NVIDIA Quadro K2100M vs NVIDIA Quadro M620

NVIDIA Quadro K2100M

The NVIDIA Quadro K2100M is a DirectX 11 and OpenGL 4.3 compatible graphics card for mobile workstations. It is a Kepler-based GPU built on the GK106 chip with 576 out of 960 shader cores activated and is manufactured in 28nm at TSMC. The Quadro K2100M is built for the Intel Shark Bay generation (Haswell) and is a successor to the Quadro K2000M (Chief River platform). As a new feature, PCIe 3.0 is supported for the first time. The K2100M usually comes with 2 GB GDDR5 VRAM clocked at 750 MHz (3000 MHz effective, 48.0 GB/s). 

The Quadro series offers certified drivers that are optimized for stability and performance in professional applications like CAD or DCC. OpenGL performance, for example, should be significantly better than with GeForce graphics cards of similar specifications.

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 K2100M, 3 of 5 blocks are active leading to the 576 CUDA cores. 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 offer similar performance to just one shader of a Fermi chip (as the latter is clocked twice as fast).

Performance

The performance is clearly above the old Quadro K2000M, but slightly below the Quadro K3000M. This places the K2100M near the consumer GT 750M GPU. Therefore, most demanding games of 2013 will run fluently with medium or high details.

Features

The improved feature set now includes support for up to 4 active displays. Furthermore, high resolution monitors of up to 3840 x 2160 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.

Using CUDA or OpenCL 1.2, the cores of the Quadro K2100M can be used for general calculations.

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.

The power consumption of the Quadro K2100M is rated at a TGP of 55 W including the board and memory components. Therefore, the card is suited for medium-sized notebooks with 15-inch displays or greater.

NVIDIA Quadro M620

The 28nm NVIDIA Quadro M620 is a mid-range DirectX 12 (FL 11_0) and OpenGL 4.5-compatible graphics card for mobile workstations. It is a 1st generation Maxwell-based GPU built on the GM107 architecture with 512 of the 640 shader cores activated. Therefore, the GPU is not similar to any current consumer card. The Geforce GTX 950M, for example, uses the full 640 shader cores. The older Quadro M1000M offers very similar specs (same amount of shader cores and also based on the same chip but more graphics memory), but was intended for the Skylake generation. The M620 is intended for the Kaby Lake generation.

The Quadro series offers certified drivers that are optimized for stability and performance in professional applications like CAD or DCC. OpenGL performance, for example, should be significantly better compared to GeForce graphics cards of similar specifications.

Performance

Due to the smaller amount of memory, the Quadro M620 should be slightly slower than the older Quadro M1000M. However, the exact clock speeds are not known up to now. In early benchmarks we have, the M1000M is about 9 % faster than the M620 in SPECviewperf 12.

Using CUDA (Compute Capability 5.0) or OpenCL 1.2, the cores of the Quadro M620 can be used for general calculations.

Power Consumption

The power consumption of the Quadro M620 is rated for a 30 Watt TGP including the board and memory components (21.2 Watt TDP), which is 10 Watt lower than the M1000M (which offers more memory). Therefore, the card is suited for 15-inch notebooks and greater.