BM Seer Unofficial thoughts from an anonymous Sun employee

Sun SPARC Enterprise M9000 tops 1 TFLOP/s - twice as fast as IBM p595

Tuesday Apr 17, 2007

The Sun SPARC Enterprise M9000 outperforms the best published single system from IBM p5 595 (1.9GHz POWER5) by over 2X on the Linpack benchmark (Highly Parallel Computing). The Sun SPARC Enterprise M9000 also tops the high-end single-system Itanium 2 based system from HP (Superdome, 1.6GHz/24MB) by 38% on the Linpack.

Of the 3 vendors Sun, IBM and HP, only Sun can deliver over a TFLOP/s of performance in a single system on the Linpack HPC benchmark. (IBM, POWER5-based systems).

This benchmark also used the Sun Performance Library which as many routines important to scientific users. This library has been enhanced to take advantage of the SPARC64 VI architecture.

LINPACK HPC Performance - GFLOPS (bigger is better)

System GFLOPS Processors
Total Peak Threads CPUs Type GHz
Sun SPARC Enterprise M9000 1032.0 1228.8 128 64 SPARC64 VI 2.4
HP Superdome 745.5 819.2 128 64 Itanium 2 1.6
IBM p5 595 418.0 486.4 64 32 POWER5+ 1.9

Benchmark Description

The Linpack benchmark suite measures the performance for factoring and solving a dense set of linear equations in double-precision floating-point.

The Linpack HPC benchmark allows the solution of any size matrix with a single right hand side. It was developed to allow vendors to show off their hardware. Because big problems allow for peak performance potentials, the benchmark is seen as an upper bound of potential performance of a machine. The run rules are much more flexible. The solution technique must use a pivoting scheme and the driver must follow the spirit of the Linpack 1000 or Linpack 100 benchmarks.

Disclosure Statement:

Linpack HPC, results from http://www.netlib.org/benchmark/index.html as of 04/13/07. Sun SPARC Enterprise M9000 (SPARC64 VI @2.4, 64 chips, 128 cores), 1.032 TFLOPS. IBM p5 595 (POWER5 1.9GHz, 32 chips, 64 cores) 418.0 GFLOPS. HP Superdome (Itanium 2 1.6GHz/24MB, 64 chips, 128 cores) 745.5 GFLOPS.

System Configuration

  • Sun SPARC Enterprise M9000
  • 64 x 2.4 GHz SPARC64 VI processors
  • 1 TB memory
  • Solaris 10
  • Sun Studio 12

    • [5] Comments
    Like this post? del.icio.us | furl | slashdot | technorati | digg
    Posted at 01:50PM Apr 17, 2007 in Benchmarks
    Tags:
    Comments:

    So, uh, a box with the double of cores than the IBM and running at more Ghz wins? The surprise would be that it wasn't faster. I know benchmarks are usually biased, but this is stupid.

    Posted by Diego Calleja on April 17, 2007 at 02:56 PM PDT #

    Just show the price of the machines, that'll put Diego's mind at ease.

    Posted by Diego's older brother on April 17, 2007 at 03:32 PM PDT #

    IBM systems cost a lot per core!

    Don't think systems with the same number of cores cost anywhere near the same.

    Posted by BM Seer on April 17, 2007 at 04:06 PM PDT #

    If this were Slashdot, I would have to say: "Imagine a Beowulf cluster of these!"

    As for the comment by Diego, yes the M9000 has twice the cores, but it also has more than twice the performance.

    Sun should have run this benchmark on the 32-socket M9000 as well.

    One more thing. 2.4 GHz? IBM's fastest is 2.3 GHz. Itanium is 1.6 GHz. That makes the SPARC64-VI the fastest enterprise RISC processor on the market.

    Posted by Mark on April 17, 2007 at 04:25 PM PDT #

    Yup, for the same area (of chip silicon), you can build a very complex core, or you can build a simpler multicore processors. Or put it another way, you can build a simpler processor that has a smaller area than a complex one.

    So price is the most important thing to look at.

    And besides, I don't think other systems have the kind of fault isolation feature:

    • memory patrol
    • memory chipkill
    • memory mirroring
    • CPU data path intrgrity with autonomous error recovery
    • redundant everything

    Those are mainframe class reliability, but traditional mainframes are slow.

    Posted by Rayson on April 18, 2007 at 07:10 AM PDT #

    Post a Comment:
    Comments are closed for this entry.