP2X can do than what I have made it do here," I'm quite sure that a few years (or even months) down the road, there would be new algorithms, methods, tricks, and clever ideas that enable those barriers to be pushed just a little farther. Granted, I'm not trying to argue that we can pull PS2-quality graphics out of the NES with "just a little more work," but I am arguing that most people will never see the day where either of the handhelds in question are pushed to their absolute limit anyway.

Not that I'm trying to dismiss this whole debate as meaningless; the basic "power" of a system usually has a direct corellation to how quickly games reach a certain level of "impressiveness," as well as at what level those games usually plateau and improvement between programs begins to be made in steps instead of leaps. But I have always subscribed to the belief that it's what you do with a system that matters most. The games make the system, and until games use a system's power fully, the remainder is merely untapped potential, worth squat. Just look at the history of the market that the GP2X is entering to see this clearly; countless handhelds which had various major advances in technology over the GameBoy came and went with hardly a notice by most consumers during the lifespan of even the original version of Ninty's handheld dynasty. And the reason was that the developers were simply not behind those systems, powerful though they were. The games people wanted were on the GB, and the people the games wanted to sell to were on the GB. Or, hell, look at the current war between the DS and the PSP. If you just try to count clock cycles, the DS seems wildly outclassed, and yet it manages to compete commercially all the same.

(EDIT: Lordy, before that last comment devolves into another flame war, would all the reactionaries on this board please understand that I'm not trying to declare either of those handhelds better than the other. Quite the opposite, I'm arguing that at this time sales figures and consumer dollars haven't shown a clear win for either side, so they're effectively deadlocked. And if you're trying to compare handhelds on any level except in terms of units sold, then you have to make a personal judgement as to which handheld is "the best," in which case I obviously vote for GP2X over either of them. )