Falkner and Boettcher, Appendix B, 2

Percentage Accurate: 100.0% → 100.0%

Time: 9.9s

Alternatives: 4

Speedup: 1.7×

Specification

Math

\[\begin{array}{l} \\ \left(\frac{\sqrt{2}}{4} \cdot \sqrt{1 - 3 \cdot \left(v \cdot v\right)}\right) \cdot \left(1 - v \cdot v\right) \end{array} \]

FPCore

(FPCore (v)
 :precision binary64
 (* (* (/ (sqrt 2.0) 4.0) (sqrt (- 1.0 (* 3.0 (* v v))))) (- 1.0 (* v v))))

C

double code(double v) {
	return ((sqrt(2.0) / 4.0) * sqrt((1.0 - (3.0 * (v * v))))) * (1.0 - (v * v));
}

Fortran

real(8) function code(v)
    real(8), intent (in) :: v
    code = ((sqrt(2.0d0) / 4.0d0) * sqrt((1.0d0 - (3.0d0 * (v * v))))) * (1.0d0 - (v * v))
end function

Java

public static double code(double v) {
	return ((Math.sqrt(2.0) / 4.0) * Math.sqrt((1.0 - (3.0 * (v * v))))) * (1.0 - (v * v));
}

Python

def code(v):
	return ((math.sqrt(2.0) / 4.0) * math.sqrt((1.0 - (3.0 * (v * v))))) * (1.0 - (v * v))

Julia

function code(v)
	return Float64(Float64(Float64(sqrt(2.0) / 4.0) * sqrt(Float64(1.0 - Float64(3.0 * Float64(v * v))))) * Float64(1.0 - Float64(v * v)))
end

MATLAB

function tmp = code(v)
	tmp = ((sqrt(2.0) / 4.0) * sqrt((1.0 - (3.0 * (v * v))))) * (1.0 - (v * v));
end

Wolfram

code[v_] := N[(N[(N[(N[Sqrt[2.0], $MachinePrecision] / 4.0), $MachinePrecision] * N[Sqrt[N[(1.0 - N[(3.0 * N[(v * v), $MachinePrecision]), $MachinePrecision]), $MachinePrecision]], $MachinePrecision]), $MachinePrecision] * N[(1.0 - N[(v * v), $MachinePrecision]), $MachinePrecision]), $MachinePrecision]

Initial Program: 100.0% accurate, 1.0× speedup

Math

\[\begin{array}{l} \\ \left(\frac{\sqrt{2}}{4} \cdot \sqrt{1 - 3 \cdot \left(v \cdot v\right)}\right) \cdot \left(1 - v \cdot v\right) \end{array} \]

FPCore

(FPCore (v)
 :precision binary64
 (* (* (/ (sqrt 2.0) 4.0) (sqrt (- 1.0 (* 3.0 (* v v))))) (- 1.0 (* v v))))

C

double code(double v) {
	return ((sqrt(2.0) / 4.0) * sqrt((1.0 - (3.0 * (v * v))))) * (1.0 - (v * v));
}

Fortran

real(8) function code(v)
    real(8), intent (in) :: v
    code = ((sqrt(2.0d0) / 4.0d0) * sqrt((1.0d0 - (3.0d0 * (v * v))))) * (1.0d0 - (v * v))
end function

Java

public static double code(double v) {
	return ((Math.sqrt(2.0) / 4.0) * Math.sqrt((1.0 - (3.0 * (v * v))))) * (1.0 - (v * v));
}

Python

def code(v):
	return ((math.sqrt(2.0) / 4.0) * math.sqrt((1.0 - (3.0 * (v * v))))) * (1.0 - (v * v))

Julia

function code(v)
	return Float64(Float64(Float64(sqrt(2.0) / 4.0) * sqrt(Float64(1.0 - Float64(3.0 * Float64(v * v))))) * Float64(1.0 - Float64(v * v)))
end

MATLAB

function tmp = code(v)
	tmp = ((sqrt(2.0) / 4.0) * sqrt((1.0 - (3.0 * (v * v))))) * (1.0 - (v * v));
end

Wolfram

code[v_] := N[(N[(N[(N[Sqrt[2.0], $MachinePrecision] / 4.0), $MachinePrecision] * N[Sqrt[N[(1.0 - N[(3.0 * N[(v * v), $MachinePrecision]), $MachinePrecision]), $MachinePrecision]], $MachinePrecision]), $MachinePrecision] * N[(1.0 - N[(v * v), $MachinePrecision]), $MachinePrecision]), $MachinePrecision]

Alternative 1: 100.0% accurate, 0.9× speedup

Math

\[\begin{array}{l} \\ \frac{\left(1 - v \cdot \left(v \cdot \left(v \cdot v\right)\right)\right) \cdot \sqrt{\mathsf{fma}\left(v \cdot v, -6, 2\right)}}{\mathsf{fma}\left(v \cdot v, 4, 4\right)} \end{array} \]

FPCore

(FPCore (v)
 :precision binary64
 (/
  (* (- 1.0 (* v (* v (* v v)))) (sqrt (fma (* v v) -6.0 2.0)))
  (fma (* v v) 4.0 4.0)))

C

double code(double v) {
	return ((1.0 - (v * (v * (v * v)))) * sqrt(fma((v * v), -6.0, 2.0))) / fma((v * v), 4.0, 4.0);
}

Julia

function code(v)
	return Float64(Float64(Float64(1.0 - Float64(v * Float64(v * Float64(v * v)))) * sqrt(fma(Float64(v * v), -6.0, 2.0))) / fma(Float64(v * v), 4.0, 4.0))
end

Wolfram

code[v_] := N[(N[(N[(1.0 - N[(v * N[(v * N[(v * v), $MachinePrecision]), $MachinePrecision]), $MachinePrecision]), $MachinePrecision] * N[Sqrt[N[(N[(v * v), $MachinePrecision] * -6.0 + 2.0), $MachinePrecision]], $MachinePrecision]), $MachinePrecision] / N[(N[(v * v), $MachinePrecision] * 4.0 + 4.0), $MachinePrecision]), $MachinePrecision]

Derivation

1. Initial program 100.0%

   \[\left(\frac{\sqrt{2}}{4} \cdot \sqrt{1 - 3 \cdot \left(v \cdot v\right)}\right) \cdot \left(1 - v \cdot v\right) \]
2. Add Preprocessing

4. Applied rewrites 100.0%

   \[\leadsto \color{blue}{\frac{\left(1 - v \cdot \left(v \cdot \left(v \cdot v\right)\right)\right) \cdot \sqrt{\mathsf{fma}\left(2, v \cdot \left(v \cdot -3\right), 2\right)}}{\mathsf{fma}\left(4, v \cdot v, 4\right)}} \]
5. Step-by-step derivation

   1. lift-*.f64 N/A

      \[\leadsto \frac{\left(1 - v \cdot \left(v \cdot \color{blue}{\left(v \cdot v\right)}\right)\right) \cdot \sqrt{2 \cdot \left(v \cdot \left(v \cdot -3\right)\right) + 2}}{4 \cdot \left(v \cdot v\right) + 4} \]

   2. lift-*.f64 N/A

      \[\leadsto \frac{\left(1 - v \cdot \color{blue}{\left(v \cdot \left(v \cdot v\right)\right)}\right) \cdot \sqrt{2 \cdot \left(v \cdot \left(v \cdot -3\right)\right) + 2}}{4 \cdot \left(v \cdot v\right) + 4} \]

   3. lift-*.f64 N/A

      \[\leadsto \frac{\left(1 - \color{blue}{v \cdot \left(v \cdot \left(v \cdot v\right)\right)}\right) \cdot \sqrt{2 \cdot \left(v \cdot \left(v \cdot -3\right)\right) + 2}}{4 \cdot \left(v \cdot v\right) + 4} \]

   4. lift--.f64 N/A

      \[\leadsto \frac{\color{blue}{\left(1 - v \cdot \left(v \cdot \left(v \cdot v\right)\right)\right)} \cdot \sqrt{2 \cdot \left(v \cdot \left(v \cdot -3\right)\right) + 2}}{4 \cdot \left(v \cdot v\right) + 4} \]

   5. lift-*.f64 N/A

      \[\leadsto \frac{\left(1 - v \cdot \left(v \cdot \left(v \cdot v\right)\right)\right) \cdot \sqrt{2 \cdot \left(v \cdot \color{blue}{\left(v \cdot -3\right)}\right) + 2}}{4 \cdot \left(v \cdot v\right) + 4} \]

   6. lift-*.f64 N/A

      \[\leadsto \frac{\left(1 - v \cdot \left(v \cdot \left(v \cdot v\right)\right)\right) \cdot \sqrt{2 \cdot \color{blue}{\left(v \cdot \left(v \cdot -3\right)\right)} + 2}}{4 \cdot \left(v \cdot v\right) + 4} \]

   7. lift-fma.f64 N/A

      \[\leadsto \frac{\left(1 - v \cdot \left(v \cdot \left(v \cdot v\right)\right)\right) \cdot \sqrt{\color{blue}{\mathsf{fma}\left(2, v \cdot \left(v \cdot -3\right), 2\right)}}}{4 \cdot \left(v \cdot v\right) + 4} \]

   8. lift-sqrt.f64 N/A

      \[\leadsto \frac{\left(1 - v \cdot \left(v \cdot \left(v \cdot v\right)\right)\right) \cdot \color{blue}{\sqrt{\mathsf{fma}\left(2, v \cdot \left(v \cdot -3\right), 2\right)}}}{4 \cdot \left(v \cdot v\right) + 4} \]

   9. lift-*.f64 N/A

      \[\leadsto \frac{\color{blue}{\left(1 - v \cdot \left(v \cdot \left(v \cdot v\right)\right)\right) \cdot \sqrt{\mathsf{fma}\left(2, v \cdot \left(v \cdot -3\right), 2\right)}}}{4 \cdot \left(v \cdot v\right) + 4} \]

   10. lift-*.f64 N/A

       \[\leadsto \frac{\left(1 - v \cdot \left(v \cdot \left(v \cdot v\right)\right)\right) \cdot \sqrt{\mathsf{fma}\left(2, v \cdot \left(v \cdot -3\right), 2\right)}}{4 \cdot \color{blue}{\left(v \cdot v\right)} + 4} \]

   11. lift-fma.f64 N/A

       \[\leadsto \frac{\left(1 - v \cdot \left(v \cdot \left(v \cdot v\right)\right)\right) \cdot \sqrt{\mathsf{fma}\left(2, v \cdot \left(v \cdot -3\right), 2\right)}}{\color{blue}{\mathsf{fma}\left(4, v \cdot v, 4\right)}} \]

   12. lift-/.f64 100.0

       \[\leadsto \color{blue}{\frac{\left(1 - v \cdot \left(v \cdot \left(v \cdot v\right)\right)\right) \cdot \sqrt{\mathsf{fma}\left(2, v \cdot \left(v \cdot -3\right), 2\right)}}{\mathsf{fma}\left(4, v \cdot v, 4\right)}} \]

6. Applied rewrites 100.0%

   \[\leadsto \color{blue}{\frac{\left(1 - v \cdot \left(v \cdot \left(v \cdot v\right)\right)\right) \cdot \sqrt{\mathsf{fma}\left(v \cdot v, -6, 2\right)}}{\mathsf{fma}\left(v \cdot v, 4, 4\right)}} \]
7. Add Preprocessing

Alternative 2: 100.0% accurate, 1.7× speedup

Math

\[\begin{array}{l} \\ \left(\mathsf{fma}\left(v, v, -1\right) \cdot \sqrt{\mathsf{fma}\left(v, v \cdot -6, 2\right)}\right) \cdot -0.25 \end{array} \]

FPCore

(FPCore (v)
 :precision binary64
 (* (* (fma v v -1.0) (sqrt (fma v (* v -6.0) 2.0))) -0.25))

C

double code(double v) {
	return (fma(v, v, -1.0) * sqrt(fma(v, (v * -6.0), 2.0))) * -0.25;
}

Julia

function code(v)
	return Float64(Float64(fma(v, v, -1.0) * sqrt(fma(v, Float64(v * -6.0), 2.0))) * -0.25)
end

Wolfram

code[v_] := N[(N[(N[(v * v + -1.0), $MachinePrecision] * N[Sqrt[N[(v * N[(v * -6.0), $MachinePrecision] + 2.0), $MachinePrecision]], $MachinePrecision]), $MachinePrecision] * -0.25), $MachinePrecision]

Derivation

1. Initial program 100.0%

   \[\left(\frac{\sqrt{2}}{4} \cdot \sqrt{1 - 3 \cdot \left(v \cdot v\right)}\right) \cdot \left(1 - v \cdot v\right) \]
2. Add Preprocessing
3. Step-by-step derivation

   1. lift-sqrt.f64 N/A

      \[\leadsto \left(\frac{\color{blue}{\sqrt{2}}}{4} \cdot \sqrt{1 - 3 \cdot \left(v \cdot v\right)}\right) \cdot \left(1 - v \cdot v\right) \]

   2. lift-*.f64 N/A

      \[\leadsto \left(\frac{\sqrt{2}}{4} \cdot \sqrt{1 - 3 \cdot \color{blue}{\left(v \cdot v\right)}}\right) \cdot \left(1 - v \cdot v\right) \]

   3. lift-*.f64 N/A

      \[\leadsto \left(\frac{\sqrt{2}}{4} \cdot \sqrt{1 - \color{blue}{3 \cdot \left(v \cdot v\right)}}\right) \cdot \left(1 - v \cdot v\right) \]

   4. lift--.f64 N/A

      \[\leadsto \left(\frac{\sqrt{2}}{4} \cdot \sqrt{\color{blue}{1 - 3 \cdot \left(v \cdot v\right)}}\right) \cdot \left(1 - v \cdot v\right) \]

   5. lift-sqrt.f64 N/A

      \[\leadsto \left(\frac{\sqrt{2}}{4} \cdot \color{blue}{\sqrt{1 - 3 \cdot \left(v \cdot v\right)}}\right) \cdot \left(1 - v \cdot v\right) \]

   6. associate-*l/ N/A

      \[\leadsto \color{blue}{\frac{\sqrt{2} \cdot \sqrt{1 - 3 \cdot \left(v \cdot v\right)}}{4}} \cdot \left(1 - v \cdot v\right) \]

   7. div-inv N/A

      \[\leadsto \color{blue}{\left(\left(\sqrt{2} \cdot \sqrt{1 - 3 \cdot \left(v \cdot v\right)}\right) \cdot \frac{1}{4}\right)} \cdot \left(1 - v \cdot v\right) \]

   8. lower-*.f64 N/A

      \[\leadsto \color{blue}{\left(\left(\sqrt{2} \cdot \sqrt{1 - 3 \cdot \left(v \cdot v\right)}\right) \cdot \frac{1}{4}\right)} \cdot \left(1 - v \cdot v\right) \]

4. Applied rewrites 100.0%

   \[\leadsto \color{blue}{\left(\sqrt{\mathsf{fma}\left(2, v \cdot \left(v \cdot -3\right), 2\right)} \cdot 0.25\right)} \cdot \left(1 - v \cdot v\right) \]

6. Applied rewrites 100.0%

   \[\leadsto \color{blue}{\left(1 - v \cdot v\right) \cdot \left(0.25 \cdot \sqrt{\mathsf{fma}\left(v \cdot v, -6, 2\right)}\right)} \]

8. Applied rewrites 100.0%

   \[\leadsto \color{blue}{\left(\mathsf{fma}\left(v, v, -1\right) \cdot \sqrt{\mathsf{fma}\left(v, v \cdot -6, 2\right)}\right) \cdot -0.25} \]
9. Add Preprocessing

Alternative 3: 99.6% accurate, 2.3× speedup

Math

\[\begin{array}{l} \\ \sqrt{2} \cdot \mathsf{fma}\left(v \cdot v, -0.625, 0.25\right) \end{array} \]

FPCore

(FPCore (v) :precision binary64 (* (sqrt 2.0) (fma (* v v) -0.625 0.25)))

C

double code(double v) {
	return sqrt(2.0) * fma((v * v), -0.625, 0.25);
}

Julia

function code(v)
	return Float64(sqrt(2.0) * fma(Float64(v * v), -0.625, 0.25))
end

Wolfram

code[v_] := N[(N[Sqrt[2.0], $MachinePrecision] * N[(N[(v * v), $MachinePrecision] * -0.625 + 0.25), $MachinePrecision]), $MachinePrecision]

Derivation

1. Initial program 100.0%

   \[\left(\frac{\sqrt{2}}{4} \cdot \sqrt{1 - 3 \cdot \left(v \cdot v\right)}\right) \cdot \left(1 - v \cdot v\right) \]
2. Add Preprocessing

3. Taylor expanded in v around 0

   \[\leadsto \color{blue}{\left(\frac{-3}{8} \cdot \left({v}^{2} \cdot \sqrt{2}\right) + \frac{1}{4} \cdot \sqrt{2}\right)} \cdot \left(1 - v \cdot v\right) \]
4. Step-by-step derivation

   1. associate-*r* N/A

      \[\leadsto \left(\color{blue}{\left(\frac{-3}{8} \cdot {v}^{2}\right) \cdot \sqrt{2}} + \frac{1}{4} \cdot \sqrt{2}\right) \cdot \left(1 - v \cdot v\right) \]

   2. distribute-rgt-out N/A

      \[\leadsto \color{blue}{\left(\sqrt{2} \cdot \left(\frac{-3}{8} \cdot {v}^{2} + \frac{1}{4}\right)\right)} \cdot \left(1 - v \cdot v\right) \]

   3. lower-*.f64 N/A

      \[\leadsto \color{blue}{\left(\sqrt{2} \cdot \left(\frac{-3}{8} \cdot {v}^{2} + \frac{1}{4}\right)\right)} \cdot \left(1 - v \cdot v\right) \]

   4. lower-sqrt.f64 N/A

      \[\leadsto \left(\color{blue}{\sqrt{2}} \cdot \left(\frac{-3}{8} \cdot {v}^{2} + \frac{1}{4}\right)\right) \cdot \left(1 - v \cdot v\right) \]

   5. unpow2 N/A

      \[\leadsto \left(\sqrt{2} \cdot \left(\frac{-3}{8} \cdot \color{blue}{\left(v \cdot v\right)} + \frac{1}{4}\right)\right) \cdot \left(1 - v \cdot v\right) \]

   6. associate-*r* N/A

      \[\leadsto \left(\sqrt{2} \cdot \left(\color{blue}{\left(\frac{-3}{8} \cdot v\right) \cdot v} + \frac{1}{4}\right)\right) \cdot \left(1 - v \cdot v\right) \]

   7. *-commutative N/A

      \[\leadsto \left(\sqrt{2} \cdot \left(\color{blue}{v \cdot \left(\frac{-3}{8} \cdot v\right)} + \frac{1}{4}\right)\right) \cdot \left(1 - v \cdot v\right) \]

   8. lower-fma.f64 N/A

      \[\leadsto \left(\sqrt{2} \cdot \color{blue}{\mathsf{fma}\left(v, \frac{-3}{8} \cdot v, \frac{1}{4}\right)}\right) \cdot \left(1 - v \cdot v\right) \]

   9. *-commutative N/A

      \[\leadsto \left(\sqrt{2} \cdot \mathsf{fma}\left(v, \color{blue}{v \cdot \frac{-3}{8}}, \frac{1}{4}\right)\right) \cdot \left(1 - v \cdot v\right) \]

   10. lower-*.f64 99.9

       \[\leadsto \left(\sqrt{2} \cdot \mathsf{fma}\left(v, \color{blue}{v \cdot -0.375}, 0.25\right)\right) \cdot \left(1 - v \cdot v\right) \]

5. Applied rewrites 99.9%

   \[\leadsto \color{blue}{\left(\sqrt{2} \cdot \mathsf{fma}\left(v, v \cdot -0.375, 0.25\right)\right)} \cdot \left(1 - v \cdot v\right) \]

6. Taylor expanded in v around 0

   \[\leadsto \color{blue}{\frac{-5}{8} \cdot \left({v}^{2} \cdot \sqrt{2}\right) + \frac{1}{4} \cdot \sqrt{2}} \]
7. Step-by-step derivation

   1. associate-*r* N/A

      \[\leadsto \color{blue}{\left(\frac{-5}{8} \cdot {v}^{2}\right) \cdot \sqrt{2}} + \frac{1}{4} \cdot \sqrt{2} \]

   2. distribute-rgt-out N/A

      \[\leadsto \color{blue}{\sqrt{2} \cdot \left(\frac{-5}{8} \cdot {v}^{2} + \frac{1}{4}\right)} \]

   3. lower-*.f64 N/A

      \[\leadsto \color{blue}{\sqrt{2} \cdot \left(\frac{-5}{8} \cdot {v}^{2} + \frac{1}{4}\right)} \]

   4. lower-sqrt.f64 N/A

      \[\leadsto \color{blue}{\sqrt{2}} \cdot \left(\frac{-5}{8} \cdot {v}^{2} + \frac{1}{4}\right) \]

   5. *-commutative N/A

      \[\leadsto \sqrt{2} \cdot \left(\color{blue}{{v}^{2} \cdot \frac{-5}{8}} + \frac{1}{4}\right) \]

   6. lower-fma.f64 N/A

      \[\leadsto \sqrt{2} \cdot \color{blue}{\mathsf{fma}\left({v}^{2}, \frac{-5}{8}, \frac{1}{4}\right)} \]

   7. unpow2 N/A

      \[\leadsto \sqrt{2} \cdot \mathsf{fma}\left(\color{blue}{v \cdot v}, \frac{-5}{8}, \frac{1}{4}\right) \]

   8. lower-*.f64 99.9

      \[\leadsto \sqrt{2} \cdot \mathsf{fma}\left(\color{blue}{v \cdot v}, -0.625, 0.25\right) \]

8. Applied rewrites 99.9%

   \[\leadsto \color{blue}{\sqrt{2} \cdot \mathsf{fma}\left(v \cdot v, -0.625, 0.25\right)} \]
9. Add Preprocessing

Alternative 4: 99.0% accurate, 3.9× speedup

Math

\[\begin{array}{l} \\ \sqrt{2} \cdot 0.25 \end{array} \]

FPCore

(FPCore (v) :precision binary64 (* (sqrt 2.0) 0.25))

C

double code(double v) {
	return sqrt(2.0) * 0.25;
}

Fortran

real(8) function code(v)
    real(8), intent (in) :: v
    code = sqrt(2.0d0) * 0.25d0
end function

Java

public static double code(double v) {
	return Math.sqrt(2.0) * 0.25;
}

Python

def code(v):
	return math.sqrt(2.0) * 0.25

Julia

function code(v)
	return Float64(sqrt(2.0) * 0.25)
end

MATLAB

function tmp = code(v)
	tmp = sqrt(2.0) * 0.25;
end

Wolfram

code[v_] := N[(N[Sqrt[2.0], $MachinePrecision] * 0.25), $MachinePrecision]

Derivation

1. Initial program 100.0%

   \[\left(\frac{\sqrt{2}}{4} \cdot \sqrt{1 - 3 \cdot \left(v \cdot v\right)}\right) \cdot \left(1 - v \cdot v\right) \]
2. Add Preprocessing

3. Taylor expanded in v around 0

   \[\leadsto \color{blue}{\frac{1}{4} \cdot \sqrt{2}} \]
4. Step-by-step derivation

   1. lower-*.f64 N/A

      \[\leadsto \color{blue}{\frac{1}{4} \cdot \sqrt{2}} \]

   2. lower-sqrt.f64 99.5

      \[\leadsto 0.25 \cdot \color{blue}{\sqrt{2}} \]

5. Applied rewrites 99.5%

   \[\leadsto \color{blue}{0.25 \cdot \sqrt{2}} \]

6. Final simplification 99.5%

   \[\leadsto \sqrt{2} \cdot 0.25 \]
7. Add Preprocessing

Reproduce

herbie shell --seed 2024220 
(FPCore (v)
  :name "Falkner and Boettcher, Appendix B, 2"
  :precision binary64
  (* (* (/ (sqrt 2.0) 4.0) (sqrt (- 1.0 (* 3.0 (* v v))))) (- 1.0 (* v v))))