From f4c1a4848378d035b835e9e2ca1c62f15a5982b1 Mon Sep 17 00:00:00 2001
From: James Almer <jamrial@gmail.com>
Date: Thu, 7 Jan 2016 00:31:56 -0300
Subject: [PATCH] x86/intmath: add sse optimized av_clipf and av_clipd

Reviewed-by: Michael Niedermayer <michael@niedermayer.cc>
Reviewed-by: Ronald S. Bultje <rsbultje@gmail.com>
Signed-off-by: James Almer <jamrial@gmail.com>
---
 libavutil/x86/intmath.h | 33 +++++++++++++++++++++++++++++++++
 1 file changed, 33 insertions(+)

diff --git a/libavutil/x86/intmath.h b/libavutil/x86/intmath.h
index 611ef882e9..2b2c869533 100644
--- a/libavutil/x86/intmath.h
+++ b/libavutil/x86/intmath.h
@@ -22,6 +22,7 @@
 #define AVUTIL_X86_INTMATH_H
 
 #include <stdint.h>
+#include <stdlib.h>
 #if HAVE_FAST_CLZ
 #if defined(_MSC_VER)
 #include <intrin.h>
@@ -98,6 +99,38 @@ static av_always_inline av_const unsigned av_mod_uintp2_bmi2(unsigned a, unsigne
 
 #endif /* __BMI2__ */
 
+#if defined(__SSE2__)
+
+#define av_clipd av_clipd_sse2
+static av_always_inline av_const double av_clipd_sse2(double a, double amin, double amax)
+{
+#if defined(ASSERT_LEVEL) && ASSERT_LEVEL >= 2
+    if (amin > amax) abort();
+#endif
+    __asm__ ("minsd %2, %0 \n\t"
+             "maxsd %1, %0 \n\t"
+             : "+x"(a) : "xm"(amin), "xm"(amax));
+    return a;
+}
+
+#endif /* __SSE2__ */
+
+#if defined(__SSE__)
+
+#define av_clipf av_clipf_sse
+static av_always_inline av_const float av_clipf_sse(float a, float amin, float amax)
+{
+#if defined(ASSERT_LEVEL) && ASSERT_LEVEL >= 2
+    if (amin > amax) abort();
+#endif
+    __asm__ ("minss %2, %0 \n\t"
+             "maxss %1, %0 \n\t"
+             : "+x"(a) : "xm"(amin), "xm"(amax));
+    return a;
+}
+
+#endif /* __SSE__ */
+
 #endif /* __GNUC__ */
 
 #endif /* AVUTIL_X86_INTMATH_H */