NVLink is a wire-based communications protocol for near-range semiconductor communications developed by Nvidia that can be used for data and control code transfers in processor systems between CPUs and GPUs and solely between GPUs. NVLink specifies a point-to-point connections with data rates of 20 and 25 Gbit/s (v1.0/v2.0) per data lane per direction. Total data rates in real world systems are 160 and 300 GByte/s (v1.0/v2.0) for the total system sum of input and output data streams. NVLink products introduced to date focus on the high-performance application space.
On 5 April 2016, Nvidia announced that NVLink would be implemented in the Pascal-microarchitecture-based GP100 GPU, as used in, for example, Nvidia Tesla P100 products. With the introduction of the DGX-1 high performance computer base it was possible to have up to eight P100 modules in a single rack system connected to up to two host CPUs. The carrier board (…) allows for a dedicated board for routing the NVLink connections – each P100 requires 800 pins, 400 for PCIe + power, and another 400 for the NVLinks, adding up to nearly 1600 board traces for NVLinks alone .Each CPU has direct connection to 4 units of P100 via PCIe and each P100 has one NVLink each to the 3 other P100s in the same CPU group plus one more NVLink to one P100 in the other CPU group. Each NVLink (link interface) offers a bidirectional 20 GB/sec up 20 GB/sec down, with 4 links per GP100 GPU, for an aggregate bandwidth of 80 GB/sec up and another 80 GB/sec down. NVLink supports routing so that in the DGX-1 design for every P100 a total of 4 of the other 7 P100s are directly reachable and the remaining 3 are reachable with only one hop. According to depictions in Nvidia’s blog based publications from 2014 NVLink allows bundling of individual links for increased point to point performance so that for example a design with two P100s and all links established between the two units would allow the full NVLink bandwidth of 80 GB/s between them.
Scalable Link Interface (SLI) is a brand name for a multi-GPU technology developed by Nvidia for linking two or more video cards together to produce a single output. SLI is a parallel processing algorithm for computer graphics, meant to increase the available processing power. The initialism SLI was first used by 3dfx for Scan-Line Interleave, which was introduced to the consumer market in 1998 and used in the Voodoo2 line of video cards. After buying out 3dfx, Nvidia acquired the technology but did not use it. Nvidia later reintroduced the SLI name in 2004 and intended for it to be used in modern computer systems based on the PCI Express (PCIe) bus; however, the technology behind the name SLI has changed dramatically.
SLI allows two, three, or four graphics processing units (GPUs) to share the workload when rendering real-time 3D computer graphics. Ideally, identical GPUs are installed on the motherboard that contains enough PCI Express slots, set up in a master-slave configuration. All graphics cards are given an equal workload to render, but the final output of each card is sent to the master card via a connector called the SLI Bridge. For example, in a two graphics card setup, the master works on the top half of the scene, the slave the bottom half. Once the slave is done, it sends its render to the master to combine into one image before sending it to the monitor.
The SLI bridge is used to reduce bandwidth constraints and send data between both graphics cards directly. It is possible to run SLI without using the bridge connector on a pair of low-end to mid-range graphics cards (e.g. 7100GS or 6600GT) with Nvidia’s Forceware drivers 80.XX or later. Since these graphics cards do not use as much bandwidth, data can be relayed through just the chipsets on the motherboard. However, if there are two high-end graphics cards installed and the SLI bridge is omitted, the performance will suffer severely, as the chipset does not have enough bandwidth.
Configurations currently include:
- 2-Way, 3-Way, and 4-Way SLI. Uses two, three, or four individual graphics cards respectively.
- Two GPUs on one graphics card. Examples include the GeForce GTX 590, GeForce GTX 690 and the GeForce GTX Titan Z. This configuration has the advantage of implementing Two-Way SLI, while only occupying one PCI-Express slot and (usually) two expansion I/O slots. This also allows for Four-Way SLI using only two cards (which is referred to as Quad SLI).
Nvidia has created a set of custom video game profiles in cooperation with video game publishers that will automatically enable SLI in the mode that gives the largest performance boost.
Nvidia has 3 types of SLI bridges:
- Standard Bridge (400 MHz Pixel Clock and 1GB/s bandwidth)
- LED Bridge (540 MHz Pixel Clock)
- High-Bandwidth Bridge (650 MHz Pixel Clock and 2GB/s Bandwidth)
The Standard Bridge is traditionally included with motherboards that support SLI and is recommended for monitors up to 1920×1080 and 2560×1440@60 Hz. The LED Bridge is sold by Nvidia,EVGA, and others and is recommended for monitors up to 2560×1440@120 Hz+ and 4K. The LED Bridges can only function at the increased Pixel Clock if the GPU supports that clock. The High-Bandwidth Bridge is only sold by Nvidia and is recommended for monitors up to 5K and Surround.
AMD CrossFire (also known as CrossFireX) is a brand name for the multi-GPU technology by Advanced Micro Devices, originally developed by ATI Technologies. The technology allows up to four GPUs to be used in a single computer to improve graphics performance.
There is also a “hybrid” mode of CrossFireX that combines on-board graphics using the AMD northbridge architecture with select graphic cards, for increased performance. The current generation is called Hybrid CrossFireX and is available for motherboards with integrated AMD chipsets in the 7 and 8 series GPUs, referred to as Hybrid CrossFireX.
This combination results in power-savings when simple or 2D graphics are used and performance increases of 25% to over 200% in 3D graphics over using a non CrossFire option. As of March 2012, it appears that this is now called “AMD Radeon Dual Graphics” and means using A-series Fusion APUs together with video cards.