NVIDIA Quadro K2100M vs Intel Iris Pro Graphics P580 vs Intel UHD Graphics 600

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.

Intel Iris Pro Graphics P580

The Intel Iris Pro Graphics P580 (GT4e) is an integrated professional graphics unit of the Skylake generation (top version). As successors of the Iris Graphics 6200 (Broadwell), the Iris P580 can be found in some high-end Xeon quad core CPUs and offers 128 MB of dedicated eDRAM memory. Furthermore, the so-called GT4e-version features 72 Execution Units (EUs). Besides the eDRAM cache, the Iris 580 is able to access the main memory (2x 64bit DDR3L-1600 / DDR4-2133).

Compared to the consumer Iris Pro Graphics 580, the P580 is only included in the Xeon processors and intended for professional applications (certified drivers?) similar to the Quadro and Fire Pro lines. 

Compared to the Iris Graphics 550 (28 W GT3e), the Iris Pro Graphics P580 offers more EUs (72 vs. 48) and a larger eDRAM Cache (128 vs. 64 MB).

Performance

The exact performance of the Iris Graphics P580 depends on memory configuration and CPU model (different clock speeds). However, it should be clearly faster than the old Broadwell Iris Pro 6200 and may compete with a dedicated GeForce 945M. Modern games of 2015/2016 should be playable in medium settings.

Features

The revised video engine now decodes H.265/HEVC completely in hardware and thereby much more efficiently than before. Displays can be connected via DP 1.2 / eDP 1.3 (max. 3840 x 2160 @ 60 Hz), whereas HDMI is limited to the older version 1.4 (max. 3840 x 2160 @ 30 Hz). However, HDMI 2.0 can be added using a DisplayPort converter. Up to three displays can be controlled simultaneously.

Power Consumption

The Iris Graphics P580 can be found in some mobile high-end quad core processors (45 W). Therefore, they are most likely not used in thin and light laptops.

Intel UHD Graphics 600

The Intel UHD Graphics 600 is an integrated processor graphics unit from the Gemini Lake generation (e. g. Pentium N4100), which was announced late 2017. The GPU can convince with low consumption figures, but the performance is only in the low-end segment and is rarely sufficient for modern games. Being the lowest configuration of the Gemini Lake GPU, the UHD Graphics 600 is equipped with 12 of the 18 Execution Units (EUs) running at up to 700 MHz. The technical specifications of the GPU are based on Intel's Gen9 architecture, which is also used for the more expensive Skylake series and also in the predecessor HD Graphics 505.

Due to its lack of dedicated graphics memory or eDRAM cache, the UHD 605 has to access the main memory via processor (2x 64bit DDR4/LPDDR4-2400).

Performance

The UHD Graphics 600 offers a similar performance as the Intel HD Graphics 500 in the Apollo Lake SoCs (same Gen 9 architecture). Therefore, the GPU is only suited for some very low demanding games like Dirt Rally or Sims 4.

Features

The video engine decodes H.265/HEVC (8b and 10b) and VP9 completely in hardware. Up to three displays can be connected via DP 1.2a/eDP 1.3 or HDMI 2.0a (including HDCP 2.2).

Power Consumption

The TDP of the whole Pentium N4100 chip is 6 Watts by default, so the GPU is primarily used for (often passively cooled) netbooks or thin notebooks. The TDP can also be reduced to 4.8 Watts, but this will obviously affect the performance.