Revision: 53843
http://brlcad.svn.sourceforge.net/brlcad/?rev=53843&view=rev
Author: brlcad
Date: 2012-11-28 00:19:59 +0000 (Wed, 28 Nov 2012)
Log Message:
-----------
pull the comment closer to the statement that assumes 16-byte alignment
Modified Paths:
--------------
brlcad/trunk/include/vector_x86.h
Modified: brlcad/trunk/include/vector_x86.h
===================================================================
--- brlcad/trunk/include/vector_x86.h 2012-11-27 23:22:19 UTC (rev 53842)
+++ brlcad/trunk/include/vector_x86.h 2012-11-28 00:19:59 UTC (rev 53843)
@@ -62,8 +62,8 @@
template<int LEN>
inline dvec<LEN>::dvec(const float* vals)
{
- /* NOTE: assumes that vals are 16-byte aligned */
for (int i = 0; i < LEN/2; i++) {
+ /* NOTE: assumes that vals are 16-byte aligned */
data.v[i] = _mm_load_ps(&vals[i*2]);
}
}
@@ -71,8 +71,8 @@
template<int LEN>
inline dvec<LEN>::dvec(const double* vals)
{
- /* NOTE: assumes that vals are 16-byte aligned */
for (int i = 0; i < LEN/2; i++) {
+ /* NOTE: assumes that vals are 16-byte aligned */
data.v[i] = _mm_load_pd(&vals[i*2]);
}
}
This was sent by the SourceForge.net collaborative development platform, the
world's largest Open Source development site.
------------------------------------------------------------------------------
Keep yourself connected to Go Parallel:
INSIGHTS What's next for parallel hardware, programming and related areas?
Interviews and blogs by thought leaders keep you ahead of the curve.
http://goparallel.sourceforge.net
_______________________________________________
BRL-CAD Source Commits mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/brlcad-commits
