Add packed unsigned saturated subtraction routines

git-svn-id: svn://mattst88.com/svn/alpha_mmintrin/trunk@4 f7d56953-e76f-4e43-a77e-20d50f6c004e

1 files changed, 14 insertions, 0 deletions

diff --git a/alpha_mmintrin.h b/alpha_mmintrin.h
index 34a2b63..525f04d 100644
--- a/alpha_mmintrin.h
+++ b/alpha_mmintrin.h
@@ -70,6 +70,20 @@ __addusw4(uint64_t m1, uint64_t m2) {
 	return m1 + __minuw4(m2, ~m1);
 }
 
+/* Subtract the 8-bit values in M1 to the 8-bit values in M2 using unsigned
+ * saturated arithmetic (psubusb) */
+static __inline uint64_t
+__subusb8(uint64_t m1, uint64_t m2) {
+	return m1 - __minub8(m2, m1);
+}
+
+/* Subtract the 16-bit values in M1 to the 16-bit values in M2 using unsigned
+ * saturating arithmetic (psubusw) */
+static __inline uint64_t
+__subusw4(uint64_t m1, uint64_t m2) {
+	return m1 - __minuw4(m2, m1);
+}
+
 /* Multiply four 16-bit values in M1 by four 16-bit values in M2 and produce
    the low 16 bits of the results (pmullw).  */
 static __inline uint64_t