História da evolução dos GPU

[Enzo]

Das "50", só tenho memórias e experiencias com as 7950. E muito boas, por sinal. Vou ter agora experiencia com a série 6xxx.

[jotinha17]

A série 6000 não foi muito famosa, contudo não é uma má série, tive duas 6950, tendo uma sido desbloqueada para 6970 e não desgostei.

Mas as 5850 e as 7950 foram o topo da AMD nos últimos anos, já que o resto me passou ao lado, tive uma 4870 mas foi de passagem.

[Enzo]

Da serie 5xxx só tive a 5570 infelizmente. Já andei por ai a namorar uma 5850 e a 5870 mas ainda não me calhou mais nenhuma na rifa. Aquela Ares que está no OLX, esteve a 100eur com outro dono que estava à rasca. Não cheguei a tempo, e agora está assim nesses preparos há mais de 3 meses...

Para ser sincero, a minha história com gráficas começou nas séries gtx7xx/hd7xxx. Depois é que andei para a frente e para trás em tempo e performance como sabes. Mas como referiste, da série 6, realmente quase nunca ouvi falar. Sei que existe cerca de uma dezena delas, mas conheco 3, basicamente, que já tive para comprar ou com elas à frente: 6850, 6870 e 6990 (manias do CF). Para já, logo vou a testes com a 6870.

[Jorge-Vieira]

A serie HD 6000 basicamente não teve grande sucesso porque nada acrescentou à serie HD 5000, basicamente foi um "rebrand" com poucas melhorias.
A grande serie foi sem duvida as HD 5000.

[Enzo]

Ah...então o vicio dos rebrands já vem mais de trás.............

[Jorge-Vieira]

Nao só na AMD, a nVidia também foi perita nisso com o chip G80... teve para aí uns 3 ou 4 rebrands

[Enzo]

Esse não é o das 8800?

[Jorge-Vieira]

Yep

[Enzo]

E quem é que foi o rebrand de quem?

[Jorge-Vieira]

O G80 apareceu inicialmente na serie 8000, uma das melhores series também da nVidia que veio para o publico, depois as duas ou três series seguintes foram rebrands com o chip G80.
Em termos de comparação o chip G80 representa para a nVidia aquilo que o chip RV 770 (HD 4000) representou para a AMD.

[Jorge-Vieira]

Arquitetura G80 e placas graficas nVividia GTX 8000 series

The G80 Architecture

Well, we've talked about what a unified architecture is and how Microsoft is using it in DX10 with all the new features and options available to game designers. But just what does NVIDIA's unified G80 architecture look like??

Click to Enlarge

All hail G80!! Well, um, okay. That's a lot of pretty colors and boxes and lines and what not, but what does it all mean, and what has changed from the past? First, compared to the architecture of the G71 (GeForce 7900), which you can reference a block diagram of here, you'll notice that there is one less "layer" of units to see and understand. Since we are moving from a dual-pipe architecture to a unified one, this makes sense. Those eight blocks of processing units there with the green and blue squares represent the unified architecture and work on pixel, vertex and geometry shading.
Even the setup events at the top of the design are completely new, from the Host and below. The top layer of the architecture that includes the "Vtx Thread issue, Geom Thread Issue and Pixel Thread Issue" units is part of the new thread processor and is responsible for maintaining the states of the numerous processing threads that are active at one time and assigning them to (or issuing) processing units as they are needed. With this many processing units and this many threads, this unit is going to keep quite busy...

Okay, so how many are there already?? There are 128 streaming processors that run at 1.35 GHz accepting dual issue MAD+MUL operations. These SPs (streaming processorss) are fully decoupled from the rest of the GPU design, are fully unified and offer exceptional branching performance (hmm...). The 1.35 GHz clock rate is independent of the rest of the GPU, though all 128 of the SPs are based off of the same 1.35 GHz clock generator; in fact you can even modify the clock rate on the SPs seperately from that of the GPU in the overclocking control panel! The new scalar architecture on the SPs benefits longer shader applicaitons to be more efficient when compared to the vector architecture of the G70 and all previous NVIDIA designs.
The L1 cache shown in the diagram is shared between 16 SPs in each block, essentially allowing these 16 units to communicate with each other in the stream output manner we discussed in the DX10 section.

Looking at the raw numbers, you can see that the GeForce 8800 SP architecture creates some impressive processing power, resulting in more than double the "multiplies" that the G71 or R580 could muster. Also, we found out that the new G80 SPs are 1 to 2 orders of magnitude faster than G71 was on branching -- this should scare ATI as their branching power was one of the reasons their R580 architecture was able to hold off the 7900 series for as long as it did.

In previous generations of NVIDIA's hardware, the texture units actually used a small portion of the pixel shader in order to keep from doubling up on some hardware. This has the potential to create "bubbles" in the GPU processing that looked like the GeForce 7-series diagram above. Math operations often had to wait for texture units to complete their work before continuing. That is no longer the case with G80; there are literally thousands of threads in flight at any given time allowing the memory access to completely decouple from processing work. This keeps those "bubbles" from occuring in this new design allowing for seemingly faster memory access times.
This threading process has been dubbed "GigaThreading" by NVIDIA and refers to the extremely high amout of active threads at any given time. In a CPU, when a cache miss occurs, the CPU usually has to wait for that data to be retrieved and the thread stalls as it waits. On the G80, if there is a data cache miss, the problem isn't so severe as there are many threads ready to be placed into one of the 128 SPs while the data is retrieved for the cache miss. And in case you were wondering what this constant thread swapping might add to computing overhead, NVIDIA told us that it technically takes 0 clocks for threads to swap!

Moving on to the texture units on the G80, there are two texture fetch (TF) units for every texture address (TA) unit; this allows for a total of 32 pixels per clock of texture addressing and 64 pixels per clock of texture filter ops. These units have been optimized for HDR processing and work in full FP32-bit specifications, but can support FP16 as well. Because of all this power, the G80 can essentially get 2x anisotropic filtering for free, as well as FP16 HDR for free.

This small table compares the 7900 GTX, X1950 XTX and the 8800 GTX in terms of texture fill rates; on 32-bit dual texturing, the X1950 XTX and the 7900 GTX could get approximately 50% performance on 2x AF while the 8800 GTX gets 100% performance because and 3.6x faster 16x AF rates than the X1950 XTX.

The ROPs on G80 are changed a bit from the G71 architecture as well, starting with support for up to 16 samples for AA; however these are not programmable samples like those on the ATI X1950 architecture; NVIDIA's are still using static, rotated grid sample patterns. As if we would allow NVIDIA to do otherwise, antialiasing is support with HDR! The ROPs can support up to 16 samples and 16 Z samples per partition with up to 32 pixels per clock Z-only per partition. The color and Z compression designs have been improved by a multiple of 2 and the ROPs now support 8 render targets.
With six ROP and Z partitions available, that gives the G80 a total of 96 AA samples and 96 Z samples per clock, as well as 192 pixels per clock of Z-only work. Also, each ROP has a 64-bit interface with the frame buffer; if you do your math you'll come up with an odd-sounding 384-bit total memory interface between the GPU (and its ROPs) and the memory on the sytem. That 64-bit interface is attached to 128MB of memory, totalling 768MB of frame buffer. Yes, the numbers are odd; they aren't the nice round numbers we are used to. But there is no trick to it as many had thought; NVIDIA is segregating some portion to vertex and some to pixel or anything like that.

The Z culling process on the G80 has been improved drastically as well, including the ability to remove pixels that are not visible during the rendering BEFORE they are processed. NVIDIA was pretty tight-lipped about the actual process on how they are doing this, but keeping in mind that the NVIDIA driver uses a just-in-time compiler before passing instructions on to the GPU, its possible that the compiler is doing some work to help the GPU out in this case. Either way, the more capable the Z-culling is on the core, the less work the GPU has to do per frame, improving performance and game play.

Ler todo o artigo:
http://www.pcper.com/reviews/Graphic...0-Architecture



Já que se falou aqui no chip G80, cá fica um artigo sobre o mesmo.
Este chip foi o primeiro chip do mercado a suportar o DX10 e na altura em que saiu, apanhou a ATI/AMD desprevenida. Este chip é considerado com um dos melhores chips da nvidia, por tudio aquilo que veio trazer ao mundo 3D.
A unica parte negativa que se pode apontar a este chip foram os sucessivos rebrands que teve nas series que se seguiram da nVidia, um pouco ao estilo daquilo que vemos hoje a AMD fazer com os rebrands das HD 7000.

[Enzo]

Por acaso pensei que as 8800 só suportassem dx9. Isto porque foi na altura do Crysis original, e penso ter visto isso como requisito.

[Jorge-Vieira]

Não, esse foi o primeiro chip no mercado a suportar o DX10, que sendo um fiasco, praticamente fez dessa placa uma placa DX9.
Na altura em que isso saiu, deixou a AMD/ATI um pouco a navegar no meio do nada.

[MTPS]

A série 58xx foi revolucionária, concordo.

Partiu a Nvidia completamente a meio, que só conseguiu responder meses mais tarde com as Fermi.

Lembro-me claramente deste exemplo:

A 275 GTX 896MB custava perto de 300€, sendo que a 5850 saiu nos 220€ com oferta do Dirt 2 a oferecer uma performance 15/20% superior à GTX 275.

E o mesmo aconteceu com a 5870 face à 285...

Na série 6xxx, tudo esteve mais equilibrado mas ainda assim, apesar da 580 ter estado sem concorrência, a HD 6970 oferecia performance ligeiramente superior à GTX 570, pelo mesmo preço e apresentando 2GB.

No entanto, o maior destaque foi mesmo a 6950 que não deu qualquer hipotese na sua gama, ao ser possível flashar para 6970, fazer OC que nem uma besta e ter 2GB, face à mera GTX 560 Ti.

Depois veio a série 7, que mais uma vez, matou tudo a lembrar a 58xx.

[Jorge-Vieira]

Isto é a prova que quando a AMD faz as coisas bem feitas, os seus produtos vendem, como aconteceu com as series HD 4000/5000 e 7000 e mesmo existindo marketing da concorrencia, a AMD ou esteve na frente a partir tudo, ou estava com quotas de mercado a rondar os 40 a 42%.