FreeBSD Boots on x86-64

craig2787 writes "FreeBSD developer Peter Wemm has successfully booted FreeBSD on a real AMD ClawHammer CPU, in both 64- and 32-bit modes. Original posting to the -current mailing list is here."

Comments

Em-Hache-Zed

[Xunker]

"CPU: AMD ClawHammer(tm) (3.14-MHz Hammer-class CPU)"

3 Megahertz? Whoohoo, looks like AMD is giving the Intel a run for it's money... and MOS, too.

Seriously, though, I'd eventually like to see some real world performance specs of Hammer running in 32 bit mode, just to see if it's going to suffer from the same 32-bit-on-64-bit problems that Itanic has been having. If they figured out a way around that, they could totally own the market because Itanium 1 is dead and all cursory tests on Itanium 2 show it sucks the glands of a large braying animal when it comes to 32 bit code.

Re:Em-Hache-Zed

[shlong]

Seriously, though, I'd eventually like to see some real world performance specs of Hammer running in 32 bit mode [...]

Benchmarks will come in time. Right now everyone that has a Hammer system is under NDA from AMD. Think about it, if everyone was posting performance numbers months before Hammer was ready for introduction, that would give Intel plenty of time to come up with some sort of response. When April 23 comes and the chip is officially released, I suspect that a ton of performance numbers will be released within a few seconds.

As for the 32-bit-on-64-bit problem, remember that the amd64 architecture is just an extension on ia32, much like ia32 was an extension of the 16-bit stuff. Code either uses the wider registers or it doesn't. The real fear is that 64-bit code won't perform as fast as 32-bit code, since 64-bit pointers/integers/etc means less efficient cache usage.

Re:Em-Hache-Zed

[MBCook]

Well, either the frequency reporting is wrong (possible) or the runs he showed are under an emulator (bochs type thing). He said it runs on real hardware, so it's most likely the first option. I agree though, I would really like to see some benchmarks. We'll have to wait untill the 22nd to see 'em though.

Re:Em-Hache-Zed

[kylef]

According to reports I've read, the new Opteron actually outperforms the current Athlon clock-for-clock in 32-bit Legacy mode (32-bit OS running 32-bit code) because at base, the decode paths and functional unit pipelines are similar to the present generation processor. There are some additional tricks they have pulled to get some more speed, like a "smart" TLB that only flushes its cache of page table entries when truly necessary (not at every context switch).

In 64-bit Mode (where a 64-bit OS runs 64-bit code), average instruction length has increased because of the addition of a preface byte to every 64-bit instruction, but overall code size has DECREASED because 8 additional general purpose registers have been added (reducing compiler generated load/store code). This decrease in code size compensates for the larger average instruction length and enables performance to remain on-par with 32-bit.

However, I will feel much better about these claims once I have seen some true performance comparisons at an independent reviewer's site! :)

Re:Em-Hache-Zed

[DarkHelmet433]

It was a joke, I changed the clock speed strings to 'pi'. This is a 10 month old pre-pre-pre-production A0-step silicon machine. I'm not allowed to talk about the speed of this particular machine. But I can say that I'm rather impressed given this particular machine's early production state. It does run very nicely in 32 bit mode. It is faster than my home desktop machine, and is faster than my work desktop (in single processor mode).

Also, note this is a Clawhammer cpu, not the Sledgehammer/Opteron that is coming up for release on April 23.

Re:Em-Hache-Zed

[mbadolato]

everyone that has a Hammer system

Everyone sing!!

If I had a Hammer, I'd benchmark in the morning
I'd benchmark in the evening
all over the net

Ok, now we now go back to your regularly scheduled BSD is dying trolls

Re:Em-Hache-Zed

[Xunker]

I was pretty sure that's what it was, either that or just a typo (gHz/mHz). Of course, if you *really* wanted to get the geek humour going you'd do "([Sideways-Eight]mHz Hammer-Class CPU)" or something equally nerdy.

What can you talk about about the machine? Do you know if the Opteron and Hammer are gonna share the same Chipsets?

Maybe I should ask something about BSD too to even things out... Uhm, In a Texas-style cage match between Tux, Beastie and that damn Mysql Dolphin, who'd win?

So,

[Anonymous Coward]

if FreeBSD is dying, it's dying in style? ;-)

Re:So,

[jo42]

> FreeBSD is dying

Who let the Iraqi Information Minister out of Baghdad?

Great News

[vga_init]

Even though they say that BSD is a dying operating system, I've had the pleasure of being able to use it quite often in the past, and it really is a fine operating system.

You've definitely got to hand it to BSD; it seems to be able boot on just about anything. One look at NetBSD's home page makes this obvious. :)

This added compatability is not only good news for BSD users, but also for the whole open source community, which doesn't seem to have any trouble keeping up with new technology.

FreeBSD / NetBSD

[edhall]

Btw, NetBSD has had x86-64 some time back. Free is just catching up, it seems.

FreeBSD has focused on Itanium up until now, given that production hardware has been available for a while. There are people who already have them in their datacenters and who want to run FreeBSD on them. It's part of the pragmatism that is at the base of FreeBSD's philosophy.

NetBSD has more of a research-focused, "climb the mountain because it's there" philosophy. Compare mottos: "FreeBSD -- The Power To Serve" vs. "Of Course It Runs NetBSD." That's not to say NetBSD doesn't make a fine, practical embedded platform (say), or that FreeBSD is useless in research (especially when that research can result in improved performance in the datacenter, FreeBSD's home turf). It's just a difference in emphasis, and the BSD community is richer for it.

-Ed