NVIDIA GeForce GTX 960M vs NVIDIA GeForce GTX 1080 Ti (Desktop) vs NVIDIA GeForce GTX 965M

NVIDIA GeForce GTX 960M

The NVIDIA GeForce GTX 960M is an upper mid-range, DirectX 11-compatible graphics card for laptops unveiled in March 2015. It is based on Nvidia's Maxwell architecture (GM107 chip) and manufactured in 28 nm. The GTX 960M offers 640 shader units clocked at 1097 - 1202 MHz (Boost) as well as fast GDDR5 memory (128 bit, 5000 MHz effective, 80 GB/s).

Compared to the previous and technically very similar GTX 860M, the GTX 960M is clocked 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. GM107 features 5 SMMs and thus 640 shader cores, 40 TMUs and 16 ROPs (128-bit interface).

Another optimization is the massively enlarged L2 cache (GM107: 2 MB). The increased size can handle some of the memory traffic to allow for a relatively narrow memory interface without significantly reducing the performance.

GM107 supports DirectX 12 with feature level 11_0 only.

Performance

Although the GTX 960M has the same memory bandwidth as the previous GTX 860M, its higher core clock leads to a slightly better performance. Overall, the 960M is almost 10 percent faster and similar to the desktop GTX 750 Ti.

Many games of 2014/2015 can be played fluently in FullHD resolution and high detail settings. However, very demanding games such as Assassin's Creed Unity will require lower resolutions and/or details.

Features

GM107 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 GTX 960M should be similar to the old GTX 860M (about 60 watts). Therefore, the GPU is best suited for 15-inch laptops or larger. The 900M series also supports Optimus to automatically switch between an integrated graphics card and the Nvidia GPU.

NVIDIA GeForce GTX 1080 Ti (Desktop)

The Nvidia GeForce GTX 1080 Ti is the fastest desktop consumer graphics card (beginning 2017). It is based on the same GP107 chip as the Titan X but with slightly higher clock speeds and a different memory configuration. It offers one memory controller less (and 11 instead of 12 GB), but the GDDR5X memory is faster clocked (11 GHz) leading to a comparable memory bandwidth. Due to the higher boost clock, the 1080Ti should be around 5 % faster compared to the Pascal Titan X and about 35 % faster compared to the GTX 1080. The TDP is equal to the Titan X with 250 Watt. A new cooler of the Founders Edition should be more efficient and quieter.

NVIDIA GeForce GTX 965M

The NVIDIA GeForce GTX 965M is a 28 nm DirectX-11 graphics card for mid- and high-end notebooks. It was introduced in January 2015 and is based on the Maxwell GM204 (later GM206) architecture. The clock rates specified by Nvidia are 924 MHz (+ Boost) for the GPU and 1250 MHz (5000 MHz effective) for the up to 4 GB of GDDR5 memory.

Early 2015 a new version of the 965M (codename N16E-GR, formerly known as 965M Ti) based on the GM206 will be available that features higher core clocks of 935 MHz base and 1151 MHz Turbo. This resulted in a 12% faster performance in games (in our tests with a MSI GE72 pre-sample in maximum detail settings). The TDP however should remain at 50 Watt like the GTX 960M and the chip is also pin compatible. In theory the GM206 also supports HDMI 2.0, but the laptop has to implement the wiring for this correctly.

Architecture

Just like the mid-range GM107 chip (GeForce GTX 860M), the GM204 is also based on Nvidia's new Maxwell architecture, which replaces the previous Kepler generation. Among other changes, Nvidia have restructured the streaming multi processors (SMM) in order to increase workload and efficiency. Now each SMM contains only 128 shader units and 8 TMUs, which is noticeably less than an equivalent Kepler GPU. The GM204 features four GPCs, and each consists of four SMMs. But, in the GeForce GTX 965M, Nvidia have deactivated 8 of 16 SMMs. As a result, only 1024 shader ALUs and 64 TMUs are active. In addition, there are 32 ROPs in two clusters with 16 units each.

The memory interface has a bandwidth of 128-bits (2x 64 bit). Thanks to an improved compression algorithm, the connection to the GDDR5 memory should be significantly more efficient per MHz. Furthermore, the L1 (96 KB per SMM) and L2 caches (2 MB) have been significantly increased to lower the needed bandwidth.

Although the GM107 and the GM204 both belong to the Maxwell generation, the newer and larger GM204 has several additional features and changes. Aside from the improved polymorphic engine in the SSMs, it is also the first Nvidia chip to support DirectX 12 Feature Level 12_1.

Performance

Thanks to the increased efficiency, the GeForce GTX 965M performs similar to the previous Kepler-GPU GeForce GTX 870M (1344 shader, 192-bit GDDR5). The more expensive, also Maxwell-based GTX 970M (1280 shader, 192-bit GDDR5) is a further 35 to 40 percent faster. Overall, the GTX 965M is fast enough to run demanding games as of 2014/2015 with high details and FullHD resolution. In some titles, even additional quality features like anti-aliasing and anisotropic filtering are possible.

Features

Most of the features are identical to the GeForce GTX 800M series. With the GTX 965M, there can be up to 4 active displays possible, but this will likely decrease due to Optimus. Displays can be connected with a maximum resolution of 3840 x 2160 pixels at 60 Hz via DisplayPort 1.2 or HDMI 2.0 (no HDCP @ 4K). HD audio formats like Dolby True HD and DTS HD can be sent to a compatible receiver as bitstream. As with previous models, 3D Vision is not supported with Optimus.

The updated video processor VP6 supports the usual formats like H.264 and can also decode and encode H.265 with a resolution of up to 4K via the NVENC API. Several parallel streams, such as picture-in-picture in a Blu-Ray movie, are also possible.

Further features of the GTX 900M series, which are also partly supported by older cards, include Battery Boost (longer battery life during gaming), Shadowplay (recording of gaming videos up to 4K60p and 130 Mbit/s) and Gamestream (game streaming on Shield console). More information on these features are available here.

Power Consumption

The power consumption of the 28 nm GeForce GTX 965M including its MXM board and memory should be significantly below the GTX 870M at an estimated 70 watts. Nevertheless, the graphics card can only be used in large gaming notebooks with powerful cooling systems.

Under low load, dynamic clock rates help the GTX 965M to save energy. While idle, the Optimus technology also allows for the complete deactivation of the GPU in favor of the integrated processor graphics card.