Official AMD Ryzen Benchmarks, Reviews, Prices, and Discussion

[sushukka]

Skylake-X is manufactured on the same high frequency 14nm + process as Kabylake. I'd be surprised if top bins didn't hit 4.6 GHz fairly easily.
Coffeelake will have a six core max (not 8).

Intel's HEDT family so far (Gulftown, Sandy Bridge-E, Ivy Bridge-E, Haswell-E, Broadwell-E)(from 32nm to 14nm):
3.33/3,60 GHz 3.30/3.90 GHz 3.60/4.00 GHz 3.00/3.50 GHz 3.00/3.50 GHz
If they can hit 4.6GHz, it will be quite a nice leap.

 

[LTC8K6]

Intel's HEDT family so far (Gulftown, Sandy Bridge-E, Ivy Bridge-E, Haswell-E, Broadwell-E)(from 32nm to 14nm):
3.33/3,60 GHz 3.30/3.90 GHz 3.60/4.00 GHz 3.00/3.50 GHz 3.00/3.50 GHz
If they can hit 4.6GHz, it will be quite a nice leap.

Well, BW-E chips overclocked to 4.5 if you got a good one.

I would think SL-X will do better than that.

 

[sushukka]

Well, BW-E chips overclocked to 4.5 if you got a good one.

I would think SL-X will do better than that.

Darn, I always forget this overclocking aspect. However, majority of professional HEDT users won't waste time to do any handmade overclocking but uses the included stock and turbo speeds. From that perspective Intel's and AMD's clock speeds are not much apart each other. Tbh, it's the same nearly everywhere except the loud enthusiast community as we here.

 

[imported_jjj]

Your previous post said it is not good when you thought they took a single frame, and you are saying that if they take the minimum FPS based on 300 ms to 1000ms, it's wrong. If both ways are wrong, what is the right way to do it?

I'm m not saying that you are saying it.
What i did say is that if they take "minimum FPS based on 300 ms to 1000ms" it is not min FPS, it's a matter of semantics. Min FPS is the absolute min not sustained min.

 

[ManyThreads]

Skylake-X is manufactured on the same high frequency 14nm + process as Kabylake. I'd be surprised if top bins didn't hit 4.6 GHz fairly easily.
Coffeelake will have a six core max (not 8).

This is what I am hoping for. If I can get 6 cores at 4.6-4.8 (given that Broadwell-E 6850k already easily hits 4.4) on either Skylake-X or Coffee Lake (6c), for my personal usage that is probably the best of both worlds. Similarly, if Ryzen 2 can improve clock speed from 4.0 --> 4.5 and optimize the CCX design, that would be outstanding and almost certainly cheaper. I want to buy AMD because I don't like how Intel has been bending everyone over for years, but they are making it difficult! That being said none of the aforementioned Intel chips are even available yet, so it's not really fair. Or maybe I should just get a 1700 right now and call it a day haha - waiting until August will suck.

 

[bystander36]

I'm m not saying that you are saying it.
What i did say is that if they take "minimum FPS based on 300 ms to 1000ms" it is not min FPS, it's a matter of semantics. Min FPS is the absolute min not sustained min.

The minimum over 1 second is a valid minimum.
The minimum single frame is also valid.

It doesn't really matter how you do it, as long as you understand what you are looking at.

 

[imported_jjj]

The minimum over 1 second is a valid minimum.
The minimum single frame is also valid.

It doesn't really matter how you do it, as long as you understand what you are looking at.

That's not how language works.

 

[Zucker2k]

That's total and utter BS and on purpose as facts have no relevance to you and it's all about defending Intel. If only i wouldn't have just explained one post above yours why there is less variance in games that scale to more cores.
Let's try with pictures maybe that's easier for you.
Crysis 3 Ryzen (red) vs 7700k, the average FPS is similar but the 7700k has a wider variance between scenes.
Just imagine that the Ryzen is an 8 cores Intel so it doesn't tickle you the wrong way.

You could have chosen a better example to demonstrate smooth gameplay but what do I know? I mean a measly 105fps! And the smoothness of that line! Time to chuck that 7700K!!

 

[zinfamous]

Man you guys are just too much. You call anybody that doesn't agree with you a troll....SAD!

he's not calling you out for disagreeing with him--he's calling you out for purposefully ignoring the actual data and claiming a verified truth to be false. This isn't about opinion, it's about confusing reality for a matter of opinion. It isn't.

....then I am reminded that you are an earth = 6,000 years-old person, and so it all makes sense

 

[imported_jjj]

You could have chosen a better example to demonstrate smooth gameplay but what do I know? I mean a measly 105fps! And the smoothness of that line! Time to chuck that 7700K!!

Don't blame me that reviewers are nutjobs and can't test for realistic scenarios and insist on 1080P with high end cards.

 

[unseenmorbidity]

 

[Markfw]

Very encouraging !

 

[inf64]

Ryzen R7 4C/8T vs BR 9800 , dGPU test in CS:GO
https://www.youtube.com/watch?v=zcJCiQD4le8

Insane perf. difference

 

[inf64]

Another YT video, Ryzen 1700X @ 4Ghz with 3600Mhz DDR4 benchmarks, some very good gains there:
edit : I'm blind
Posted above .

 

[imported_jjj]

BW scaling and some perf scaling (2 pages) http://lab501.ro/featured-articles/amd-ryzen-7-1800x-overclocking-ddr4-si-nvme/8

 

[unseenmorbidity]

Data from MindBlank Tech's latest review: https://www.youtube.com/watch?v=RZS2XHcQdqA

He claims the recent Windows Update changed the results so his previous review numbers didn't match and he had to do it again, even for the 3200mhz DDR4. Now he manages a 3600mhz DDR4 clocks and with worse timings, saw a performance uplift.

 

[james1701]

Is everyone getting a different VID reading on their chip. My 1800X is listed with a vid of 1.55.

 

[bystander36]

That's not how language works.

There are many ways to interpret it. You can just as easily read it as minimum "frames per second". Meaning exactly as it is written, the minimum number of frames over the course of a second. Word for word, that is accurate. Generally speaking, when it comes to online reviews, it's typically established that minimum FPS are the lowest number of frames you get in a full second. And the maximum frame time is used for single frame measurements.

 

[swilli89]

Graphs from the Youtube Video! 3.96ghz Ryzen 1700 wins 4 out of 6 tests versus 5.0ghz 7700k!! (Really it wins all 6 if you look at minimum frames.

Look at those minimum 0.1% frame rates in GTA 5, Mass Effect, and Crysis 3...

 

[krumme]

Graphs from the Youtube Video! 3.96ghz Ryzen 1700 wins 4 out of 6 tests versus 5.0ghz 7700k!! (Really it wins all 6 if you look at minimum frames.

Look at those minimum 0.1% frame rates in GTA 5, Mass Effect, and Crysis 3...

Its just reviewers starting to understand how to bm a game more than ryzen obviously have greater benefit of higher speed ram. Its old news. If we take 0.1 mins who wouldnt select a 1700 with 2667 ram any time of the weeks for these games anyway?

Its a matter of how you test in the games and what you are looking for. Computerbase frametime bm of 7700 vs 1800x shows same extreme uplift of ryzen. They just play different maps and select the hard situations. Had he done the same ryzen would also dominate here.

Its the old story. 4 extra cores obviously gives a huge benefit when the game can use it and in high load situations.

Besides:
Solving the ccx speed issue via faster ram obviously works everywhere and gives the benefit of faster ram as sideeffect but its also a brutal and expensive way of adressing it. New uefi and the ability to alter it via software is a bit more elegant but probably comes at some efficiency loss. Still for desktop that seems like a solution to me. Give the fabric a voltage hike alter the timings and let us oc it.

But at the end of the day writing software that fits the processor and not only Intel is the elegant and perf efficient solution. As explained in the technical thread there is several possibilities to adress and solve most of the ccx problem. At the same time adapting to the entire cache and core typology will give a nice boost imo.

I am still surprised how damn fast this processor is for desktop out the gate. Obviously its a balanced design but imo there must be some technical gems hidden in eg branch prediction that really is a good deal faster than what Intel does to outweight for this beeing a new platform.

 

[mohit9206]

What's the opinion on R5 1400 vs i5-6400. Both are the same price £170/$170.

 

[bjt2]

I hope that the next ryzen stepping (or maybe this if it is possible with an AGESA update) has unlinked CCX bus and RAM bus, and higher memory multipliers. I will be happy also with linked bus, but double the frequency. I don't think that operate a bus up to 3600MHz instead 1800MHz would be a problem apart from power drain...

 

[CatMerc]

What's the opinion on R5 1400 vs i5-6400. Both are the same price £170/$170.

Locked 4c/4t vs unlocked 4c/8t.

Yeah, that i5 is dead.

 

[imported_jjj]

While at it, a slightly older Ryzen slide as a reminder that there is a large disconnect between reviews and what gaming is for most.
Granted frame rates graphs or 5% lows data at 1440p would be nice.

 

[mohit9206]

Locked 4c/4t vs unlocked 4c/8t.

Yeah, that i5 is dead.

What about those who don't overclock?