Microprocessor Forum 85
Manufacturers are strutting their stuff at the Microprocessor Forum. Some of the rollouts: Turmoil writes "AMD has demonstrated working SMP. http://www.amd.com/news/prodpr/20165.html" hol writes: "German news site Heise.de reports that a German startup named PACT surprise-announced their processor design at the Microprocessor Forum in San Jose. Apparently this thing is a 128 cpu parallel computing deal which has its roots in the programmable gate array world." infodragon writes "All Linux Devices.com is running a pretty cool article about an X86 chip running on 1 AA battery. They demonstrated it by playing a VCD movie. They also say that mp3s can be decoded/played on it."
Is Linux AMD-SMP Ready? (Score:2)
This article says that 3D Studio Max was used for the demonstration which means NT/2000 to me.
If dual-proc Thunderbird motherboards were to arrive on the market a month from now, is the code for linux to take advantage already in place?
Did I just get information when I heard that AMD's SMP is different?
--Cycon
Re:iDragon - wowzers! (Score:1)
Re:Is Linux AMD-SMP Ready? (Score:1)
And I'll start building my next system a few days later. It's dual T-Bird 133xDDR or bust, for me.
ps - Whence the fixed-width font? Are you posting from a dumb terminal or something?
--
Give me a candidate who speaks out against the war on drugs.
Re:Motorola annoucment (Score:1)
Re:yes, sir (Score:1)
Just as you pour over your posters of Natalie Portman, just as you beat your tiny penis to a bloody pulp, the Rock is gonna beat your candy ass!
So bring it jabroney, just bring it!
Now, the Rock says this. You see, that first posting lameness thing has pushed the Rock just a little too far. Just a little TOO far....
So here's what the Rock is gonna do. The Rock's gonna take your first post, turn that sumbitch sideways, and shove it straight up, your candy ass!
The people's champion isn't going to put up with the first posting morons. It's time for someone to stand up to the foolishness. It's time once again for the people's champ to take the ring.
You stand up there, every story. You stand up there and run your mouth. You run your mouth, and you whine, and you bitch, and you wine some more. Well, the Rock says this, he doesn't care how much crap you whine about! He doesn't care how much garbage you bitch about! But what the Rock does care about is WHIPPING THAT CANDY ASS ALl OVER SLASHDOT!
So you go on and whine. You go on and bitch. You go on and be a lame ass first poster. You go ahead and lick that lama's anus! The Rock is gonna take you out. And he's gonna take you out, TONIGHT!
If you SMELLLLLLLLLLLLLLOW! What the Rock! Is cookin'.
Signed, The Rock
PACT/XPP: At last a decent new architecture! (Score:5)
But PACT's XPP is a different thing altogether, a dataflow computing engine on a chip. This thing is so far outside the current norm that it holds exhalted company with only a very few select others: my list of such exceptional architectures would probably comprise the Intel iA432, the Inmos Transputer, the Crusoe, and now the XPP. (I'm only including real candidates for implementation as micros, not research or demonstrator platforms of which there have been many hundreds of great ones.)
It's beautiful!
My research work on parallel architectures and concurrent languages really needed hardware like this to blossom. I wish the XPP had appeared then!
Re:Wow (Score:1)
I still say that turning off Javascript was the best thing that ever happened to my Web usage.
Re:Definition of 'mini-watt' (Score:2)
Not there.
http://physics.nist.gov/cuu/Units/prefixes.html
Hrm not there either.
http://computer.org/author/style/mno.htm
Fer crying out loud, not there EITHER!
Put up or shut up now, troll.
Re:Meanwhile, in the exclusive Wintel Clubhouse... (Score:3)
Come on, that's so last year. In order to gain karma these days you need to say whatever is against the perceived party-line, and complain about how all the moderators will moderate you down for being so avant-garde.
Re:What?!! (Score:1)
--
Michael Sims-michael at slashdot.org
Be a brain donor (Score:3)
Thankyou, once again, for donating your unused brain.
Re:Motorola annoucment (Score:1)
Motorola announcements used to excite me. Now they just make me angry.
Where the fuck is my POP board?! Anyone sellin'? If Motorola doesn't start shipping their damn chips, I'm just gonna buy more Athlons...
---
Re: (Score:1)
Re:Dual Athlons should be better than dual PIII's (Score:1)
bats = bugs
Re: (Score:1)
Re:Rise iDragon (Score:1)
Which is really amazing, as he didn't know
Chinese before he installed Linux!
Chris Mattern
Re:Mini Watts?!? (Score:1)
They meant Mini-Wheat. It's a cereal and a measure of power.
Re:iDragon - wowzers! (Score:1)
And a processor (chip) is one IC.
Re:Duron Duron [Karma Whoring (Score:1)
A
Re:Meanwhile, in the exclusive Wintel Clubhouse... (Score:1)
--
Chief Frog Inspector
Re:Is Linux AMD-SMP Ready? (Score:1)
Of more interest is tha APIC (SMP interrupt controller) implementation - rumor has it that the AMD one is different - mostly to avoid Intel IP/patent issues (think of AMD as playing space invaders with Intel lawyers dropping from the sky ...) - can anyone confirm this?
Re:iDragon - wowzers! (Score:1)
Try this [slashdot.org].
Re:Wow (Score:1)
I can see the right frame, but no menu. Then again, lots of stupid web sites are not made to work with a real standard browser like Opera.
-
Rise iDragon (Score:1)
Maybe I'm having a mental fit or something, I don't recall ever seeing that anywhere.
Not that powerful (Score:3)
I bought a Micro-ATX Cyrix MediaGX mobo a while back, $59/+shipping, to use as a part of a custom router setup. Well, lo and behold, I'm reading the manual, and it states that it will do full-frame rate MPEG1 (VCD) and DVD playback. Now, don't get me wrong, but this is a 166 chip. What do I do? I pop in a DVD drive, ghost Windows 98SE to it and install the software player (OEM version of PowerDVD, with support for the funny accelerated video chipset.) And it plays 'The Road Warrior' just fine!
It doesn't take much to do VCD/DVD playback. The 166 Cyrix is about equivalent to a Pentium 120. The Transmeta Crusoe is equivalent to a Pentium III-500, for a max of seven times faster.
How? (Score:1)
Re:Wow (Score:1)
Seriously now, anyone have trouble seeing anything at all on that page?
It requires javascript. Just look at the source. I had to look at the source for AMD's site because they chose a font size of "1", which on my system equates with "a few pixels". I'm not even going to enable javascript to look at PACT's site. If they don't care about security minded people then I don't care about them.
Re:Is Linux AMD-SMP Ready? (Score:1)
Re:who knows (Score:1)
K7s are essentially RISC, and have more in common with a G4 [apple.com] than with a PIII.
Check out the comparison [arstechnica.com] at Ars Technica [arstechnica.com].
Reasons for MS not to port to Sledgehammer (Score:1)
AMD have yet to ship engineering samples of Sledgehammer, for the simple reason that the design isn't fully nailed yet.
Intel have largely stopped marketing Merced/Itanium, because their later designs will probably blow it out of the market.
What is wrong with a company failing to support a non-existant product?
</RANT>
If you need 64-bit processors in your server, you buy Sun SPARC, IBM PPC/64 or DEC Alpha. You spend a lot of money, you get a lot of them in one box, and you don't care about the price, because $5,000,000 for a server (OK, maybe $200,000 at the low end) is trivial.
The good thing is that the companies that sell these chips support Linux (and other free OS projects). The bad thing is that no sane company will ever run a free OS on a box that costs this much.
AMD and Intel are both building 64-bit chips. That's nice. Real computers, running real operating systems have had them for years. Until you need >4GB RAM in your cute little desktop peecee, forget about 64-bit processors. One day they will be there for you, and AMD and Intel will be selling them, But the real processors, in the world of the grown-ups, will still be so far ahead that the leet peecee brigade won't be able to comprehend it
*Apologies to Kryten
And in other news... (Score:1)
Re:why bother (Score:1)
Possibly the burden of all that bloated code has taxed their agility and finally pinned them to the mat.
Appearances being what they are, these days, M$ _could_ be viewed as exercising monopoly power by _not_ supporting a platform. I'd expect them to be better tactful, but that's still something they haven't grasped. A better choice of reply would have been, "It certainly is an interesting architecture and we're very eager to see what we can do with it", just before returning to a hotel suite and finishing with, "the day after hell freezes over."
--
Chief Frog Inspector
Re:Not that powerful (Score:1)
The higher the quality you want, the higher the strain on the CPU. For hardware-quality DVD playback, a K6-2 500 would be quite on the LOW end.
Re:How? (Score:1)
Re:Is Linux AMD-SMP Ready? (Score:1)
The <blockquote></blockquote> tag, designed to display formatted text...
--
You think being a MIB is all voodoo mind control? You should see the paperwork!
Re:SMP Athlons (Score:1)
--Ulrich
Re: Not that powerful (Score:3)
I note here that the MediaGX chip is not just "yer average CPU", it's a CPU+media operations. It's designed in a similar but broad vein than MMX and SSE. The idea is to allow one chip to be the heart of a el-cheapo media box, such as the mythical "set top box" that will make some hungry MBA a jazillionaire.
Cyrix created this chip to try and pre-empt-slash-cash in on the "set top" market. The idea was to allow you to use the MediaGX by itself (one chip, cheaper to build and easier to design) versus a "standard" CPU + media copros. Hence the MediaGX has a whole bunch of instructions tuned for sound and video processing.
When you add the fact that DirectX has native support for MediaGX instructions, you find that it's quite feasible for it to handle a DVD decoding load. I'm not sure that the same could be said, however, of a vanilla Pentium of the same era (without MMX).
be well;
JC.
--
"Don't declare a revolution unless you are prepared to be guillotined." - Anon.
Alpha better... (Score:1)
One AA Battery (Score:1)
"All linux Devices.com is running a pretty cool article about an X86 chip running on 1 AA battery.
Finally. Maybe I'll get a laptop that can actually last from Atlanta to SeaTac on one battery pack, and not even sear my crotch in the process. And a bonus, running Linux
1Alpha7
Re:One AA Battery (Score:2)
It probably isn't all that powerful. I'd rather see someone do power-reduction like this on more power-friendly platforms. By the time you get some of the other archs out there down to one-battery power levels, they'll probably put this thing to shame.
--
It's a
Dual Athlons... (Score:1)
Great! (Score:1)
Mini Watts?!? (Score:2)
Ask Slashdot - What is a mini-watt?
Al Gore - I invented mini-watts.
G. Bush - My daddy gave me mini-watts.
Re:Is Linux AMD-SMP Ready? (Score:1)
who knows (Score:1)
Motorola annoucment (Score:3)
iDragon - wowzers! (Score:2)
An entire VCD with an AA Battery? Now that is slick... and even though the Voltage slipped from 1.5V to 1.1V, the processor remained functional? Man, this is very cool... Anyone know how the Transmetta chips take a slipping Voltage? can it handel this?
Re:iDragon - wowzers! (Score:2)
This is nothing that should be seen as impressive, it's just PR that will fool the masses and make the engineers wonder why it would exist any other way.
Re:One AA Battery (Score:2)
Well, here's another answer to the recent question about why companies still tinker with x86 devices. Apparently the recent technologies still can improve upon the original behavior.
Dual Athlons should be better than dual PIII's (Score:3)
But when it comes to SMP, the Athlons should have a BIG advantage; the EV6-protocol.
The EV6 which is the bus used by the Athlon-arcitechture, and licensed from Compaq (Alpha)
provides DEDICATED bandwith for each of the CPUs,
(to the chipset). The PIII's however must all share the bandwith, which is not really sufficient for optimal operation. Don't know what Intel has done for the P4 though..
Re:who knows (Score:1)
They do CISC emulation, for backwards compatibility sake.
The line between RISC and CISC is really blurred nowadays anyway, with RISC chips with > 150 opcodes, and CISC chips translating CISC stuff to faster RISC codes.
Re:Rise iDragon (Score:1)
is MS's set-top box OS for the Chinese market.
Here's an article about it:
http://www.china2thou.com/9907p5.htm
Don't seem to be able to find an MS web
site for it.
Chris Mattern
Re:Rise iDragon (Score:1)
Re:Great! (Score:1)
I think lack of SMP for the AMD fans is probably schadenfreude enough, though -- they can't have too much bad luck or they'll lose the market niche they've got.
This seems strangely familiar... (Score:2)
Re:iDragon - wowzers! (Score:3)
This is nothing that should be seen as impressive, it's just PR that will fool the masses and make the engineers wonder why it would exist any other way.
Individual IC's can, yes. The point is that when you have many many IC's strung together to make a chip, the tolerances for the whole chip become much tighter. Perhaps you've heard of fan-out/fan-in? This is extremely impressive, dude. Don't believe me, try switching the voltage for your P3 from 1.6V to 1.2V and see how it does.
AMD has kick ass names (Score:1)
Re:Great! (Score:1)
But the dual Athlon will be a fun toy, no doubt.
kabloie
interesting, but... (Score:1)
I am currently involved in some research where we are trying to solve the same problem, roughly. However, we are trying to make the change as transparent to users (i.e. compiler writers & assembly code writers) as possible by making small tweaks to the standard RISC concept that will allow our chip to extract large amounts of parallelism. It is clear that with these reconfiguration based architectures it is possible to have huge performance gains at the expense of programming complexity. Hopefully our architecture will be to these reconfigurable systems what superscalar was to VLIW. VLIW has been around for a long time, but it wasn't popularized until architects came up with ways of making a VLIW core look like a scalar processor to the outside world.
We'll see.
Ben
Re:One AA Battery (Score:2)
Meanwhile, in the exclusive Wintel Clubhouse... (Score:3)
--
Chief Frog Inspector
SMP Athlons (Score:1)
Wow (Score:1)
Seriously now, anyone have trouble seeing anything at all on that page?
Meanwhile.. (Score:1)
Analysts bemoan the downfall of Intel, as yet another Slashdot article fails to mention the aging chipmaker. Insiders say this is a great tradgedy that geeks actually have choices in the PC x86 processor market. "We used to run the show," said one anonymous employee. Analysts also mentioned that unless Intel can discover a way to compete in a non-monoplistic market, hoards of "Open Source" assembler and processor gurus will migrate to helping Transmeta and AMD build better products.
Re:One AA Battery (Score:1)
What?!! (Score:1)
--
Re:Rise iDragon (Score:1)
Re:Meanwhile, in the exclusive Wintel Clubhouse... (Score:2)
Only dual Eh? (Score:1)
Re:Motorola annoucment (Score:1)
Re:Great! (Score:2)
"Always"?
Translation: the last six months since you started reading slashdot and grew pubic hair.
History lesson: Go back before AMD bought nexgen in mid-90's. If it wasn't for Nexgen, AMD would have folded long ago. On their own, all they had was a K5, which sucked. Once they bought all of NexGen's brainpower with the chump change they made from ramping flash (Intel fumbled the flash market in 93-94, which let AMD win some capital $$$), Nexgen all but handed over the k6 and k7.
So does AMD deserve credit for the K6 and K7?
Reworded: does a company deserve credit for intellectual property that it purchases?
Tough call. I would say, yes, they do. It all comes from talented engineers, and whatever faceless company that they're a slave to owns the rights to their intellect. AMD had very little talent in the late 80's-early 90's, then they bought some. The exact same way that Intel is trying to buy dominance in the networking world. Isn't that capitalism?
Personally, I love the competition, and I want to see AMD get spanked because Sanders is an idiot and the underdog deserves a boot to the head once and while... but then again I'm a big fan of schadenfreuda (sp?)
---
Unto the land of the dead shalt thou be sent at last.
Surely thou shalt repent of thy cunning.
Zero AA batteries, MP3, VCD (Score:1)
X86 chip running on 1 AA battery. They demonstrated it by playing a VCD movie. They also say that mp3s can be decoded/played on it."
This gadget [amaxhk.com] is portable, plays MP3s, VCDs, audio CDs and comes with a lithium rechargeable. You can buy it already in the UK from Jungle [jungle.com]. I have one on my desk, my only complaint is that it doesn't play some CD-RWs reliably.
Re:This seems strangely familiar... (Score:1)
As far as I understand, the XPU128 itself doesn't run Linux:
The GNU C Compiler and related tools allow programming of sequential parts of algorithms for the Risc processor. The API for Communication with Host supports NT and Linux operating systems.
Parallel parts of the algorithms are programmed in the high level language LELA or Assembler language. A communication class library provides simple integration of C programs and XPU programs.
Linux is only running at the risc processor, used as an interface between the XP128 and the PC.
I don't believe, you can translate C to efficient parallel code. applications and algorithms have been optimized for the common sequential architectures over the last 20, 30 years. Switching to massive parallel devices will demand new software.
Re:yes, sir (Score:1)
Dataflow is more than just FPGA + RC (Score:2)
I'll tell you why
In contrast, Xilinx [xilinx.com]'s strides in FPGA and RC technology tend not to feature because there's a gulf between a beautiful RC chip like the 6200 and actually being able to compute with it. Even Xilinx know that now -- their newer devices are more advanced FPGAs but they don't even attempt to carry the generic RC mantle like the 6200 tried to do, unsuccessfully. It came close, but you need a lot more than just an FPGA to make a useful RC: you needs a preconfigured computing architecture to start with, otherwise the programmer needs to think in terms of gates, and that's one paradigm shift too far. The 6200 suffered from not being specific enough. That's a peculiar observation to make in the FPGA field, but it reflects reality in the computing field, and even RCs need to take that into account.
And that's what PACT seem to have done with their XPP. Sure, its reconfigurable parts are based on FPGA technology (the only sensible way of doing it), but they've created a whole new dataflow computing engine with that RC resource, and it's the latter that's interesting for computing people, not the FPGA itself nor the internal RC mechanism.
Re:Motorola annoucment (Score:1)
Pointer to new thread on PACT/XPP (Score:2)
Re:yes, sir (Score:1)
Oh yeah, and it's not like I've got much choice. My wife watches it (for obvious reasons, I feel so inadequate), and wants me to watch it with her (I don't think it's working, I'm still fat and lazy).
Re:Mini Watts?!? (Score:1)
Not as simple as that, there are extra details... (Score:1)
It does reduce the contention some, make the board easier to design, but to make best use of this on a dual processor board, you should have two independent PCI busses and two independent memory banks.
Re:Meanwhile, in the exclusive Wintel Clubhouse... (Score:1)
Ya think? I like the idea of MS running scared
IA64 has had a large push corporation wise for Linux support, does Hammer have anyone besides AMD pushing for Linux support?
-Nathan
Re:Wow (Score:1)
XPU128 EXTREME PERFORMANCE
51.2 Peak GigaOps (32 bit)
12.8 Peak GigaMACS (32 bit)
6.4 GigaByte/sec I/O bandwidth
3.2 GigaByte/sec external memory bandwidth
12.8 GigaByte/sec internal memory bandwidth
The core of the XPU128 is an array of 128
parallel Processing Array Elements (PAEs)
implemented in advanced, reprogrammable technology. Each PAE performs high-speed 32-bit
arithmetic signed and unsigned operations that execute in a single clock cycle.
Cut
n pasted..
It also handles clock cycles for you and handles all the syncing there, and had quite a few other things that made it seem rather impressive for running at 100 mhz and posting those kind of stats..... Imagine this thing as fast as some of todays processors..
Jeremy
GHz+ SOI G4 from Moto (Score:1)
Check this [chipanalyst.com] out. (Scroll down to the middle of the "PC Processors" session.)
Pretty interesting for us PPC-heads....
Re:iDragon - wowzers! (Score:1)
Aparrently the thing can also do DSP with low power consumption.
Maybe a super badass MP3 and video playing handheld is not that far away after all.
Re:SMP Athlons (Score:2)