Threadripper 7000 on Linux: The Return of HEDT is Imminent!
Vložit
- čas přidán 12. 05. 2024
- Timestamps
0:00 - Intro
0:35 - Things to be aware of
2:20 - Memory Channels
4:12 - Benchmarks
7:56 - Gaming
9:06 - Fluid Dynamics
11:04 - Closing thoughts
**********************************
Thanks for watching our videos! If you want more, check us out online at the following places:
+ Website: level1techs.com/
+ Forums: forum.level1techs.com/
+ Store: store.level1techs.com/
+ Patreon: / level1
+ L1 Twitter: / level1techs
+ L1 Facebook: / level1techs
+ Wendell Twitter: / tekwendell
+ Ryan Twitter: / pgpryan
+ Krista Twitter: / kreestuh
+ Business Inquiries/Brand Integrations: Queries@level1techs.com
IMPORTANT Any email lacking “level1techs.com” should be ignored and immediately reported to Queries@level1techs.com.
-----------------------------------------------------------------------------------------------------------
Intro and Outro Music By: Kevin MacLeod (incompetech.com)
Licensed under Creative Commons: By Attribution 3.0 License
creativecommons.org/licenses/b... - Věda a technologie
The WiFi on the motherboard we used for testing is WiFi 7, forgot to mention that in the video!
Can you make a guide on how to set up your own software on a home-server?
PiHole (Also to be used to have a local domain with subdomains for the same computer)
Nginx (Reverse Proxy)
Apache2
Docker
And some web-page stuff for a hub for the services.
I have been trying to make it work but it's all just so confusing, i'm no software engineer or watever, so i thought of there was a "fit all" video guide it would make it much easier for people to be able to self-host on their old laptops with a broken screen that they can leave on forever.
To me the single number WiFi don't tell me anything, I have to look it up, and it seems like it's not incorporating the 60GHz band.
The change from the protocol standard to some arbitrary numbers have dumbed down things severely.
So IEEE 802.11be is what it can do (but it's not expected to be in effect until May 2024, so I'd expect changes to the spec). No IEEE 802.11ay support on that motherboard.
That said - I'll prefer to run wired networking on a high end worstation anyway.
@@ehsnils Agreed. WPA3 in most WiFi 6 implementations is all that will be needed for now, with exception of niche applications when mm bands like 60 GHz starts to become available.
@@ehsnils Pretty sure after that brief experement with 802.11ad "WiGig" 60 GHz has more or less been relegated mostly to vendor specific P2P communication. MikroTik has P2P solutions using 11ay for a while but I really don't see it being used outside of WISP networks aside form like some niche and goofy wireless monitory relay stuff that's probably not sold in volumes anyways.
WiFi is a serious reliability issue in and of itself.
Anything that sends data over the air WILL suffer from interference and multipath issues.
Speaking as a retired RF comm *AND* long time computer hardware and network tech, leave the WiFi to PORTABLE and frequently moved MOBILE devices where it belongs.
Workstations are intended to use REAL Ethernet or Fiber connections, NOT connections specifically designed to be easily movable but with MUCH lower reliability.
FYI: Not sure if you noticed, but those Video benchmarks that "don't show a doubling" seem to be limited to 16 and 32 threads respectively i.e. they're not anywhere close to loading a 64 core 128 thread system. A lot of video tasks don't scale too well with core count anyway - that's why there's software like av1an to split up encodes into parallel tasks.
Could they use MP or OpenMP?
@@64BBernard For video encode? Not really. Parallelisation is just difficult on video encode in general, because you have to have all your threads working on a single frame, and any subtask can interact with any other subtask i.e. there's a major bottleneck. Software like av1an automates splitting the video into multiple chunks which can then be encoded separately and concatenated, thus bypassing the bottleneck.
Looking forward to the IOMMU tests and how the CPU lanes are laid out on the MB. The 2900 series threadrippers were already excellent in that regard.
I hope this pushes the 3K threadrippers to the 2ndary market cheap
Second hand TRX40 is already the price to I/O king right now I feel, you can get the 24c for around 600; the 32c for 900 and a motherboard between 250-400. Been tempting me for the past month or 2 or so, but I did a lot to make a consumer platforms work for me so I can't see myself moving away from bleeding edge now.
Thank you Wendell! :) Really interested in your comments re: memory starvation.... if I remember back a few years ago your testing showed earlier Threadripper high core count processors had this issue when not populating the maximum lanes. Given the mighty strong and fast cores of ZEN4 - it will be really intriguing to see if 8 lanes vs 4 lanes is a significant factor for memory intensive tasks that exceed the large amount of cache.
Are you going to do a separate video on how awesome the registered ECC memory is?
🤲
Wendel is consistently delivering higher and higher quality videos with every upload! Great work! And yes, I disagree with anyone who says these new Threadripper 7000's can't game, they are a entire new paradigm for PC gaming! No console may ever match, not because of the fastest FPS on Threadripper, you don't buy Threadripper (HEDT & Threadripper PRO), Apple's M3 Max or Ultra, or Intel Xeon for that purpose, you purchase Threadripper and Threadripper PRO (and yes Apple Silicon and/or Intel Xeon w9's) for easily above playable FPS while doing literally a million and one other tasks in parallel!!!
super cool, thanks Wendell
Thanks for the video. It would be really interesting to see the threadripper plus amd workstation video cards working together in a system doing some design and blender stuff.
I would love to see a comparisom between 4 channel and 8 channel Threadripper / Threadripper Pro in COMSOL acoustic simulations.
Idealy including paralelled batch simulations ( running multiple simulations at once to really push the CPU and memory bandwidth)
The same solvers are used for all models regardless of the physics involved (with some exceptions).
An interesting comparison would be the different BLAS implementations and their performance on Intel/AMD.
@@rarelycomments I am only familiar with the acoustic modules. I guess all other modules are sensitive to memory bandwidth too?
@@rarelycomments Different physics solved will have widely varying matrix sparsity and consequently different behavior even if the same solver is used.
Comsol does have the AOCL BLAS as part of the default installation now, but in my experience the MKL BLAS is superior most of the time, even running on AMD processors.
@@paulblair898 Good point.
AOCL is an option, I get a 20-30% improvement in speed in my models on AMD. I've not tested all solvers or a wide range of model sizes or physics.
Good old virtualizing. I want to run Proxmox on a TR 7000 for virtualizing my servers and my desktop. So, Linux + Windows desktop (including a GPU each) and some light network stuff like pihole, vpn, Home Assistant. Basically everything I need to run my home. Also maybe a NAS. It should work, but I am not so sure about the power usage, like, if it is even less than with individual systems.
Why would you need a threadripper for this?
@@r0galik PCIe lanes, lots of it.
Is Threadripper like the Xeons? Can use it for ESXi/Proxmox?
@@c.m.7037 Yes you can.
Would love to see a kubernetes/Openshift simulation/stress test
Thanks!
Still sad there isn't a 12/16 core HEDT chip for those who want more PCIE lanes but don't necessarily need a ton of cores. Might build one of these next year but will also have to keep an eye on sapphire rapids W and TR5000 prices, if they come down after this is available might go one of those routes instead.
Yeah AMD was slick about this, they have a Threadripper PRO 7945WX which is 12c/24t for the 8 channels of ram, but if you use the HEDT motherboard is will only be quad channel.. stillt eh whole systems gonna be a pretty penny even for that CPU, I think it's gonna be $1,500ish USD.
@@bes12000 I think AMD missed an opportunity by not having a 12 core option but it is what it is.
Why don't you get an older threadripper then?
@@MickenCZProfi I might but TR7000 is quite an improvement over TR3000. On the other hand I've seen 3960X + motherboard selling for less than MSRP for the 7960X so definitely an option.
Yeah, struggling with the some considerations.
I would love to see "large" Docker (compose) projects build times. i have one project that has 13 services that each have their own docker file(s). My 7950X makes this a thing of about 15 minutes, but that's with partial cache enabled.
Isn't that hugely dependent on their contents? Ours are mostly copying files around and compiling stuff, which doesn't make a difference if done on the "host" or when building the images (at least in our case).
@@Gramini in my case it's actually compiling binaries, extensions, etc.. , so it's not just copying files.
Would love to see how fast Android AOSP could be compiled on these CPUs. It really scales well with more cores, although disk bandwidth needs to keep up
Finally some Linux news on these monsters!
I'm a bit disappointed in 4-channel instead of 6 (EPYC Siena, also Zen4c, gets 6) . But getting RDIMMs on TR is a step upwards from 3000 series non-Pro.
Intel Quartus FPGA compiler works on Linux. The only problem I've found is a few years ago when the Memory IP generator messed up on Linux, while the windows version was able to generate the memory unit. For a large test job maybe one of the CPU samples would work for a heavy workload. The only problem is that the "lite" version is limited to single threaded. Note that this is less intensive than Open CL for FPGA, but single threaded my project takes over 30 minutes to compile. The process is memory limited, but my project is small enough to fit in the "3D cache" of the newer parts. So I am thinking that would be a better upgrade route.
The 24 core 7960X would be such a good entry point into HEDT at $200 more than the top mainstream 7950X, plus the expected platform/motherboard costs. it costs $900 more than the part immediately below it in the stack. It's not far off triple the price.
This just makes me miss CPUs like 5820K. That was a beast entry into HEDT back in the day. Decent performance and affordable enough to be bought by amateur enthusiasts.
5820k was god back in the day
That's also my gripe with the new rippers. Their pricing seems to completely ignore the huge value shift in the mainstream segment. I'd go as far as saying the entire TR 7000 series should be slashed by half if they want to win back any of the mindshare they squandered after ditching TRX40.
Wendell's looking good 👌
Hey Wendell. Speaking of bleeding edge kernels, what do you do when your kernel is incompatible with zfs? On arch it's a nightmare (6.6, 6.3, etc). Makes me miss btrfs. 😢
For a college senior project, a group of four of us clustered together 24 Dell P4 machines and used BOIC to calculate factorials of 1-2000 for a total of 4000 work units with a few errors. The script took less than an hour. I wonder what that fancy Threadripper's time would be for the same calculation?
Given that you can literally buy three 7950Xs for more or less the same as one of the lowest end Threadrippers though, clustering together machines is still a more budget friendly way of getting the same or better results.
@@cakeisamadeupdrug6134 True.
There are some TR features not availible with the ryzen lineup [aside from core computes per second,] which are a requirement for some setups. But I think AMD has overestimated the value of those features[which are low cost additions] and so they are still missing a large slice of the market. They need the TR volume to bring down motherboard costs, even if it means sharing a common socket with Epyc and offering a low cost 8 core TR for users that just want the extra PCIe lanes and registered ecc memory with cores designed more for efficiency than the raw speed of a gaming-type setup.
@@cakeisamadeupdrug6134 Or go 5950X instead, the 7000 series still has "new" pricing while the 5xxx has dropped in price a LOT - and uses much less expensive RAM as well - for performance that's not a LOT lower.
I can also testify that my 5950x works quite nicely on LINUX.
Given that my 5900X can calculate factorial(2000) in 2 nanoseconds, rounding up, whilst keeping a list of all the intermediate factorials between 1-2000, I think you need a better benchmark
EDIT: Should be 2ms - managed to misread ms as ns. Still stand by the point that a 2ms benchmark is not useful.
@@habilain Your 2ns number is dubious (like the compiler optimizer has just replaced the function with a precalculated answer.), but yeah even in an less optimized case it shouldn't take more than a few hundred thousand FPU clock cycles on an old single core CPU. Even a pentium3 would do that a few milliseconds, you can hardly pass a message between cluster nodes in that time. (edit, changed the estimated numbers, I forgot the need for multiprecision carry math, the result is too big for a single long.)
Can you bench mark LLama2 70 B and Falcon 180 B on thread ripper and thread ripper pro. i am very curious about memory band with (4 channel vs 8 channel) and core count scaling. The GUF format and oobabooga_textgen repo could be very useful. if you set the temperature to 0 they will be deterministic. How many tokens per second would it get on a couple of combinations should be enough to determine the sweet spot . if the systems are idle i can write a couple of scripts to run and benchmark these ai inference tasks.
Help me out by posting a quickie how to on the forum?
@@wendelltron Okay, will do.
Wow, on my bucket list to own one of these CPUs.
Microsoft is trying their hardest to make Linux the desktop OS of choice by completely fucking everything up.
Really, it's mainly their hold on gamers and the deals they cut with corporate bulk licenses [both windows and for stuff like office as a service and exchange mail server] that have retained their market share for this long. They don't make much direct profit on home windows, they just sell OEM licenses dirt cheap to retain the user base.
The Orange L1 banner!
Doing a 7970X build right now with the Gigabyte AERO D TRX50 Motherboard.
No, I'm still rocking 1950X for my workstation :)
@2:20, what happened to those poor innocent pci-e slots??
In 1979 I tried to get TI to include ECC in the RAM refresh circuit. Since you have to read and write every refresh cycle, do a read, correct, write cycle. This automatically scrubs the RAM and allows ECC on access. TI Management Ignored me as usual.
"It's gonna get fixed with a bios update. Don't worry". Right. I've been waiting for those sleep fixes for years now. Still counting :)
I need to migrate my 2990wx to Linux. I remember running Linux on a 486/dx2... As a server when I was an ISP in the 90's.
Hey, thank you for the lovely threadripper reviews. One question. DevOps/SRE engineer with 10 years of XP here, not sure why anyone in my space working in AWS, Azure and on-prem would need such a machine. Have been running my 32GB i7 12700H Dell XPS laptop for about 1.5 years now and to be honest I don't think I would need more in the next 3-5 years. Linting and dynamic precompilation, docker containers and WSL, no issues. Could you please give some scenarios of why DevOps would benefit from such a workstation. Devs, for sure, Ops, not so much.
For large memory workloads, would it be possible to use TR none pro with CxL memory to get to around the 1TB RAM area?
|*Literally*| some of the best tech content on YT. Thanks!
vr testing on Linux would be fun
What would happen if you ran your benchmarks on a better architecture? A direct execution stack-based processor like the GreenArray GA-144?
Like to know about the linux suspend-to-ram story. The lack of it is a dealbreaker for me
Would love a video on registered ECC.
I would love to see a test of IO for pro audio/visual. I currently run 3 CamLink Pros for 12 HDMI feeds and tried to run a DeckLink SDI card and couldn't due to the audio latency on SDI output. Try to do all this while recording and streaming in OBS :D
i love how you say pro, and then simultaneously blow it by saying camlink. Its time for the big boy cards
@@magog6852 that's fine, but it still should have been able to do it.
@@magog6852 also just for clarity, I reinstalled windows, took out all extra cards (so just video card), and LatencyMon will not give my build a clean bill of health. It always at some point measures latency too high for real time audio. This is with C states, threading, and any unused mobo features disabled. I have a post on Level1Tech forums if you're interested in reading my saga.
Any chance of a video on Thinkpad with Linux?
did you forget to turn on the mic during recording for this episode?
Do you know of any motherboards that use the 2011 Ćuk-buck2 VRM instead of the standard 1920 buck VRM?
Will these make a good virtualization platform with Proxmox?
How do you benchmark that?
I remember Wendell running/ emulating networking and over 100 virtual desktops on prior threadripper .
not sure if it was running pros mox or vsphere.
thumbs up for the linux
Non-pro HEDT TR can return all it wants, but AMD should understand that not even The Braindead will touch this after that 100% insane move by AMD in EOLing TRX40 after one(!!!) CPU release, despite their "long term support promise", in that now infamous 'take the money and run' move.
Not posted on Patreon first?
Or at all?
i have to be honest with you guys I do not really care about gaming on linux, overclocking or gpu pass trough. I am pragmatically just going to use the os with the best support for the software or hardware I am going to use if I am not bottlenecked by cost or a certain form factor. What I am trying to say I rarely turn on your channel any more. I think Wendell has so much esoteric knowledge and interests that would make for far more interesting videos than what he is doing now. I get that he is quit busy with work outside CZcams but I would really love for him to make more content like that. Clearly he is not concerned about generating as much views as possible so please do the needful sir.
what happend with the PCIe slots.. they look damaged (or dirty?) was it tape?
11:42 😧 What happened?
Asus Pro WS TRX50-Sage and the Pro WS WRX90 are the best for Threadripper 7000
Please do a rdimm video
this video feels "personal" because of the charisma and camerawork (GOOD) but 2 camera agles nullify the effect a little bit.
Who would go for these vs the epyc ones ? It's a bit confusing.
@Level1Linux
Wendell, would you pls run a video transcode job using Handbrake on Linux using these new Threadrippers?
Details of the job:
Source:
Any 4K H.265 HDR 10-bit video file
Target:
4K AV1-10bit SVT(do not use CUDA or any other acceleration, this needs to be purely a CPU Encode)
colourspace:BT.2020
profile:Main
Encoder tune:Off
Level: 5.0 and up
(MOST IMPORTANT WHILE ENCODING)Encoder Preset:Placebo(value 0 on the scale)
I am thinking of buying a Threadripper Machine for these tasks, but before I buy I need to be sure about the speedup that I am getting. There are no benchmarks on the net that use these compute heavy settings to look for before buying them.
Please please can u try these tests.
Huge Fan by the way
Wendel, how does this compare to the 64 core 3990X ? In a few short years I'm behind the curve again!
Aside from DDR5 memory, the general topology has been changed over the years to greatly reduce the core to core, cache and memory latency, so if you experience any bottlenecks there I would give this a serious look. If all you are looking for is threads and I/O then yeah you are going to see a performance bump from IPC and frequency improvements, but it requires quite an investment to achieve that could possibly be better spend elsewhere.
Video transcoding needs to decode as well, and decoders are pretty unthreaded last time i checked. Maybe try with uncompressed yuv video?
TRX50 4 Channel memory wrx90 8 channel memory? I see wow great job amd and asus
Still salty that higher frequency, higher capacity DDR5 ECC RDIMMs become more common while ECC UDIMMs don’t even get the possible 48 GB per module upgrade :(
Back in the day the top of the line Intel HEDT CPU cost about $2000 if I remember correct. But that was in the days when Intel could take whatever they wanted. One year later they had to slash their HEDT pricing in half due to AMD competition. So with that in mind I do not think the pricing is outraging
Intel dropped the price of the i9 10980XE by 50% (!) compared to the i9 9980XE shows how long Sintel had been *price gouging.*
Yes, but the serious grown-up question is: do they still come with PSP backdoor/spywarez baked in?
No 3D v-cache versions??? 😢
What about memory, does it behave with all slots loaded? Better or worse?
I think the usage of registered dimms negates these issues experienced on normal desktop platforms.
DDR5 on servers has been fine and TR7000 is basically using server memory. Training takes forever the first time around but it's like Epyc, no problem using all the slots and you can overclock if you want to go there as well. Wendel mentioned that in his other TR7000 video.
4 channel and restricted to only 1 DIMM per channel? YUCK!
For that price I expect 2 DIMMs per channel at the very least, memory capacity is one of the key selling points for HEDT in my opinion.
At the 10:00 mark you mention a xeon system, what are the specs of that system?
What about 24core?
will this platform run ableton ?
Am I blind or can I not see a comparison between the new 64 core and the old TR Pro 64 core?
Well it’s Linux so how about running Openfoam, code Saturn,SalomeCFD and Code Aster?😊 Pretty Please. I have an aging HP Z840 which back in 2017 was a beast, but my company went under, and I am semi poor, and need to upgrade. A thread ripper pro with a 100 gig ram disk seems to me like it would handle just about everything I could throw at it. I have 48 cores of Haskell the v4 chip I believe. I have been watching and listening for years. You are my tech God. Can 32 cores of threadripper pro be my answer to simulation heaven?
Things like video compression benchmarks simply do not scale on their own to so many cores. They do not have enough parallelism to exploit it all. I am pretty sure if you look at cpu utilization, you will see it cores are not loaded super high. Others on 7980X are memory limited. 7980x definitively not great for memory hungry and parallelization simulations (pro and epyc is for that), because they will saturate memory bus with their super optimized codes, and basically get same result as 7970x, which also saturates the bus, but if you use stuff using less memory bandwidth (i.e. compilation / build kind of things, doing a lot of io), then 7980x can almost double over 7970x. CFD, I am pretty sure big part of CFD is dead on CPU. Everything runs on GPUs. A lot of CFD packages only support CPU, because their models and code are really complex, and decades old, so hard to port to GPU. But some do support GPU. Plus for decent results, you need to have double precision capable GPU, and most GPUs are really slow at this, or do not have enough memory to run big models. But if you get big HPC GPUs, then it is the best option. I am pretty sure if you are into CFD, then you will have way bigger machine (pro or dual socket epyc) or run simulations on the cluster / cloud.
GPU-compute double precision was a big selling point of "pro" graphics cards a decade back. Now they most of them seem to have dropped doubles and gone to half precision as the "pro" selling point (16bit is optimal for machine learning neural net type of loads).
There are also GPU-like accelerator cards for computation such as the Tesla and Xeon-phi.
i thought you're matt damon
Speaking of CFD -- I would LOVE to be able to see what it can do with OpenFOAM.
They should give you comsol for Linux
Really doubtfull of these CFD results, generally CFD scale very well with CPU cores and tend to be quite optimized these days.
I would like to have confirmation if you could do more tests and dig into it.
You migth want to give a look at OPEN FOAM wich is a beautiful open source software for CFD and CLI friendly, a less known alternative could be Code_Saturne.
But as you tell this beahviour could be a software or system, don't think so since you are in control, optimization wich could dramaticaly hammer performance.
To my knowledge Comsol is more into FEM whereas Ansys is more FV (for real CFD purpose) wich lead to very different beahviour on CPU usage, it might be that comsol could scale more with memory (or cache) because directly solving this big matrices rely on RAM.
I had to check papers, this should be a well known territory for computer scientists.
Thanks for your work !
PostCognatum : Might be, that the previous pro version has much more compute units or are better used by the library used with the bench ?
Where did the Linux in 1812 joke originate from lol
I'd be super curious about how llama.cpp's llama-bench performs (say on a llama2-7b Q4_0/Q4_K_M quants, 4K context (I do all my testing -p 3968 -n 128). Might be also nice to see how it does on a 33/34B model as the SOTA open code assistant LLMs are all that size atm.
LLama2 70 B and Falcon 180 B would be also interesting.
Sound is weird. Has some background hissing.
i can only dream about this CPU, cost to much !!!
350w? Nice of AMD to put in 64 efficiency cores.
Looks like someone sneezed all over the motherboard like 5 times.
but at those prices is it not HEDT as we all are used to and remember.. this is proper workstation stuff.
Never knew level1 had a linux channel
you my friend are in for a treat. the rabbit hole is deep enjoy
AMD statement to every influencer - "Do not EVER compare TRX50 motherboards with TRX40".
Want a shocking eye opener? compare every non-pro TRX50 previewed (of course, you can't buy any!) with the greatly extended feature sets of TRX40, in particular, asking yourself "Where are the Zenith II / Aourus Extremes etc??". For your answer, ask MSI - they pulled out of supporting TRX50, primarily because of how AMD treated every customer and motherboard maker of TRX40...
AMD themselves said that "non-pro TRX50 is a welcome return for the desktop HEDT enthusiast". That is, exactly 4 years ago, after they publicly baited potential buyers with "long term support promises" for their then new TR system, TRX40, and then proceeded to lie to every TRX40 purchaser by breaking those promises in immediately EOLing it. No more expected CPU's. AMD literally killed their own non pro HEDT userbase!
So, what about TRX50? Well, in truth, TRX50 is a shocking, feature-depleted embarrassing shell of what TRX40 was and stood for, a shell that not even The Braindead enthusiast would purchase.
i would say hell no just wait and get zen5 with 20% more ipc and better efficiency and build 2 or 3 and still save money - zen5 will have much better support and development - if you need more powah then go to server chip with 12 chan rather than zen5 cluster
No RGB headers? So RGB RAM and GPU to compensate, lol
I received an e-mail claiming that the Linux scheduler had a hard-coded limit of 8 threads. Is this true? How does having more than 8 cores help if there is a limit of 8? What is the current Linux limit?
@@mytech6779 Thank you. There is so much disinformation out there it is often difficult to know what is true.
[revised repost] The linux scheduler[s] can handle hundreds of threads. The 8 core thing is about scaling the time slices to emulate true concurrency on systems with only one or a few cores, at the expense of extra context switching overhead. That timeslice scaling just levels off at 8 because above 8 there is sufficient true concurrency that the primary concern becomes efficient use of CPU cycles.
No RGB? I'm out
So freaking glad cheaper Ryzen Threadripper CPUs finally returned - a lot of people have been clamoring to AMD for them for a while, it's good that AMD respected their wishes.
I am not upgrading for a while though as Dark Silicon issues are getting somewhat bad particularly with TSMC 3N fabrication (Silicon is becoming useless the smaller the transistors get), so I am waiting for Ryzen Threadripper CPU to finally switch to III-V semiconductors transistor materials before I buy it to upgrade from Threadripper 1900x, this older Threadripper was and still is a cheaper option even brand new right now - I bought for work and play (I'd game on Linux OS as it got better CPU scheduler - I bought my Threadripper CPU more for astrophotography as 25+ MP RAW image files took 15 minutes on Phenom II 955BE processor to denoise).
Still, the Ryzen Threadripper 7000 series CPUs are truly off the cuffs, 7995wx is as powerful as a decent video card, up to 96 to 128 CPU cores.
can you elaborate Dark Silicon issues what are they ? are you referring to unused silicon ?
you're going to be waiting 20+ years for a CPU upgrade if your waiting for group III-V semis.
@@paulblair898 His current TR may actually be relevant for that long if he has decent quality periphrials.(Long lasting capacitors and such). I remember the 90s when you were lucky to get 3 years without a big upgrade but the cycle has been slowing, so now 15years is actually pretty reasonable. (With minor upgrades like a new mouse or harddrive.)
Couldn't disagree more. I have a Threadripper 3960x. It performs the same as a similarly clocked 3800xt in consumer workloads. My x79 and x58 systems before it all did the same.
I was looking forward to the Threadripper 7000 launch, and was planning on buying a 16 or 24 core model at launch, but I was very disappointed. This time they have moved more towards traditional workstation. The consumer workload performance is terrible, falling behind even the Ryzen 5 7600. Just not worth it if you ask me. I'm keeping my 3960x for a bit longer and reassessing later once the 8000 series comes out.
If someone would only make an AM5 motherboard that lets me use a full electrical x8 slot without dropping the primary x16 slot into x8 mode I'd be thrilled. The lanes are there! I'd even take gen 3 lanes off the 670E chipset for my x8 slot. The fact that not a single board maker is doing this, when the lanes are there and available is just so frustrating.
I hope in 10 years these chips will be $10 on ali express like the old xeons
Sure, but they will be 10 years old. The market price is low for a reason.
sorry to say it but wendell you lost alot weight! since i watched last time!! well done Sir
There are some strange artifacts in your audio recording. Really distracting.
with those ripoff prices, HEDT is absolutely dead LMAO.
But why linux? It is less reliable than Windows these days. And now with SNAP it's twice as slow. Linux has been infiltrated and sabotaged by MS. They've won. Linux is dead.
If by linux you mean "ubuntu". Most of the rest of the linux world doesn't want nor use snaps.
You should see a doctor, I think your herpathalimus is producing too much derpamine.