Jump to content

AMD Ryzen Threadripper 1950X Benchmarks Show It 45%+ Ahead Of The Skylake X Competition

Mr_Troll
6 hours ago, Taf the Ghost said:

Considering some of the early Epyc tests with AVX, it appears at the memory bandwidth is actually the real key with the calculation over even the extra processing units. Which is why I'm really curious as well, though detailed testing is probably a few weeks off.

EPYC AVX tests just confirm what some of us already knew. Consumer Ryzen is bottlenecked.

Come Bloody Angel

Break off your chains

And look what I've found in the dirt.

 

Pale battered body

Seems she was struggling

Something is wrong with this world.

 

Fierce Bloody Angel

The blood is on your hands

Why did you come to this world?

 

Everybody turns to dust.

 

Everybody turns to dust.

 

The blood is on your hands.

 

The blood is on your hands!

 

Pyo.

Link to comment
Share on other sites

Link to post
Share on other sites

5 hours ago, Evolution90 said:

That was from just a few days after launch (over 5 months ago), before any AGESA code updates or game updates.  Not terribly relevant today.

Link to comment
Share on other sites

Link to post
Share on other sites

17 hours ago, ARikozuM said:

I'm going to assume these benches use 3000+ MHz RAM and overclocks until proven otherwise. 

 

Edit: How is a 16-core CPU getting about 30% more performance over a 10-core? Shouldn't it be closer to 50%?

you can see the clock in cinebench.

Link to comment
Share on other sites

Link to post
Share on other sites

7 hours ago, Evolution90 said:

AMD should easily rip intel apart with Threadripper, the prices of intel's upcoming chips are retarded.

 

Still though... IPC.. Ryzen vs 3570K.

 

http://www.pcworld.com/article/3176100/computers/amd-ryzen-7-1700-vs-a-5-year-old-gaming-pc-or-why-you-should-never-preorder.html

Now it has higher IPC than the 7820X when both are using DDR4 3200. Check when both are at 4GHz:

 

.

Link to comment
Share on other sites

Link to post
Share on other sites

16 hours ago, Drak3 said:

Most tasks benefit from having better single core performance, when comparing identical core count

Yeah, but it doesn't seem like you'd be getting Skylake-X when you're going to be using lots of single threaded applications. Even internet browsers are multi-threaded now. 

Make sure to quote or tag me (@JoostinOnline) or I won't see your response!

PSU Tier List  |  The Real Reason Delidding Improves Temperatures"2K" does not mean 2560×1440 

Link to comment
Share on other sites

Link to post
Share on other sites

28 minutes ago, JoostinOnline said:

Yeah, but it doesn't seem like you'd be getting Skylake-X when you're going to be using lots of single threaded applications. Even internet browsers are multi-threaded now. 

Multithreaded apps still care about single thread performance. It is part of the equation to multithread performance.

Come Bloody Angel

Break off your chains

And look what I've found in the dirt.

 

Pale battered body

Seems she was struggling

Something is wrong with this world.

 

Fierce Bloody Angel

The blood is on your hands

Why did you come to this world?

 

Everybody turns to dust.

 

Everybody turns to dust.

 

The blood is on your hands.

 

The blood is on your hands!

 

Pyo.

Link to comment
Share on other sites

Link to post
Share on other sites

20 hours ago, ApolloFury said:

Does quad channel help in single-thread performance?

It should help with any kind of performance. Cpu's tend to have trouble working around memory read and writes since it's so much slower than the rest of the pipeline. They get around this by trying to predict what instructions will be coming up next so they can prefetch the instructions and data they will need. Even then prediction isn't 100% and faster memory will ultimately lead to less time wasted by the cpu. As far as how much it helps, I have no idea.

Link to comment
Share on other sites

Link to post
Share on other sites

9 hours ago, juretrn said:

STOP BEING STUPID INTEL (and drop those stupid prices)

Ok, here's a thought experiment. Let's say Intel dropped their pricing comparable to AMD in a similar configuration. Would that change what you choose to buy? If AMD offers the right performance at the right price, why does it matter if Intel charges more? The only reason I can think of for calling Intel to be cheaper is you want to buy Intel CPUs at AMD like pricing. Or is there something else I'm missing? Threadripper uses will focus on well scaling workloads, but it doesn't over all uses and it isn't a universal win.

Main system: i9-7980XE, Asus X299 TUF mark 2, Noctua D15, Corsair Vengeance Pro 3200 3x 16GB 2R, RTX 3070, NZXT E850, GameMax Abyss, Samsung 980 Pro 2TB, Acer Predator XB241YU 24" 1440p 144Hz G-Sync + HP LP2475w 24" 1200p 60Hz wide gamut
Gaming laptop: Lenovo Legion 5, 5800H, RTX 3070, Kingston DDR4 3200C22 2x16GB 2Rx8, Kingston Fury Renegade 1TB + Crucial P1 1TB SSD, 165 Hz IPS 1080p G-Sync Compatible

Link to comment
Share on other sites

Link to post
Share on other sites

21 minutes ago, luckydog32 said:

It should help with any kind of performance. Cpu's tend to have trouble working around memory read and writes since it's so much slower than the rest of the pipeline. They get around this by trying to predict what instructions will be coming up next so they can prefetch the instructions and data they will need. Even then prediction isn't 100% and faster memory will ultimately lead to less time wasted by the cpu. As far as how much it helps, I have no idea.

The question of how much core do you need to stress ram was asked elsewhere on the forums in the past, and I don't recall anyone managing to prove a single thread on a CPU being able to max out a typical dual channel ram setup. You really need multiple threads hitting ram at the same time to stress it. I had concerns that seem largely not to have happened with Ryzen's 8 cores and still dual channel interface, and expect Threadripper to be similarly not limited as it scales both. Further note for smaller data sets, the on-CPU caches help a lot. Once you exceed that, depending on workload, you can start being influenced by ram performance. Some may be more sensitive to raw bandwidth, others to latency. If you can throw money at it, get both and don't worry :)

Main system: i9-7980XE, Asus X299 TUF mark 2, Noctua D15, Corsair Vengeance Pro 3200 3x 16GB 2R, RTX 3070, NZXT E850, GameMax Abyss, Samsung 980 Pro 2TB, Acer Predator XB241YU 24" 1440p 144Hz G-Sync + HP LP2475w 24" 1200p 60Hz wide gamut
Gaming laptop: Lenovo Legion 5, 5800H, RTX 3070, Kingston DDR4 3200C22 2x16GB 2Rx8, Kingston Fury Renegade 1TB + Crucial P1 1TB SSD, 165 Hz IPS 1080p G-Sync Compatible

Link to comment
Share on other sites

Link to post
Share on other sites

2 hours ago, dexT said:

Now it has higher IPC than the 7820X when both are using DDR4 3200. Check when both are at 4GHz

 

@4Ghz Intel is just throttling due to power draw!

 

Intel doesn't have inferior IPC.

 

I would even bet on that being the case. Either way it's interesting and exiting AMD having a superior product in some ways. Less configuration, knowledge and actual equipment (cooler) needed to achieve better performance more easily.

 

The way I see it it's a clear win for AMD in the workstation and server space this time.

\\ QUIET AUDIO WORKSTATION //

5960X 3.7GHz @ 0.983V / ASUS X99-A USB3.1      

32 GB G.Skill Ripjaws 4 & 2667MHz @ 1.2V

AMD R9 Fury X

256GB SM961 + 1TB Samsung 850 Evo  

Cooler Master Silencio 652S (soon Calyos NSG S0 ^^)              

Noctua NH-D15 / 3x NF-S12A                 

Seasonic PRIME Titanium 750W        

Logitech G810 Orion Spectrum / Logitech G900

2x Samsung S24E650BW 16:10  / Adam A7X / Fractal Axe Fx 2 Mark I

Windows 7 Ultimate

 

4K GAMING/EMULATION RIG

Xeon X5670 4.2Ghz (200BCLK) @ ~1.38V / Asus P6X58D Premium

12GB Corsair Vengeance 1600Mhz

Gainward GTX 1080 Golden Sample

Intel 535 Series 240 GB + San Disk SSD Plus 512GB

Corsair Crystal 570X

Noctua NH-S12 

Be Quiet Dark Rock 11 650W

Logitech K830

Xbox One Wireless Controller

Logitech Z623 Speakers/Subwoofer

Windows 10 Pro

Link to comment
Share on other sites

Link to post
Share on other sites

Not surprising with 60% more cores.

20 hours ago, PocketNerd said:

16c/32t CPU vs 10c/20t CPU...

I WONDER WHICH WOULD WIN?!

More news @ 11

(That said, GO-GO ThreadRipper!)

Well, given the prices the 10 core is its direct competitor.

Don't ask to ask, just ask... please 🤨

sudo chmod -R 000 /*

Link to comment
Share on other sites

Link to post
Share on other sites

10 hours ago, Evolution90 said:

I find it odd that CPU-Z shows single thread on Ryzen to be that of a highly OC'd Nehalem CPU, so if we deduct that a 4.1ghz i7 920 is around the speed of a 3.7ghz Sandy, and Sandy at 3.7ghz is around even with Ivy, i would put the Ryzen CPU's single core speed at that of Ivy Bridge, not Haswell.

 

 

Look at this.

 

X4QML6d.png

 

4.35ghz BTW.

 

how does GeekBench show such a massive difference?

If you had two of those Xeons that PC would outperform the Ryzen 7 1700.

Link to comment
Share on other sites

Link to post
Share on other sites

1 hour ago, Vode said:

@4Ghz Intel is just throttling due to power draw!

 

Intel doesn't have inferior IPC.

 

I would even bet on that being the case. Either way it's interesting and exiting AMD having a superior product in some ways. Less configuration, knowledge and actual equipment (cooler) needed to achieve better performance more easily.

 

The way I see it it's a clear win for AMD in the workstation and server space this time.

Intel's IPC is much better than AMD's. The main issue is that these new Core X series are getting hot as hell are not reaching their maximum performance due to thermal hotting. People shouldn't waste their time and money with Core-X. They should just get an AMD Threadripper or Intel Xeon CPU.

Link to comment
Share on other sites

Link to post
Share on other sites

12 hours ago, TheCherryKing said:

Intel's IPC is much better than AMD's. The main issue is that these new Core X series are getting hot as hell are not reaching their maximum performance due to thermal hotting. People shouldn't waste their time and money with Core-X. They should just get an AMD Threadripper or Intel Xeon CPU.

Intel IPC is a little better than AMDs for a single thread per core, for non-AVX workloads. This can swap over to a slight AMD lead if you run two threads per core. Bring in AVX2 into the argument, AMD are way behind, offset in part by that they can offer many more cores at a price point. Also Skylake-X is fine, the problems only occur if you go for heavy overclocks, which is nothing new on either side. I haven't seen any potential signs of throttling until I hit 4.9 GHz on my sample, which was less consistent than 4.8 results.

Main system: i9-7980XE, Asus X299 TUF mark 2, Noctua D15, Corsair Vengeance Pro 3200 3x 16GB 2R, RTX 3070, NZXT E850, GameMax Abyss, Samsung 980 Pro 2TB, Acer Predator XB241YU 24" 1440p 144Hz G-Sync + HP LP2475w 24" 1200p 60Hz wide gamut
Gaming laptop: Lenovo Legion 5, 5800H, RTX 3070, Kingston DDR4 3200C22 2x16GB 2Rx8, Kingston Fury Renegade 1TB + Crucial P1 1TB SSD, 165 Hz IPS 1080p G-Sync Compatible

Link to comment
Share on other sites

Link to post
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now

×