NVIDIA GeForce GTX 770M SLI vs NVIDIA GeForce RTX 4050 Laptop GPU vs NVIDIA GeForce GTX 765M

NVIDIA GeForce GTX 770M SLI

The NVIDIA GeForce GTX 770M SLI is a high-end DirectX 11-compatible graphics solution for laptops, consisting of two GeForce GTX 770M. Each card has a 28nm GK106 core based on the Kepler architecture. The clocks for the SLI-setup are identical to a single GTX 770M. With SLI, each card usually renders a single frame (AFR mode). Therefore, it may suffer from micro stuttering in low fps ranges of 30fps. This happens because of different timespans between two frames (e.g., irregular delays between sequential frames).

Architecture

The Kepler architecture is the successor to the Fermi architecture that first appeared in laptops with the GeForce 400M series. The GK106 Kepler core offers five shader blocks, called SMX, that are clocked at the same speed as the central core. In the GTX 770M, all five blocks are activated (= 960 CUDA-Cores for each 770M). Although the Kepler architecture can utilize more shader cores than a Fermi chip, its shaders can 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 of similar speed to 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 GPU Boost 2.0 can automatically overclock the card if the laptop cooling system allows it. This feature is available on any notebook with a graphics card of the 700M series.

Performance

The GeForce GTX 770M SLI is about 70 - 80 percent faster than a single GTX 770M, leading to a performance somewhere between a single GeForce GTX 680 (desktop) and GTX 780M. Therefore, most games (as of 2013) are playable at the highest detail setting and in FullHD resolution. In many cases it is even possible to activate additional anti-aliasing.

Features

The feature set 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 GK106 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.

Power consumption

The power consumption of the GeForce GTX 770M SLI should double to about 150 watts (including board and memory) compared to a single GTX 770M. Therefore, only large desktop replacements can handle the heat.

NVIDIA GeForce RTX 4050 Laptop GPU

The NVIDIA GeForce RTX 4050 Laptop GPU (codename GN21-X2) is a mid-range laptop GPU. It is based on the AD107 chip and uses the Ada Lovelace architecture. The RTX 4050 Laptop offers 2560 shaders and uses 6 GB GDDR6 dedicated graphics memory with a clock speed of 16 Gbps (effective) and a 96 Bit memory bus. The TGP (Total Graphics Power) can be configured between 35 and 115 Watt (+ 10-25 Watt Dynamic Boost from the CPU) leading to different performance levels. The boost clock depends on the TGP settings and ranges from 1605 MHz (35 Watt) to 2370 MHz (115 Watt). The performance therefore is also highly depending on the laptop and TDP settings.

In our benchmarks, the RTX 4050 stays slightly behind the older mobile RTX 3060 but is clearly faster than the mobile RTX 3050 Ti. Therefore, it is best suited for 1920x1080 gaming at high to ultra settings depending on the game (see benchmarks below).

The RTX 4050 offers 80 tensor cores and therefore supports DLSS 3 including frame generation that can have a big impact in supported games. The raytracing cores however will see less usage, as the RTX 4050 does not offer enough performance for high detail settings and raytracing in demanding games.

The AD107 chip is manufactured in 5nm at TSMC (4N process).

NVIDIA GeForce GTX 765M

The NVIDIA GeForce GTX 765M is an upper mid-range DirectX 11-compatible graphics card for laptops. Compared to the GTX 760M, the 765M offers a higher core clock rate from the same GK106 architecture.

As a novelty, the GeForce 700M series implements GPU Boost 2.0 to automatically overclock the core clock rate. Depending on the cooling headroom provided by the laptop and the application or game, up to 15 % performance gains are possible.

Architecture
The Kepler architecture is the successor to the Fermi architecture that first appeared in laptops with the GeForce 400M series. The GK106 Kepler core offers five shader blocks, called SMX, that are clocked at the same speed as the central core. In the GTX 765M, four blocks are active for a total of 768 CUDA cores. Although the Kepler architecture can utilize more shader cores than a Fermi chip, its shaders can 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 of similar speed to 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 graphics performance of the GeForce GTX 765M is clearly above the GTX 660M thanks to the higher amount of shaders. The maximum performance may differ a bit depending on the cooling solution of the laptop due to better utilization of GPU Boost 2.0 on laptops with more effective cooling solutions. In our tests the average performance of the GTX 765M was above the older GTX 670MX. Demanding games like Metro: Last Light, Crysis 3, Far Cry 3 or even SimCity were playable in 1366x768 pixels and high detail settings at fluent frame rates. Older and less demanding games like Star Craft 2 however were playable in Full HD with all settings set to max.

Features
The feature set of the GTX 765M is identical to the GTX 670MX as both are based on the same GK106 core. Therefore the GPU supports 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 GK104 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. Finally, the dedicated video encoding engine called NVENC API similar to Intel QuickSync is integrated in the chip.

The power consumption of the GeForce GTX 765M should be between 50 and 75 Watt (similar to the 660M and 670MX, respectively, according to rumors) and is therefore best suited for large notebooks (15-inches or greater) and desktop replacements.