|
From: <sv...@va...> - 2005-11-18 21:19:49
|
Author: sewardj
Date: 2005-11-18 21:19:46 +0000 (Fri, 18 Nov 2005)
New Revision: 5198
Log:
Document PPC32 FP limitations.
Modified:
trunk/docs/xml/manual-core.xml
Modified: trunk/docs/xml/manual-core.xml
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D
--- trunk/docs/xml/manual-core.xml 2005-11-18 21:12:52 UTC (rev 5197)
+++ trunk/docs/xml/manual-core.xml 2005-11-18 21:19:46 UTC (rev 5198)
@@ -1669,8 +1669,8 @@
=20
<listitem>
<para>As of version 3.0.0, Valgrind has the following limitations
- in its implementation of floating point relative to the IEEE754 stand=
ard.
- </para>
+ in its implementation of x86/AMD64 floating point relative to=20
+ the IEEE754 standard.</para>
=20
<para>Precision: There is no support for 80 bit arithmetic.
Internally, Valgrind represents all such "long double"
@@ -1741,6 +1741,19 @@
can warn about, attempts to enable either mode.</para>
</listitem>
=20
+ <listitem>
+ <para>As of version 3.1.0, Valgrind has the following limitations
+ in its implementation of PPC32 FP arithmetic, both scalar and
+ Altivec.</para>
+
+ <para>Scalar: essentially as with x86/AMD64: no exceptions,=20
+ and limited observance of rounding mode. For Altivec, FP arithmetic
+ is done in IEEE/Java mode, which is more accurate than the Linux defa=
ult
+ setting. "More accurate" means that denormals are handled properly,=20
+ rather than simply being flushed to zero.
+ </para>
+ </listitem>
+
</itemizedlist>
=20
=20
|