Geforce 425/445 GT vs GTX260 and 5850/70

Hi,

I was wondering if the new nvidia fermi cards are any good (the mobile ones) namely the GT 425 and 445 in comparison to the gtx260 (which i currently own) and the 5850/5870s. I'm thinking of buying one of the new dell xps laptops which have them in it. Might be more powerful then my M15x

 

the 445 has 144 cuda cores, the it should be better than the 260, but 425 only has 96, about the ati cards, i dont know

 

NVIDIA GeForce GT 445M

The NVIDIA GeForce GT 445M is a fast mid-range laptop graphics card presented in 2010. It is based on the GF106 core, which is related to the Fermi architecture. Therefore, it supports DirectX 11 and OpenGL 4.0. In contrast to the GTX 460M, the card only features 144 of the 192 shader cores. The chip can be used with a 128 Bit and 192 Bit memory bus and DDR3 or GDDR5. Depending on the configuration, the performance can differ significantly.

GF106 architecture

The GF106 core of the GTX 445M is related to the GF100 core of the GeFore GTX 480M and offers 192 shader and a 192 Bit memory bus for GDDR5. The GT 445M offers only 144 shaders and in some variants also a smaller memory bus with DDR3. 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 core were not only shortened, 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 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 shader are FP64-capable and therewith 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 5830).

Detailed information on the GF104 architecture (and therewith also the GF106 and GF108) can be found in the desktop GTX 460 article by Anandtech.

Performance

Because the GeForce GT 445M features a new architecture, the performance is not comparable to older chips with a similar core count. It heavily depends on the used memory, as DDR3 should be a bottleneck for the performance. The gaming performance is intended to be on a level with the Mobility Radeon HD 5830-5850 (with the same type of graphics memory). However, the Fermi based chips offer a higher Tessellation performance than DX11 chips of the Radeon HD 5000 series.

Features

A novelty of the GF104/106/108 chips is the support of Bitstream HD Audio (Blu-Ray) output via HDMI. Alike the Radeon HD 5730, the GT 445M can transfer Dolby True HD and DTS-HD bitstream-wise without quality loss to a HiFi receiver.

The GT445M 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).

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 GT 445M can be of help in general calculations. For example, the stream processor can considerably faster encode videos than a fast CPU can. Furthermore, physics calculations can be done by the GPU using PhysX (e.g. supported by Mafia 2 or Metro 2033).

According to Nvidia, support for 3D Vision on the new graphics cards is also new. It enables the laptop to send 3D contents (3D games, 3D Web Streaming, 3D photos, 3D Blu-Rays) to a built-in 3D enabled screen or an external 3D TV (only if supported by the laptop manufacturer).

According to rumors, the power consumption of the GeForce GT 445M should be about 45 Watt (TDP including the MXM board and memory), which is about the level of the Mobility Radeon HD 5830. Without load, the chip is clocked at 50/100 MHz (chip/shader) in 2D respectively 200/400 in 3D mode to save power. Furthermore, the 400M series supports Optimus to automatically switch between the integrated graphics card from Intel and the Nvidia GPU. However, the laptop manufacturers need to implement it and it cannot be upgraded.

 

NVIDIA Geforce GT 425M


The NVIDIA GeForce GT 425M is a fast mid-range laptop graphics card presented in 2010. It is based on the GF108 core, which is related to the Fermi architecture. Therefore, it supports DirectX 11 and OpenGL 4.0. In contrast to the GTX 415M, the card features the full 96 shader cores. The difference of the GT420M, GT425M and GT435M is only the core and memory speed.

GF108 architecture

The GF108 core of the GT 425M is related to the GF100 core of the GeFore GTX 480M and offers 96 shaders and a 128 Bit memory bus for DDR3. Except for the memory controllers the GF108 can basically be considered a halved GF106. 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 core were not only shortened, 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 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 shader are FP64-capable and therewith 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 5650).

Detailed information on the GF104 architecture (and therewith also the GF106 and GF108) can be found in the desktop GTX 460 article by Anandtech.

Performance

Because the GeForce GT 425M features a new architecture, the performance is not comparable to older chips with a similar core count. The DDR3 graphics memory combined with the 128 Bit bus should be the bottleneck of the GT 425M. In our tests with an Acer Aspire 5745PG pre-sample, a GT 420M performed on average between a GeForce GT 330M and GT 335M. Therefore, the GT 425 should be a bit faster than the GT 335M. Nvidia positions the card against the Mobility Radeon HD 5650.

The gaming performance of the GT 425M is sufficient for medium detail settings in modern games like Battlefield Bad Company 2. Less demanding games should run in high detail settings. The best resolution to choose is about 1360x768 due to the limited performance. Benchmarks and comparison charts on the 3D performance can be found below.

Features

A novelty of the GF104/106/108 chips is the support of Bitstream HD Audio (Blu-Ray) output via HDMI. Alike the Radeon HD 5730, the GT 425M can transfer Dolby True HD and DTS-HD bitstream-wise without quality loss to a HiFi receiver.

The GT425M 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).

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 GT 425M can be of help in general calculations. For example, the stream processor can considerably faster encode videos than a fast CPU can. Furthermore, physics calculations can be done by the GPU using PhysX (e.g. supported by Mafia 2 or Metro 2033).

According to Nvidia, support for 3D Vision on the new graphics cards is also new. It enables the laptop to send 3D contents (3D games, 3D Web Streaming, 3D photos, 3D Blu-Rays) to a built-in 3D enabled screen or an external 3D TV (only if supported by the laptop manufacturer).

According to rumors, the power consumption of the GeForce GT 425M should be about 35 Watt (TDP including the MXM board and memory), and therefore suited for 15” laptops.which is about the level of the Mobility Radeon HD 5700. Without load, the chip is clocked at 50/100/135 MHz (chip/shader/memory) in 2D respectively 200/400/325 in 3D mode to save power. Furthermore, the 400M series supports Optimus to automatically switch between the integrated graphics card from Intel and the Nvidia GPU. However, the laptop manufacturers need to implement it and it cannot be upgraded.

According to overclock.net, the card performs as fast, as a GeForce GT 335M.

 

Don't much care for ati so the ati lovers can post there stuff ....

 

some ati owners said that the gtx460m is worst than 5850 in performance, but it depends on your needs, if you do a lot of encoding or editing nvidia is the way to go

 

^^^^ If you're doing anything that heavily uses Physx or CUDA then the GT445 will most likely be the top dog here, the GTX260m and GT445 are going to be close but from what's been released I think the 445 will have a slight edge. Now if you're not going to be doing encoding, rendering, etc then the 5850/5870 currently has the edge over the rest not only in performance but cost as well. The 425 IMO is a card that doesn't even belong in this comparison. Now the toss up between the 460m and 5850/70 is something that only time and drivers from nVidia will determine.

 

How about the 470m? Being the highest in terms of cores and clock (that is within the 75w range of the m15x)

 

NVIDIA GeForce GTX 470M


The NVIDIA GeForce GTX 470M is a high-end laptop graphics card presented in 2010. It is based on the GF104 core, which is related to the Fermi architecture. So, it supports DirectX 11 and OpenGL 4.0. The faster GeForce GTX 480M is already based on the GF100 chip.

GF104 architecture

The GF104 core of the GTX 470M is related to the GF100 core of the GeFore GTX 480M and offers 352 shaders and a 192 Bit memory bus for GDDR5. The GTX 470M however offers only 288 cores of the 352. 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 core were not only shortened, 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.

en.wikipedia.org/wiki/Superscalar

In theory, the shaders can thereby be utilized more efficiently and the performance per core is 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 shader are FP64-capable and therewith 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 therewith also the GF106 and GF108) can be found in the desktop GTX 460 article by Anandtech.

NVIDIA?s GeForce GTX 460: The $200 King - AnandTech :: Your Source for Hardware Analysis and News

Performance

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 HD 5850, which could optionally use DDR3 memory, the 192 Bit memory bus is compulsively combined with GDDR5. Furthermore, the Fermi based chips offer a higher Tessellation performance than DX11 chips of the Radeon HD 5000 series. The performance of the GTX470M should be a bit above the Mobility Radeon HD 5870. Therefore, all modern games of 2010 (except Metro 2033 and Crysis) should run in highest detail settings fluently.

Features

A novelty of the GF104/106/108 chips is the support of Bitstream HD Audio (Blu-Ray) output via HDMI. Alike 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 GTX470M 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 470M can be of help in general calculations. For example, the stream processor can considerably faster encode videos than a fast CPU can. Furthermore, physics calculations can be done by the GPU using PhysX (e.g. supported by Mafia 2 or Metro 2033). E.g., the X500’s GPU ran Fluidmark more than 3x faster than its CPU (36 versus 11 fps).

According to Nvidia, support for 3D Vision on the GTX graphics cards is also new. It enables the laptop to send 3D contents (3D games, 3D Web Streaming, 3D photos, 3D Blu-Rays) to a built-in 3D enabled screen or an external 3D TV (only if supported by the laptop manufacturer).

According to rumors, the power consumption of the GeForce GTX 470M should be 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) in 2D respectively 200/400 in 3D mode to save power. Furthermore, the 400M series supports Optimus to automatically switch between the integrated graphics card from Intel and the Nvidia GPU. However, the laptop manufacturers need to implement it and it cannot be upgraded. As today’s quad cores 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 similar called desktop GeForce GTX 470 is based on the GF100 chip and offers 448 shader cores. Therefore it is significantly faster (even as the desktop GTX 460 is faster than the mobile 470M).

 

Right I'm getting me one of these as soon as there is bios support for it!

 

I had a hard time believe the 445m competes with the 5850 since the 460m is very close to performance in most items. Tessellation is just a marketing ploy for NVIDIA. If you read the developer blogs, Tessellation adds a bunch of graphic overhead to divide the pixels down even further to allow for greater detail and movement. Of course Nvidia is putting all their money into this boat and they are going to shove it down everyones throats no matter what. In general terms only... The 460 is close to the 5850. So if that is the case it will be more powerful than the 445m. I dont know about the 425. Probably close to the 335mGT. Which is less than half as powerful as the 5850.

StevenX

 

The 445M is crippled by it's 128-bit GDDR3 interface. It will definitely blow away the 335M GT but especially at high resolution and detail, be significantly weaker than the GTX 460M and HD 5850.

 

Yeah, I don't think the 445 is a true competitor in raw power to the 5850 but I do think the 445 will probably beat out the 260m in CUDA and Physx performance. So if you're after raw performance but don't need all the shiny nVidia stuff then the 5850 is the way to go, but given the choice between the 445 and 260 when Physx and CUDA are necessities I'd choose the 445 all day.

Now on the 470 I've said it before, between the 5850/70 and the 470 I would have a very hard time choosing. I think nVidia would have to screw up pretty bad to not have the 470 beat the 5850 and maybe even the 5870 with better tesselation physx and cuda, but the price is also substantially different. Tough choice on that one.