Recent content by kllrnohj

If this was 10 years ago this would maybe be true, but it's not. Just look at how well a 4770k (22nm) continues to hold up against Intel's latest 14nm++, and how Broadwell was not an upgrade from Haswell. Surely if process node mattered as much as you are claiming this would be utterly...

Neither. It's a reject MI25. Last gens part. Stadia's specs per Google: Custom AMD GPU with HBM2 memory and 56 compute units capable of 10.7 teraflops 16 GB of RAM with up to 484 GB/s of performance Radeon MI25's specs: 16GB of HBM2 memory at 484 GB/s with 64 compute units capable of 12.29...

High end workstations are 2p systems which the W3175X isn't. So I'm not really sure who this the target audience of this CPU actually is. Those with truly deep pockets for workstations with parallel workloads get things like the HP Z8 or Lenovo P920 which can run 2p Xeon's, pushing upwards of 56...

How do you figure? What does the W-3175X have that puts it in Epyc 7451 territory? The W-3175X is strictly single socket, whereas the Epyc 7451 is 2p compatible. Threadripper supports ECC & has more PCI-E lanes, so it's not like the W-3175X has any advantage there that warrants comparison to the...

AMD had something equivalent last year, the TR 2990WX, which is currently going for around $1,700 and plops into the same sTR4 socket as the rest of the Threadripper lineup. Intel's late to the party on this one, although the higher single thread performance and lack of NUMA complexity does give...

That's 72 very, very slow cores, though. Not only are they clocked low, they are also Atom cores. Their IPC is terrible. The entire point of it is purely the SIMD floating point performance. That chip isn't competing against other Xeons or Epyc chips, it's competing against Nvidia's Tesla. It's...

At the same clock speeds Intel has a ~10% advantage (Zen2 seems to be changing that), and on the low-core count CPUs Intel can clock higher (again, Zen2 appears to be changing that). But once you hit HEDT territory where Intel can't clock as high as they can AMD's raw core count advantage just...

No. The slower your GPU the more important VRR becomes. The point is so that you can have zero-tearing at any framerate. Think VSYNC + 40fps actually working well and not being a stuttery disaster. vsync where you don't need to have a super high minimum fps. It's why consoles & TVs have it now...

If it's just a dick measuring contest then get the 32c/64t Threadripper? x299/i9 can't match that, and you can brag about all 64 PCI-E lanes you have as well. Fuck it, run 12 NVME drives in raid 0 because you can. That's your untouchable bragging rights there if you don't care about price at all...

There is always that possibility that AMD decides not to do it for market segmentation reasons. I was just referring to whether or not the socket can actually do it. But we currently have a 32c/64t threadripper despite Epyc topping out at 32c/64t as well, so I wouldn't be surprised if we get a...

4 chiplets would be 32c/64t. They already sell a threadripper with those specs, so they're definitely going to sell the zen2 version. The 8 chiplet one is the 64c/128t, and AMD already publicly stated that the 64c/128t Epyc Rome will be socket-compatible upgrade. Since TR4 is the same physical...

AMD previously committed to AM4 being good for a couple generations and they publicly announced that Rome (Zen2 in Epyc form) will be socket compatible with current Epyc. So very probably yes, it will be AM4. And very probably you won't need a motherboard upgrade, either, unless you want the...

I didn't say a 15% performance difference, I said a 15% *clock speed* difference. Which you can't really agree or disagree with, it's a simple fact. Then on top of that you have the sub-10% IPC difference. I talked about both clock & IPC, so I'm not sure why you seem to be implying I talked...

All AMD needs is a 15% bump to clock speed to match the 9900K. That's not an unreasonable amount to get out of the shrink to 7nm based off of the clock boosts that we already see from the 7nm shrink for the MI60 The actual IPC difference is rather minimal, we're talking single digit percentage...

You run untrusted code all the time in the form of Javascript. It'd be unreasonable for anything to default to not having these mitigations when a javascript page could instantly own your entire system. These fixes are not causing any problems at all. The performance loss is not so severe as to...