Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

AMD Lists Threadripper 3000 CPU with 32 Cores, Possible New Socket

tomshardware.com

Post reply on HN
Print view View original

41–49 of 49 posts

Re: AMD Lists Threadripper 3000 CPU with 32 Cores, Possible New Socket

#41

Post by bjoli »

driverdan wrote: post #29
bjoli wrote: post #12

Earlier quoted context omitted.

Isn't the ryzen 9 3950x 16core as well, but with a much lower TDP? (Whatever that means in this case). Comparing tdp is pretty useless.

It's not useless. Higher TDP means more electricity and more heat. Running costs add up.

For AMD it is. They calculate it using a formula with constants that differ for each processor.

Gamers nexus does a pretty good job explaining it: https://youtu.be/tL1F-qliSUk

There are loads of videos on YouTube about how AMD 105tdp processors beat intel processors with a lot lower TDP

Re: AMD Lists Threadripper 3000 CPU with 32 Cores, Possible New Socket

#42

Post by vbezhenar »

chris11 wrote: post #32
vbezhenar wrote: post #25

Earlier quoted context omitted.

I can get 5.2 GHz from Intel using 8 cores. That's like 10% extra performance.

I'd compare CPUs using benchmarks. I don't think clock speed is as good as a measurement, especially between AMD and Intel.

In this case I'm comparing Intel with Intel. AMD did not release Threadripper numbers yet.

Re: AMD Lists Threadripper 3000 CPU with 32 Cores, Possible New Socket

#43

Post by frankling_ »

strangenessak wrote: post #11
dTal wrote: post #9

Earlier quoted context omitted.

And yet, GPUs have hundreds to thousands of cores, and we find them very useful... There are many, many useful tasks which are embarassingly parallel or nearly so. For those tasks, doubling the core count doubles the performance. Single core gains have stagnated, so a performance doubling is a huge win. There's no other way to just up and double performance for any class of problem. And even outside those tasks, more…

> GPUs have hundreds to thousands of cores That's not exactly true. The GPU equivalent of a CPU core is called a Streaming Multiprocessor (in NVIDIA language), and it's latest GPU, GTX 2080 has 72 of them. Each of these SMs can run hundreds of threads, but they run the same code in lock-step.

That has never been true: on NVIDIA hardware the 32 threads of each Warp run in lockstep, certainly not all threads. And starting with Volta, each thread even got its own program counter and call stack.

Re: AMD Lists Threadripper 3000 CPU with 32 Cores, Possible New Socket

#44

Post by myrryr »

vbezhenar wrote: post #2

I wonder what's the good core count for development workstation. While it's obvious that increase from 4 cores to 12 cores is useful, for me it's not obvious that increase from 12 cores to 32 cores is similarly useful. Sure, if I'm compiling huge project from the scratch, every core will be loaded, but that's more suitable for CI machine. For everyday development people usually use incremental compilation and in my e…

Depends on the language.

As a Julia dev, 32 cores would be great.

Re: AMD Lists Threadripper 3000 CPU with 32 Cores, Possible New Socket

#45

Post by p_l »

robto wrote: post #35
driverdan wrote: post #28

Earlier quoted context omitted.

> Our developers are using PHP, Python, and Visual Basic so none of it gets used. Why aren't they being used? Even for single threaded languages you can spawn multiple processes.

Making programs concurrent is hard, especially if you don't have good support from the language. I, too, would hesitate before attempting to make a highly concurrent application in PHP, Python, or Visual Basic. And even then you're looking at considerable investment rewriting stuff that already works. Maybe it works out if the cost savings from being able to purchase fewer machines outweighs the rewrite and the risk…

Still, even single threaded applications can be distributed across the cores by the simple fact that you can run many of them.

And web browsers eat a lot these days :-|

Re: AMD Lists Threadripper 3000 CPU with 32 Cores, Possible New Socket

#46

Post by waste_monk »

plopz wrote: post #20
ahbyb wrote: post #19

Earlier quoted context omitted.

That's the trick: they can't make single cores faster so they just throw more cores at the problem and call it a day. Obviously that doesn't work but who cares? It looks good in benchmarks.

Thats why they should sell cpus that sacrifice security for speed. I'll take a cpu thats vulnerable to spectre/meltdown if its 20% faster.

At least on Linux it's pretty easy to disable the mitigations: https://linuxreviews.org/HOWTO_make_Linux_run_blazing_fast_(...

I'm not sure how easy it is to disable on Windows though.

Re: AMD Lists Threadripper 3000 CPU with 32 Cores, Possible New Socket

#47

Post by rwmj »

diroussel wrote: post #37
phaedrus wrote: post #36

Earlier quoted context omitted.

I have codebases which scale almost linearly with cores. I built a 56-thread Xeon machine. One of my projects compiles in two minutes with single threaded make and two seconds with all 56 threads going.

Interesting. What language and build tool is this with?

Not the OP, but we have big projects written in C containing hundreds or thousands of source files and builds scale almost linearly, at least up to 96 cores (I tested on ARM servers).

You have to be careful about how you write Makefiles - not using Makefiles in subdirectories, but writing non-recursive Makefiles. And you have to sometimes divide up large source files.

It's usually a good idea to do a test build with make -j1 and pipe the output through moreutils “ts” utility, then sort by which operation takes longest and try to break it up / parallelize it.

Re: AMD Lists Threadripper 3000 CPU with 32 Cores, Possible New Socket

#48

Post by rbanffy »

vbezhenar wrote: post #2

I wonder what's the good core count for development workstation. While it's obvious that increase from 4 cores to 12 cores is useful, for me it's not obvious that increase from 12 cores to 32 cores is similarly useful. Sure, if I'm compiling huge project from the scratch, every core will be loaded, but that's more suitable for CI machine. For everyday development people usually use incremental compilation and in my e…

> good core count for development workstation

As many as you can afford.

The reasoning is that your code, when it's ready and in production, will run on machines with more cores than they had available last year. If your code can now face its future runtime environment, then you'll have fewer surprises later.

A second reason is that machines with many cores degrade more gracefully under high load. You may be compiling across a dozen cores, but you'll still be able to search Stack Overflow or answer Gmail.

You may also consider going for higher memory bandwidth. 8x8GB DIMMs is better than 2x32GB ones.

Re: AMD Lists Threadripper 3000 CPU with 32 Cores, Possible New Socket

#49

Post by UK-Al05 »

vbezhenar wrote: post #2

I wonder what's the good core count for development workstation. While it's obvious that increase from 4 cores to 12 cores is useful, for me it's not obvious that increase from 12 cores to 32 cores is similarly useful. Sure, if I'm compiling huge project from the scratch, every core will be loaded, but that's more suitable for CI machine. For everyday development people usually use incremental compilation and in my e…

Large tests suits. If you design them well can be run in parallel.
Post reply on HN