580a2656d1
Identical to cd527bb324 but for doubles.
This gives a -2.754% improvement on bm_float.py, and -35% improvement on
calling sqrt in a loop.
11 lines
252 B
C
11 lines
252 B
C
// 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;
|
|
}
|