Intel's Habana Labs Driver Quietly Drops References To The Greco AI Processor

Announced last year at the Intel Vision conference was the Habana Labs Gaudi2 and Greco AI hardware. Since then we've seen a lot of Linux kernel driver work happen for enabling the Gaudi2 second-generation training and inference AI processor while there hasn't been anything real in the way for Greco, which was the successor to the Goya AI processor. Now references to Habana Labs Greco are being removed from the driver.

Habana Labs Greco was announced for second-generation inference and providing better deep learning inference efficiency over Goya. Greco was supposed to be shipping in the second half of 2022 with mass production in Q1'2023. While there has been a lot of Gaudi2 open-source driver activity by Intel (Habana Labs) over the past year, there hasn't been anything real for Greco.

A patch was sent out today removing Greco references from the upstream Habana Labs Linux kernel accelerator driver. The patch comments:

"accel/habanalabs: change Greco to Gaudi2

Greco was not upstreamed so no point of mentioning it here."

Beyond the lack of driver code for Greco, references to Greco also appear to have been removed from Habana.ai with the listed products being just Gaudi and Gaudi2 for hardware and then their SynapseAI software suite. So while I haven't seen any news articles officially proclaiming Habana Labs Greco as cancelled nor any announcements out of Intel, it would appear now that Greco is not being released given today's Linux kernel patches or that it's just being used for some niche customers/deployments.