No, since we know that 3.4Ghz already makes it cut dangerously close to the 95W power consumption in a light load.Have you guys considered the possibility of 8C/16T clocking to 4.3 GHz as rumored on all cores and staying within 95W TDP target?
Meh, let's just hang The Stilt, why wait for frequency/power correlation? Never mind that in the New Horizon press event the power consumption info hinted towards Zen having lower static power and a tad higher dynamic power than BDW, the people want 4.5Ghz+ overclocks!Shall we wait for the information about the clocks Ryzen is going to ship at, and the information about how much the power consumption increases when you push it beyond the stock speeds?
If above 4.0GHz is commonly achievable as 24/7 on all cores, at let's say over twice the original power consumpion I find the absolute overclock rather irrelevant regardless. Or do you disagree?
Also I haven't found any clock estimations you have made, 9kk prior to the launch of the product? Let alone one which would have potential being more accurate than mine? Hindsight etc
I have two rows of data for you:Have you guys considered the possibility of 8C/16T clocking to 4.3 GHz as rumored on all cores and staying within 95W TDP target?
Have you guys considered the possibility of 8C/16T clocking to 4.3 GHz as rumored on all cores and staying within 95W TDP target?
you know....there's an actual word for that.
Have you guys considered the possibility of 8C/16T clocking to 4.3 GHz as rumored on all cores and staying within 95W TDP target?
Shall we wait for the information about the clocks Ryzen is going to ship at, and the information about how much the power consumption increases when you push it beyond the stock speeds?
If above 4.0GHz is commonly achievable as 24/7 on all cores, at let's say over twice the original power consumpion I find the absolute overclock rather irrelevant regardless. Or do you disagree?
Also I haven't found any clock estimations you have made, 9kk prior to the launch of the product? Let alone one which would have potential being more accurate than mine? Hindsight etc
M Zen having lower static power and a tad higher dynamic power than BDW
No, since we know that 3.4Ghz already makes it cut dangerously close to the 95W power consumption in a light load.
When we guess some will get close some will be far away. Meh thats the nature of it. Its not interesting. But we should be ready to take a bit flak otherwise the betting is not so fun. Your flag was captured. We dont need final freq to know its not gona get 2.8 3.2. The interesting part was imo the high freq came with what we asume is more or less hsw bwe level ipc sans avx2. Its seems you were off here too. Thats two flags at the same time. But man what about smt perf vs HT? I kind of remember that to. Woops. Perhaps its even 3 flags at the same time.Shall we wait for the information about the clocks Ryzen is going to ship at, and the information about how much the power consumption increases when you push it beyond the stock speeds?
If above 4.0GHz is commonly achievable as 24/7 on all cores, at let's say over twice the original power consumpion I find the absolute overclock rather irrelevant regardless. Or do you disagree?
Also I haven't found any clock estimations you have made, 9kk prior to the launch of the product? Let alone one which would have potential being more accurate than mine? Hindsight etc
Man that is radical ! - if i understand you correctly?I will not be that radical, as you guys are.
If you want my opinion, Highest end Ryzen CPU will top at 4.0 GHz base clock, and 4.2 GHz all core turbo and 95W TDP.
The interesting part was imo the high freq came with what we asume is more or less hsw bwe level ipc sans avx2. Its seems you were off here too. Thats two flags at the same time. But man what about smt perf vs HT? I kind of remember that to. Woops. Perhaps its even 3 flags at the same time.
No need to defend when all flags is captured. I ran weeks ago. Just move to next sector before retreat fails.
How BDE behaves has nothing to do with what will happen with Ryzen. You are looking in the wrong places for clues.Man that is radical ! - if i understand you correctly?
Look at bwe 8c and see what base it runs at. And thats for a 140tdp. Even if gpu is included whever zen will not get like 20% higher base freq at 95w tdp.
How should it run so high within 95w tdp?
You refer to my IPC estimation, which was made based on the inaccurate figure released from AMD?
My estimation regarding that subject never was and never will be inaccurate (for obvious reasons), just the 40% figure from AMD was.
Regarding the average SMT yield, I have nothing to be shamed of
Flags...
You gotta be kidding me
If zen is 4 base at 95w tdp how much more efficient than bwe do you think it is then for eg a blender or handbrake load?How BDE behaves has nothing to do with what will happen with Ryzen. You are looking in the wrong places for clues.
Yep. But the 2.8 3.2 assesment was made while using the sb ib ipc.
Secondly the assumption that 40% was sb ib level was questionable also.
You are presenting it like it was amd numbers. No it wasnt. It was yours and some others asumption.
It was debated also back then.
You were wrong here too. Its that simple.
Yep. But the 2.8 3.2 assesment was made while using the sb ib ipc.
Secondly the assumption that 40% was sb ib level was questionable also.
You are presenting it like it was amd numbers. No it wasnt. It was yours and some others asumption.
It was debated also back then.
You were wrong here too. Its that simple.
On the other hand, Zen is said to be built on a low power node, 14FF LPE... why on earth would we all even think that Zen could clock over 4GHz on this node, with no reference point because of it being a clean sheet design? Somehow it does. Maybe there's another 14FF version of Glofo/Samsung's process that fits a high clocking CPU uarch better?
GLOBALFOUNDRIES’ advanced 14nm FinFET technology (14LPP), supports a wide range of products from mobile devices to servers, such as AMD and IBM’s server chip products. Enabled chip x86 processor performance by 3GHz+, the GLOBALFOUNDRIES’ 14nm FinFET technology taps the benefits of three-dimensional, fully-depleted FinFET transistors, and offers impressive gains over 28nm bulk CMOS with up to 50 percent increase in performance and a 65 percent reduction in total power.
So does the IPC dictate the Fmax of the design?
I based my estimation mostly on the known characteristics of the manufacturing process and some of the design parameters (which had been the biggest limitation in the past) such as the L2 cache latency. You may use search if you wish to
Can you provide contradicting data that 40% increase of the IPC of Excavator doesn't result in IPC closely / exactly matching Sandy / Ivy Bridge level?
AMD has directly stated "40% IPC improvement over Excavator" in various official presentations. That isn't a fact, but just an invention of my own?
I am not a native english, but this word was accepted on a scientific paper that i submitted some year ago, so i thought that was ok... Anyway now i tried with google translate from italian and it used this word...
As for the 40% uplift that was for a fact sb ib level where do you want me to look - r11.5, r15 or povray?
It is not same meaning.Something being inhomogeneous doesn't mean it's heterogeneous;as always context.really? publishing in science and heterogeneous didn't first come to mind?
Google translate would probably do a direct translation of the negative, anyway.
Anyway, OT, I know--it was just funny seeing that use. English is weird that way. It technically wouldn't be improper to create a word like inhomogeneous, but hetero/homogeneity are such prolific scientific terms that it just seems odd to resort to that.