Intel Xe


Intel Xe is general purpose GPU and discrete GPU product line under development by Intel, reportedly codenamed Arctic Sound.
Intel Xe includes a new instruction set architecture – the technology is expected to become available with Intel's Tiger Lake products.

History

Intel Xe is not Intel's first attempt at a dedicated graphics card, that being the Intel740, released in February 1998. Released to a hyped audience the Intel740 was a dissapointment and failure, being discontinued just 18 months after release but its technology lived on the Intel Extreme Graphics lineup. Intel made another attempt with the Larrabee before cancelling it in 2009, this time the technology developed was used in the Xeon Phi which was discontinued in 2020.
In April 2018, it was reported that Intel was assembling a team to develop discrete graphics processing units, targeting both datacenters, as well as the PC gaming market, and therefore competitive with products from both Nvidia and AMD. Rumors supporting the claim included that the company had vacancies for over 100 graphics-related jobs, and had taken on former Radeon Technologies Group leader Raja Koduri in late 2017 – the new product was reported to be codenamed "Arctic Sound". The project was reported to have initially been targeting video streaming chips for data centers, but had its scope expanded to include desktop GPUs.
In June 2018, Intel confirmed it planned to launch a discrete GPU in 2020.
In September 2019, hothardware.com reported that the Xe graphics would represent a large change in the instruction set architecture of Intel's GPUs, with practically all instruction encodings being altered. The Xe graphics ISA is expected to ship with the Tiger Lake product line.
The first functional discrete "Xe" GPU, codenamed "DG1", was reported as having begun testing in October 2019.
According to a report by hexus.net in late 2019, a discrete GPU would launch in mid 2020; combined GPU/CPU products were also expected, for data center and autonomous driving applications. The product is expected to be initially built on a 10 nm node and use Intel's Foveros die stacking packaging technology.
Intel officially announced their Xe general HPC/AI GPU codenamed Ponte Vecchio on November 17, 2019. The chip is to use Intel's 'Embedded Multi-Die Interconnect Bridge' and Foveros die stacking packaging on a 7 nm node. The new GPU is expected to be used in Argonne National Laboratory's new exascale supercomputer, Aurora, with compute nodes comprising two Intel Xeon CPUs, and six Ponte Vecchio GPUs.