erek
[H]F Junkie
- Joined
- Dec 19, 2005
- Messages
- 8,842
Anyone else excited?
"Had everything gone to plan, particularly cost-effective availability of a 7 nm-class foundry node, "Battlemage" was supposed to take off in 2022. Instead, the the group crawled with a first-gen "Alchemist" launch in 2022, by which time NVIDIA and AMD had advanced their architectures (to "Ampere" and RDNA2, respectively). "Now as we go forward in our roadmap, we realized this is a very, very expensive - the QA process and the segmentation. The Thinking was we needed to differentiate our IP and customize it per each segment," said Tom Peterson, an Intel Fellow from the former AXG. "[…] We are going to just have one thing and it goes everywhere unmodified. That's more the strategy we are looking at going forward. And that's because, that's really the only way to get IP reused to really work," he added."
Source: https://www.techpowerup.com/304375/intel-talks-battlemage-xe2-lpg-and-xe2-hpg-graphics-architectures
"Had everything gone to plan, particularly cost-effective availability of a 7 nm-class foundry node, "Battlemage" was supposed to take off in 2022. Instead, the the group crawled with a first-gen "Alchemist" launch in 2022, by which time NVIDIA and AMD had advanced their architectures (to "Ampere" and RDNA2, respectively). "Now as we go forward in our roadmap, we realized this is a very, very expensive - the QA process and the segmentation. The Thinking was we needed to differentiate our IP and customize it per each segment," said Tom Peterson, an Intel Fellow from the former AXG. "[…] We are going to just have one thing and it goes everywhere unmodified. That's more the strategy we are looking at going forward. And that's because, that's really the only way to get IP reused to really work," he added."

Source: https://www.techpowerup.com/304375/intel-talks-battlemage-xe2-lpg-and-xe2-hpg-graphics-architectures