DegustatoR
Legend
Those who measure a GPU performance by its VRAM size deserve to be confused.
50% more VRAM in a lower end 3060 definitely won't be confusing for consumers.
That mobile 3080 will likely be slower than desktop 3060Ti.The mobile 3080 is also 16GB. Cue griping from early adopters in 3,2....
Those who measure a GPU performance by its VRAM size deserve to be confused.
3060 30% faster than ps5 gpu? my ass ;d it will be very similar performance in standard raster but in rt geforce will be faster for sure
That mobile 3080 will likely be slower than desktop 3060Ti.
3060ti is around 30% faster than 5700xt and 3060 will not have same performance as 3060tiDont think their lying. Its the least i'd expect from a 3060 in rasterization performance.
3060ti is around 30% faster than 5700xt and 3060 will not have same performance as 3060ti
3060Ti is a 200W part and runs at 1665MHz boost.TDP limited? It's a full GA104 with reasonably high boost clocks so I would be surprised if it's slower than the 3060 Ti.
3060Ti is a 200W part and runs at 1665MHz boost.
A notebook part on the same chip will probably need to be 100W at max which means that it will have to clock significantly less, probably down to 1000MHz less.
Even a fully enabled GA104 at 1GHz would be slower than 3060Ti. It should be close to the just announced 3060 in fact.
Exactly.3060 30% faster than ps5 gpu? my ass
RDNA2 has a significantly higher performance-per-TFLOP than Ampere on rasterization
This is about the same level of bullshit Jen Hsu Huang pulled when he claimed a laptop with a RTX2080 Max-Q (which performs similar to a desktop GTX1070) would be faster than the PS5 and the Xbox Series X.
Nvidia does show a tendency to spew this kind of outrageous claims whenever they're hard to debunk, which is the case of PC vs. console comparisons.
And Ampere has a significantly higher performance-per-rasterized pixels, performance-per-texture filtering, performance-per-triangle setup, etc on rasterization, considering the 172 Gigapixels/s RTX 3080 beats 294 Gigapixels/s 6800XT.RDNA2 has a significantly higher performance-per-TFLOP than Ampere on rasterization, considering the 30 TFLOPs RTX3080 competes with the 20TFLOPs 6800XT.
And Ampere has a significantly higher performance-per-rasterized pixels, performance-per-texture filtering, performance-per-triangle setup, etc on rasterization, considering the 172 Gigapixels/s RTX 3080 beats 294 Gigapixels/s 6800XT.
Total performance in rasterization is a weighted sum of all those metrics. Obviously, TFLOPs is still the most important metric, which is likely equal to the sum of all the rest metrics and it's even more important in compute heavy workloads, such as Ray-tracing, so I wouldn't be surprised if 3060 can beat PS5 by 30% in RT heavy games and I wouldn't be surprised if it's slower in pure rasterization (depends rather on GPC count than TFLOPs).
And Ampere has a significantly higher performance-per-rasterized pixels, performance-per-texture filtering, performance-per-triangle setup, etc on rasterization, considering the 172 Gigapixels/s RTX 3080 beats 294 Gigapixels/s 6800XT.
Total performance in rasterization is a weighted sum of all those metrics. Obviously, TFLOPs is still the most important metric, which is likely equal to the sum of all the rest metrics and it's even more important in compute heavy workloads, such as Ray-tracing, so I wouldn't be surprised if 3060 can beat PS5 by 30% in RT heavy games and I wouldn't be surprised if it's slower in pure rasterization (depends rather on GPC count than TFLOPs).
December Steam hardware survey shows 3080 at 0.48%, which is a very fast 2-month ramp. Wish I had historical data to compare vs. prior $700 GPU launches, but comparing that number with other current numbers, e.g., 1650Ti (a 2019 GPU with both desktop and mobile parts) at 0.57% and 5700XT at 0.89% tells me that there are a large number of 3080s in the hands of gamers. Maybe they were all bought from scalpers, I don't know, but the numbers are high. There's no question that both Nvidia and AMD have supply problems, and demand is so high that to end users hitting F5 it seems like the cards don't exist. Sucks to be us, sucks to be them.Here's hoping this time period will be enough to produce a volume of cards that isn't only enough for reviewers and bot-wielding scalpers.
Yes you love Ampere and the 3060 and how much it would hypothetically beat the PS5 in a hypothetical RT-heavy scenario that will never happen because games made for the PS5 won't run RT-heavy scenarios that only run decently on RTX30 hardware.
The slide in question makes no reference to raytracing whatsoever and it even refers to the 3060 Mobile with lower clocks and TDP.
Though since some have now been fully indoctrinated into thinking RT performance is the only metric that matters and it's in every game in existence, I guess it's normal for those to assume RT performance is in all circumstances forever.
Discrete sub-$100 GPUs? I don’t know if that’s a market any more.I wonder how far downmarket this generation will go. The $100 segment can definitely benefit from HDMI 2.1. I want a cheap 2.1 card to stream at 120fps.