Compiler provided built-ins, or intrinsics can be leveraged for TMU instructions that are not yet generated by the compiler.

• 1/sqrtf() with ISQRTF, using the intrinsic "float __builtin_c29_i32_isqrtf32_m(float f0)"

Example: 
y =__builtin_c29_i32_isqrtf32_m(x);

• 1/expf() with IEXP2F, using the intrinsic float __builtin_c29_i32_iexp2f32_m(float f0) and the formula 1/expf(x) = IEXP2F(x * 1.44269504088896f)

 Example:
y = __builtin_c29_i32_iexp2f32_m(x * 1.44269504088896f);

• expf() with IEXP2F, using the intrinsic float __builtin_c29_i32_iexp2f32_m(float f0) and the formula expf(x) = IEXP2F(x * -1.44269504088896f)

Example:
y = __builtin_c29_i32_iexp2f32_m(x * -1.44269504088896f);

• 1/exp2f() with IEXP2F, using the intrinsic float __builtin_c29_i32_iexp2f32_m(float f0)

Example:
y = __builtin_c29_i32_iexp2f32_m(x);

• exp2f() with IEXP2F, using the intrinsic float __builtin_c29_i32_iexp2f32_m(float f0)

Example:
y = __builtin_c29_i32_iexp2f32_m(-x);

• atanf() with PUATANF, using the intrinsic float __builtin_c29_i32_puatanf32_m(float f0)

Example:
// x is per-unit in [-1,1]
// y is per-unit in [-0.125, 0.125] i.e. [-pi/4, pi/4] radians
y = __builtin_c29_i32_puatanf32_m(x);

• atan2f() with PUATANF and QUADF, using the intrinsics float __builtin_c29_i32_puatanf32_m(float f0) and float __builtin_c29_quadf32(unsigned int * tdm_w_uip0, float * rw_fp1, float * rw_fp2)

Example:
test_output =puatan2f32(y_input,x_input);

static inline float32_t puatan2f32(float32_t y, float32_t x)
{
   uint32_t flags;
   return __builtin_c29_quadf32(&flags, &y, &x) +      __builtin_c29_i32_puatanf32_m(y / x);
}