Sun Considers Opteron

Sanjay writes "Official from Sun spokesman. Sun is considering using AMD's Opteron chip in a server it expects to deliver to the market shortly. Intead of fighting Win of Wintel (like Redhat is doing), Sun can choose to fight both with Linux AMD's servers and also fight with HP/IBM as Itanium is anyway a non starter. Sun can rise again! "

Comments

CNET covers the story too

[yerricde]

and Slashdot has covered CNET's story

Re:Dupe, I think.

[barzok]

As I read it, the "dupe" was an unofficial speculation. This sounds as though Sun has made an official statement that the speculation was correct.

Not a complete dupe...

[phoebus1553]

... It's a new story, and one that actually confirms that they ARE using AMD for something. The first one was saying 'don't count on it, but it might happen'.

So it's only a dupe in general topic, but if that's a true dupe, then everything that says 'New hole found in MS software' should also be a dupe.

The Sun is Setting

[Anonymous Coward]

Check out the SPEC web site. The performance of Sun's SPARC processors is pathetic. Sun is forced to migrate to the x86 instruction-set architecture (ISA). Sun is forced to use Opteron or Xeon. The irony is that the Opteron, the descendant of the lowly 4-bit 4004 traffic-light controller, beats the pants off of the UltraSPARC.

The problem for Sun is that Linux on Opteron does not give Sun much in the way of profits because the profit margin is low and competition is fierce. Sun cannot compete against IBM and HP in this area. Worse, Sun has no services organization to make any money by helping its customers to use Linux on Opteron.

Anyhow remember that stupid comment by Scott McNealy, who claimed that Sun is a one system -- one OS and one processor -- company. Now, Sun is distributing 2 OSes and 2 processors. Read the article at the Economist web site . It says that Sun will lose out big time in the Linux marketplace.

The Sun is setting. Good Riddance.

Re:The Sun is Setting

[Waffle Iron]

The irony is that the Opteron, the descendant of the lowly 4-bit 4004 traffic-light controller, beats the pants off of the UltraSPARC.

I looked this into this topic a while ago out of curiousity. X86's are actually descendants of the Intel 8008 microcontroller, not the 4004. Today's x86 chips are still assembly-source compatible with the 8008 (not binary compatible; there were automatic tools available to convert 8008 source to 8080 source, for example).

Even though the 4004 was the first microprocessor on the market, the 8008 design was started at Intel prior to the 4004. However, that project was put on the back burner before the 4004 was developed. After the 4004 design was finished, work resumed on the 8008. The 8-bit 8008 and 4-bit 4004 CPUs were not source or binary compatible with each other. (Here is some more info.)

Re:The Sun is Setting

[pmz]

Check out the SPEC web site [spec.org]. The performance of Sun's SPARC processors is pathetic.

SPECint-for-SPECint, UltraSPARC has lagged in single-CPU performance for several years, now. This is not news to anyone. However, Sun clearly out-classes x86 in SMP. Sun actually competes very well on the throughput-based benchmarks. If you look slightly past the SPECint2000, you'll see the SPECrate benchmarks and things like TPC. Sun regulary makes press releases about world records for throughput (leap-frogging with people like IBM, HP, and SGI, etc.). Even in small SMP configs with 2 CPUs, 1GHz UltraSPARCs will easily match Pentium 4 of well over twice the clock for floating-point throughput. Throughput is more important for large simulations and other big tasks.

Don't forget that the Pentium 4, for example, focuses on marketing buzz. Theoretical benchmark this, theoretical bandwidth that, etc. without divulging the inherent limitation in the PC architecture (one AGP slot, non-linear SMP scaling, memory limit hacks, high power consumption, you name it).

Re:difference from a PC

[chill]

You've GOT to be kidding? If you were running desktops or small workstations, maybe. But, servers?!

Ever hot swap a CPU on a SMP PC? How about adding a CPU or RAM module without powering down? Hot sawp PCI? How about 4-way machines scalable to 64-way? 64+ Gb of RAM? Terabytes of storage?

PCs are only starting to be able to compete in that market, which is why Sun, IBM, and HP still sell those types of machines.

If you don't need those types of options, then PCs are fine.

Re:Dupe, I think.

[glitchvern]

You're suppose to email the editor who posted it. In this case malda@slashdot.org.

AMD Chip

[HedRat]

Sun plans to use them in inexpensive blade servers which means they aren't totally abandoning RISC servers.

You're parked in the dark alone with your girl when she suddenly introduces you to Tammy and Buffy. "Girls Who Name Their Breasts" on the next Geraldo.

Ultra Sparc IIIi ready to roll

[Asdex]

Sun is now offering UltraSparc IIIi processors:
http://www.sun.com/processors/UltraSPARC-IIIi/

They do have some similarities to AMD's opteron processor:
- 1 MB on-chip L2 cache
- integrated memory controller
- 128bit DDR Ram
- large L1 cache

It should be interesting to compare those two processors.

Sun is not so slow as you think

[AShuvalov]

Check out the SAP benchmark site: http://www.sap.com/benchmark/index.asp 1. Sun is the fastest computer available: Sun Fire 15000, 104-way SMP, UltraSPARC III, 1200 MHz, 8 MB L2 cache, score is 8000 2. If you divide the score by the amount of processors: 8000/104 = 76.9 compare with : IBM eServer xSeries 440 Model 8687-38X, 16-way SMP, Intel Xeon MP 2.0 GHz, 256 kB L2 cache, score 1090 score per cpu: 1090/16 = 68.1 So, even per-cpu basis, trivial UltraSparc III is faster that P4 Xeon 2.0 Ghz. Want to compare with Itanium? NEC Express5800, 1000series Highend Server, 32-way SMP, Itanium2, 1.0 GHz, 3MB L3 cache, score 2750. Per cpu: 2750/32 = 85 Ups! Super-duper Itanium with 3 (!!) Mb of cache is just a little bit faster.

Sun performs much better you may think

[AShuvalov]

Check out the SAP benchmark site: http://www.sap.com/benchmark/index.asp

1. Sun is the fastest computer available:
Sun Fire 15000, 104-way SMP, UltraSPARC III, 1200 MHz, 8 MB L2 cache, score is 8000

2. If you divide the score by the amount of processors: 8000/104 = 76.9

compare with :
IBM eServer xSeries 440 Model 8687-38X, 16-way SMP, Intel Xeon MP 2.0 GHz, 256 kB L2 cache, score 1090

score per cpu: 1090/16 = 68.1

So, even per-cpu basis, trivial UltraSparc III is faster that P4 Xeon 2.0 Ghz.

Want to compare with Itanium?

NEC Express5800, 1000series Highend Server, 32-way SMP, Itanium2, 1.0 GHz, 3MB L3 cache, score 2750.

Per cpu: 2750/32 = 85

Ups! Super-duper Itanium with 3 (!!) Mb of cache is just a little bit faster.

So, you need to consult real benchmarks, SPECint is just interesting exersise, which should not be taking into account for anything above 2-way servers.

More SPARC fud!

[MrPerfekt]

For those of you bitching that sun4u sucks and yada yada, I'm willing to bet you have never seen anything bigger than an Ultra 10.

Sun Fires are massive boxes. Will all the options that PC's could only dream about: System partitioning, Hot swap _everything_, killer backplane speeds (quad-port fast ethernet cards anyone?)..

True the lone UltraSPARC processor is fairly unimpressive, but in an E12K you can have up to 256 of them if I recall. That's on one single, operating system. So take your silly 48-node Athlon clusters and go home.

Just trying to come to the defense of an arch that really isn't bad when you're not trying to run Lunix on it and play games with WineX.