Oracle plans to talk up Sun hardware

Print Friendly, PDF & Email

We’ve been wondering aloud for months now about what might happen to Sun’s hardware once (and if, I guess) the deal finally finishes (we’re waiting on EU approval now). I really don’t see much hope for HPC hardware or software at Oracle, but what happens to the more commercial stuff is a question.

Evidently Oracle recognizes that keeping everyone guessing forever isn’t a good thing, as indicated by plummeting financials at the troubled hardware maker, and they’ve decided to talk up the database performance of their soon-to-be servers

Sun logoAccording to this teaser pre-announcement, Oracle will be doing something that Sun hasn’t done for eight years: showing off the performance of Sparc machines using the Transaction Processing Council’s TPC-C benchmark, which is used to display the oomph of database servers.

“Oracle and Sun together are hard to match,” Oracle says in the teaser. “Just ask IBM. Its fastest server now runs an impressive 6 million TPC-C transactions, but on October 14 at Oracle OpenWorld, we’ll reveal the benchmark numbers that prove that even IBM DB2 running on IBM’s fastest hardware can’t match the speed and performance of Oracle Database on Sun systems. Check back on October 14 as we demonstrate Oracle’s commitment to Sun hardware and Sun Sparc.”

If they are targeting IBM they are aiming at the company’s POWER line, which is of course also used in one of IBM’s supercomputing products. That said, I’m still not moved to believe that HPC at Sun will survive the acquisition. It might be pretty happy at HP, however, given that that company’s HPC business has been very (very) quiet over the past 8 months or so.


  1. […] as John West pointed out yesterday, Oracle realizes that they have to say something … anything at this point … about the […]


  1. I was wondering about this – given Sun’s announcements about Rainbow Falls at Hotchips, they could be planning a large SSI box, which could of course then be clustered with RAC. With the inherently high I/O capabilities of Niagara, they could push some serious numbers with a solution like that.
    More speculation over at
    The key for me is how close Rainbow Falls is to being an actual product, capable of being benchmarked. If it’s close as Rock was, they could pull it off.