added updated version of simdmathlibrary-1.0.1

Extras/simdmathlibrary/spu/simdmath/divf4.h

@@ -0,0 +1,50 @@
+/* divf4 - for each of four float slots, divide numer by denom.
+   Copyright (C) 2006, 2007 Sony Computer Entertainment Inc.
+   All rights reserved.
+
+   Redistribution and use in source and binary forms,
+   with or without modification, are permitted provided that the
+   following conditions are met:
+    * Redistributions of source code must retain the above copyright
+      notice, this list of conditions and the following disclaimer.
+    * Redistributions in binary form must reproduce the above copyright
+      notice, this list of conditions and the following disclaimer in the
+      documentation and/or other materials provided with the distribution.
+    * Neither the name of the Sony Computer Entertainment Inc nor the names
+      of its contributors may be used to endorse or promote products derived
+      from this software without specific prior written permission.
+
+   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+   AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+   IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+   ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+   LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+   CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+   SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+   INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+   CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+   ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+   POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef ___SIMD_MATH_DIVF4_H___
+#define ___SIMD_MATH_DIVF4_H___
+
+#include <simdmath.h>
+#include <spu_intrinsics.h>
+
+static inline vector float
+_divf4 (vector float numer, vector float denom)
+{
+  // Reciprocal estimate and 1 Newton-Raphson iteration.
+  // Uses constant of 1.0 + 1 ulp to improve accuracy.
+
+  vector float y0, y0numer;
+  vector float oneish = (vector float)spu_splats(0x3f800001);
+
+  y0 = spu_re( denom );
+  y0numer = spu_mul( numer, y0 );
+  return spu_madd( spu_nmsub( denom, y0, oneish ), y0numer, y0numer );
+}
+
+#endif