RSX: 1.1 billion vertices/sec?

[one]

If the RSX can setup 1.1 Billion VERTICES per second that would come out to be 366 Million TRIANGLES per second (1 triangle = 3 vertices and 1 square = 4 vertices).

Aren't you just skipping what have been said in this thread so far?

 

[nickguy94]

"If the RSX can setup 1.1 Billion VERTICES per second that would come out to be 366 Million TRIANGLES per second (1 triangle = 3 vertices and 1 square = 4 vertices)"

I take it you don't know too much about polygons. For a triangle, you need 3 inital vertices and 1 additional vertice for every new triangle. Not quite sure why you mentioned a four sided polygon because game engines convert polygons into triangles but even still, you need 4 inital vertices and 2 additional vertices for every new four-sided polygon.

Edit: So the only time when the polygon count would be significantly lower than the vertex count is when you have many(hundreds or thoasands) of seperate polygon-objects in a scene because you're starting a new polygon everytime you start a new mesh object.

 

[ralexand]

"If the RSX can setup 1.1 Billion VERTICES per second that would come out to be 366 Million TRIANGLES per second (1 triangle = 3 vertices and 1 square = 4 vertices)"

I take it you don't know too much about polygons. For a triangle, you need 3 inital vertices and 1 additional vertice for every new triangle. Not quite sure why you mentioned a four sided polygon because game engines convert polygons into triangles but even still, you need 4 inital vertices and 2 additional vertices for every new four-sided polygon.

What happens if polygons aren't connected in one mesh, I know unlikely, but if you do have free floating polygons do you still equate vertices to polygons. I ask because of the person who mentioned that the xbox had to use fanned polys to reach its performance numbers.

 

[ERP]

The best you can achieve is 1/2 vertex/polgon. This has to be closed genus 1 surface, with completly regular tessalation.

Most IHV's quote numbers based on a single contiguous strip of verts which is 1 vert/tri.

Most real models with material and texture boundaries run in the 1.0 to 1.3 verts/tri range.

Orphaned quads (as in particles) take 2 verts/tri's.
Orphaned Tri's take 3 verts/tri.

 

[ralexand]

The best you can achieve is 1/2 vertex/polgon. This has to be closed genus 1 surface, with completly regular tessalation.

Most IHV's quote numbers based on a single contiguous strip of verts which is 1 vert/tri.

Most real models with material and texture boundaries run in the 1.0 to 1.3 verts/tri range.

Orphaned quads (as in particles) take 2 verts/tri's.
Orphaned Tri's take 3 verts/tri.

Got it. Thanks.

 

[V3]

In NV CineFX4.0 pdf, there is a heading "Faster Triangle Setup" But it doesn't give any performance number.

So what was the triangle setup like in NV40 ?

 

[richardpfeil]

Let's see...

Assuming ~1 vert per triangle. 1 triangle set up per clock. The vertex shaders need to produce one vertex per clock to keep up. This means a maximum of 48 Vec4+Scalar ops per vertex. A more well balanced scenario between vertex and pixel shading might mean 12 Vec4+Scalar ops per vertex. Not all that fancy, but also not trivial. The 500 million polygons per second number of the 360 looks a lot more reasonable than the 125 million number thrown around when the original XBox was announced, or the 67 million number for the PS2.

On the RSX side, running the same vertex shader...
12 ops (Vec4+Scalar) per shaded vertex gives us, 8 * 550 / 12 = 367 million polygons per second.

 

[Megadrive1988]

some other things I was going to say:

Cell itself should be able to calculate several billions of polygons, much like Xenos could also calculate / transform several billion polygons. but then to setup that amount would be impossible. so then we need to know how many polygons can PS3/RSX setup, and also render/display on screen with at least some level of texture & pixel shading.

I'll bet that with the max level of pixel shading it can do, plus lighting and everything else, Xbox1 only gets a few million polygons per second in games. lets say that amount is 5 to 9 million (and that is being generous) going to a few hundred million (not billion) with actual Xbox360 and PS3 *games* is going to be a huge leap.

Why do you think we'll get closer to those theoretical numbers than we got with the xbox1? Xbox1 was quoted at 100 million polys vs. 500 million for xenos and 1.1 billion for RSX. We got no where close to those numbers on xbox. What makes you think we'll get there this gen?

because, Xbox 360/Xenos can actually calculate several billion vertices/sec (6B) according to someone at ATI, and games will never come close to that. but 500 million is meant to be the achievable figure for actual games, with non-trivial shaders.

with that said, as I said before, if we see a 200 to 300 million polygons/sec in some games with moderate pixel shaders and lighting that will be a huge leap from actual performance of current consoles. then if we get 50 to 75 million polygons with heavy pixel shaders, lighting and next-gen effects, that will also be a huge leap from current consoles.

still, there is always the desire to have MORE of everything. the level of visuals and performance that I once had wanted for PS3 and Xbox 360 will not arrive until the next-next generation, early in the next decade

 

[Megadrive1988]

Let's see...

Assuming ~1 vert per triangle. 1 triangle set up per clock. The vertex shaders need to produce one vertex per clock to keep up. This means a maximum of 48 Vec4+Scalar ops per vertex. A more well balanced scenario between vertex and pixel shading might mean 12 Vec4+Scalar ops per vertex. Not all that fancy, but also not trivial. The 500 million polygons per second number of the 360 looks a lot more reasonable than the 125 million number thrown around when the original XBox was announced, or the 67 million number for the PS2.

On the RSX side, running the same vertex shader...
12 ops (Vec4+Scalar) per shaded vertex gives us, 8 * 550 / 12 = 367 million polygons per second.

regarding the part I highlighted in bold, I agree. just to add to that, the 500 million polygons per second figure for Xenos/Xbox360 does indeed look more reasonable than the peak polygon figures of Xbox: 300M micro / 150M T&L'd polygons per second originally - later got reduced to 233M micro / 116M T&L'd polygons per sec. still MS claimed 100M sustained even after the two core clockspeed downgrades - and also PS2: 66M transformed / 75M rasterized polygons per second.

If Xenos/Xbox360 was measured the way Sony and MS measured PS2 and Xbox1, Xenos/Xbox360 would be at 1.5 to 6 billion per second. so again, 500M seems very possible.

 

[Iron Tiger]

Not quite sure why you mentioned a four sided polygon because game engines convert polygons into triangles

This has been true of every successful 3D gaming architecture so far, but is it possible that the Xenos non-traditional could bring about the use of a non-traditional primitive (quads)? Triangles have all 3 vertices existing on one plane, while a quad may have multiplanar vertices. We can make organic (curved) shapes with fewer primitives. There would be no reduction in the amount of vertices used, but I imagine there would be some savings derived from the use of a more "flexible" primitive.

 

[Love_In_Rio]

And what if someone used in Xenos an engine which used only vertex and no pixel shaders ? Wouldn´t use the 48 ALUs to transform vertices and this way get the 500 million polys in fact ? Supposing 60 fps 500 million polys would show us in screen near 8 million polys... wouldn´t it be great to have characters with more than 100000 polys and stuff made of many polys instead of using pixel shaders to simulate them ?

 

[Thegameman]

regarding the part I highlighted in bold, I agree. just to add to that, the 500 million polygons per second figure for Xenos/Xbox360 does indeed look more reasonable than the peak polygon figures of Xbox: 300M micro / 150M T&L'd polygons per second originally - later got reduced to 233M micro / 116M T&L'd polygons per sec. still MS claimed 100M sustained even after the two core clockspeed downgrades - and also PS2: 66M transformed / 75M rasterized polygons per second.

IGN Xbox: Last year Seamus Blackley was quoted as saying in an interview with us that "The only changes that you'd ever possibly see -- and I think that the probability of there being any changes is extraordinarily low -- would be upgrades to system performance." What happened?

J. Allard: The honest truth is that the goal that we always had for the system was 3x the graphical and computational performance of PlayStation 2. Initially, we thought that a 600MHz CPU and a 300MHz GPU was about right -- and that was in March. Now that Nvidia's got the NV20 in production, and we've got NV20 cards working with the operating system out in dev kits, and we've got games up and running on NV20s, we learned a bit more about the production and the manufacturing, and we decided that the 250MHz combined with the 733MHz is really the right balance. We'll still hit the 3x, but we guessed bad with the 300Mhz.



IGN Xbox: The poly performance has changed as well though, from 300 million polys a second to 125.


J. Allard: The funny thing about poly performance is that that's a theoretical number, and it's a good number to talk about because competitors talk about theoretical numbers, but we've long held that the most important number is what game performance looks like. So the fact that NV20s are in developers hands is great, and the final hardware will be in their hands in a couple of months. I think we'll have no problem making the 3x differentian in real game performance, and maybe even more.




IGN Xbox: You've said once before that there wouldn't be spec changes -- what's to stop more announcements in the coming months?

J. Allard: It's more of a spec refinement, not a change. Technically it's a change -- that's the clock rate we're going to be able to achieve and still maintain the 3x performance. From a physics change it's what's possible and what's right. It's not like there's a 300MHz part that's appropriate and we're shaving some money. It's really the right thing overall in the system architecture. We need to get final hardware to the developers in the next couple months to get them to write games for 2001 that shine.

This ^^^^ s the end of the story,that last question put J Allard against the wall,you can clearly see that he din't even know what to answer,first he say is not a change then he say technically it's a change.


The problems was that MS lie a little much on those xbox specs,in fact they go on saying that they still hit 3 times the perfomance of the PS2,which is a realy big and open lie,i hope they don't do the same again.

 

[Shogmaster]

regarding the part I highlighted in bold, I agree. just to add to that, the 500 million polygons per second figure for Xenos/Xbox360 does indeed look more reasonable than the peak polygon figures of Xbox: 300M micro / 150M T&L'd polygons per second originally - later got reduced to 233M micro / 116M T&L'd polygons per sec. still MS claimed 100M sustained even after the two core clockspeed downgrades - and also PS2: 66M transformed / 75M rasterized polygons per second.

IGN Xbox: Last year Seamus Blackley was quoted as saying in an interview with us that "The only changes that you'd ever possibly see -- and I think that the probability of there being any changes is extraordinarily low -- would be upgrades to system performance." What happened?

J. Allard: The honest truth is that the goal that we always had for the system was 3x the graphical and computational performance of PlayStation 2. Initially, we thought that a 600MHz CPU and a 300MHz GPU was about right -- and that was in March. Now that Nvidia's got the NV20 in production, and we've got NV20 cards working with the operating system out in dev kits, and we've got games up and running on NV20s, we learned a bit more about the production and the manufacturing, and we decided that the 250MHz combined with the 733MHz is really the right balance. We'll still hit the 3x, but we guessed bad with the 300Mhz.



IGN Xbox: The poly performance has changed as well though, from 300 million polys a second to 125.


J. Allard: The funny thing about poly performance is that that's a theoretical number, and it's a good number to talk about because competitors talk about theoretical numbers, but we've long held that the most important number is what game performance looks like. So the fact that NV20s are in developers hands is great, and the final hardware will be in their hands in a couple of months. I think we'll have no problem making the 3x differentian in real game performance, and maybe even more.




IGN Xbox: You've said once before that there wouldn't be spec changes -- what's to stop more announcements in the coming months?

J. Allard: It's more of a spec refinement, not a change. Technically it's a change -- that's the clock rate we're going to be able to achieve and still maintain the 3x performance. From a physics change it's what's possible and what's right. It's not like there's a 300MHz part that's appropriate and we're shaving some money. It's really the right thing overall in the system architecture. We need to get final hardware to the developers in the next couple months to get them to write games for 2001 that shine.

This ^^^^ s the end of the story,that last question put J Allard against the wall,you can clearly see that he din't even know what to answer,first he say is not a change then he say technically it's a change.


The problems was that MS lie a little much on those xbox specs,in fact they go on saying that they still hit 3 times the perfomance of the PS2,which is a realy big and open lie,i hope they don't do the same again.

Are we talking about XBox vs PS2? I think 3X is reasonable for ingame polygon performance for some scenarios. For instance I think Sony stated something like 16 million PPS max for games texured, lit, etc.. And I heard that some XBox games go as high as 50M PPS textured and lit.

Also, for car games, Forza, RSC2 and other top XBox games are budgeted like 15,000~20,000 polys per car while I think GT4 is budgeted around 5000~6000 polys. That's why top XBox car games usually have car damage for instance.

 

[marconelly!]

And I heard that some XBox games go as high as 50M PPS textured and lit.

I don't think there's a game that came even close to that. The highest I've ever heard was about half of that figure.

Also, for car games, Forza, RSC2 and other top XBox games are budgeted like 15,000~20,000 polys per car while I think GT4 is budgeted around 5000~6000 polys. That's why top XBox car games usually have car damage for instance.

There are games on PS2 that have a lot more polys on cars than GT4. I forgot the numbers but I think resident devs can chime in on this. I think that one F1 game in particular was said to push around 18Mp/s by it's developers. Also, consider most of the Xbox racing games run at 30FPS (except for RSC/2) which effectively halves their poly/sec throughput. Frankly, I can't think of a game where you'd actually have 3x more polys/sec on Xbox than on a comparable PS2 game. More yes, but not nearly that much more.

 

[nAo]

Also, consider most of the Xbox racing games run at 30FPS (except for RSC/2) which effectively halves their poly/sec throughput

Poly/sec throughput is the same, it doesn't depend upon your frame rate

 

[London Geezer]

I guess he meant poly count is basically doubled per frame when going from 60 to 30fps.

 

[nAo]

I guess he meant poly count is basically doubled per frame when going from 60 to 30fps.

primitives count doubles, frame time doubles too, so the ratio is the same

 

[marconelly!]

Not per frame, but per second.

Game that renders say 1000 polygons per frame, will display 30000 polys/sec if a game is running at 30FPS game, and 60000 polys/sec if the game is running at 60FPS. That's what I meant.

primitives count doubles, frame time doubles too, so the ratio is the same

Exactly, so if you take an example of a game that renders a car using 1000 polys and runs at 60FPS, the poly/sec number is the same as another game that renders a car using 2000 polys but runs at 30FPS.

 

[nAo]

It was not clear you were keeping triangles count per second constant

 

[London Geezer]

Not per frame, but per second.

Game that renders say 1000 polygons per frame, will display 30000 polys/sec if a game is running at 30FPS game, and 60000 polys/sec if the game is running at 60FPS. That's what I meant.

Same thing i was saying, just from the other side.

When going from 30 to 60 fps, when polys per frame are constant, you'd have to push double the polys per second.

When polys per second is constant, going from 30 to 60 will halve your polys per frame.