Linux: Use -mfpmath=sse to remove differences between opt and debug

build/SConscript.main

 # Copyright (c) 2006-2008 The Chromium Authors. All rights reserved.
 # Use of this source code is governed by a BSD-style license that can be
 # found in the LICENSE file.
 
 import os
 import shutil
 import sys
 
 
 if sys.platform == 'win32':
@@ skipping 457 matching lines @@
   '-Wno-deprecated',  # Needed for using ext/hash_map on GCC 4.3
 ]
 if not root_env.get('_GYP'):
   linux_env.Append(
     BUILD_SCONSCRIPTS = [
         '$LIBEVENT_DIR/libevent${_GYP}.scons',
     ],
   )
 linux_env.Append(
     ASFLAGS = ['-32'],
-    CCFLAGS = ['-m32', '-pthread', '-march=i686', '-fno-exceptions'],
+    CCFLAGS = ['-m32', '-pthread', '-march=pentium4', '-fno-exceptions',
+    # All floating-point computations on x87 happens in 80-bit precision.
+    # Because the C and C++ language standards allow the compiler to keep the
+    # floating-point values in higher precision than what's specified in the
+    # source and doing so is more efficient than constantly rounding up to
+    # 64-bit or 32-bit precision as specified in the source, the compiler,
+    # especially in the optimized mode, tries very hard to keep values in x87
+    # floating-point stack (in 80-bit precision) as long as possible. This has
+    # important side effects, that the real value used in computation may
+    # change depending on how the compiler did the optimization - that is, the
+    # value kept in 80-bit is different than the value rounded down to 64-bit
+    # or 32-bit. There are possible compiler options to make this behavior
+    # consistent (e.g. -ffloat-store would keep all floating-values in the
+    # memory, thus force them to be rounded to its original precision) but they
+    # have significant runtime performance penalty.
+    #
+    # -mfpmath=sse -msse2 makes the compiler use SSE instructions which keep
+    # floating-point values in SSE registers in its native precision (32-bit
+    # for single precision, and 64-bit for double precision values). This means
+    # the floating-point value used during computation does not change
+    # depending on how the compiler optimized the code, since the value is
+    # always kept in its specified precision.
+               '-msse2', '-mfpmath=sse'],
     # GCC will generate ident directives with the GCC version. Accumulate
     # these all up and you end up with ~80K repeated in a .comment section.
     CCFLAGS_OPTIMIZED = ['-fno-ident'],
     CXXFLAGS = ['-Wall', '-Werror', '-march=i686'] + excluded_warnings,
     LINKFLAGS = ['-m32', '-pthread'],
 )
 
 linux_env.Replace(
     # Linking of large files uses lots of RAM, so serialize links
     # using the handy flock command from util-linux.
@@ skipping 370 matching lines @@
         'all_libraries',
         'all_languages',
         'all_programs',
         'all_test_programs',
     ], projects = [p],
     COMPONENT_VS_PROJECT_SCRIPT_PATH=(
         'cd $$(ProjectDir)/$VS_PROJECT_TO_MAIN_DIR && hammer.bat'),
 )
 
 # -------------------------------------------------------------------------