From 580a2656d10cc7c1fc93e094d7eb71f04d99c329 Mon Sep 17 00:00:00 2001
From: Jim Mussared <jim.mussared@gmail.com>
Date: Wed, 9 Oct 2019 22:59:35 +1100
Subject: [PATCH] stm32: Use hardware double sqrt on F7/H7 MCUs.

Identical to cd527bb324ade952d11a134859d38bf5272c165e but for doubles.
This gives a -2.754% improvement on bm_float.py, and -35% improvement on
calling sqrt in a loop.
---
 lib/libm_dbl/thumb_vfp_sqrt.c | 10 ++++++++++
 ports/stm32/Makefile          |  6 +++++-
 2 files changed, 15 insertions(+), 1 deletion(-)
 create mode 100644 lib/libm_dbl/thumb_vfp_sqrt.c

diff --git a/lib/libm_dbl/thumb_vfp_sqrt.c b/lib/libm_dbl/thumb_vfp_sqrt.c
new file mode 100644
index 000000000..dd37a07b0
--- /dev/null
+++ b/lib/libm_dbl/thumb_vfp_sqrt.c
@@ -0,0 +1,10 @@
+// an implementation of sqrt for Thumb using hardware double-precision VFP instructions
+
+double sqrt(double x) {
+    double ret;
+    asm volatile (
+            "vsqrt.f64  %P0, %P1\n"
+            : "=w" (ret)
+            : "w"  (x));
+    return ret;
+}
diff --git a/ports/stm32/Makefile b/ports/stm32/Makefile
index 1a4e3c690..28b90199a 100644
--- a/ports/stm32/Makefile
+++ b/ports/stm32/Makefile
@@ -173,12 +173,16 @@ SRC_LIBM = $(addprefix lib/libm_dbl/,\
 	scalbn.c \
 	sin.c \
 	sinh.c \
-	sqrt.c \
 	tan.c \
 	tanh.c \
 	tgamma.c \
 	trunc.c \
 	)
+ifeq ($(MCU_SERIES),$(filter $(MCU_SERIES),f7 h7))
+SRC_LIBM += lib/libm_dbl/thumb_vfp_sqrt.c
+else
+SRC_LIBM += lib/libm_dbl/sqrt.c
+endif
 else
 SRC_LIBM = $(addprefix lib/libm/,\
 	math.c \