>From 75ad4e8ec4abc6ce1d801017679c9e9e50fdfcf5 Mon Sep 17 00:00:00 2001
From: Szabolcs Nagy <nsz@port70.net>
Date: Wed, 24 Apr 2019 23:29:05 +0000
Subject: [PATCH 2/3] x86: optimize fp_arch.h

Use inline asm constraints instead of volatile store: fp_barrier does
not need to drop excess precision when x87 fpu is used, fp_force_eval
uses memory constraint to drop excess precision, when sse2 math is
available xmm register constraint is used.

This saves 416 and 322 bytes in .text on x86_64 and i386 respectively.
---
 arch/i386/fp_arch.h   | 48 +++++++++++++++++++++++++++++++++++++++++++
 arch/x32/fp_arch.h    | 40 ++++++++++++++++++++++++++++++++++++
 arch/x86_64/fp_arch.h | 40 ++++++++++++++++++++++++++++++++++++
 3 files changed, 128 insertions(+)
 create mode 100644 arch/i386/fp_arch.h
 create mode 100644 arch/x32/fp_arch.h
 create mode 100644 arch/x86_64/fp_arch.h

diff --git a/arch/i386/fp_arch.h b/arch/i386/fp_arch.h
new file mode 100644
index 00000000..33ac222d
--- /dev/null
+++ b/arch/i386/fp_arch.h
@@ -0,0 +1,48 @@
+#include <float.h>
+
+#ifdef __SSE2_MATH__
+#define FP_BARRIER(x) __asm__ __volatile__ ("" : "+x"(x))
+#define FP_EVAL(x) __asm__ __volatile__ ("" : "+x"(x))
+#else
+#define FP_BARRIER(x) __asm__ __volatile__ ("" : "+t"(x))
+#define FP_EVAL(x) __asm__ __volatile__ ("" : "+m"(x))
+#endif
+
+#define fp_barrierf fp_barrierf
+static inline float_t fp_barrierf(float_t x)
+{
+	FP_BARRIER(x);
+	return x;
+}
+
+#define fp_barrier fp_barrier
+static inline double_t fp_barrier(double_t x)
+{
+	FP_BARRIER(x);
+	return x;
+}
+
+#define fp_barrierl fp_barrierl
+static inline long double fp_barrierl(long double x)
+{
+	__asm__ __volatile__ ("" : "+t"(x));
+	return x;
+}
+
+#define fp_force_evalf fp_force_evalf
+static inline void fp_force_evalf(float x)
+{
+	FP_EVAL(x);
+}
+
+#define fp_force_eval fp_force_eval
+static inline void fp_force_eval(double x)
+{
+	FP_EVAL(x);
+}
+
+#define fp_force_evall fp_force_evall
+static inline void fp_force_evall(long double x)
+{
+	__asm__ __volatile__ ("" : "+t"(x));
+}
diff --git a/arch/x32/fp_arch.h b/arch/x32/fp_arch.h
new file mode 100644
index 00000000..af4309d9
--- /dev/null
+++ b/arch/x32/fp_arch.h
@@ -0,0 +1,40 @@
+#include <float.h>
+
+#define fp_barrierf fp_barrierf
+static inline float_t fp_barrierf(float_t x)
+{
+	__asm__ __volatile__ ("" : "+x"(x));
+	return x;
+}
+
+#define fp_barrier fp_barrier
+static inline double_t fp_barrier(double_t x)
+{
+	__asm__ __volatile__ ("" : "+x"(x));
+	return x;
+}
+
+#define fp_barrierl fp_barrierl
+static inline long double fp_barrierl(long double x)
+{
+	__asm__ __volatile__ ("" : "+t"(x));
+	return x;
+}
+
+#define fp_force_evalf fp_force_evalf
+static inline void fp_force_evalf(float x)
+{
+	__asm__ __volatile__ ("" : "+x"(x));
+}
+
+#define fp_force_eval fp_force_eval
+static inline void fp_force_eval(double x)
+{
+	__asm__ __volatile__ ("" : "+x"(x));
+}
+
+#define fp_force_evall fp_force_evall
+static inline void fp_force_evall(long double x)
+{
+	__asm__ __volatile__ ("" : "+t"(x));
+}
diff --git a/arch/x86_64/fp_arch.h b/arch/x86_64/fp_arch.h
new file mode 100644
index 00000000..af4309d9
--- /dev/null
+++ b/arch/x86_64/fp_arch.h
@@ -0,0 +1,40 @@
+#include <float.h>
+
+#define fp_barrierf fp_barrierf
+static inline float_t fp_barrierf(float_t x)
+{
+	__asm__ __volatile__ ("" : "+x"(x));
+	return x;
+}
+
+#define fp_barrier fp_barrier
+static inline double_t fp_barrier(double_t x)
+{
+	__asm__ __volatile__ ("" : "+x"(x));
+	return x;
+}
+
+#define fp_barrierl fp_barrierl
+static inline long double fp_barrierl(long double x)
+{
+	__asm__ __volatile__ ("" : "+t"(x));
+	return x;
+}
+
+#define fp_force_evalf fp_force_evalf
+static inline void fp_force_evalf(float x)
+{
+	__asm__ __volatile__ ("" : "+x"(x));
+}
+
+#define fp_force_eval fp_force_eval
+static inline void fp_force_eval(double x)
+{
+	__asm__ __volatile__ ("" : "+x"(x));
+}
+
+#define fp_force_evall fp_force_evall
+static inline void fp_force_evall(long double x)
+{
+	__asm__ __volatile__ ("" : "+t"(x));
+}
-- 
2.21.0