NVIDIA GeForce GTX 470M vs NVIDIA GeForce GTX 480M
NVIDIA GeForce GTX 470M► remove
The NVIDIA GeForce GTX 470M is a high-end laptop graphics card introduced in 2010. It is based on the GF104 core as part of the Fermi architecture (as opposed to the GF100 core that the faster GTX 480M is based off of). As a result, the GTX 470M supports both DirectX 11 and OpenGL 4.0.
The GF104 core of the GTX 470M is related to the GF100 core of the GeFore GTX 480M and offers 384 shaders and a 256 Bit memory bus for GDDR5. The GTX 470M, however, offers only 288 cores of the 384 and a 192 Bit memory bus. The architecture of the GF104 is not comparable to the old GT215 (e.g., GeForce GTS 350M) or G92b (e.g., GeForce GTX 285M) cores. Unlike the GF100, the smaller GF104, GF106, and GF108 cores were not only reduced in size, but also considerably modified. In contrast to the GF100, which was designed for professional applications, these chips target the consumer market. They feature more shaders (3x16 instead of 2x16), more texture units (8 instead of 4) and SFUs per streaming multi-processor (SM). As there are still only 2 warp schedulers (versus 3 shader groups), Nvidia now uses superscalar execution to use the higher amount of shaders per SM more efficiently. In theory, the shaders can thereby be utilized more efficiently and the performance per core is improved.
However, in worst case scenarios the performance of the GTX 470M can also be worse than of the GF100 and its predecessors. The ECC memory protection, which is important for professional applications, was completely omitted and the FP64 hardware reduced (only 1/3 of the shader are FP64-capable and thereby only 1/12 of the FP32’s performance). Because of these cutbacks, the size of the SM grew only by 25% despite the higher number of shaders and larger warp schedulers with superscalar dispatch capabilities. Due to the different shader architectures and the higher clock rate of the shader domain, the core count can not be directly compared to AMD cores of the Radeon 5000 series (e.g. HD 5850).
Detailed information on the GF104 architecture (and thereby also the GF106 and GF108) can be found in the desktop GTX 460 article by Anandtech.
Because the GeForce GTX 470M features a new architecture, the performance is not comparable to older chips with a similar core count. In contrast to the Radeon HD 5850, which could optionally use DDR3 memory, the 192 Bit memory bus of the GTX 470M is combined with GDDR5. Furthermore, the Fermi-based chips offer higher Tessellation performance than DX11 chips of the Radeon HD 5000 series. The performance of the GTX470M should also be a bit above the Mobility Radeon HD 5870 and first tests even show performance scores above a GTX 480M. Therefore, all modern games of 2010 (except Metro 2033 and Crysis) should run in highest detail settings fluently.
A novel feature of the GF104/106/108 chips is the support for Bitstream HD Audio (Blu-Ray) output via HDMI. Similar to the Radeon HD 5850, the GTX 470M can transfer Dolby True HD and DTS-HD bitstream-wise without quality loss to a HiFi receiver.
The GTX 470M offers PureVideo HD technology for video decoding. The included Video Processor 4 (VP4) supports feature set C and therefore the GPU is able to fully decode MPEG-1, MPEG-2, MPEG-4 Part 2 (MPEG-4 ASP - e.g., DivX or Xvid), VC-1/WMV9, and H.264 (VLD, IDCT, Motion Compensation, and Deblocking).
Furthermore, the GPU is able to decode two 1080p streams simultaneously (e.g., for Blu-Ray Picture-in-Picture).
Through CUDA, OpenCL, and DirectCompute 2.1 support, the GeForce GTX 470M can be of use in general calculations. For example, the stream processor can encode videos considerably faster than can many modern CPUs. Furthermore, physics calculations can be done by the GPU using PhysX if supported (e.g., Mafia 2 or Metro 2033).
According to Nvidia, support for 3D Vision on the GTX graphics cards is also enabled. It enables the laptop to send 3D content (3D games, 3D Web Streaming, 3D photos, 3D Blu-Rays) to a built-in 3D enabled screen or an external 3D TV if supported by the laptop manufacturer.
Unofficially, the power consumption of the GeForce GTX 470M should be at about 75 Watt (TDP including the MXM board and memory), which is about the level of the Mobility Radeon HD 5870. Without load, the chip is clocked at 50/100 MHz (chip/shader) and 200/400 MHz in 2D mode and 3D mode, respectively, to save power. Furthermore, the 400M series supports Optimus to automatically switch between the integrated graphics card from Intel and the Nvidia GPU. However, whether or not this feature is included on a notebook will be dependent on the notebook manufacturer. As modern quad cores (2010) don’t house an integrated GPU, we won’t see many Optimus designs with GTX 470M before the launch of Sandy Bridge in 2011.
The similarly named desktop GeForce GTX 470 is based on the GF100 chip and offers 448 shader cores. Therefore, it is significantly faster than a GTX 470M. Instead, a more comparable desktop GPU to the GTX 470M in terms of overall performance would be the GeForce GTS 450.
NVIDIA GeForce GTX 480M► remove
The NVIDIA GeForce GTX 480M is a high-end graphics card for laptops based on the Fermi architecture. As a result, it supports DirectX 11 and is produced in 40nm at TSMC. Featuring 352 cores, the GTX480M is similar to the desktop GTX 465 but with a lower clock rate. The GeForce GTX 480M is combined with 2 GB of fast dedicated GDDR5 graphics memory and the overall performance should be generally superior to the Mobility Radeon HD 5870.
The GF100 (aka. Fermi) chip was redesigned from scratch and features 3 billion transistors, assuming all 512 shaders are present. Compared to the desktop HD 5870 with 2.13 billion transistors or the Mobility Radeon HD 5870 (RV870) with 1.04 billion transistors, the GTX 480M die is physically quite large.
The mobile Fermi chip is stripped down to 352 shader cores (1-dimensional) with 32 ROPs and 44 Texture Units. The memory bus is 256 bit wide, but due to the fast GDDR5 memory, this should not be a bottleneck. The power consumption has been specified to 100 Watt TDP when taking into account the MXM board and the 2 GB GDDR5. AMD usually specifies the TDP of the chip alone, therefore this value is not directly comparable with competing Radeon cards. Still, the GTX 480M is only suited for very large desktop replacement (DTR) laptops with an excellent cooling solution. Originally, only Clevo was offering the GTX 480M in its 17" (D901F) and 18" (X8100) barebones.
The performance of the Nvidia GeForce GTX 480M is about 10% better on average than the ATI Mobility Radeon HD 5870. In demanding DirectX 11 games and benchmarks (that make use of the Tessellation engine), the GTX 480M is even faster. That means the GTX480M is the fastest single GPU graphics solution for laptops as of early to mid 2010. Modern DirectX 10 games should run fluently in high resolutions and details with antialiasing. Only very demanding games like Crysis or Metro 2033 may need some reduced settings (see list below). Due to the DirectX 11 hardware support (and the good tessellation implementation), the Fermi based laptop graphics card should be well suited for upcoming DirectX 11 games.
As the GeForce 300M series, the GeForce GTX 480M supports PureVideo HD with VideoProcessor 4 (VP4 with Feature Set C). This means the GPU is able to fully decode HD videos in H.254, VC-1, MPEG-2, and MPEG-4 ASP. The graphics card can also accelerate Flash videos by using Flash 10.1 or greater.
The rendering cores of the Nvidia GeForce GTX 480M can be used for general calculations with CUDA or DirectCompute. For example, the encoding of HD videos can be done significantly faster than most modern CPUs by using the shader cores of the GPU instead. PhysX is also supported by the mobile Fermi chip to calculate physics effects in supported games.
Compared to desktop GPUs, the Geforce GTX 480M is comparable to a nunderclocked Nvidia GeForce GTX 465 (607/1200 clock speed) and is therefore on par with a desktop Radeon HD 5770.
|NVIDIA GeForce GTX 470M||NVIDIA GeForce GTX 480M|
|GeForce GTX 400M Series|
|288 -||352 -|
|Core||535 MHz||425 MHz|
|Shader||1070 MHz||850 MHz|
|Memory||1250 MHz||1200 MHz|
|Bus||192 Bit||256 Bit|
|DirectX||DirectX 11, 5.0||DirectX 11, 5.0|
|Technology||40 nm||40 nm|
|Max. Memory||2048 MB|