Recent content by Picao84

You don't say so 🤔

Interesting! I hadn't fully grasped that Nvidia sees Neural Shaders as a completely new paradigm to replace the existing Pixel, Vertex, Compute and Geometry shaders. It's quite ambitious, let's see if AMD and Intel follow through..

I surely hope not. I'm still refusing to upgrade my PSU beyond 650W. Going over 1000W just for gaming purposes is a complete waste of energy, IMO.

We must have different ideas about what considers architecture scaling because the history of GPUs is full of examples? Going from specific units for pixel and vertex shaders to the unified shader model that improved GPU utilisation by avoiding stalled units, while also bringing about the age of...

Duplicate Error.

If you really believe that than you either believe that there is no other way to scale up now but through AI, or you believe the only way to do that is by increasing power budgets massively (of which the 5090 is an example). Are we really at the Netburst age of GPUs?

You should add power consumption figures. I recall that the impressive thing between Kepler and Maxwell was not only performance but also a big jump in power efficiency. A GTX 750 Ti 4GB, which didn't need an external power connector was nearly as fast as the 650 Ti Boost (a salvaged GTX660 that...

What's the point of putting 3 8 pin connectors if one of pins is not required? If OC versions really need a 3rd pin then it either clocks like a champ or there is something really wrong with it's efficiency. I guess we'll know soon.

Either we are in for a big surprise from AMD or their power efficiency went backwards so much they discovered time travel.

In the laptop market that isn't simply not true. Not every laptop with a discrete GeForce or Radeon chip is a "gaming laptop". I know plenty of people, usually from my parents generation, that have laptops with x50 tier and sometimes even x60 tier because they like to buy "quality things" and...

Cost, assuming it's a smaller node. Heat, assuming it's the same node. This is all very reminiscent of discussions around Switch 1 Tegra X1. Many people were expecting a more customised chip or at a smaller node but it didn't happen. Tegra X1 was already old tech by the time Switch launched. Why...

What? AFAIK, it runs at 307Mhz? Where are you getting 160 from?

Why are we debating Nvidia products for the past 2 pages in an RDNA4 thread? I get that they factor in on pricing as they are competing products, but we should not be going down memory lane as it's irrelevant for the thread...

Can someone explain how they conclude a higher cost per transistor when the table above shows a drop in sale price per chip? Are they considering a fixed chip size in all nodes, not accounting for foundry clients using all the margin available for larger chips?

What you showed here is not the same as cost per transistor, which was what I was replying to. Your own original chart had the cost pretty much stagnant. Wafers are more expensive because they hold more transistors, so even if the cost per transistor would stay the same, they would still be more...