added more references and rules based on gcc's -ffast-math implementa…

…tion

Numeric/FastMath.hs

@@ -1,16 +1,18 @@
 -- | This module loads all rewrite rules.  Unless you know that some rules
 -- will be unsafe for your application, this is the module you should load.
+-- Importing this module is roughly equivalent to gcc's @-ffast-math@ 
+-- compilation flag.
 --
 -- The best way to figure out what optimizations these modules do is by 
 -- looking at the source code.  RULES pragmas are surprisingly readable.
 
 module Numeric.FastMath
     ( module Numeric.FastMath.Approximation
     , module Numeric.FastMath.NaN
-    , module Numeric.FastMath.Infinitesimal
+    , module Numeric.FastMath.SignedZeros
     )
     where
 
 import Numeric.FastMath.Approximation ()
 import Numeric.FastMath.NaN ()
-import Numeric.FastMath.Infinitesimal ()
+import Numeric.FastMath.SignedZeros ()

Numeric/FastMath/Approximation.hs

@@ -9,6 +9,9 @@
 --
 -- All of these RULES should be safe in the presence of `NaN` and `Infinity`
 --
+-- Importing this module is similar to compiling with gcc's
+-- @-funsafe-math-operations@.
+--
 module Numeric.FastMath.Approximation
     where
 

Numeric/FastMath/NaN.hs

@@ -1,18 +1,35 @@
 -- | This module contains rules that break the way NaN is handled for "Float" 
 -- and "Double" types.  Still, these rules should be safe in the vast majority of
 -- applications.
+--
+-- Importing this module is similar to compiling with gcc's @-fno-signaling-nans@
+-- and @-ffinite-math-only@.
+--
 module Numeric.FastMath.NaN
     where
 
 import GHC.Exts
 
+{-# RULES
+"minusDouble x x"   forall x. (-##) x       x           = 0.0##
+
+"timesDouble 0 x"   forall x. (*##) 0.0##   x           = 0.0##
+"timesDouble x 0"   forall x. (*##) x       0.0##       = 0.0##
+
+"divideDouble x 1"  forall x. (/##) x       1.0##       = x
+"divideDouble x -1" forall x. (/##) x       (-1.0##)    = negateDouble# x
+"divideDouble 0 x"  forall x. (/##) 0.0##   x           = 0.0##
+  #-}
+
 {-# RULES
 "minusFloat x x"    forall x. minusFloat#  x    x       = 0.0#
+
 "timesFloat x 0"    forall x. timesFloat#  x    0.0#    = 0.0#
 "timesFloat 0 x"    forall x. timesFloat#  0.0# x       = 0.0#
 
-"minusDouble x x"   forall x. (-##) x       x       = 0.0##
-"timesDouble 0 x"   forall x. (*##) 0.0##   x       = 0.0##
-"timesDouble x 0"   forall x. (*##) x       0.0##   = 0.0##
+"divideFloat x 1"   forall x. divideFloat# x       1.0#         = x
+"divideFloat x -1"  forall x. divideFloat# x       (-1.0#)      = negateFloat# x
+"divideFloat 0 x"   forall x. divideFloat# 0.0#    x            = 0.0#
+
   #-}
 

Numeric/FastMath/SignedZeros.hs

@@ -0,0 +1,24 @@
+-- | IEEE 754 math makes a distrinction between -0.0 and +0.0.  This module
+-- contains RULES that ignore this distinction.  
+--
+-- Importing this module is similar to compiling with gcc's
+-- @-fno-signed-zeros@.
+
+module Numeric.FastMath.SignedZeros () where
+
+import GHC.Exts
+
+{-# RULES
+
+"minusDouble 0 x"   forall x. (-##)         0.0##   x   = negateDouble# x
+"divideDouble 0 x"  forall x. (/##)         0.0##   x   = 0.0##
+  #-}
+
+{-# RULES
+
+"minusFloat 0 x"    forall x. minusFloat#   0.0#    x   = negateFloat# x
+"divideFloat 0 x"   forall x. divideFloat#  0.0#    x   = 0.0#
+
+  #-}
+
+

README.md

@@ -6,7 +6,7 @@ This package enables a number of "unsafe" floating point optimizations for GHC.
 x*y + x*z == z*(y+z)
 ```
 
-does not hold for `Float` or `Double` types.  The lowest order bits may be different due to rounding errors.Therefore, GHC (and most compilers for any language) will not perform this optimization by default.   Instead, most compilers support special flags that enable these unsafe optimizations.  See for example the [-ffast-math flag in the gcc documentation](https://gcc.gnu.org/onlinedocs/gcc/Optimize-Options.html).  GHC, however, has [no built in flags for these optimizations](http://www.haskell.org/ghc/docs/7.8.2/html/users_guide/flag-reference.html).  But that's okay.  GHC's `RULES` pragmas are sufficiently powerful to achieve most of the performance benefits of `-ffast-math`. This package provides those `RULES` pragmas.  
+does not hold for `Float` or `Double` types.  The lowest order bits may be different due to rounding errors.Therefore, GHC (and most compilers for any language) will not perform this optimization by default.   Instead, most compilers support special flags that enable these unsafe optimizations.  See for example the [-ffast-math flag in the gcc documentation](https://gcc.gnu.org/onlinedocs/gcc/Optimize-Options.html) and the [gcc wiki page FloatingPointMath](https://gcc.gnu.org/wiki/FloatingPointMath).  GHC, however, has [no built in flags for these optimizations](http://www.haskell.org/ghc/docs/7.8.2/html/users_guide/flag-reference.html).  But that's okay.  GHC's `RULES` pragmas are sufficiently powerful to achieve most of the performance benefits of `-ffast-math`. This package provides those `RULES` pragmas.  
 
 ### Enabling the optimizations
 

fast-math.cabal

@@ -2,14 +2,14 @@ name:           fast-math
 version:        1.0
 synopsis:       Non IEEE-754 compliant compile-time floating-point optimisations
 description:
-    The "Numeric.FastMath" module brings into scope RULES for 'Float's and
-    'Double's that rewrite @x-x@, @0*x@ and @x*0@ to @0@. This disagrees
-    with IEEE-754 when @x@ is @NaN@, but is acceptable for most
-    applications.
+    The "Numeric.FastMath" module brings into scope many unsafe @RULES@ for 
+    'Float's and 'Double's that can greatly improve run time performance.
+    It is roughly equivalent to gcc\'s @-ffast-math@ compiler flag.
+    Optimisation (at least @-O1@) must be enabled for any @RULES@ to take effect.
     .
-    Importing "Numeric.FastMath.Infinitesimal" also rewrites @0/x@ to @0@.
-    .
-    Optimisation (at least @-O1@) must be enabled for any RULES to take effect.
+    These rules are unsafe because they don't strictly adhere to the
+    IEEE-754 regulations and may subtly change the results of your numeric computations.
+    See the <http://github.com/liyang/fast-math/ README> on github for more details.
 
 license:        BSD3
 license-file:   LICENSE
@@ -31,8 +31,8 @@ library
     exposed-modules:
         Numeric.FastMath
         Numeric.FastMath.Approximation
-        Numeric.FastMath.Infinitesimal
         Numeric.FastMath.NaN
+        Numeric.FastMath.SignedZeros
     default-extensions:
         NoImplicitPrelude
         MagicHash