Theoretical gaming/emulation performance level..?


Garrett

Advanced Member
Joined
Aug 24, 2011
Messages
1,255
Location
Workington, Cumbria, UK
I know Craig has said that he aims for the Pandora 2 to be THE most powerful handheld gaming device.. just wondering what we could realistically expect in terms of the emulation & games possible.


I'm guessing full speed Dreamcast, Saturn (even given it's notoriously convoluted architecture) emulation would be a given, & Sega model 2/3, how about Gamecube..? and what level of PC gaming could be potentially achieved..?


Thanks.


I'd also love to see the PC pinball emulators Visual & Future Pinball.
 
Last edited by a moderator:
PC gaming - I'm betting the original Tomb Raider might run - something along the lines of a 100Mhz 486 to Pentium pro levels. And yes, that is just a wild ass guess.
 
Gamecube? I wouldn't expect anything more than sub 1 FPS performance :p

Yeah I realise it's optimistic to say the least, but until Craig dismisses it out of hand I'll remain hopeful.. minimum requirements with Dolphin are:


CPU: Pentium 4/Athlon 64 SSE2


GPU: OpenGL 2.1/DirectX 9.0c
 
With a lot of ram, multiple cpucores and qemu with arm kvm, we could run multiple android vms from angstrom ;)
 
Yeah I realise it's optimistic to say the least, but until Craig dismisses it out of hand I'll remain hopeful.. minimum requirements with Dolphin are:

CPU: Pentium 4/Athlon 64 SSE2


GPU: OpenGL 2.1/DirectX 9.0c

Craig is not the sole qualified expert on what can and can't be emulated on given hardware, and if Pandora 2 is to be released before 2014 there are hard limits on the performance levels that will be available. Listen to other people. Minimum requirements, especially for emulators, are often not actually reflective of what you need to run any meaningful percentage of games at correct speed.
 
The Pandora's OMAP 3530 600MHz can run Quake 3 with almost the same settings i used on a Athlon 1.4GHz + standard geforce 2.


I'm pretty sure Doom3/Quake4 generation games will run fine.


Nintendo DS should be fullspeed, with some ASM assembly tweaks.


We can also expect a decent win2000/XP virtualization.
 
Comparing the pure HW specs of Consoles like XBox360, PS3 and Handhelds like PSP / Vita / NDS /3DS I must say that Pandora 1 is actualy not that bad, hey, even the PS3 only has 256MB of RAM for example! :D


I still believe that powerful HW alone does just nothing if you can't make usage of it. How hard/easy is it to code for? Is it well documented? Are there good drivers and access to all HW features? This is waht's important imho. Powerful HW alone is useless if you can't make usage of it. Look what can be pulled out of all the current/past Consoles/Handhelds, there were so highly optimized Software for, easy to see in early/late games of each Gaming HW Generation.


So for Pandora 2 I hope that this time a well better documented WH is choosen so that coders can code much more efficient than it's the case of Pandora 1, I know that TI did not the best job in documenting all the OMAP and SGX secrets that could have helped our beloved Community Devs. ;)


Pandora 2 should get powerful but "easy to access" Hardware that does NOT waste Gigahertz because of bad Drivers or unsupported Software etc... Just Overclocking and forcing everything to run by pure Processor Power without any other optimizing is the WRONG way to do it, but seems to be more and more common.


Just my Opinion.
 
Last edited by a moderator:
I don't think it's a secret anymore that we expect the P2, if it happens, to be 2Ghz+ as the first spec.


So work your stats off that.
 
Would it be too much to pray for ps2 ? Of course it depends on how much money Craig can squeeze from kickstarter ( I mean what else would he use venture capitalists like Romney was ? He was actually in the company that got staples on its feet ... But killed many other companies ) , how much space is there to squeeze in the tech , and lastly is it affordable to those who would buy it ?
 
Last edited by a moderator:
I think Dreamcast should be the benchmark. P2 should come out when fullspeed dreamcast is available.


Each new gen of Pandora should represent emulation for a more powerful console.
 
For crying out loud. TI announcing that they're de-emphasizing their presence in the wireless market does NOT mean they're altogether canceling products that are almost ready to be released.


According to people who worked there TI decided to make this transition years ago, this isn't a sudden move, and they aren't being forced to do it to avoid bankruptcy. So it'd be really, really stupid of them to decide to spend all this money and company resources developing a chip knowing the entire time they'll see zero returns on it. They're even the lead license partner on Cortex-A15, alleged to have helped develop the processor itself.


And bear in mind that OMAP chips are not even exclusively directed at mobile phones and tablets (the market TI doesn't want to try to fight over scraps in). For instance, OMAP6xxx and DM37xx are the same damn silicon.
 
Even a single Cortex-A15 core at 2GHz, on a 28nm SoC, will use much more power than a Cortex-A8 at 1GHz on a 45nm SoC (like DM3730). Never mind a second core. So unless Pandora 2 has a much higher capacity battery or the rest of the system uses a lot less power (doubt that a much higher resolution LCD and a bunch of faster RAM over multiple channels will facilitate this, not to mention a much stronger GPU) I don't see how the battery life at full utilization can be the same as the battery life at full utilization of Pandora 1. But this only matters for something that actually would put it at full utilization. For things that run full speed on both Pandora 2 could be capable of giving similar or better battery life.
 
For crying out loud. TI announcing that they're de-emphasizing their presence in the wireless market does NOT mean they're altogether canceling products that are almost ready to be released.


According to people who worked there TI decided to make this transition years ago, this isn't a sudden move, and they aren't being forced to do it to avoid bankruptcy. So it'd be really, really stupid of them to decide to spend all this money and company resources developing a chip knowing the entire time they'll see zero returns on it. They're even the lead license partner on Cortex-A15, alleged to have helped develop the processor itself.


And bear in mind that OMAP chips are not even exclusively directed at mobile phones and tablets (the market TI doesn't want to try to fight over scraps in). For instance, OMAP6xxx and DM37xx are the same damn silicon.
Maybe, but this doesn't make TIs OMAP support and documentation better I guess. I doubt it will get better for an possible Pandora 2 than it was for our Pandora 1. So better look out for Hardware with more support and more "openess". Actualy, I first would look how good are the available drivers and then decide what hardware can be used to best fit our needs.
 
Please stop going on about support and documentation, this problem with Pandora 1 not having enough documentation is in your mind, I don't know how many times I need to tell you this >_< No alternative solution is going to have open GPU specifications, none of them are going to come with OpenGL drivers, etc..
 
Back
Top