AMD Radeon 530 vs NVIDIA GeForce GT 750M

AMD Radeon 530

The Radeon 530 is a dedicated entry-level graphics card for laptops that was released in 2017. According to AMD, there are several different versions with 384 or 320 shader units and DDR3 or GDDR5 64-bit graphics memory. However, they are not based on one of the newer RX series Polaris chips, but most likely using the same architecture as the Radeon R7 M445 / M440 / M340 / M260 / 8650M / 8590M (384 shader units, 28 nm GCN) and M430 / M330 / M230 (320 shader units, 28 nm Sun GCN). AMD claims that the clock speed of the Radeon 530 can reach 1,024 MHz.

Considering the above, the game performance of the Radeon 530 should fall between the Radeon R7 M440 (320 shader units, DDR3), Radeon R7 M460 (384 shader units, DDR3) and Radeon R7 M445 (320 shader units, GDDR5) (see these pages for detailed gaming benchmarks). Graphically intensive games such as Dishonored 2, Call of Duty: Infinite Warfare or XCOM 2 should not run smoothly on this GPU. Less demanding games like Overwatch, Fifa 17 (with a fast CPU), or Farming Simulator 17, would run well, but using low to medium detail settings. For detailed game benchmarks, visit the pages of the previously linked cards. According to the specs, the DDR3 version could be slower than the Radeon 520, that is specified with 320 shaders and GDDR5.

NVIDIA GeForce GT 750M

The NVIDIA GeForce GT 750M is a DirectX 11 graphics card of the middle class. It is based on the Kepler architecture and manufactured by TSMC in a 28-nanometer process. The GK107 chip (384 shaders) is clocked at up to 967 MHz plus boost and has a 128 bit memory interface (mostly DDR3, but GDDR5 also possible).

Architecture

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 processor core. Although more shader cores are available in the Kepler architecture as compared to the Fermi design, the Kepler shaders are expected to be up to two times more power efficient. However, due to the missing hot clock of the shader domain, two shaders of a Kepler chip are as fast as one shader of a Fermi chip, even though Fermi shaders are clocked at twice the speed.

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

Depending on clock speed, the GT 750M with DDR3 memory is about 10 - 15 percent faster than the GT 650M. The very rare GDDR5 version even beats the GTX 660M. Most current games (as of 2013) can be played fluently in high settings. In older titles, there are also reserves for additional quality features like AA and AF. Detailed benchmarks can be found further down on this page.

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), also integrated in the GK107 core, 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 feature is the inclusion of a dedicated video encoding engine similar to Intel QuickSync that can be accessed via the NVENCI API.

Power Consumption

The power consumption of the GeForce GT 750M should be somewhere between the GT 650M and GTX 660M (about 35 - 40 watts). As a result, the Nvidia GPU is best suited for notebooks 15 inches in size or greater.