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

High End CPUs – Intel vs. AMD

cpubenchmark.net

Post reply on HN
Print view View original

91–98 of 98 posts

Re: High End CPUs – Intel vs. AMD

#91

Post by jacquesm »

powercf wrote: post #90
cbetz wrote: post #59

Earlier quoted context omitted.

This. I've been trying to put together a small home lab xeon e3 system that can theoretically support nvme+gpu+infiniband. It's tough. Typically you get something like 3 full length PCIe slotson a xeon e3 board (c236 chipset). BUT they can't all run full speed at 16x (16/16/16). You have to then choose between 16/8/8 and 16/16/0 due to the lack of PCI lanes.

Can you explain why you need 16/16/16? Wikipedia tells me that one x16 PCIe 4.0 connection has a capacity of 32GB/sec (x8 is 16GB/sec). A quick search shows NVMe drives with a sustained read or write speed of ~2-4 GB/sec. Equally for the GPU - you need to move a lot of data in/out of the GPU to saturate a x8 connection.

It's rare to run that sustained, usually it's bursty so the extra bandwidth is very much needed.

Re: High End CPUs – Intel vs. AMD

#92

Post by rxhernandez »

rbanffy wrote: post #84
rxhernandez wrote: post #76

Earlier quoted context omitted.

If I invent a fantastic new algorithm in a space people are hamfistedly competing in, does my manager get the credit for inventing the algorithm because he pushed me, or do I? This type of thinking makes great engineers move into other non-engineering ventures.

If your manager drove you through several iterations, pointing where your previous attempts were flawed and guiding you to the One True Implementation, then yes, your manager deserves some credit for making you implement their idea. The implementation may be yours, as well as the flawed ones, but it's the manager's idea in the end. You deserve credit for making it possible, but so does your manager. A good manager is…

Let's pretend this is a journal article, if he pointed out flaws but didn't really do much else, does he end up in the list of authors at the beginning of the paper or does he end up as a thank you at the end?

It seems in this case people like Jobs end up as first author.

Re: High End CPUs – Intel vs. AMD

#93

Post by rxhernandez »

bluGill wrote: post #86
rxhernandez wrote: post #76

Earlier quoted context omitted.

If I invent a fantastic new algorithm in a space people are hamfistedly competing in, does my manager get the credit for inventing the algorithm because he pushed me, or do I? This type of thinking makes great engineers move into other non-engineering ventures.

Everybody deserves credit. Your manager could have told you to work on a different problem. Are you really a better engineer than me - working for a different company in a different problem space where that algorithm isn't needed? Is it something special about you that nobody else could develop it, or is it just the circumstances put you in a place where you couldn't help but develop it? So you developed a new algori…

Let's pretend this is a journal article, if he pointed out flaws but didn't really do much else, does he end up in the list of authors at the beginning of the paper or does he end up as a thank you at the end?

It seems in this case people like Jobs end up as first author.

The rest is irrelevant. There might be several scientists far better than me, all that matters is that I got there first. My manager could also be irrelevant as I've had technically capable managers that didn't truly do anything except put me on a project, that they hadn't known beforehand if it was even possible to do, and tell me to do it with next to zero feedback throughout the entire process.

Re: High End CPUs – Intel vs. AMD

#94

Post by 0xbear »

DonPellegrino wrote: post #85
0xbear wrote: post #42

In case someone from AMD is reading this: guys, you need to fix stability issues on Linux, or your Epyc is DOA. People are having some serious lock-up trouble with Ryzen, even with the latest AGESA updates and kernels. This is the only issue preventing me from recommending to purchase threadripper workstations at work. We do need that pcie bandwidth for GPU, but we absolutely can't tolerate instability.

AMD has confirmed that they've been able to replicate the Linux bug and that it only happens on Ryzen , ThreadRipper and Epyc do not suffer from that issue.

They also have also inadvertently confirmed that their Linux testing efforts are lacking. Which just blows my mind TBH, because they're also in the server market, dominated completely by Linux.

Re: High End CPUs – Intel vs. AMD

#95

Post by mistermann »

rxhernandez wrote: post #92
rbanffy wrote: post #84

Earlier quoted context omitted.

If your manager drove you through several iterations, pointing where your previous attempts were flawed and guiding you to the One True Implementation, then yes, your manager deserves some credit for making you implement their idea. The implementation may be yours, as well as the flawed ones, but it's the manager's idea in the end. You deserve credit for making it possible, but so does your manager. A good manager is…

Let's pretend this is a journal article, if he pointed out flaws but didn't really do much else, does he end up in the list of authors at the beginning of the paper or does he end up as a thank you at the end? It seems in this case people like Jobs end up as first author.

Why didn't the people who were actually responsible form their own company then, but rather wait for Steve come along to assemble the team and take all the credit? I also assume he made more money than them, how did so many people stand for that?

Re: High End CPUs – Intel vs. AMD

#96

Post by hbogert »

Amazed by the little difference between the following two Ryzens and their scores:

- Ryzen 5 1600x - Passmark: 13130; single: 1942

- Ryzen 7 1700 - Passmark: 13819; single: 1760

Why would you go for octa-core which is only marginally faster in multi-core workloads, but considerably slower in single-threaded workloads. On top of that, it's 25% more expensive.

Re: High End CPUs – Intel vs. AMD

#98

Post by daemin »

dis-sys wrote: post #48
daemin wrote: post #46

Earlier quoted context omitted.

But if you're dropping 50% of the lanes and only getting a 20% speed drop, then it looks like you're not using those 16 lanes to capacity. Logically you'd expect closer to a 50% performance drop.

each Intel upgrade gives you 5-10% performance improvement. 20% is like 3 generations of Intel "innovation".

What I'm saying is that if the video card you were using had 16 lanes available and got X performance. Then you took away half the lanes available to graphics card, so now you have 8 lanes available, but performance has only decreased by 20%. Meaning that the game or application was only using a fraction of those extra lanes. So basically it wasn't fully exploiting the hardware available.
Post reply on HN