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

Intel Processor N95 vs. N97 vs. N100 vs. Core I3-N305 Benchmarks Comparison

cnx-software.com

Post reply on HN
Print view View original

41–50 of 55 posts

Re: Intel Processor N95 vs. N97 vs. N100 vs. Core I3-N305 Benchmarks Comparison

#41

Post by cromka »

adrian_b wrote: post #32
MBCook wrote: post #13

Earlier quoted context omitted.

Intel uses ECC as a differentiator between consumer chips and server chips (and pro-sumer?) They’d never do that. They SHOULD. Everyone had too much memory and it’s too dense. We should all have ECC by now. Unless AMD does it I don’t think it will happen. Even if they do I feel like OEMs wouldn’t want it because memory would suddenly cost 2¢ per GB (or whatever) and refuse.

The recent generations of Atom CPUs for industrial applications include an in-band ECC controller, which works with non-ECC DDR or LPDDR memory. Besides the Alder Lake N or Amston Lake CPUs that are branded as the Atom x7000 series, some of the models branded as N CPUs, e.g. N97 and i3-N305 also have a functional IBECC controller, if the computer BIOS provides means to enable it.

But DDR5 has inband ECC by default, so it’s hardly any consolation to be honest.

Re: Intel Processor N95 vs. N97 vs. N100 vs. Core I3-N305 Benchmarks Comparison

#42

Post by sirn »

cromka wrote: post #40
sirn wrote: post #29

Earlier quoted context omitted.

Some N100 do have In-Band ECC (which uses the same data lane as regular memory channel, so less usable memory space/effective memory bandwidth), such as the Beelink S12 Pro box (DDR4) and is recognized by EDAC subsystem on Linux. [ 8.485808] [ T703] caller igen6_probe+0x138/0x780 [igen6_edac] mapping multiple BARs [ 8.487601] [ T703] EDAC MC0: Giving out device to module igen6_edac controller Intel_client_SoC MC#0: D…

DDR5 has in-band ECC by default on all platforms, though.

DDR5 doesn't have an In-Band ECC. What they have is On-Die ECC, and is not visible to the memory controller (i.e. error information won't be reported by EDAC), and only corrects 1-bit when they're stored/retrieved, where Side-Band ECC (regular ECC) and In-Band ECC can correct 1-bit and detect 2-bits, and can also correct/detect memory corruption during transit.

Re: Intel Processor N95 vs. N97 vs. N100 vs. Core I3-N305 Benchmarks Comparison

#43

Post by cromka »

sirn wrote: post #42
cromka wrote: post #40

Earlier quoted context omitted.

DDR5 has in-band ECC by default on all platforms, though.

DDR5 doesn't have an In-Band ECC. What they have is On-Die ECC, and is not visible to the memory controller (i.e. error information won't be reported by EDAC), and only corrects 1-bit when they're stored/retrieved, where Side-Band ECC (regular ECC) and In-Band ECC can correct 1-bit and detect 2-bits, and can also correct/detect memory corruption during transit.

Ohhh right, right, I had them mixed up! Thanks for the clarification.

Re: Intel Processor N95 vs. N97 vs. N100 vs. Core I3-N305 Benchmarks Comparison

#44

Post by cromka »

cromka wrote: post #41
adrian_b wrote: post #32

Earlier quoted context omitted.

The recent generations of Atom CPUs for industrial applications include an in-band ECC controller, which works with non-ECC DDR or LPDDR memory. Besides the Alder Lake N or Amston Lake CPUs that are branded as the Atom x7000 series, some of the models branded as N CPUs, e.g. N97 and i3-N305 also have a functional IBECC controller, if the computer BIOS provides means to enable it.

But DDR5 has inband ECC by default, so it’s hardly any consolation to be honest.

I stand corrected, DDR5 has on-die, not in-band ECC.

Re: Intel Processor N95 vs. N97 vs. N100 vs. Core I3-N305 Benchmarks Comparison

#45

Post by johnklos »

shiroiushi wrote: post #7
johnklos wrote: post #5

Earlier quoted context omitted.

True. I've wondered the same thing, and always come back to inexpensive Ryzens on ASRock motherboards that I simply underclock.

The problem with those inexpensive Ryzens is that they don't have iGPUs with Intel QuickSync so they can't transcode video with high efficiency. This makes them unsuitable for use for media servers, which is what a lot of people are doing with these chips these days: building home NAS/media servers that combine both functions into a single, small, low-power unit. You put a bunch of HDDs in it so you can store tens of…

Transcoding using hardware acceleration is one of those things that some people insist upon, like wanting "gaming" everything and overclocking everything, but most people don't need.

First, the quality of output of hardware accelerated transcoding is in most instances noticeably worse than CPU transcoding, as in most people can discern the difference watching two videos side-by-side.

Second, CPU transcoding is more than enough to keep up with most streams. For instance, 1920x1080 h.264 streams can be done in real time by even a modest 4 core processor. People who want 4K h.265 can buy a fancier CPU.

Third, most people are served perfectly fine by pre-transcoded files. Your comment about subtitles isn't correct - most streaming devices can accept subtitle metadata, and even if subtitles need to be burned in, they can be burned in to a static file and/or generated in real time by a CPU.

What's interesting is that the same people who want Intel Quicksync claim they want to transcode to the best quality that a device can support, then say they don't want to transcode to a static file because they don't want to transcode to a lower resolution / bitrate than what their best device can support, but want to be able to view things at the highest quality wherever they want. They've been tricked, because if they really cared about quality, they'd care about the difference in quality between QuickSync and CPU encoding.

That's why I tell people that if the really want highest quality real time transcoding and have sources that are ultra high quality, they'd be much happier with a Ryzen 7900 than with Intel QuickSync. Side-by-side comparisons would bear this out every time.

Re: Intel Processor N95 vs. N97 vs. N100 vs. Core I3-N305 Benchmarks Comparison

#46

Post by johnklos »

nullindividual wrote: post #12
johnklos wrote: post #4

There are lots of people out there saying to get one of these low(er) power Intel systems instead of, say, an Orange Pi 5 or some other ARM machine, but I think some of the information from the comments tells us a little more about their suitability for certain applications: "In fact ‘whole systems’ were benchmarked and not just Intel CPUs (under identical environmental conditions) since as we know in the meantime on…

N100 and fans? What fans? https://www.servethehome.com/fanless-intel-n100-firewall-and... The advantage over Arm is that it is x86-64.

Some of us don't download and run binaries. For some of us, the advantage of ARM is exactly that it isn't x86.

Re: Intel Processor N95 vs. N97 vs. N100 vs. Core I3-N305 Benchmarks Comparison

#47

Post by JamesSwift »

johnklos wrote: post #45
shiroiushi wrote: post #7

Earlier quoted context omitted.

The problem with those inexpensive Ryzens is that they don't have iGPUs with Intel QuickSync so they can't transcode video with high efficiency. This makes them unsuitable for use for media servers, which is what a lot of people are doing with these chips these days: building home NAS/media servers that combine both functions into a single, small, low-power unit. You put a bunch of HDDs in it so you can store tens of…

Transcoding using hardware acceleration is one of those things that some people insist upon, like wanting "gaming" everything and overclocking everything, but most people don't need. First, the quality of output of hardware accelerated transcoding is in most instances noticeably worse than CPU transcoding, as in most people can discern the difference watching two videos side-by-side. Second, CPU transcoding is more t…

> People who want 4K h.265 can buy a fancier CPU.

Or they can just get an N95

Re: Intel Processor N95 vs. N97 vs. N100 vs. Core I3-N305 Benchmarks Comparison

#48

Post by JamesSwift »

shiroiushi wrote: post #26
the_snooze wrote: post #22

Earlier quoted context omitted.

I run Jellyfin on an 8-year-old Intel NUC. Works great. Don't need to worry about transcoding on the fly because I make sure all video files are in H264 going in, which can be direct-streamed to pretty much all clients. https://jellyfin.org/docs/general/clients/codec-support/#vid...

>Don't need to worry about transcoding on the fly because I make sure all video files are in H264 going in, which can be direct-streamed to pretty much all clients. That doesn't work if you use subtitles. With many formats, the subtitles have to be transcoded on-the-fly into the video, even if the source and destination resolution and codec are the same. Also, the Intel NUC might be fine just running Jellyfin (withou…

Subtitles, or bitrate conversion for streaming devices.

Re: Intel Processor N95 vs. N97 vs. N100 vs. Core I3-N305 Benchmarks Comparison

#49

Post by shiroiushi »

justinclift wrote: post #38
shiroiushi wrote: post #28

Earlier quoted context omitted.

>These days though, people are probably better off buying an appropriate Ryzen processor and motherboard that explicitly supports ECC. As I pointed out before, you can't do that for a media server. Transcoding is necessary for many (most?) users. >That's not really relevant to the point of them only allowing ECC on Xeon chips though. They do (or at least did) support ECC on non-Xeon chips. That's a distinction withou…

They look pretty easily available to me, or are you going to exclude Ebay now as well? https://www.ebay.com/itm/305342386279 (note: I don't know the seller)

Yes, I'd exclude anything on the secondhand market, especially things you have to buy from overseas sellers where there's no possibility of support or returns. This is not like a normal new part where you can purchase it firsthand and expect it to perform as advertised or else get a refund. Furthermore, the (Intel) chipsets on motherboards sold to consumers don't normally support ECC either, so it seems you'd have to get something that's not designed to Intel specifications, probably on Aliexpress, so it's questionable if ECC would even work, and you can certainly forget about any warranty or returns.

Seriously, if you can't just buy it at Best Buy/NewEgg/Amazon (not from 3rd-party overseas sellers), then it's not applicable to this discussion at all.

Re: Intel Processor N95 vs. N97 vs. N100 vs. Core I3-N305 Benchmarks Comparison

#50

Post by shiroiushi »

justinclift wrote: post #39
shiroiushi wrote: post #20

Earlier quoted context omitted.

It looks like these CPUs were specifically targeted at embedded devices; they aren't things you can normally purchase yourself easily like the regular desktop chips, and if you look at the desktop variants (the ones without any letter suffixes), they don't support ECC. You can still see it even in 13th generation CPUs: https://ark.intel.com/content/www/us/en/ark/products/232105/... But as you can see here, this is an…

> if you look at the desktop variants (the ones without any letter suffixes), they don't support ECC. That's not correct. I literally linked to some non-suffixed processors that support ECC in the comment you're replying to.

I don't see any currently-sold CPUs there. Everything is years out-of-date, maybe even a decade.
Post reply on HN