facebook rss twitter

Review: AMD Ryzen Threadripper 1950X and 1920X

by Tarinder Sandhu on 10 August 2017, 14:01

Tags: AMD (NYSE:AMD)

Quick Link: HEXUS.net/qadkcu

Add to My Vault: x

Conclusion

AMD Ryzen Threadripper is an unashamed attempt to rip the performance legs off Intel's best consumer CPUs to date.

AMD has used the word disruptive to describe the new Zen CPU architecture that powers Ryzen desktop CPUs, Epyc server processors and now, in August 2017, a trio of Threadripper chips designed to rip up the existing high-end desktop rule book.

Threadripper practically doubles the performance potential of Ryzen 7 by effectively building a new chip that houses two of them side by side. Gargantuan in size and equally gargantuan with respect to multi-threaded performance, it is the first time in recent history that Intel's best is hacked off the performance throne in no small measure. Threadripper 1950X isn't just a bit faster than Core i9-7900X in core-loaded benchmarks, it is way more rapid, thanks to 16 Zen-based cores humming along at high speeds and backed by quad-channel memory.

And this is where Threadripper shines most brightly, in benchmarks that take advantage of its muscular, many-core design. Digital content creators need to sit up and take notice, because AMD brings true premium workstation-class performance, massive I/O and all, to the desktop.

Yet as impressive as Threadripper can certainly be in the right circumstances, it is not the all-conquering hero. Intel retains a commanding lead in the multitude of applications that are lightly threaded, gaming performance is decent but not table-topping, and the flitting between Creator and Game Modes is not ideal. Intel, too, has its own massive-core powerhouses in the pipeline, meaning the second half of 2017 has become very interesting in the high-end desktop space.

AMD Ryzen Threadripper is an unashamed attempt to rip the performance legs off Intel's best consumer CPUs to date. The big, $999 beastie, 1950X, does this effortlessly, leaving the Core i9-7900X in its multi-core wake. This was its design philisophy. This is how it has played out.

Think very carefully about what you want your next premium PC build to do. Threadripper does brilliantly in certain respects and average in others, so we'd recommend it to those of you who can leverage its multi-core potential. Though for those who focus on gaming alone, a decent four-core chip is far more cost effective.

Bottom line: all in all, is Threadripper disruptive? Absolutely, and it brings back some much-needed competition in an area that has been bereft of it for far too long.

The Good
 
The Bad
16 cores and 32 threads for $999
Extremely fast in multi-threaded tasks
Forward-looking X399 platform
Quad-channel memory
Brings competition back to HEDT
 
Single-thread not as good as Intel
Game Mode and Creator Mode confusion



AMD Ryzen Threadripper 1950X and 1920X

HEXUS.where2buy

AMD Ryzen Threadripper processors are available to purchase from Scan Computers.

HEXUS.right2reply

At HEXUS, we invite the companies whose products we test to comment on our articles. If any company representatives for the products reviewed choose to respond, we'll publish their commentary here verbatim.



HEXUS Forums :: 41 Comments

Login with Forum Account

Don't have an account? Register today!
Has intel given us evidence that infinity fabric inside these chips has latency issues?
lumireleon
Has intel given us evidence that infinity fabric inside these chips has latency issues?
Pretty sure AMD themselves have said there is a small latency increase when using infinity fabric, nothing to worry over with multithreaded software like cinebench etc but in gaming it can have a small impact (as shown in the game mode tables).

Having said that, it might be easy enough to overcome with some add in code by AMD and the game devs so we don't need to keep switching mode via restart. At the same time the majority of people buying threadripper will likely be looking at multithreaded performance over gaming I would guess but it's not like it's a slouch in gaming even when in ‘creation’ mode imo either.
lumireleon
Has intel given us evidence that infinity fabric inside these chips has latency issues?

What's that got to do with Intel? Why would Intel have evidence of what causes latency in a competitor's processor?

As it is, Hexus have provided evidence, if you'd bothered to read the review properly. Switching to Game Mode - which forces local-only memory access - drops the memory latency from 90ns to 65ns. The only possible reason for that difference is that the infinity fabric between the two dies is causing increased latency.


Anyway, with that out of the way:

Speculation time :) In the Intel Core-X reveal thread I suggested that 16 core Threadripper would probably be faster than 16 core Core X due to its relatively high base clock speed. Now we've got some numbers, we can have a bit of a play. I'm going to assume that cinebench runs all the processors at their base clock speeds, and scales perfectly with both frequency and core count. I'm sure that's not entirely accurate, but it should give us a ball park. Let's see how the 7960X (16C) and 7980XE (18C) might score, extrapolated from the 7900X (using Core ratio * base clock ratio * 7900X score):

7960X - 1.6 * (2.8/33) * 2187 = 2969 (oops, just behind TR 1950X)
7980XE - 1.8 * (2.6/3.3) * 2187 = 3102 (yay, a whole 69 points ahead of 1950X)

So there you have it ladies and gentlemen - pay twice the amount for your processor, get 2% more cinebench performance….
Dunno singlethread is possibly on the way out anyway ad developers now has a new aim to go towards for better multi threaded performance overall.
QuorTek
Dunno singlethread is possibly on the way out anyway ad developers now has a new aim to go towards for better multi threaded performance overall.

That's not strictly true - there will always be algorithms that simply can't be parallelised, and sometimes over-agressive threading can make code run slower (something I've fallen foul of myself a few times ;) ). But developers are getting better at working out what works in parallel, and there are a lot of optimisation tools now that will do some of the work for you. But it's worth remembering that, for certain tasks, individual thread performance will still be key.