NVIDIA Quadro K620M

The Nvidia Quadro K620M is a DirectX 11 and OpenGL 4.5-compatible graphics card for mobile workstations. It is a Maxwell-based GPU built on the GM108 chip with 384 shader cores and manufactured in 28 nm by TSMC. The Quadro K620M is the successor to the significantly slower Quadro K610M. Usually, the GPU comes with 2 GB DDR3 memory clocked at 1000 MHz (2000 MHz effective, 16 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

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% 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 reduce some of the memory traffic to allow for a relatively narrow memory interface without significantly hurting performance.

GM108 supports DirectX 11.2 (feature level 11.0 only) as well as DirectX 12.

Performance

Due to their identical specifications, the Quadro K620M offers a similar 3D gaming performance as the consumer GeForce 840M. Most games from 2014/2015 will run fluently in low or medium settings. Compared to other Quadro GPUs, the K620M performs almost similar to the older K1100M.

Features

The feature set should include support for up to 4 active displays. High-resolution monitors of up to 3840x2160 pixels can be connected using DisplayPort 1.2 or HDMI 1.4a (HDMI 2.0 not supported). 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, the cores of the Quadro K620M can be used for general calculations.

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).

Power Consumption

The power consumption of the Quadro K620M should be about 30 W including the board and memory components. Therefore, the GPU is best suited for laptops 13 - 14-inches in size and above. The K620M also supports Optimus to automatically switch between an integrated graphics card and the Nvidia GPU.

Quadro K Series Quadro K5100M 1536 @ 0.77 GHz 256 Bit @ 3600 MHz Quadro K5000M 1344 @ 0.71 GHz 256 Bit @ 3000 MHz Quadro K4100M 1152 @ 0.71 GHz 256 Bit @ 3200 MHz Quadro K4000M 960 @ 0.6 GHz 256 Bit @ 2800 MHz Quadro K3100M 768 @ 0.71 GHz 256 Bit @ 3200 MHz Quadro K3000M 576 @ 0.65 GHz 256 Bit @ 2800 MHz Quadro K2100M 576 @ 0.67 GHz 128 Bit @ 3000 MHz Quadro K1100M 384 @ 0.71 GHz 128 Bit @ 2800 MHz Quadro K620M 384 @ 1.03 - 1.12 GHz 64 Bit @ 2000 MHz Quadro K2000M 384 @ 0.75 GHz 128 Bit @ 1800 MHz Quadro K1000M 192 @ 0.85 GHz 128 Bit @ 1800 MHz Quadro K610M 192 @ 0.95 GHz 64 Bit @ 2600 MHz Quadro K510M 192 @ 0.85 GHz 64 Bit @ 2400 MHz Quadro K500M 192 @ 0.85 GHz 64 Bit @ 1800 MHz
Architecture	Maxwell
Pipelines	384 - unified
Core Speed	1029 - 1124 (Boost) MHz
Memory Speed	2000 MHz
Memory Bus Width	64 Bit
Memory Type	DDR3
Max. Amount of Memory	2048 MB
Shared Memory	no
API	DirectX 11, Shader 5.0, OpenGL 4.3
Power Consumption	30 Watt
technology	28 nm
Features	Optimus, PhysX, CUDA, OpenCL, 3D Vision, 3DTV Play
Date of Announcement	01.03.2015
Link to Manufacturer Page	http://www.nvidia.de/object/mobile-works...

Benchmarks