Back to home page

DOS ain't dead

Forum index page

Log in | Register

Search:  
Back to the forum
Board view  Mix view

FAT image creation (Emulation)

posted by marcov, 19.02.2020, 10:37

> > > As an aside, most newer cpus (2015+ ??) seems to have VT-X nowadays,
> >
> > Much earlier (like Sandy Bridge, which is afaik the 2011 generation),
> > though Intel played games with that support, initially reserving that
> > support for the more expensive (i7) series.
>
> My Lenovo desktop (Core i5, dual core, quasi four with HTT) from 2011 has
> Nehalem Westmere (tail end of gen 1) with VT-X and nested page tables
> (unrestricted guest mode, unreal/big real, whatever).
Westmere was server, and mostly labeled as "Xeons", not "i5". If you have a 650 or 655, that is "enthusiast" variant Clarkdale. Still it was impressive stuff for the time. I skipped those however, goign from Core2 6600 (the original Conroe) jumping over three generations (core 8xxx, Nehalem and Sandy Bridge) to i7-3770.

> Trying to emulate
> anything on my 2009 Dell (Penryn?) dual-core laptop was like pulling teeth.
> (I vaguely recall shortening build time for p7zip under QEMU/FreeDOS from
> 11 hours to 5 just by avoiding LFNs. Yeah, I know, fairly pointless, but
> it's still a useful util, even if nobody cares about rebuilding in DOS like
> they should.) Now that BIOS/CSM is effectively dead (no more native
> booting), VT-X is very crucial (if you "need" legacy that badly).
Yes. Note that VT-X is mainly for non-cooperating (full emulation) OSes. Stuff like Linux runs better, because some high bandwidth drivers are replaced by ones that hand it nicely to the hypervisor.

> This low-end Chromebook is only supported until (I think) June 2022. The
> battery will "probably" die before then. (My 2011 Lenovo Android tablet
> lasted six years with its battery before the *software* failed!) There are
> of course much more expensive Chromebooks (Pixelbook?). This one has Intel
> N3060, Braswell/Airmont, only dual core, only SSE 4.2, no AVX. (So, a
> shrunken Celeron 2016 cpu in a 2019 model Chromebook from 2013 cpu tech.)
> So not really worse than the older hardware I already have. It's impossible
> to fully know or appreciate these things without taking a leap of faith and
> buying one.
Chromebooks are mainly intended to do some surfing (and then mostly "on the road"). I avoid them, and the N series in general (though I know some of the later ones are out of order, and not as bad as the early Atom ones).

I do a lot of FPC compiling, and while that doesn't require a umpteen core threadripper, a basic quad core is nice. Higher core counts are less utilized. (e.g. my Ryzen 2600 hexa core is about 25-35% faster than the i7-3770 compiling FPC).

Zen is nice though. The old core AMD advantages, price/performance, working well also if code isn't particularly optimized for it, and less playing games with the processor lineup than Intel does (this one gets vt-x, that one gets hyperthreading etc). A large part of the lineup has all features enabled.

At work we have the budget AMDs (about Eur 50, tax inclusive) as workhorse, Athlon 200GE, based on original Zen. Even those are nice.

> There's too many cpus. Zen was from early 2017. MS Surface has Zen+. Zen 2
> was just released. Intel's on, what, gen 10 or 11?? It's too much. I did
> briefly online look at some Dell Ryzen laptops, but I really wanted a
> reasonable Linux one, not Windows.
Wait. This summer a Ryzen 4xxx series laptops should come out, and they will be good. My work laptop is up for a change, so I might snap one up myself.

Buying "official" linux branded hardware is maybe not wise. Usually they are targeted at education and research institutions and relatively overpriced.

> > I cleaned out all Core2's early last year. So the oldest that I have now
> > (except some Pentium-Ds) are Ivy Bridges. All have VT-X, since I looked
> out
> > for that while buying :-)
>
> You mentioned AVX2 on FASM's forum. I'm a bit underwhelmed there, but
> obviously all the math (Fortran?) nerds love it.

Remember that for work I'm in image processing. We had quite some projects lately that required some whole image processing, and then using SIMD matters. Speedups of 4 or 6 times are common if not too large (relative to the cache), and this is often the most expensive operation done on an image.

For normal programming it matters less if a few primitives (like memcpy/strlen and search for a byte/word/dword/qword in memory) optimized.

For fun here is one of my older SSE2/3 experiments, rotating an 1 byte per pixel image by 90 degrees: http://www.stack.nl/~marcov/rot8x8.txt

But it only slowly progresses since it is half an hobby, and the projects that I'm preparing for sometimes simply don't get realized, or only much later than planned.

> I'm just not trendy or
> smart enough to care. Did you hear about AMD Threadripper 3 or whatever? 64
> cores/128 threads! Phoronix did some
> tests
> vs. 2004 cpus, shows quite an increase!
That thing is a beast, but also expensive (Eur 4000) a very unpractical power requirement (noisy) etc.

But the fun part of the CPU market now is that the moderate (Eur 100-200) pricerange is quite nice too!

> I don't know what Delphi or FPC supports regarding multiple cores (a la
> OpenMP).

There is a binding for openmp, but not much. Of course normal threadsupport works. OpenMP is mainly for clustering purposes, not for cores within one machine.

The FPC project's build process uses Make in parallel mode on directories, getting about two to four times as fast when enabling multi core. But going from quad to hexacore or higher doesn't bring much, since due to dependencies they are underutilized.

But that is compiling FPC, not compiling WITH FPC.


> And everything is ARM64 or x64 nowadays. One guy did write a
> C++11/17 book on
> multithreading,
> but I've not bothered learning C++ ('20 just finalized? ugh, "coming
> soon"). The world has barely caught up to '14/'17 yet. Even Delphi has too
> many versions (and books), so I worry about even pretending to care about
> that.
Yes. All main apps are 64-bit at work except for one. That exception does a lot of x87 math. (like sin/cos etc), which seems to be faster in 32-bit, at least with Delphi.

C++20 has exciting new features like Modules and Coroutines. You know, the features that Modula2 had in 1980, and Modules were backported to Turbo Pascal as units in '86 or so :-)

Maybe in 2040 they finally realize that = vs == is not smart either.

Post reply
 

Complete thread:

Back to the forum
Board view  Mix view
22049 Postings in 2034 Threads, 396 registered users, 149 users online (1 registered, 148 guests)
DOS ain't dead | Admin contact
RSS Feed
powered by my little forum