NVIDIA Quadro K4000M vs AMD FirePro M6000 vs NVIDIA Quadro K620M

NVIDIA Quadro K4000M

The NVIDIA Quadro K4000M is a high-end, DirectX 11.1 compatible graphics card for mobile workstations. It is a Kepler-based GPU built on the GK104 chip (but using only 960 shader cores) and is manufactured in 28nm at TSMC. The Quadro K4000M is built for the Intel Chief River generation (Ivy Bridge) and is the successor to the Fermi-based Quadro 4000M (Huron River platform).

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 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 GK104 Kepler core offers eight shader blocks, called SMX, that are clocked at the same speed as the central core. In the K4000M, 5 blocks are active leading to the 960 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). 

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 performance is significantly above the level of the older Quadro 5010M and also beats the GeForce GTX 675M. Therefore, the card will manage both CAD software and demanding 3D games of 2013 in high quality settings.

Features

The improved feature set now 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 GK107 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 K4000M is rated at 100 Watt (TGP according to Nvidia) and is therefore suited for large-sized notebooks 17-inches or greater.

AMD FirePro M6000

The AMD FirePro M6000 is an upper middle-class mobile workstation graphics card with DirectX 11 support. It is based on the same Cape-Verde-chip found in the Radeon HD 7700M / 7800M series.

Compared to the Radeon consumer line, the FirePro offers certified drivers for professional 3D applications. Due to optimizations and some unlocked features, the performance when using professional applications is more efficient with the FirePro M6000.

The integrated 640 Stream processors of the FirePro M6000 are based on the new GCN-architecture. 

The gaming performance is somewhere between the Radeon HD 7850M and 7870M. Therefore, the card is able to run modern games (2013) in medium or high details and HD resolution fluently.

The FirePro M6000 also supports automatic graphics switching between the integrated GPU and discrete GPU. Called Enduro, the technology supersedes AMD's Dynamic Switchable Graphics and is similar to Nvidia's Optimus. Furthermore, the card can directly support up to 6 connected monitors using Eyefinity Technology if Enduro is disabled.

Other features of the series include ZeroCore for reducing power consumption when the display is turned off and Power Gating to power down areas of the chip that are not used. PowerTune allows automatic overclocking and underclocking of the graphics card as long as the GPU is within its TDP range. For example, the chip may be underclocked when running FurMark and OCCT, but will overclock in certain games like Lost Planet, Crysis or Resident Evil 5.

The integrated HD audio processor is able to transmit HD Audio (TrueHD or DTS Master Audio) over HDMI and DisplayPort (e.g., for Blu-Ray videos). Additionally, it now allows audio to output simultaneously and in parallel to multiple devices with the new Discrete Digital Multipoint Audio (DDMA) feature.

The power consumption of the M6000 is best suited for notebooks 15 inches or greater.

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.