lavu/riscv: implement floating point clips

Unlike x86, fmin/fmax are single instructions, not function calls. They
are much much faster than doing a comparison, then branching based on its
results. With this, audiodsp.vector_clipf gets almost twice as fast, and
a properly unrollled version of it gets 4-5x faster, on SiFive-U74.
This is only the low-hanging fruit: FFMIN and FFMAX are presumably
affected as well.

This likely applies to other instruction sets with native IEEE floats,
especially those lacking a conditional select instruction.

1 files changed, 19 insertions, 0 deletions

diff --git a/libavutil/riscv/intmath.h b/libavutil/riscv/intmath.h
index 3e7ab864c5..24f165eef1 100644
--- a/libavutil/riscv/intmath.h
+++ b/libavutil/riscv/intmath.h
@@ -22,6 +22,7 @@
 #define AVUTIL_RISCV_INTMATH_H
 
 #include <stdint.h>
+#include <math.h>
 
 #include "config.h"
 #include "libavutil/attributes.h"
@@ -72,6 +73,24 @@ static av_always_inline av_const int av_clip_intp2_rvi(int a, int p)
     return b;
 }
 
+#if defined (__riscv_f) || defined (__riscv_zfinx)
+#define av_clipf av_clipf_rvf
+static av_always_inline av_const float av_clipf_rvf(float a, float min,
+                                                    float max)
+{
+    return fminf(fmaxf(a, min), max);
+}
+#endif
+
+#if defined (__riscv_d) || defined (__riscv_zdinx)
+#define av_clipd av_clipd_rvd
+static av_always_inline av_const float av_clipd_rvd(double a, double min,
+                                                    double max)
+{
+    return fmin(fmax(a, min), max);
+}
+#endif
+
 #if defined (__GNUC__) || defined (__clang__)
 static inline av_const int ff_ctz_rv(int x)
 {