Wednesday, February 17th 2016

AMD Ryzen 1700X, 1600X & 1300 Benchmarks Leaked

A number of sites have been reporting on some leaked (as in, captured from Futuremark's database) scores on AMD's upcoming CPUs. Now, some benchmarks seem to have surfaced regarding not only the company's 8-core, 16-thread monsters, but also towards its sweet-spot 6-core, 12-thread CPUs and its more mundane 4-core offerings.

Taking into account some metrics (which you should, naturally, take with some grains of salt), and comparing Intel's and AMD's Ryzen offerings on 3DMark's Fire Strike Physics scores, we can see that a $389 Ryzen 7 1700X (8 cores, 16 threads) at its base clock of 3.4 GHz manages to surpass Intel's competing (in thread count alone, since it retails for $1089) 6900K running at its base 3.2 GHz frequency - with the Ryzen processor scoring 17,878 points versus the 6900K's 17,100. Doing some fast and hard maths, this would mean that if the R7 1700X was to be clocked at the same speed as the 6900K, it would still be faster, clock for clock (though not by much, admittedly). We don't know whether Turbo was disabled or not on these tests, for either AMD's or Intel's processor, so we have to consider that. However, if Turbo were enabled, that would mean that the R7 1700X's clockspeed would only be 100 MHz higher than the 6900K's (3.8 GHz max, vs 3.7 GHz max on the Intel CPU).
We see the same when comparing AMD's six-core, $259 R5 1600X against Intel's $617 6850K, with the Ryzen sample posting virtually the same score, despite running at a 300 MHz lower base clock (3.3 Ghz against Intel's 3.6 Ghz).
Jumping to a per-core analysis of processor speed in the same test suite, though, also reveals some very interesting metrics. here is a test which clearly doesn't scale all that well with extra cores, actually becoming more inefficient, per core, as the number of those increases. However, we can clearly see how much of an improvement AMD has achieved in per-core performance, with the R7 1700X scoring within spiting distance of its much more expensive i7 6900K competition.

Can we just get some real reviews of these pieces of silicon already? Sources: Videocardz, WCCFTech
Add your own comment

99 Comments on AMD Ryzen 1700X, 1600X & 1300 Benchmarks Leaked

#1
mouacyk
"Doing some fast and hard maths, this would mean that if the R7 1700X was to be clocked at the same speed as the 6900K, it would still be faster, clock for clock (though not by much, admittedly)."

What kind of math exactly?

1700X @ 3.2GHz = 17878 / 3.4 * 3.2 = 16826 (How is this faster than 6900K at 17100?)
6900K @ 3.4GHz = 17100 / 3.2 * 3.4 = 18168

Must be Friday math.
Posted on Reply
#2
NdMk2o1o
These can no longer be called leaks but tsunami's!!! may aswell just rename the site TECHPOWERyzenUP.COM lol just give us some real benches AMD!!!!!
Posted on Reply
#3
bug
Strangely enough, I don't care about all those cores. But I would love to be able to get a dirt cheap 4-core CPU, because that's all I need at home.
I can hardly believe that after all these years AMD may finally have something I can actually consider buying, after so many let downs. Ok, I considered a 480 last year, but decided to pass till they get their Linux support straightened up.
Posted on Reply
#4
Brusfantomet
in your second pic, the "score per core" does not seam ti increase with the clock speed, is that just the alcohol and loud music afflicting my brain or does that look weird?
Posted on Reply
#5
MrGenius
Brusfantomet said:
in your second pic, the "score per core" does not seam ti increase with the clock speed, is that just the alcohol and loud music afflicting my brain or does that look weird?
Let me quote myself from a previous thread.
MrGenius said:
There's results from 3 different CPUs being shown there... With the results from ONLY ONE of them being shown at 2 different frequencies. So that's the ONLY ONE you can judge for any performance gained by clocking it higher. And it clearly shows that it, in fact, does gain performance at a higher frequency.

AMD Ryzen: ZD3406BAM88F4_38/34_Y @ 3.4 GHz = 2235
AMD Ryzen: ZD3406BAM88F4_38/34_Y @ 4.0 GHz = 2531

Which makes perfect sense actually. ;)

....
  • AMD Ryzen: ZD3406BAM88F4_38/34_Y — Eight-Core CPU
  • AMD Ryzen: ZD3301BBM6IF4_37/33_Y — Six-Core CPU
  • AMD Ryzen: ZD3201BBM4KF4_34/32_Y — Quad-Core CPU
https://videocardz.com/65913/how-fast-is-ryzen
Posted on Reply
#6
kruk
bug said:
Ok, I considered a 480 last year, but decided to pass till they get their Linux support straightened up.
I have been using the opensource driver for years, first radeonsi on my SI card, now amdgpu on Polaris (since approx september). It works great and it's fast enough, however, I won't deny there might be problems with AAA games ...
Posted on Reply
#7
JalleR
so far the price is the most exciting thing.
Posted on Reply
#8
cdawall
where the hell are my stars
Raevenlord said:
Jumping to a per-core analysis of processor speed in the same test suite, though, also reveals some very interesting metrics. here is a test which clearly doesn't scale all that well with extra cores, actually becoming more inefficient, per core, as the number of those increases. However, we can clearly see how much of an improvement AMD has achieved in per-core performance, with the R7 1700X scoring within spiting distance of its much more expensive i7 6900K competition.
It scales perfectly if you assume the clockspeed is wrong. Every other CPU scales perfectly yet the 4 AMD chips do not. It is a pretty easy assumption to make that they are all clocked at the same speed. Don't feed the hype especially not based off of a WCCF article with data pulled by a russian GPU page...
Posted on Reply
#9
buggalugs
Hey Raevenlord, can I give you some advice bro? I know you're new, and you're doing a good job, but you need to improve your sentence structure.

It's something I've noticed in many of your news posts. You have too many run-on sentences.

This is a good example of what I mean:

"Taking into account some metrics (which you should, naturally, take with some grains of salt), and comparing Intel's and AMD's Ryzen offerings on 3DMark's Fire Strike Physics scores, we can see that a $389 Ryzen 7 1700X (8 cores, 16 threads) at its base clock of 3.4 GHz manages to surpass Intel's competing (in thread count alone, since it retails for $1089) 6900K running at its base 3.2 GHz frequency - with the Ryzen processor scoring 17,878 points versus the 6900K's 17,100. "

That's one sentence, its way too long. It reads very clumsily and it sounds awkward. It's a whole paragraph in one sentence. You need more full stops, and less run-on sentences.

Also, less information in brackets in the one sentence. No more than one or two brackets in the same sentence, three is too much. Unless it's just basic information like CPU clockspeeds (3.4Ghz) or something, but if the brackets contain whole sentences, try to keep them to a minimum in the one sentence.

I hope you dont take this personally, it's meant to be constructive criticizm.
Posted on Reply
#10
doel
damn, just damn!
i just move-on from amd to skylake a couple month ago, , , ,
Posted on Reply
#11
Da Rooster
mouacyk said:
"Doing some fast and hard maths, this would mean that if the R7 1700X was to be clocked at the same speed as the 6900K, it would still be faster, clock for clock (though not by much, admittedly)."

What kind of math exactly?

1700X @ 3.2GHz = 17878 / 3.4 * 3.2 = 16826 (How is this faster than 6900K at 17100?)
6900K @ 3.4GHz = 17100 / 3.2 * 3.4 = 18168

Must be Friday math.
let get to the math! 6900k $1049 1700x $389 there the math that matters!
Posted on Reply
#12
TheLaughingMan
cdawall said:
It scales perfectly if you assume the clockspeed is wrong. Every other CPU scales perfectly yet the 4 AMD chips do not. It is a pretty easy assumption to make that they are all clocked at the same speed. Don't feed the hype especially not based off of a WCCF article with data pulled by a russian GPU page...
Yeah. What he said. I believe nothing until someone can say, "NDA over. I tested Ryzen with high-end mobo, quality RAM, and compared it to B with the following the same and I got these metrics."
Posted on Reply
#13
Jism
JalleR said:
so far the price is the most exciting thing.
AMD needs to gain market back again. And todo this is to offer performance that's equal if not equivalent towards intel's current offerings. It will proberly be the Zen+ that starts to hit at a higher price with even more performance.

If these leaks are genuine, then it means that the 1700X will be of best value. I cant wait to upgrade my system towards a AMD platform. I just love them being back in the game, taking a huge dump on Goliath with a much smaller budget & R&D.
Posted on Reply
#14
Beastie
Performance/price is what counts and it looks like AMD is doing spectacularly well on that front if these leaks are anywhere near accurate.

If so it is a win for everyone.
IMO even for Intel, they needed a kick up the posterior.
Posted on Reply
#15
Brusfantomet
MrGenius said:
Let me quote myself from a previous thread.
Hmm.
If the 3.4 GHz = 2235 is true then a linear scaling should give:
2256 /3,4*4= 2654
Now it could be throttling and the 3.4 ghz chip is boosting but still, callously optimistic.
IF the leaks are true and zen is a power users wet dream and oc better than a nealhelm I will get one, have had enough problems with x99.

The leaks looks nice, and if they hold AMD will kick some intel ass, amd as MrGenius points out, a AMD chip at $400 that beats a $1000 intel chip does makes the CPU market interesting
Posted on Reply
#16
puma99dk|
mby it's time to try smth new with AMD Ryzen from all this looks like.
Posted on Reply
#17
YautjaLord
I'll dig more thoroughly into this thing in about 8 to 10 hours from now, (you don't exactly do math after an evening of melodic death metal & few litres of beverage, now do you? lol) but these pics/graphs draw some impressive picture for me. If these (1700X, 1600X & 1300) run at their base clocks, i can hardly imagine what will happen when Precision Boost kicks in. The real (call it slightly sober, lol) question for me is - what AM4 mobo was used.
Posted on Reply
#18
Jism
There is no more logical difference in AM4 motherboards, since the chipset is moved into the CPU. The difference would be a better VRM and all that stuff, but it's not like buying a Crosshair series would guarantee you a cherry picked chipset for example.
Posted on Reply
#19
horsemama1956
mouacyk said:
"Doing some fast and hard maths, this would mean that if the R7 1700X was to be clocked at the same speed as the 6900K, it would still be faster, clock for clock (though not by much, admittedly)."

What kind of math exactly?

1700X @ 3.2GHz = 17878 / 3.4 * 3.2 = 16826 (How is this faster than 6900K at 17100?)
6900K @ 3.4GHz = 17100 / 3.2 * 3.4 = 18168

Must be Friday math.
Is this a joke?
Posted on Reply
#20
Nuckles56
Another day and yet another leak, I just want them to be released so the speculation can end
Posted on Reply
#21
ensabrenoir
.....leaks....yeah right. People really do under estimate Amd's marketing. Careful on all the hype though. While i wish it well....don't wanna see Zen identical to Haswell on launch day..... My pipe dream is intel cpu with Amd graphics core...from that other thread :)
Posted on Reply
#23
Naito
horsemama1956 said:
Is this a joke?
Must be! :laugh:


1700X @ 3.2GHz = (17878 / 3200) * 3400 = 18995
6900K @ 3.4GHz = 17100

OR

1700X @ 3.2GHz = 17878
6900K @ 3.4GHz = (17100 / 3400) * 3200 = 16094

This is what I think @mouacyk was trying to show - a rough estimation of score if we assume both processors share the same frequency. Obviously other factors come into play, in reality.
Posted on Reply
#24
HD64G
I just wish those numbers are for stock Ryzen CPUs. If so, the party for the PC HW enthusiasts will be on for long after their sale starts.
Posted on Reply
#25
Vego
should i be worry that my 6950X clock onlu 4,3 and my 5960X clocks only 4,7?
thats alot of money wasted :(
Posted on Reply
Add your own comment