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.

1 files changed, 10 insertions, 0 deletions

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;
+}