Intel’s stunningly successful Rocket Lake teaser went up yesterday with some curious claims. SemiAccurate dug into the details and a very interesting detail emerged about what Rocket Lake really is.
In yesterday’s article we went over the highlight, singular, and the lowlights, plural. One of the interesting bits we noticed was the GPU performance or lack thereof. As you can see below, Intel is claiming a 50% graphics performance lead over the now ancient 14nm Gen 9 graphics found in those two generation older devices. This compares unfavorably to the >2x GPU performance that the 10nm Tiger Lake achieves with the same GPU at a fraction of Rocket’s 125W TDP.
Rocket to nowhere
This can be explained fairly easily by the backporting process which brings out the worst of both architecture and process. While SemiAccurate can’t explain why Intel did this rather than using their tuned 14nm cores, we did point out why they were mistaken to even attempt it. While pondering the numbers and the vague wording of the above slide and a few others, something important clicked about the Xe graphics in Rocket Lake.
Note: The following is for professional and student level subscribers.
Disclosures: Charlie Demerjian and Stone Arch Networking Services, Inc. have no consulting relationships, investment relationships, or hold any investment positions with any of the companies mentioned in this report.
Charlie Demerjian
Latest posts by Charlie Demerjian (see all)
- Intel updates roadmaps at Analyst Day 2023 - Mar 29, 2023
- Intel’s Emerald Rapids has a big secret - Mar 27, 2023
- Raja Koduri and Dr. Randhir Thakur out at Intel - Mar 21, 2023
- What does Intel’s Emerald Rapids bring to the fight - Mar 21, 2023
- A new ARM code name for a new market pops up - Mar 20, 2023
