Author Topic: NVIDIA GF100 GPU Fermi Architecture 1 of 3  (Read 855 times)

Offline javajolt

  • Administrator
  • Hero Member
  • *****
  • Posts: 36193
  • Gender: Male
  • I Do Windows
    • windows10newsinfo.com
NVIDIA GF100 GPU Fermi Architecture 1 of 3
« on: January 18, 2010, 08:36:08 PM »

The CPU is nearly obsolete. At least that's the way it looks when you understand how quickly GPU's have matured to overtake CPU evolution. While the list of processor manufacturers numbers into the hundreds, most personal computer enthusiasts are concerned with the Central Processing Unit (CPU). It's true that CPU's have long enjoyed the attention of overclockers and hardware enthusiasts while less-powerful audio, network, and storage processors work in the background, yet it is the GPU that handles everything we see displayed from our computer system. Gamers rely on powerful graphics adapters to deliver the fast frame rates needed to enjoy high-performance video games, and everyone else needs graphics processing power to enjoy movies and multimedia. But the term 'video game' is coming extremely close to being a liternal interpretation: games are in fact becoming closer to filmed video footage than ever before.

NVIDIA's latest GPU is codenamed GF100, and is the first graphics processor based on the Fermi architecture. In this article, Benchmark Reviews explains the technical architecture behind NVIDIA's GF100 graphics processor and offers an insight into upcoming Fermi-based GeForce video cards. For those who are not familiar, NVIDIA's GF100 GPU is their first graphics processor to support DirectX-11 hardware features such as tessellation and DirectCompute, while also adding heavy particle and turbulence effects. The GF100 GPU is also the successor to the GT200 graphics processor, which launched in the GeForce GTX 280 video card back in June 2008. NVIDIA has since redefined their focus, and GF100 proves a dedication towards next generation gaming effects such as raytracing, order-independent transparency, and fluid simulations. Rest assured, the new GF100 GPU is more powerful than the GT200 could ever be, and early results indicate a Fermi-based video card delivers far more than twice the gaming performance over a GeForce GTX-280.

New products are expected to get better with each new revision, but it amazes me how different the end-goals appear to be between CPU manufacturers such as Intel when compared to a GPU manufacturer such as NVIDIA. While Intel keeps loading their processors with a growing cache buffer and refining the fabrication process to achieve higher speeds, NVIDIA designs a GPU that is really made to compute to a higher level by increasing the number of actual processor cores in addition to the refining process. As of the GF100 GPU, NVIDIA delivers 512 processor cores, which now earn the term 'CUDA cores', compared to Intel's six (6) cores on the upcoming 'Gulftown' Core-i7 processor. I realize that we're comparing apples to oranges here, but the end goals are identical: higher performance. Remember this point as I near my conclusion, and you'll understand what the future holds for processor architecture.

What's new in Fermi?

With any new technology, consumers want to know what's new in the product. The goal of this article is to share in-depth information surrounding the Fermi architecture, as well as the new functionality unlocked in GF100. For clarity, the 'GF' letters used in the GF100 GPU name are not an abbreviation for 'GeForce'; they actually denote that this GPU is a Graphics solution based on the Fermi architecture. The next generation of NVIDIA GeForce-series desktop video cards will use the GF100 to promote the following new features:

•Exceptional Gaming Performance (increased video frame rates and 3D-Vision Surround)

•First-rate image quality (32x CSAA antialiasing mode)

•Film-like Geometric Realism (DirectX-11 particle and turbulence effects)

•Revolutionary Compute Architecture for Gaming (CUDA and PhysX for GPGPU)

About NVIDIA Corporation:

NVIDIA is the world leader in visual computing technologies and the inventor of the GPU, a high-performance processor which generates breathtaking, interactive graphics on workstations, personal computers, game consoles, and mobile devices. NVIDIA serves the entertainment and consumer market with its GeForce® products, the professional design and visualization market with its Quadro products, and the high-performance computing market with its Tesla products. These products are transforming visually-rich and computationally-intensive applications such as video games, film production, broadcasting, industrial design, financial modeling, space exploration, and medical imaging.

NVIDIA Product Lines

GeForce - GPUs dedicated to graphics and video.
Desktop and notebook PCs equipped with GeForce GPUs deliver unparalleled performance, crisp photos, high-definition video playback, and ultra-realistic games. GeForce notebook GPUs also include advanced power management technology to deliver high performance without sacrificing battery life.

Quadro - A complete range of professional solutions engineered to deliver breakthrough performance and quality.
Certified for all leading professional graphics applications. #1in professional graphics segment share. NVIDIA Quadro Plex is the industry's first dedicated visual computing system (VCS).

Tesla - A massively-parallel multi-threaded architecture for high-performance computing problems.
A dedicated, high-performance GPU computing solution that brings supercomputing power to any workstation or server and to standard, CPU-based server clusters. Tesla delivers a 128-processor computing core per GPU, C-language development environment for the GPU, and a suite of developer tools - allowing users to develop applications faster and to deploy them across multiple generations of processors. It also can be used in tandem with multi-core CPU systems to create a scalable computing solution that fits seamlessly into existing workstation or IT infrastructures.

Geometric Realism

In my introduction I stated that video games are will soon reproduce film-quality video footage as their primary graphic. Expect that gamers will soon enjoy lifelike full-motion graphics that replace animated textures. The 2D style of video games (think original Doom or Duke Nukem) is yesteryear, and the 3D future in video games will look like some of the best CG movies we already enjoy (think Final Fantasy VII: Advent Children or Transformers the Movie to a lesser extent). Gamers already experience Toy Story-like CG graphics is many games, and thanks to NVIDIA's Fermi architecture, the GF100 will bridge the gap to playing games that feel like you're controlling a movie.

While programmable shading has allowed PC games to mimic film in per-pixel effects, geometric realism has lagged behind. The most advanced PC games today use one to two million polygons per frame. By contrast, a typical frame in a computer generated film uses hundreds of millions of polygons. This disparity can be partly traced to hardware-while the number of pixel shaders has grown from one to many hundreds, the triangle setup engine has remained a singular unit, greatly affecting the relative pixel versus geometry processing capabilities of today's GPUs. For example, the GeForce GTX 285 video card has more than 150× the shading horsepower of the GeForce FX, but less than 3× the geometry processing rate. The outcome is such that pixels are shaded meticulously, but geometric detail is comparatively modest.

In tackling geometric realism, NVIDIA looked to the movies for inspiration. The intimately detailed characters in films are made possible by two key techniques: tessellation and displacement mapping. Tessellation refines large triangles into collections of smaller triangles, while displacement mapping changes their relative position. In conjunction, these two techniques allow arbitrarily complex models to be formed from relatively simple descriptions.

GF100's entire graphics pipeline is designed to deliver high performance in tessellation and geometry throughput. The NVIDIA GF100 GPU replaces the traditional geometry processing architecture at the front end of the graphics pipeline with an entirely new distributed geometry processing architecture that is implemented using multiple "PolyMorph Engines" . Each PolyMorph Engine includes a tessellation unit, an attribute setup unit, and other geometry processing units. Each SM has its own dedicated PolyMorph Engine (more details on the Polymorph Engine come in another section). Newly generated primitives are converted to pixels by four Raster Engines that operate in parallel (compared to a single Raster Engine in prior generation GPUs). On-chip L1 and L2 caches enable high bandwidth transfer of primitive attributes between the SM and the tessellation unit as well as between different SMs. Tessellation and all its supporting stages are performed in parallel on GF100, enabling breathtaking geometry throughput.

While GF100 includes many enhancements and performance improvements over past GPU architectures, the ability to perform parallel geometry processing is possibly the single most important GF100 architectural improvement. The ability to deliver setup rates exceeding one primitive per clock while maintaining correct rendering order is a significant technical achievement never before done in a GPU.

Photograph? It's actually NVIDIA OptiX technology.

The Bugatti Veyron was computer-rendered in the image above with path tracing techniques using NVIDIA OptiX technology... it is not a photograph. NVIDIA OptiX integrates easily with game engines, allowing racing games to leverage ray tracing for near-photorealistic glamour shots in gallery mode.

Compute Architecture

The rasterization pipeline has come a long way, but as games aspire to film quality, graphics is moving toward advanced algorithms that require the GPU to perform general computation along with programmable shading. G80 was the first NVIDIA GPU to include compute features. GF100 benefits from what we learned on G80 in order to significantly improve compute features for gaming.

GF100 leverages Fermi's revolutionary compute architecture for gaming applications. In graphics, threads operate independently, with a predetermined pipeline, and exhibit good memory access locality. Compute threads on the other hand often communicate with each other, work in no predetermined fashion, and often read and write to different parts of memory. Major compute features improved on GF100 that will be useful in games include faster context switching between graphics and PhysX, concurrent compute kernel execution and an enhanced caching architecture which is good for irregular algorithms such as ray tracing, and AI algorithms.

Atomic operations performance has improved, and allows threads to safely cooperate through work queues, accelerating novel rendering algorithms. For example, fast atomic operations allow transparent objects to be rendered without presorting (order independent transparency) enabling developers to create levels with complex glass environments. For seamless interoperation with graphics, GF100's GigaThread engine reduces context switch time to about 20 microseconds, making it possible to execute multiple compute and physics kernels for each frame. For example, a game may use DirectX 11 to render the scene, switch to CUDA for selective ray tracing, call a Direct Compute kernel for post processing, and perform fluid simulations using PhysX.

Delivering Geometric Realism

According to NVIDIA, tessellation and displacement mapping is the de facto standard in geometric realism for film. While tessellation and displacement mapping are not rendering techniques new to the industry, up until now they have mostly been used in movie development (such as Disney's Pirates of the Caribbean). With the introduction of DirectX 11 and NVIDIA's GF100 GPU, developers will be able to harness these powerful techniques for gaming applications. In this section Benchmark Reviews will discuss the benefits of tessellation and displacement mapping in regard to game development and high-quality real time graphics rendering.

Game assets (such as world objects and characters) are typically created using software modeling packages like Mudbox, ZBrush, 3D Studio Max, Maya, or SoftImage. These packages provide tools based on surfaces with displacement mapping to aid the artist in creating detailed characters and environments. Today, the artist must manually create polygonal models at various levels of detail as required by the various rendering scenarios in the game, required to maintain playable frame-rates. These models are
meshes of triangles with associated texture maps needed for proper shading. When used in a game, the model information is sent per frame to the GPU through its host interface. Game developers tend to use relatively simple geometric models due to the limited bandwidth of the PCI-Express bus and the modest geometry throughput of current GPUs.

continued