They have been sneakily silent about it, being circumspect doesn't serve them well considering the power problems with Polaris and Vega at stock settings.
They have been sneakily silent about it, being circumspect doesn't serve them well considering the power problems with Polaris and Vega at stock settings.We still haven't seen any power draw numbers, and everybody already have said it is high. Interesting.
That is only your assumption, not a fact.
Then why they have blatantly shown in the slides situations where they blatantly lose to both Intel and Nvidia counter offerings, eh?This is a marketing event. Anything that can paint them in a positive light will be emphasized. Anything that can paint them in a negative light will be downplayed. What isn't said is as important as what is said.
This is a marketing event. Anything that can paint them in a positive light will be emphasized. Anything that can paint them in a negative light will be downplayed. What isn't said is as important as what is said.
Will always remember (and chuckle) at this:
Best to wait for HotChips in 2-2.5 months for exact specs of the Media Engine.Even GCN 1.0's UVD can do 4K encoding/decoding with H.264, VC-1, and MPEG-2. They added HEVC on 14nm, but Raven Ridge is the only AMD product so far that can do full hardware decoding of VP9.
Sounds about right.
Not too long ago, I had like . . . 4 of those things running full bore in a mining rig, right next to me. Sooooo muuuuuch nooooise.
Then later I had my VegaFE, also running full blast. It ran solo though, so it was "silent". Ha ha.
Can't wait to see someone put together a mining rig with 5700s.
@railven
Relax, I doubt Navi will mine all that well. Could be wrong. Market's depressed anyway, blah blah blah.
Anyone "serious" about mining got Radeon VII day one and started making $2/day off it. Only one year to pay off the card! Yey.
Relax, I doubt Navi will mine all that well. Could be wrong. Market's depressed anyway, blah blah blah.
This was awfull, the are launching these cards a whole 10 months behind the RTX2070 launch and the best they could is a $50 lower price? Whiout RTX that was Nvidia excuse for increasing the prices?
I think i rather buy a Vega 56 at its new $300 price tag. In fact Vega 56 should me matching RX5700 perf.
"The one exception to all of this is the primitive shader. Vega’s most infamous feature is back, and better still it’s enabled this time. The primitive shader is compiler controlled, and thanks to some hardware changes to make it more useful, it now makes sense for AMD to turn it on for gaming. Vega’s primitive shader, though fully hardware functional, was difficult to get a real-world performance boost from, and as a result AMD never exposed it on Vega."
It's
It's 10 months after the 2070 released and it's still $500. If $450 is awful, what does that say about $500?
These are some fundamental changes. Watch as people still spout nonsense like that it's not a "new" uArch..."Starting with the architecture itself, one of the biggest changes for RDNA is the width of a wavefront, the fundamental group of work. GCN in all of its iterations was 64 threads wide, meaning 64 threads were bundled together into a single wavefront for execution. RDNA drops this to a native 32 threads wide. At the same time, AMD has expanded the width of their SIMDs from 16 slots to 32 (aka SIMD32), meaning the size of a wavefront now matches the SIMD size. This is one of AMD’s key architectural efficiency changes, as it helps them keep their SIMD slots occupied more often. It also means that a wavefront can be passed through the SIMDs in a single cycle, instead of over 4 cycles on GCN parts. "
https://www.anandtech.com/show/14528/amd-announces-radeon-rx-5700-xt-rx-5700-series/2
I like what I am reading.
It's
It's 10 months after the 2070 released and it's still $500. If $450 is awful, what does that say about $500?
Most people said it was also awful. It's like no one remembers why the $500 price points are catching so much hate.
It is pretty much the same as Turing from Architecture point of view.These are some fundamental changes. Watch as people still spout nonsense like that it's not a "new" uArch...
Anandtech's article confirms the leaked slides: 225W "typical board power" for the RX 5700 XT, and 180W for the RX 5700.
Absolutely shameful - if the architectural efficiency was on par with Nvidia, then taking into account the node shrink, the 5700 XT should be no more than 180W and the 5700 no more than 150W. That it isn't demonstrates either that their binning process still sucks, or that the same old ugly GCN design is still lurking in there no matter how much they've tried to polish the turd.