NVIDIA GeForce GTX 485M vs NVIDIA GeForce GTX 460M SLI

The NVIDIA GeForce GTX 460M SLI consists of two high end DirectX 11 capable Geforce GTX460M cards connected with an SLI bridge. Therefore, it offers 2x 192 cores of the GF106 chip. Due to the alternating frame rendering (AFR), the SLI solution may suffer from micro stuttering in low fps ranges (around 30fps). Furthermore, the 2x1536 MB GDDR5 cant be added together as each card uses the same date in the graphics memory.

GF106 architecture

The GF106 core of the GTX 460M is related to the GF100 core of the GeFore GTX 480M and offers 192 shaders and a 192 Bit memory bus for GDDR5. Except for the memory controllers, the GF106 can basically be considered a halved GF104. Therefore, the architecture is not comparable to the old GT215 (e.g., GeForce GTS 350M) or GT216 (e.g., GeForce GT 330M) cores.

Unlike the GF100, the smaller GF104, GF106, and GF108 cores have all been shortened and considerably modified. In contrast to the GF100, which was designed for professional applications, these GF10x 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 should be improved. However, in worst case scenarios the performance 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 shortened (only 1/3 of the shaders 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 by extension the GF106 and GF108) can be found in the desktop GTX 460 article by Anandtech.

Performance

The SLI performance with the current drivers (mid 2010) should be about 15-20% faster than a single GTX 460M in high settings and resolutions. Therefore, all current games (as of 2011) should run fluently in highest detail settings with antialiasing and Full HD resolution, with the exception of Metro 2033 and Crysis.

Features

A novelty 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 460M can transfer Dolby True HD and DTS-HD bitstream-wise without quality loss to a HiFi receiver.

The GTX460M offers the 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). The X500 tester was able to decode the VC-1 encoded Elephants Dream video with about 3-6% CPU load (according to the task manager). The H.264 coded Big Buck Bunny video was played back with 1-3% CPU load (both 1080p videos).

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 460M can used for 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 (e.g. supported by Mafia 2 or Metro 2033). A single GTX 460M of the SLI combination can also be used for dedicated calculations.

According to Nvidia, support for 3D Vision on the GTX graphics cards is also enabled. It allows the laptop to send 3D content (3D games, 3D Web Streaming, 3D photos, 3D Blu-Rays) to a supported 3D enabled screen or an external 3D TV if compatible.

The power consumption of a single GeForce GTX 460M is supposedly about 72 Watts (TDP including the MXM board and memory). By extension, the GTX 460M SLI should use twice as much power. However, a single 460M in the SLI setup can be deactivated in the drivers to save power. If idle, each chip is clocked at 50/100 MHz and 200/400MHz (chip/shader) in 2D mode and 3D mode, respectively, to save power.

The similar desktop GeForce GTX 460 SLI is based on the GF104 chip and offers significantly more shader cores at 2x336 cores. Therefore, the desktop setup is significantly faster than the 460M SLI and even the 470M SLI graphics solutions.