Slashdot Mirror
AMD Desktops Outsell Intel
prostoalex writes "For the week ending August 21st AMD managed to capture 54% market share among new desktops sold. Intel's share during the week was 45%. While Intel leads the U.S. CPU market with 82.7% market share, folks from AMD are proud to announce this is the second week this year - they also outsold Intel on the desktop market one time in April 2004."
I'm not sure I buy this. Maybe for enthusiast and home gaming PCs, but if you include business desktops I'd venture to say that Intel still carries somewhere around 75%. Go look at the business-oriented desktop lines from HP, IBM and Dell and you'll see very few AMDs in there.
Better go whip them Euro-Dell's, no Intel? First the stick, _then_ the carrot.
I'm actually amazed that quality can win over brand. Maybe there's hope, after all.
Duboise continues: "promotions continue to be the driving force behind retail PC sales and AMD's successes. In fact, $699 notebook promotions have been the driving force behind three incidents this year when notebook sales were able to overcome desktop sales. As long as Intel continues to place more emphasis on the more lucrative and successful notebook market, it leaves the door open for AMD's desktop wins."
I wonder if they believe that they can eventually drive notebook sales upward to the point that they outsell Intel more often than a handful of times a year?
Cheers,
Erick
http://www.busyweather.com/
First ATI outsold Nvidia on desktops, and now this! Good to see theres not a monopoly on core hardware components! now if only software were the same way, :\
I was an ardent fan of intel until the Athlon 64 came out. My brothers new PC has an Athlon 64 along with other goodies (1gig ram, dual layer dvd writer...) for a very reasonable $1,000 USD.
There is no way I could have done that with an intel chip and motherboard and still get the same performance.
What could possibly go wrong?
If you can't beat 'em, change games.
Are you listening?
"It's the height of ridiculousness to say for those 9 lines you get hundreds of millions."
Does AMD have any Hyper-Threading-like technologies in their chips or in the works?
It's such a high bang-for-your-buck optimization that I'd feel a lot more comfortable buying AMD chips if I knew they weren't hobbled by not exploiting it.
I'd be really stoked if they started maintaining an extra execution context internally, but use it for speculative execution. Sair got some pretty impressive results doing that, and single-threaded apps actually stand to benefit from that application of the technology.
-Scott
The thing about monopolies is that, as in a business sense, it's the equivilent of launching the space shuttle at the end of Civilisation - you win, you achieved the ultimate goal, and every company wants to be in that place.
Therefore, behind a monopoly, there's always another monopoly watching and waiting in the shadows, looking to take over from the popular and dominant market force. For example:
Microsoft (Apple)
Intel (AMD)
Nvidia (ATI)
iTunes (Napster)
IBM (Sun)
Gnome (KDE)
They'll tell you that they wouldn't ever want to be a monopoly, but it's poppycock - the whole principles of business are based on monopoly.
Sunday you're Thinking Different, Monday you're a huge tool, paying too much and waiting to think like everyone else.
AMD is going HT one better by putting two Athlon 64 cores on one die next year. Much better performance bump than HT provides in a single processor core.
"It's the height of ridiculousness to say for those 9 lines you get hundreds of millions."
Uh, a theoretical 4-fold speed increase isn't anything to laugh at. Ask AMD, Intel, and IBM if they'd like to have a new idea in microprocessor design that had a theoretical 4-fold speed increase, and I'm sure they'd all say: "Yes."
I feel bad for Intel and HP though. Sunk quite a bit into making sure Linux could run on the Itanium from the very start, getting little for it. Really, the Itanium and Opteron are like apples and oranges.
One major problem is gcc. GCC just can't handle EPIC stuff yet. The compiler from Microsoft, Intel and HP are quite a bit much better than gcc. But gcc is the defacto complier in Linuxland, like it or not. (Even though Intel's x86 compiler for linux can do better too).
Their processors aren't as fast as Intel's but for the price, they're so much better. If a $500 AMD processor is almost as fast as a $800 Intel processor, that $300 buys an iPod. Most of the people I know share that view. So what if a 3.8Ghz Xeon performs better than a Athlon64 3800, the Athlon is $300 cheaper!
Click here or a puppy gets stomped!
At work we have both AMD and Intel hardware, but I tell you, we will buy only AMD from now on. It works as good for us (servers & workstations), and they're cheaper.
Ummm...
Last time I checked I used AMD for pro audio applications. In fact, I've won more awards than many other audio producers I know (not that it has anything to do with AMD... or doesn't or whatever). My 700 mhz PC worked fine. I still use a 1.2 GHZ AMD PC as well too. I've done some corporate video work on both PCs as well.
Unless Intel gets better and cheaper, I'll be sticking with AMD.
Honestly, I just built a desktop and didn't even consider Intel processors. It seemed that all the boards I wanted were AMD.
Coincidence?
It's embarrassing when a company makes a mobile chip, that at 1.6GHz outperforms their "desktop" 2.8GHz chip, especially if 1.6GHz chip uses their previous generation core with bits and pieces of P4 core thrown in for compatibility. I just hope they pull their heads out of their butts and release a replacement for "fast but dumb" P4. And for the love of god, someone tell them to make this replacement 64 bit. There's no point in denying that 4GB of address space is no longer "enough for everybody".
With that many digits after the dot, what number system are you using? That could be either 10 GHz or 10 Mhz, depending on what kind of audience is viewing...
I'd like them to make a dual core Pentium M, add the latest SSE stuff (SSE3?), an on-die, dual channel memory controller, a HyperTransport bus, and sell it for the desktop crowd.
Is that too much to ask? *sigh*
I have an N2U400A from ECS. It is a cheap ass mobo, but when I get it installed and running I was surprised at how sweet the NForce 2 Ultra chipset is. Fast, and I do mean FAST and stable. I put some stress on my system. I'll run the distributed.net client in the background, while I have a VPN connection open to the database server, I'll be importing records into that database, A VNC session running, and all while while playing Counter Strike in the foreground. System stays smooth and responsive.
Via needs to change something, because the NForce chipset is kicking ass all over their offerings for only a few dollars more.
I was kind of wary when I heard that NVidia was releasing a mobo chipset, I thought that since they were a "video card" company that they wouldn't be able to make a good chipset. I am so glad I was wrong. Now, I'd like to see what ATI can do.
LK
"Hi. This is my friend, Jack Shit, and you don't know him." - Lord Kano
Funny, I've never had the problems you've described short of bad configs or bad boards. Shall we cite chapter and verse of Intel's mistakes lately? WE don't even have to talk about direct mistakes. The 810/815 series isn't exactly what I would call 'stable'. All things being equal there are ALWAYS cheaper alternatives that aren't quite as stable from Intel, VIA, SiS, and Nvidia. That's why you plan to get the better ones when stability is a must.
Last week I purchased a NEO2 board (NFORCE 3) and a 3800+ Athlon 64. It TOTALLY rules. Know what else? I do video and 3D rendering - a LOT of it. I have it OC'd about 5% so far too. No lockups. No 'crackles' from the Audigy. Everything is cool and I can't believe how frigging CHEAP it was!
"...Well, there's egg and bacon; egg sausage and bacon; egg and spam; egg bacon and spam; egg bacon sausage and spam..."
Uh, this is a VERY well known problem with Via 686B Southbridges (among others) and Creative labs soundcards. Neither company knows how to follow the PCI 2.0 or 2.1 spec and so burst data transfers done by the sound card are corrupted. Some Firewire cards also have problems transfering to the iPod for the same reason. The problems were enough to put me off VIA permenantly. I now use SiS chipsets for my AMD systems and have had no problems (I don't need any of the expensive integrated stuff from a NForce board).
There are 4 boxes to use in the defense of liberty: soap, ballot, jury, ammo. Use in that order. Starting now.
I posted in a reply that doesn't appear to be getting modded up, so:
The figures for Intel's total share are worldwide, not US. (I should know, my company is the source cited in the link.) Meanwhile the AMD weekly share data (from another company) is for US Retail system sales. So the two data points really aren't comparable on any basis.
I know the figures I cite are exclusive to x86 CPUs. Someone mentioned PowerPC in this thread, and Apple provides sales figures as part of their financials -- based on Q2 data, PowerPCs in Apples comprise about 1.8% of the market if you included them in the calculations.
As I understand it (which may be fulla holes) the N/S bridge chipset matters a lot. Professional audio apps are notorious for having problems on the PC platform and the problem is that the PC platform was not designed with realtime (or even psuedo realtime) constraints in mind.
Even if you have a pro audio card that does a/d conversion, the data still has to get from the card to HDD fast enough. The system is probably way more than fast enough on average, but you get pops anyway if some other process keeps the cpu busy long enough for a buffer somewhere to fill up.
The chipset is key because audio is much more i/o intensive than compute intensive. So, the bottlenecks are definitely on the i/o bus (or maybe memory bus? I dunno.). I would guess that any pro audio app will have code that's been hand tuned to work with the patterns of latency typical in intel hardware.
But still, cheers to AMD for kicking some flabby, complacent, celeron-crippling, market-segmenting, mhz-is-everything intel ass.
-chris
-cbare
Very true. Also, Intels seem to be more vulnerable to the dreaded P4 denormalisation behaviour (whereby many older plugins cause massive cpu spikes when not being used), which is a Very Bad Thing for audio work.
I remember building a Z80 single board computer when pursuing my electronics degree.
The Z80 CPU was so stable that we could actually hook a potentiometer up to the timing circuit and scroll the system clock speed up or down and it just went on about its business of running happily. As I recall, it maxed out about 1 megahertz, but you could reduce it way down without trouble.
Heck, isn't it slower clock-for-clock than the PIII?
The grandparent post mentioned Pentium M, but Pentium III counts as Pentium M is true successor to the P6 (Pentium Pro, II & III) heritage, but with a FSB speed (400MHz vs 133). They have larger caches available as affordable consumer chips, 1MB & 2MB are available in Pentium M when those were available in PII, PIII Xeon, but not cheap.
All iterations of Pentium IV (Willamette, Northwood, Prescott) have a lower IPC than Pentium III.
Not that I think IPC is a useful measure on its own, much like GHz is not a useful figure on its own. I really didn't see that lower IPC was necessarily a negative when the increase GHz more than made up for it, which it did for two or three years, except for a brief period when 1GHz was the latest, it wasn't until Athlon64 did AMD match or beat Intel's performance at the top end. Up until then, AMD's selling point was mostly the more affordabe midrange. Now, AMD has the top end, the midrange and price.
Smaller engine=less area=less heat.
That rule would seem to be inverted for CPUS.
Actually, it's not.
Power consumption in CPUs is dictated by clock speed, die size, and feature size (90nm, 130nm, 180nm, etc.).
If you were to take the old Pentium II design, and re-engineer it for the modern 90nm process (or better yet, the upcoming 65nm), you'd be able to shrink it down to a smaller die size. This would yield both a smaller physical chip (which would be cheaper to produce because it's using less silicon), and lower power consumption, assuming you ran it at the same 300 MHz or so that the old P2s ran at.
The problem is that chip companies and consumers don't care about lower power consumption; they want faster performance, or more precisely, they want bigger numbers so they can brag to their friends and feel like they're doing better than the Joneses. So while going to smaller feature sizes helps reduce power consumption, going to a higher clock speed more than makes up for it, so the actual power consumption is continually rising.
Even worse, with transistors becoming ever smaller, the heat they produce is being concentrated into smaller regions, which causes localized heat problems on the chip, necessitating more engineering solutions to keep those areas from overheating. If you look at a thermal map of a CPU in operation, you'll see that a very small part of the CPU is generating the majority of the heat--the ALU and execution units, which are constantly utilized, produce most of the heat, while the SRAM cache produces very little even though it probably accounts for a majority of the die real estate.
For plain GHz monsters, AMD simply is the better price/performance deal. Now lets look at the situation from a different angle. Intel has a kick ass processor in their line. Yes the Pentium-M faster than most except the high end P4s only sold in servers and laptop computers. Outside of the US there is a huge market for machines which save energy (well in the US nobody thinks about energy, except for a god given right to be consumed probably) But the market currently is dominated by the rather measly VIA CPUs which have a huge following over here in Europe (and probably Asia) Well AMD currently reacts to the trend with their own line of new fast energy savers (which we will see probably in desktop boards soon, but definitely not from via :-) )
Via currently sells boatloads of their C3 stuff, and Transmeta probably would also if their stuff was available.
So where is Intel in that game. Basically nowhere, Intel itself says this is a notebook processor only.
Some third companies already produce industrial boards because the advantages of the PM over other intel designs are huge, blazingly fast, with a rather low power consumption. But those boards cost a fortune.
But the end user market is left to VIA. What happens here is basically the same thing Intel did in the 64 bit market, which basically was handed over to AMD. And if AMD can get their act together and have several companies producing boards in the ATX format using their new low powere cores, they basically will win the slowly but rapidly emerging home server market, which currently is a hobbyists market, but in a few years will become the mass market.