home *** CD-ROM | disk | FTP | other *** search
/ Executor 2.0 / executorv2.0.iso / pc / dos / extra / docs / maillist / text / archive.95 / text7110.txt < prev    next >
Encoding:
Internet Message Format  |  1996-03-31  |  2.8 KB
  1. Date: Fri, 24 Nov 1995 00:31:38 -0600 (CST)
  2. From: "Jeffrey A. Halverson" <jeff@Ika.umn.edu>
  3. Reply-To: halv0019@gold.tc.umn.edu
  4. To: executor@nacm.com
  5. Subject: Executor on Xaccel & XFree
  6. Message-ID: <Pine.LNX.3.91.951124001537.205A-100000@Ika.umn.edu>
  7. MIME-Version: 1.0
  8. Content-Type: TEXT/PLAIN; charset=US-ASCII
  9. Sender: owner-paper@nacm.com
  10. Precedence: bulk
  11.  
  12. Hello,
  13.  
  14. I thought Linux users might be interested in the following benchmarking 
  15. that I did on my system.  I ran speedometer under the standard 
  16. XFree3.1.2, then under the exact same configuration I ran it under 
  17. Xinside's Xaccel...  Here's what I found:
  18.  
  19.  
  20. ===========P.R. Results:
  21.                               Xaccel                          XFree
  22. CPU:                          8.606                           6.628
  23. Graphics:                     2.014                           1.682
  24. Disk:                         1.576                           1.462
  25. Math:                        22.401                          17.339
  26. Performance Rating (OLD PR):  6.602                           5.182
  27. Performance Rating (NEW PR):  3.060                           2.623
  28.  
  29.  
  30. ==========Benchmark Results:
  31.  
  32. KWhetstones:        384.615  52.687                 319.148  43.719 
  33. Dhrystones:        4942.339   5.072                4255.319   4.367
  34. Towers:                       8.432                           7.898
  35. Quicksort:                    7.253                           7.923
  36. BubbleSort:                   8.901                          11.250
  37. Queens:                      10.177                          11.170
  38. Puzzle:                      13.659                          14.095
  39. Permutations:                 8.191                           6.792
  40. FastFourier:                 17.952                          13.571
  41. F.P.MatrixMultiply:          19.192                          13.571
  42. IntegerMatrixMultiply:       11.445                           8.822
  43. Sieve:                       17.467                          13.069
  44.                              ======                          ====== 
  45. Benchmark Average:           15.036                          12.973
  46.         
  47.  
  48. ==========ColorTests
  49.  
  50. Black & White:                 .537                            .449
  51. 4 Colors:                      .730                            .574
  52. 16 Colors:                     .774                            .647
  53. 256 Colors:                    .719                            .624
  54.                                ====                            ====
  55. Color Average:                 .690                            .574
  56.  
  57.  
  58. What I thought was particularly interesting was that calculations seem to 
  59. actually speed up with AccelX also.  Why is this?  I was expecting those 
  60. to stay constant, but only have the video-related tests to improve...  
  61. Can anyone explain this odd phenomena?
  62.  
  63. Jeff
  64.  
  65.