NVIDIA GeForce 940M vs NVIDIA GeForce GT 650M

NVIDIA GeForce 940M

The NVIDIA GeForce 940M is a mid-range DirectX 11-compatible graphics card for laptops unveiled in March 2015. It is based on Nvidia's Maxwell architecture (GM108 chip) and manufactured in 28 nm. The 940M offers 384 shader units as well as 2 GB of DDR3 memory (64 bit, 2000 MHz effective).

Compared to the previous and technically very similar GeForce 840M, the GeForce 940M is clocked just slightly higher.

Architecture

Compared to Kepler, Maxwell has been optimized in several details to increase power efficiency. Smaller Streaming Multiprocessors (SMM) with only 128 ALUs (Kepler: 192) and an optimized scheduler should lead to better utilization of the shaders. Nvidia promises that a Maxwell SMM with 128 ALUs can offer 90 percent of the performance of a Kepler SMX with 192 ALUs. GM108 features 3 SMMs and thus 384 shader cores, 24 TMUs and 8 ROPs (64-bit interface).

Another optimization is the massively enlarged L2 cache. The larger size can process some of the memory traffic to allow for a relatively narrow memory interface without significantly reducing performance.

Similar to Fermi and Kepler, the GM107/GM108 support DirectX 12 with feature level 11_0 only.

Performance

Due to its just 5 percent higher core clock, the GeForce 940M is only marginally faster than the previous GeForce 840M and similar to the older GeForce GT 750M (DDR3 version). Many games of 2014/2015 can be played fluently in WXGA resolution (1366 x 768) and medium detail settings. However, very demanding games such as Assassin's Creed Unity will require lower resolutions and/or details.

Features

GM108 integrates the sixth generation of the PureVideo HD video engine (VP6), offering a better decoding performance for H.264 and MPEG-2 videos. Of course, VP6 supports all features of previous generations (4K support, PIP, video encoding via NVENC API). Unfortunately, HDMI 2.0 is still not supported.

Power Consumption

The power consumption of the GeForce 940M should be about 30 Watts or lower. Therefore, the GPU is best suited for laptops 13 - 14 inches in size and above. The 900M series also supports Optimus to automatically switch between an integrated graphics card and the Nvidia GPU.

NVIDIA GeForce GT 650M

The NVIDIA GeForce GT 650M is a mid-range, DirectX 11.1 compatible graphics card that was announced in the first quarter of 2012 for laptops. It is a Kepler-based GPU built on the GK107 architecture and is manufactured in 28nm at TSMC. The graphics card uses a 128-Bit wide memory interface with either the more common but slower DDR3 for VRAM or the more expensive and faster GDDR5. Due to a higher core clock of up to 850 MHz the GT 650M is noticably faster than the 640M.

Architecture

The Kepler architecture is the successor to the Fermi architecture that first appeared in laptops with the GeForce 400M series. The GK107 Kepler core offers two shader blocks, called SMX, each with 192 shaders for a total of 384 shader cores that are clocked at the same speed as the central core. Although more shader cores are available in the Kepler architecture as compared to the Fermi design, the Kepler shaders are still expected to be up to twice as power efficient. However, due to the missing hot clock of the shader domain, two shaders of a Kepler chip are about as fast as one shader of a Fermi chip (as the latter is clocked twice as fast). PCIe 3.0 is now supported by the mobile Kepler series and an optional Turbo mode can automatically overclock the Nvidia card by a theoretical 15 percent if the laptop cooling system allows it. The implementation of this boost mode is done in the BIOS, but it is ultimately dependent upon the manufacturer of the laptop.

Performance

The gaming performance of the GeForce GT 650M equipped with DDR3 graphics memory is somewhere in the former 2011 high-end category between the GeForce GTX 460M and GTX 560M. The performance is exceptionally good in shader-heavy DirectX 11 games and benchmarks. However, the 128-Bit memory interface can be a bottleneck if DDR3 graphics memory is employed. Despite the slower core clock of only 735 MHz, the GDDR5-version of the card should be similar fast. Demanding games of 2011 like Battlefield 3 will be playable in 1366x768 and medium or high settings. Less demanding games, such as Modern Warfare 3, are easily playable with maxed out settings and 1080p resolution.

Features

The improved feature set now includes support for up to 4 active displays. Furthermore, high resolution monitors of up to 3840x2160 pixels can now be connected using DisplayPort 1.2 or HDMI 1.4a if available. HD-Audio codecs, such as Dolby TrueHD and DTS-HD, can be transmitted via bitstream mode through the HDMI port. However, as most laptops will feature Optimus, the integrated GPU will likely have direct control over the display ports and may limit the feature set available by the Nvidia Kepler cards.

The 5th generation PureVideo HD video processor (VP5) is also integrated in the GK107 core and offers hardware decoding of HD videos. Common codecs such as MPEG-1/2, MPEG-4 ASP, H.264 and VC1/WMV9 are fully supported up to 4K resolutions while VC1 and MPEG-4 are supported up to 1080p. Two streams can be decoded in parallel for features such as Picture-in-Picture. Another novelty is the inclusion of a dedicated video encoding engine similar to Intel QuickSync that can be accessed by the NVENC API.

The power consumption of the GeForce GT 650M should be best suited for medium-sized notebooks 15-inches or greater.