>From 21ece1306d717665c03fc9a118fe17811b69ec89 Mon Sep 17 00:00:00 2001
From: Szabolcs Nagy <nsz@port70.net>
Date: Sat, 22 Sep 2018 21:43:42 +0000
Subject: [PATCH 4/5] x86_64: add single instruction fma

fma is only available on recent x86_64 cpus and it is much faster than
a software fma, so this should be done with a runtime check, however
that requires more changes, this patch just adds the code so it can be
tested when musl is compiled with -mfma or -mfma4.
---
 src/math/x32/fma.c     | 23 +++++++++++++++++++++++
 src/math/x32/fmaf.c    | 23 +++++++++++++++++++++++
 src/math/x86_64/fma.c  | 23 +++++++++++++++++++++++
 src/math/x86_64/fmaf.c | 23 +++++++++++++++++++++++
 4 files changed, 92 insertions(+)
 create mode 100644 src/math/x32/fma.c
 create mode 100644 src/math/x32/fmaf.c
 create mode 100644 src/math/x86_64/fma.c
 create mode 100644 src/math/x86_64/fmaf.c

diff --git a/src/math/x32/fma.c b/src/math/x32/fma.c
new file mode 100644
index 00000000..4dd53f2a
--- /dev/null
+++ b/src/math/x32/fma.c
@@ -0,0 +1,23 @@
+#include <math.h>
+
+#if __FMA__
+
+double fma(double x, double y, double z)
+{
+	__asm__ ("vfmadd132sd %1, %2, %0" : "+x" (x) : "x" (y), "x" (z));
+	return x;
+}
+
+#elif __FMA4__
+
+double fma(double x, double y, double z)
+{
+	__asm__ ("vfmaddsd %3, %2, %1, %0" : "=x" (x) : "x" (x), "x" (y), "x" (z));
+	return x;
+}
+
+#else
+
+#include "../fma.c"
+
+#endif
diff --git a/src/math/x32/fmaf.c b/src/math/x32/fmaf.c
new file mode 100644
index 00000000..30b971ff
--- /dev/null
+++ b/src/math/x32/fmaf.c
@@ -0,0 +1,23 @@
+#include <math.h>
+
+#if __FMA__
+
+float fmaf(float x, float y, float z)
+{
+	__asm__ ("vfmadd132ss %1, %2, %0" : "+x" (x) : "x" (y), "x" (z));
+	return x;
+}
+
+#elif __FMA4__
+
+float fmaf(float x, float y, float z)
+{
+	__asm__ ("vfmaddss %3, %2, %1, %0" : "=x" (x) : "x" (x), "x" (y), "x" (z));
+	return x;
+}
+
+#else
+
+#include "../fmaf.c"
+
+#endif
diff --git a/src/math/x86_64/fma.c b/src/math/x86_64/fma.c
new file mode 100644
index 00000000..4dd53f2a
--- /dev/null
+++ b/src/math/x86_64/fma.c
@@ -0,0 +1,23 @@
+#include <math.h>
+
+#if __FMA__
+
+double fma(double x, double y, double z)
+{
+	__asm__ ("vfmadd132sd %1, %2, %0" : "+x" (x) : "x" (y), "x" (z));
+	return x;
+}
+
+#elif __FMA4__
+
+double fma(double x, double y, double z)
+{
+	__asm__ ("vfmaddsd %3, %2, %1, %0" : "=x" (x) : "x" (x), "x" (y), "x" (z));
+	return x;
+}
+
+#else
+
+#include "../fma.c"
+
+#endif
diff --git a/src/math/x86_64/fmaf.c b/src/math/x86_64/fmaf.c
new file mode 100644
index 00000000..30b971ff
--- /dev/null
+++ b/src/math/x86_64/fmaf.c
@@ -0,0 +1,23 @@
+#include <math.h>
+
+#if __FMA__
+
+float fmaf(float x, float y, float z)
+{
+	__asm__ ("vfmadd132ss %1, %2, %0" : "+x" (x) : "x" (y), "x" (z));
+	return x;
+}
+
+#elif __FMA4__
+
+float fmaf(float x, float y, float z)
+{
+	__asm__ ("vfmaddss %3, %2, %1, %0" : "=x" (x) : "x" (x), "x" (y), "x" (z));
+	return x;
+}
+
+#else
+
+#include "../fmaf.c"
+
+#endif
-- 
2.18.0