AMD 7nm Vega 20 AI GPU Leaked in Linux Patch

AMD’s next generation Vega 20 GPU, designed for AI and machine learning, has just popped up in a Linux patch a couple of days ago. The Sunnyvale California based chip maker announced earlier this year at CES that it’s building a new Vega chip on cutting edge 7nm process technology to be deployed in deep neural networks for AI and machine learning applications by the end of the year.
AMD announced that it will begin sampling 7nm Vega in Q4 2018.

AMD’s 7nm Vega 20 Pops up in Linux Patch

A peculiar set of code has been spotted in a recent Linux patch that makes reference to Vega 20 by name. The new patch appears to introduce support for more than 50 new Vega specific hardware-level features that were previously absent from the Linux kernel or had only been partially implemented. This indicates that AMD could be approaching final post-silicon testing and validation of Vega 20.

"+ /* Vega 20 */
+ {0x1002, 0x66A0, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA20},
+ {0x1002, 0x66A1, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA20},
+ {0x1002, 0x66A2, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA20},
+ {0x1002, 0x66A3, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA20},
+ {0x1002, 0x66A7, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA20},
+ {0x1002, 0x66AF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA20},"

We brought you news of Vega 20 in as early as January of 2017. So we have known about AMD’s plans to introduce a high performance Vega chip based on the 7nm process for quite a while. Confirmation of such a project ,however, did not come until exactly a year later at this year’s CES.

Although the company has not referred to its new 7nm Vega chip as Vega 20, previously leaked internal slides clearly described a 7nm based “Vega 20” GPU that’s specifically designed for AI and intended for market entry in 2018.

This means that it can be equipped with up to 32GB of HBM2 vRAM, and have access to a whopping 1TB/s of bandwidth. Paired with the significant improved in double precision compute, Vega 20 will make for an exceedingly powerful compute engine.