AMD presented with Ryzen 7000, but disappointed with Radeon RX 7000. And what does Nvidia do tomorrow at 5 a.m., which is uncomfortable for Europeans? Is there really a first hint of Lovelace aka RTX 4000?
The Computex 2022 got off to a convincing start – at least from a CPU point of view. While little can be expected from Intel at the IT trade fair in Taiwan, after all there was only a few days ago at the Intel in-house trade fair Vision, AMD has already shown what can be expected from Ryzen 7000 and socket AM5 in autumn. However, one topic has not yet been addressed.
Nvidia live stream at Computex
Actually, one could expect AMD to at least tease its GPU line-up for the fall. But there was no beep for RDNA 3 or Radeon RX 7000 during the Computex keynote. This is of course relatively disappointing and hopefully not a bad omen for the graphics card year 2022, because after all PCI Express 5 was one of the main topics at AMD – but the focus so far has been on corresponding PCI Express 5 SSDs and not on graphics cards. Since little can be expected from Intel and Arc, after all, one would like to start the desktop launch in China first, only Nvidia actually remains.
At 5 a.m. our time, i.e. Tuesday morning, the Computex keynote, which should last one hour, begins. CEO Jensen Huang will not be holding his legendary leather jacket in the live stream, but there are six speakers from different disciplines such as AI, accelerated computing and embedded. Hints of technologies for gamers make you sit up and take notice, and with Jeff Fisher (Senior Vice President Geforce), Brian Kelleher (Senior Vice President for Hardware Engineering) and Michael Kagan (Chief Technology Officer), there is quite an interesting staff at the start.
| AD102 | Navi 31 | |
|---|---|---|
| nodes | TSMC N4P | TSMC N5 & N6 |
| architecture | Ada (Lovelace) | AMD RDNA3 |
| GPU package | monolithic | Multi-Chip Modules (MCM) |
| GPU size | ~ 600mm² | ~ 800mm² |
| This | 1 | 2 GCD + 4 MCD + 1 IOD |
| GPU mega clusters | 12 graphics processing clusters (GPC) | 2×3 shader engines |
| GPU super clusters | 72 Texture Processing Clusters (TPC) | 2×30 RDNA Workgroups (WGP) |
| GPU clusters | 144 streaming multiprocessors (SM) | 120 Compute Units (CU) |
| FP32 cores | 18,432 CUDAs | 15,360 stream processors |
| GPU clock | ~ 2.7GHz | ~ 3.0GHz |
| FP32 performance | ~ 100 TFLOPs | ~ 92 TFLOPs |
| memory size | 24 GiB | ? |
| memory speed | 21Gb/s | ~ 18Gbps |
| storage type | GDDR6X | GDDR6 |
| memory bus | 21 Gb/s, 384 bits | ~18Gbps, 256bits |
| caches | 96MiB (L2 cache) | 256/512MiB Infinity Cache |
| power consumption | 600 watts | ? |
| performance | ~ Q3/2022 | ~ Q3/2022 |
| sales launch | ~Q4/2022 | ~Q4/2022 |
But we won’t find out until 5 a.m. whether there will really be a Geforce teaser. The rumor mill recently gave enough hope that Nvidia can’t put off a corresponding announcement for too long. Leakers like Kopite7kimi recently even brought the early third quarter into play, which would mean July for very big optimists – at least for the presentation. Entire books could be written about the latest rumors about power limits, FP32 performance and PCI-Express 5. It would be nice if Tuesday morning started out with some of the rumors either dissipating or becoming facts. In any case, we are very excited about the live stream from Nvidia.
What are your expectations for the Nvidia live stream tomorrow? Use the comment function and let us know what you think. You must be logged in to PCGH.de or the Extreme forum to comment. If you don’t have an account yet, you can consider registeringwhich brings many advantages.
The post Nvidia: Computex live stream tomorrow at a nasty time appeared first on Gamingsym.