BM Seer Unofficial thoughts from an anonymous Sun employee

update: Solaris beating Linux Performance

Wednesday Jan 03, 2007

(Update with corrections of previous entry)

Sun Fire X4100/X4200M2 4-thread 2-socket World Record, shows that Solaris 10 and Sun Studio 11 are faster than Opterons running Linux (31% faster than PGI and 8% faster than Pathscale compilers). The Sun Fire X4100/X4200M2 two-way dual-core server produced best SPECompM2001 result of 13222.

Sun Solaris 10/Studio11 was 31% faster than Linux/PGI with AMD Tyan system using SuSE Linux SLES9 SP3 64-bit/PGI 6.2-4. The AMD Tyan even used faster CL4 DIMMs. Both results submitted Nov 2006. The Sun Fire X4100/X4200M2 also topped the IBM p5 520 POWER5+ 1.9GHz AIX5L V5.3 result by 61%.

Solaris/Studio 11 is 8% faster than Linux SuSE SLES9 SP3 64bit using QLogic PathScale Compiler Suite v2.5.

There is a growing body of favorable comparisons showing Solaris advantages over Linux on performance. Remember the previous BM Seer posting on Java performance.

Even more examples of Solaris beating Linux coming soon.

SPECompM2001 Results (bigger is better)
SPECompM2001 Cores Chips Thrds System
13222 4 2 4 Sun Fire X4100/X4200 M2, Opteron 2220SE, 2.8GHz
12574 4 2 4 Sun Fire X2200 M2, Opteron 2218, 2.6GHz
12172 4 2 4 AMD Tyan n6650w, Opteron 8220, 2.8GHz
10085 4 2 4 AMD Tyan n6650w, Opteron 8220, 2.8GHz
8174 2 1 4 IBM System p5 520 (1900 MHz, 2 CPU)

Benchmark Description

The SPEC OMPM2001 Benchmark Suite was released in June 2001 and tests HPC performance using OpenMP for parallelism. It consists of 11 programs (8 in Fortran and 3 in C) parallelized using OpenMP API.

Goals of the benchmark:

  • Targeted to mid-range (4-32 processor) parallel systems
  • Run rules, tools and reporting similar to SPEC CPU2000
  • Programs representative of HPC and Scientific Applications

    • See Also:
    SPEC OMP2001 Page
    sun.com X4100 Benchmark Page
    sun.com X4200 Benchmark Page

    Disclosure Statement:

    SPEC, SPEComp reg tm of Standard Performance Evaluation Corporation. Results from www.spec.org Results as of Jan 2, 2007. Sun Fire X4100/X4200 M2 (4 cores, 2 chips, 4 threads), 13,222 SPECompM2001. AMD Tyan n6650w (4 cores, 2 chips, 4 threads), 10,085 SPECompM2001 PGI compiler. AMD Tyan n6650w (4 cores, 2 chips, 4 threads), 12,172 SPECompM2001 Pathscale compiler. Sockets refers to chips.

    Results Summary

      X4100/X4200 M2 4-threads: 13222 SPECompM2001
      X2200 M2 4-threads: 12574 SPECompM2001
      Reference Date: Oct 16, 2006
      System: Sun Fire X4100/X4200M2 16GB memory (4x2GB per chip), DDR667
      Processors: two Opteron 2220SE, 2.8 GHz
      Operating System: Solaris 10
      Compiler: Sun Studio 11

    [3] Comments
    Like this post? del.icio.us | furl | slashdot | technorati | digg
    Posted at 10:39AM Jan 03, 2007 in Benchmarks
    Tags:
    Comments:

    "It consists of 11 programs (8 fp and 3 int intensive) in C and Fortran parallelized using OpenMP API." Actually, I don't think this is correct. AFAIK, 10 out of 11 programs in SPEC OMP were taken from SPECfp2000, which indicates that they are fp intensive. The 11th program (326.gafort) was a candidate for SPEC CPU2000. It uses a genetic algorithm, and while I don't know any specifics, I would assume on this basis that it is fp intensive as well. The Sun SPEC OMP results are pretty impressive though - and the Sun Fire Servers beat the Woodcrest very thoroughly as well in this benchmark. In SPECfp2006, however, the Sun results are not as compelling yet. Let's see how that develops in 2007 ...

    Posted by IA-63 on January 07, 2007 at 07:35 AM PST #

    My mistake from my notes, it should be 8 fortran and 3 C. Now corrected in the text.

    ...more results coming soon.

    Posted by BM Seer on January 08, 2007 at 09:28 AM PST #

    See the last of the SPECfp2000 results in the recent posting.

    Interesting to see your focus only on SPECfp2006, what we're finding is Opteron is beating Woodcrest on many customer apps and in the real world.

    Posted by BM Seer on January 08, 2007 at 09:51 AM PST #

    Post a Comment:
    Comments are closed for this entry.