I'm curious about the 280 watt TDP, especially for the 16 core part. The 16 core Threadripper 2 had a 180 watt TDP, so what are they doing with the extra hundred watts on a smaller process? Could these chips be running at much higher frequencies? We might really be at the brink of no-compromise super high end workstation computing!
280W is for the 32 core chip. Rumor has it that there won't be a 16 core TR, but if there were the TDP would certainly be much lower.
AMD Lists Threadripper 3000 CPU with 32 Cores, Possible New Socket
21–30 of 49 posts
Re: AMD Lists Threadripper 3000 CPU with 32 Cores, Possible New Socket
#22Earlier 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.
Re: AMD Lists Threadripper 3000 CPU with 32 Cores, Possible New Socket
#23Earlier 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.
Re: AMD Lists Threadripper 3000 CPU with 32 Cores, Possible New Socket
#24I 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…
Re: AMD Lists Threadripper 3000 CPU with 32 Cores, Possible New Socket
#25I 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…
A few years ago, when Intel had no competition, going for more than 6 cores meant that you had to sacrifice single-thread performance. Now, if you want more than 8 cores, single-thread performance is not a reason to use less than 16 cores (AMD @ 4.7 GHz) or 18 cores (Intel @ 4.8 GHz). You may want to use less cores for cost reasons, but not for performance reasons. We do not know yet the frequencies for the 24-core T…
Re: AMD Lists Threadripper 3000 CPU with 32 Cores, Possible New Socket
#26I 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…
Re: AMD Lists Threadripper 3000 CPU with 32 Cores, Possible New Socket
#27Earlier quoted context omitted.
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.
Are you sure that they sacrifice speed for security? It's not obvious to me. Hardware fixes are supposed to be fast. That 20% slowdown comes from software implementation (and you can actually disable it).
Re: AMD Lists Threadripper 3000 CPU with 32 Cores, Possible New Socket
#28I 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…
I wish core counts hadn't gone crazy. Our developers are using PHP, Python, and Visual Basic so none of it gets used. A 6-core system is perfect. However, we end up buying 12, 14, 16 cores. And to make it worse, we buy dual CPU's on the servers. The buyer has determined core count > * Give me 8 cores and all the clockspeed I can get (for our workloads)
Why aren't they being used? Even for single threaded languages you can spawn multiple processes.
Re: AMD Lists Threadripper 3000 CPU with 32 Cores, Possible New Socket
#29I'm curious about the 280 watt TDP, especially for the 16 core part. The 16 core Threadripper 2 had a 180 watt TDP, so what are they doing with the extra hundred watts on a smaller process? Could these chips be running at much higher frequencies? We might really be at the brink of no-compromise super high end workstation computing!
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.
Re: AMD Lists Threadripper 3000 CPU with 32 Cores, Possible New Socket
#30Earlier quoted context omitted.
I wish core counts hadn't gone crazy. Our developers are using PHP, Python, and Visual Basic so none of it gets used. A 6-core system is perfect. However, we end up buying 12, 14, 16 cores. And to make it worse, we buy dual CPU's on the servers. The buyer has determined core count > * Give me 8 cores and all the clockspeed I can get (for our workloads)
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.