[lmi-commits] [lmi] master 7066049 8/8: Record speed measurements

[Greg Chicares]

branch: master
commit 7066049a9d88ca99a0957f703592973b4f27c452
Author: Gregory W. Chicares <gchicares@sbcglobal.net>
Commit: Gregory W. Chicares <gchicares@sbcglobal.net>

    Record speed measurements
    
    The last dozen commits cost an extra one or five percent for i686 and
    x86_64 respectively. Cumulative penalty compared to the last production
    release is very roughly five and ten percent respectively. Branch
    valyuta/005 is faster than this, though (particularly because it caches
    all product files), and much of it has already been ported to master.
---
 Speed_gcc_i686-w64-mingw32    | 12 ++++++------
 Speed_gcc_x86_64-pc-linux-gnu | 12 ++++++------
 Speed_gcc_x86_64-w64-mingw32  | 12 ++++++------
 3 files changed, 18 insertions(+), 18 deletions(-)

diff --git a/Speed_gcc_i686-w64-mingw32 b/Speed_gcc_i686-w64-mingw32
index 78c0496..2bc5727 100644
--- a/Speed_gcc_i686-w64-mingw32
+++ b/Speed_gcc_i686-w64-mingw32
@@ -1,7 +1,7 @@
 Test speed:
-  naic, no solve      : 5.509e-02 s mean;      53999 us least of  19 runs
-  naic, specamt solve : 1.010e-01 s mean;      97000 us least of  10 runs
-  naic, ee prem solve : 8.984e-02 s mean;      89110 us least of  12 runs
-  finra, no solve     : 2.257e-02 s mean;      22016 us least of  45 runs
-  finra, specamt solve: 6.155e-02 s mean;      60858 us least of  17 runs
-  finra, ee prem solve: 5.745e-02 s mean;      56634 us least of  18 runs
+  naic, no solve      : 5.528e-02 s mean;      55165 us least of  19 runs
+  naic, specamt solve : 1.015e-01 s mean;      97908 us least of  10 runs
+  naic, ee prem solve : 9.162e-02 s mean;      89757 us least of  11 runs
+  finra, no solve     : 2.215e-02 s mean;      22028 us least of  46 runs
+  finra, specamt solve: 6.132e-02 s mean;      61166 us least of  17 runs
+  finra, ee prem solve: 5.696e-02 s mean;      56847 us least of  18 runs
diff --git a/Speed_gcc_x86_64-pc-linux-gnu b/Speed_gcc_x86_64-pc-linux-gnu
index bf155d4..5c23840 100644
--- a/Speed_gcc_x86_64-pc-linux-gnu
+++ b/Speed_gcc_x86_64-pc-linux-gnu
@@ -1,7 +1,7 @@
 Test speed:
-  naic, no solve      : 2.059e-02 s mean;      20123 us least of  49 runs
-  naic, specamt solve : 3.542e-02 s mean;      34962 us least of  29 runs
-  naic, ee prem solve : 3.256e-02 s mean;      32208 us least of  31 runs
-  finra, no solve     : 8.059e-03 s mean;       7764 us least of 100 runs
-  finra, specamt solve: 2.173e-02 s mean;      21377 us least of  47 runs
-  finra, ee prem solve: 2.028e-02 s mean;      19877 us least of  50 runs
+  naic, no solve      : 2.178e-02 s mean;      20987 us least of  46 runs
+  naic, specamt solve : 3.889e-02 s mean;      36510 us least of  26 runs
+  naic, ee prem solve : 3.404e-02 s mean;      33501 us least of  30 runs
+  finra, no solve     : 7.953e-03 s mean;       7555 us least of 100 runs
+  finra, specamt solve: 2.237e-02 s mean;      21737 us least of  45 runs
+  finra, ee prem solve: 2.080e-02 s mean;      20081 us least of  49 runs
diff --git a/Speed_gcc_x86_64-w64-mingw32 b/Speed_gcc_x86_64-w64-mingw32
index 8178b09..950f4cb 100644
--- a/Speed_gcc_x86_64-w64-mingw32
+++ b/Speed_gcc_x86_64-w64-mingw32
@@ -1,7 +1,7 @@
 Test speed:
-  naic, no solve      : 2.886e-02 s mean;      28558 us least of  35 runs
-  naic, specamt solve : 4.584e-02 s mean;      45372 us least of  22 runs
-  naic, ee prem solve : 4.259e-02 s mean;      42151 us least of  24 runs
-  finra, no solve     : 1.496e-02 s mean;      14718 us least of  67 runs
-  finra, specamt solve: 3.061e-02 s mean;      30245 us least of  33 runs
-  finra, ee prem solve: 2.894e-02 s mean;      28568 us least of  35 runs
+  naic, no solve      : 3.023e-02 s mean;      29896 us least of  34 runs
+  naic, specamt solve : 4.808e-02 s mean;      47848 us least of  21 runs
+  naic, ee prem solve : 4.458e-02 s mean;      43719 us least of  23 runs
+  finra, no solve     : 1.515e-02 s mean;      14998 us least of  67 runs
+  finra, specamt solve: 3.133e-02 s mean;      30518 us least of  32 runs
+  finra, ee prem solve: 2.954e-02 s mean;      29373 us least of  34 runs