Helping Normalize NVIDIA Vera to AMD EPYC
This is a hotly requested topic, so we help cut through the framing
Over the past day or so, NVIDIA released its whitepaper on its Vera CPU. Ryan did a look at the architecture on the STH main site. About five minutes after the release, I started getting requests to help translate what was presented. To be clear, I have been covering new server CPUs for over a decade and a half, and I think NVIDIA has a really interesting part. Vera will sell many units. At the same time, NVIDIA took some fairly significant liberties in framing Vera’s performance to get headline figures, and I wanted to help our Substack audience understand what they did, why, and then give a perhaps more balanced view of what a comparison to AMD EPYC will look like.
We will post a portion of this on the STH main site later today, but I wanted to give our Substack supporters a head start and also provide a bit more on how to frame an AMD EPYC “Venice” comparison.
Where NVIDIA Vera Fits in the Data Center
One of the more interesting discussions I have had in the past 24 hours started something along the lines of “if NVIDIA wins by so much, why will it not take over every data center socket?” To be clear, NVIDIA does not even position Vera as the right CPU for that ambition.