Implement SSE2 floating-point support in the x86 native code generator (#594)

[ghc-hetmet.git] / docs / users_guide / using.xml

diff --git a/docs/users_guide/using.xml b/docs/users_guide/using.xml
index 5ad34fa..329c31f 100644 (file)
--- a/docs/users_guide/using.xml
+++ b/docs/users_guide/using.xml
@@ -1667,6 +1667,26 @@ f "2"    = 2
 
        <varlistentry>
          <term>
+            <option>-fno-float-in</option>
+            <indexterm><primary><option>-fno-float-in</option></primary></indexterm>
+          </term>
+         <listitem>
+           <para>Turns off the float-in transformation.</para>
+         </listitem>
+       </varlistentry>
+
+       <varlistentry>
+         <term>
+            <option>-fno-specialise</option>
+            <indexterm><primary><option>-fno-specialise</option></primary></indexterm>
+          </term>
+         <listitem>
+           <para>Turns off the automatic specialisation of overloaded functions.</para>
+         </listitem>
+       </varlistentry>
+
+       <varlistentry>
+         <term>
             <option>-fspec-constr</option>
             <indexterm><primary><option>-fspec-constr</option></primary></indexterm>
           </term>
@@ -2054,9 +2074,27 @@ f "2"    = 2
     <variablelist>
 
       <varlistentry>
+       <term><option>-msse2</option>:</term>
+       <listitem>
+          <para>
+            (x86 only, added in GHC 6.14.1) Use the SSE2 registers and
+            instruction set to implement floating point operations
+            when using the native code generator.  This gives a
+            substantial performance improvement for floating point,
+            but the resulting compiled code will only run on
+            processors that support SSE2 (Intel Pentium 4 and later,
+            or AMD Athlon 64 and later).
+          </para>
+          <para>
+            SSE2 is unconditionally used on x86-64 platforms.
+          </para>
+        </listitem>
+      </varlistentry>
+
+      <varlistentry>
        <term><option>-monly-[32]-regs</option>:</term>
        <listitem>
-         <para>(iX86 machines)<indexterm><primary>-monly-N-regs
+         <para>(x86 only)<indexterm><primary>-monly-N-regs
           option (iX86 only)</primary></indexterm> GHC tries to
           &ldquo;steal&rdquo; four registers from GCC, for performance
           reasons; it almost always works.  However, when GCC is