RSX = Stream Processor!?!
- Thread starter "Nerve-Damage"
- Start date
"Nerve-Damage"
Regular
mrdarko said:
WHAT!?!
When did graphic cards get cache???
Vram (texture) memory yes...cache no.........
"Nerve-Damage"
Regular
mrdarko said:
No, No, No,
I got what Barbarian was saying!!
That (Cache) would make RSX unique to its PC brethren (i.e. 7800 GTX).
Barbarian was hinting that RSX will contain some cache along with the reported 256MB of Vram Sony stated at 2005 E3.
Most (if not all) todays graphic cards do not contain any cache…from what I can remember.
RSX having cache guarantees to a certain existent faster texture swapping, less redundant data processing, faster post processing routines, ECT…
Last edited by a moderator:
"Nerve-Damage"
Regular
ROG27 said:
Yeah, I remember now..........
Nerve-Damage said:No, No, No,
I got what Barbarian was saying!!
That (Cache) would make RSX unique to its PC brethren (i.e. 7800 GTX).
Barbarian was hinting that RSX will contain some cache along with the reported 256MB of Vram Sony stated at 2005 E3.
Most (if not all) todays graphic cards do not contain any cache…from what I can remember.
RSX having cache guarantees to a certain existent faster texture swapping, less redundant data processing, faster post processing routines, ECT…
this "feature" sounds like a very good thing to me.....but do you believe it to be viable on rsx?
"Nerve-Damage"
Regular
mrdarko said:
Honestly, only time will tell….
If the cache becomes a bottleneck for some odd reason for a developer; will they have the option of bypassing it by hardware/software control? That’s my only concern...anyway.
Anyhow, there’s plenty of advantages of having on die cache (proper amount of it anyway) compared too the disadvantages of not having it.
The G70 architecture has 24 KB of texture cache per pipeline. Now times that by 24 pipelines. Up from the 16 KB texture cache from the previous generation (the 6800 series).
Saying their is no cache in a GPU is just silly. There is lots of cache, but for whatever reason the amount of cache is very rarely mentioned by the GPU manufacturers.
Saying their is no cache in a GPU is just silly. There is lots of cache, but for whatever reason the amount of cache is very rarely mentioned by the GPU manufacturers.
Mintmaster
Veteran
Umm, that's not remotely true. Today's cards have plenty of cache. Texture cache is there, but if you write your pixels and access your data intelligently you don't need a whole lot. More on-chip memory is found in fifos/register cache/pixel cache/whatever you want to call it, and there's a ton in any graphics chip. This is what makes them good at absorbing texture latency and sustaining their peak throughput. You also have caches for storing information about Z and colour compression, and in the case of ATI, for Hi-Z data.
That's pretty much all wrong. Only in the worst cases (e.g. tons of textures, or very non-coherent dependent texture access) is texture swapping an issue, in which case more cache isn't the solution. Post processing has very predictable memory access, and again more cache won't help much. Don't know where you could save redundant data processing.
I guarantee you that G70 has already optimized the cost/benefit ratio of caches to the point where you'll only get a few percent more performance with bigger caches. Any tricks to maximize memory usage are already in use now to minimize costs and maximize profits for the low bandwidth budget cards in the PC sector.
All cache does is help you achieve perfect efficiency. For bilinear texture filtering you need the nearest 4 texels, and under magnification many neighbouring pixels will need the same 4 texels, and that's what the cache is for. Even under minification, adjacent pixels need 2 of those texels. If you draw your pixels in an intelligent order (and believe me, these chips have done so since the GF3/Radeon days), you're unlikely to need to load many of those texels again.
There's a fundamental limit to how little bandwidth you'll need, and modern GPU's from ATI and NVidia aren't far from achieving that.
The only time cache will actually save you significant bandwidth is if a whole texture can fit in the cache and that texture is tiled and repeated, which we'll see less of in next-gen graphics, or if you're doing tiled rendering like Xenos or PVR's TBDR chips do.
"Nerve-Damage"
Regular
Edge said:
Well I learned something new today!!
My eVGA(s) 7800 GTX have itty bitty cache modules on the GPU die
"Nerve-Damage"
Regular
Mintmaster said:
Your opinion anyway.....
Mintmaster
Veteran
Well this opinion is based on hard data while working at ATI a few years back, and my extrapolation of that data to current GPU's based on public synthetic tests. I am also very familiar with 3D coding, which you do not seem to be judging by your assertions.Nerve-Damage said:
Barbarian said:
Haha. Funny.
DirectX 1 (back then called GameSDK) didn't have Direct3D in it. Way back in 1995, it was just DirectDraw, DirectInput, DirectPlay, and DirectSound.
Direct3D didn't make it into DirectX until DirectX 2.
Barbarian said:
The correct answer is zero megs, since they don't exist they always fit.
Last edited by a moderator:
Similar threads
