Disney BSSRDF, sample scattering profile, lower

Percentage Accurate: 61.3% → 99.4%

Time: 12.1s

Alternatives: 15

Speedup: 11.4×

Specification

\[\left(0 \leq s \land s \leq 256\right) \land \left(2.328306437 \cdot 10^{-10} \leq u \land u \leq 0.25\right)\]

Math

\[\begin{array}{l} \\ s \cdot \log \left(\frac{1}{1 - 4 \cdot u}\right) \end{array} \]

FPCore

(FPCore (s u) :precision binary32 (* s (log (/ 1.0 (- 1.0 (* 4.0 u))))))

C

float code(float s, float u) {
	return s * logf((1.0f / (1.0f - (4.0f * u))));
}

Fortran

real(4) function code(s, u)
    real(4), intent (in) :: s
    real(4), intent (in) :: u
    code = s * log((1.0e0 / (1.0e0 - (4.0e0 * u))))
end function

Julia

function code(s, u)
	return Float32(s * log(Float32(Float32(1.0) / Float32(Float32(1.0) - Float32(Float32(4.0) * u)))))
end

MATLAB

function tmp = code(s, u)
	tmp = s * log((single(1.0) / (single(1.0) - (single(4.0) * u))));
end

Initial Program: 61.3% accurate, 1.0× speedup

Math

\[\begin{array}{l} \\ s \cdot \log \left(\frac{1}{1 - 4 \cdot u}\right) \end{array} \]

FPCore

(FPCore (s u) :precision binary32 (* s (log (/ 1.0 (- 1.0 (* 4.0 u))))))

C

float code(float s, float u) {
	return s * logf((1.0f / (1.0f - (4.0f * u))));
}

Fortran

real(4) function code(s, u)
    real(4), intent (in) :: s
    real(4), intent (in) :: u
    code = s * log((1.0e0 / (1.0e0 - (4.0e0 * u))))
end function

Julia

function code(s, u)
	return Float32(s * log(Float32(Float32(1.0) / Float32(Float32(1.0) - Float32(Float32(4.0) * u)))))
end

MATLAB

function tmp = code(s, u)
	tmp = s * log((single(1.0) / (single(1.0) - (single(4.0) * u))));
end

Alternative 1: 99.4% accurate, 1.1× speedup

Math

\[\begin{array}{l} \\ \mathsf{log1p}\left(u \cdot -4\right) \cdot \left(-s\right) \end{array} \]

FPCore

(FPCore (s u) :precision binary32 (* (log1p (* u -4.0)) (- s)))

C

float code(float s, float u) {
	return log1pf((u * -4.0f)) * -s;
}

Julia

function code(s, u)
	return Float32(log1p(Float32(u * Float32(-4.0))) * Float32(-s))
end

Derivation

1. Initial program 63.8%

   \[s \cdot \log \left(\frac{1}{1 - 4 \cdot u}\right) \]
2. Add Preprocessing

3. Taylor expanded in s around 0

   \[\leadsto \color{blue}{s \cdot \log \left(\frac{1}{1 - 4 \cdot u}\right)} \]
4. Step-by-step derivation

   1. *-commutative N/A

      \[\leadsto \color{blue}{\log \left(\frac{1}{1 - 4 \cdot u}\right) \cdot s} \]

   2. log-rec N/A

      \[\leadsto \color{blue}{\left(\mathsf{neg}\left(\log \left(1 - 4 \cdot u\right)\right)\right)} \cdot s \]

   3. distribute-lft-neg-out N/A

      \[\leadsto \color{blue}{\mathsf{neg}\left(\log \left(1 - 4 \cdot u\right) \cdot s\right)} \]

   4. distribute-rgt-neg-in N/A

      \[\leadsto \color{blue}{\log \left(1 - 4 \cdot u\right) \cdot \left(\mathsf{neg}\left(s\right)\right)} \]

   5. lower-*.f32 N/A

      \[\leadsto \color{blue}{\log \left(1 - 4 \cdot u\right) \cdot \left(\mathsf{neg}\left(s\right)\right)} \]

   6. cancel-sign-sub-inv N/A

      \[\leadsto \log \color{blue}{\left(1 + \left(\mathsf{neg}\left(4\right)\right) \cdot u\right)} \cdot \left(\mathsf{neg}\left(s\right)\right) \]

   7. metadata-eval N/A

      \[\leadsto \log \left(1 + \color{blue}{-4} \cdot u\right) \cdot \left(\mathsf{neg}\left(s\right)\right) \]

   8. lower-log1p.f32 N/A

      \[\leadsto \color{blue}{\mathsf{log1p}\left(-4 \cdot u\right)} \cdot \left(\mathsf{neg}\left(s\right)\right) \]

   9. *-commutative N/A

      \[\leadsto \mathsf{log1p}\left(\color{blue}{u \cdot -4}\right) \cdot \left(\mathsf{neg}\left(s\right)\right) \]

   10. lower-*.f32 N/A

       \[\leadsto \mathsf{log1p}\left(\color{blue}{u \cdot -4}\right) \cdot \left(\mathsf{neg}\left(s\right)\right) \]

   11. lower-neg.f32 99.5

       \[\leadsto \mathsf{log1p}\left(u \cdot -4\right) \cdot \color{blue}{\left(-s\right)} \]

5. Applied rewrites 99.5%

   \[\leadsto \color{blue}{\mathsf{log1p}\left(u \cdot -4\right) \cdot \left(-s\right)} \]
6. Add Preprocessing

Alternative 2: 94.3% accurate, 1.9× speedup

Math

\[\begin{array}{l} \\ u \cdot \left(s \cdot \mathsf{fma}\left(u, \frac{64 - u \cdot \left(\mathsf{fma}\left(u, 64, 21.333333333333332\right) \cdot \left(u \cdot 21.333333333333332\right)\right)}{\mathsf{fma}\left(\mathsf{fma}\left(u, 64, 21.333333333333332\right), -u, 8\right)}, 4\right)\right) \end{array} \]

FPCore

(FPCore (s u)
 :precision binary32
 (*
  u
  (*
   s
   (fma
    u
    (/
     (-
      64.0
      (* u (* (fma u 64.0 21.333333333333332) (* u 21.333333333333332))))
     (fma (fma u 64.0 21.333333333333332) (- u) 8.0))
    4.0))))

C

float code(float s, float u) {
	return u * (s * fmaf(u, ((64.0f - (u * (fmaf(u, 64.0f, 21.333333333333332f) * (u * 21.333333333333332f)))) / fmaf(fmaf(u, 64.0f, 21.333333333333332f), -u, 8.0f)), 4.0f));
}

Julia

function code(s, u)
	return Float32(u * Float32(s * fma(u, Float32(Float32(Float32(64.0) - Float32(u * Float32(fma(u, Float32(64.0), Float32(21.333333333333332)) * Float32(u * Float32(21.333333333333332))))) / fma(fma(u, Float32(64.0), Float32(21.333333333333332)), Float32(-u), Float32(8.0))), Float32(4.0))))
end

Derivation

1. Initial program 63.8%

   \[s \cdot \log \left(\frac{1}{1 - 4 \cdot u}\right) \]
2. Add Preprocessing

3. Taylor expanded in u around 0

   \[\leadsto \color{blue}{u \cdot \left(4 \cdot s + u \cdot \left(8 \cdot s + u \cdot \left(\frac{64}{3} \cdot s + 64 \cdot \left(s \cdot u\right)\right)\right)\right)} \]

5. Applied rewrites 90.5%

   \[\leadsto \color{blue}{\left(u \cdot s\right) \cdot \mathsf{fma}\left(u, \mathsf{fma}\left(u, \mathsf{fma}\left(u, 64, 21.333333333333332\right), 8\right), 4\right)} \]
6. Step-by-step derivation

7. Applied rewrites 90.5%

   \[\leadsto \left(u \cdot s\right) \cdot \mathsf{fma}\left(u, \frac{64}{8 - u \cdot \mathsf{fma}\left(u, 64, 21.333333333333332\right)} - \color{blue}{\frac{u \cdot \left(\mathsf{fma}\left(u, 64, 21.333333333333332\right) \cdot \left(u \cdot \mathsf{fma}\left(u, 64, 21.333333333333332\right)\right)\right)}{8 - u \cdot \mathsf{fma}\left(u, 64, 21.333333333333332\right)}}, 4\right) \]

8. Taylor expanded in u around 0

   \[\leadsto \left(u \cdot s\right) \cdot \mathsf{fma}\left(u, \frac{64}{8 - u \cdot \mathsf{fma}\left(u, 64, \frac{64}{3}\right)} - \frac{u \cdot \left(\mathsf{fma}\left(u, 64, \frac{64}{3}\right) \cdot \left(u \cdot \frac{64}{3}\right)\right)}{8 - u \cdot \mathsf{fma}\left(u, 64, \frac{64}{3}\right)}, 4\right) \]
9. Step-by-step derivation

10. Applied rewrites 92.3%

    \[\leadsto \left(u \cdot s\right) \cdot \mathsf{fma}\left(u, \frac{64}{8 - u \cdot \mathsf{fma}\left(u, 64, 21.333333333333332\right)} - \frac{u \cdot \left(\mathsf{fma}\left(u, 64, 21.333333333333332\right) \cdot \left(u \cdot 21.333333333333332\right)\right)}{8 - u \cdot \mathsf{fma}\left(u, 64, 21.333333333333332\right)}, 4\right) \]
11. Step-by-step derivation

12. Applied rewrites 92.6%

    \[\leadsto \left(s \cdot \mathsf{fma}\left(u, \frac{64 - u \cdot \left(\mathsf{fma}\left(u, 64, 21.333333333333332\right) \cdot \left(u \cdot 21.333333333333332\right)\right)}{\mathsf{fma}\left(\mathsf{fma}\left(u, 64, 21.333333333333332\right), -u, 8\right)}, 4\right)\right) \cdot \color{blue}{u} \]

13. Final simplification 92.6%

    \[\leadsto u \cdot \left(s \cdot \mathsf{fma}\left(u, \frac{64 - u \cdot \left(\mathsf{fma}\left(u, 64, 21.333333333333332\right) \cdot \left(u \cdot 21.333333333333332\right)\right)}{\mathsf{fma}\left(\mathsf{fma}\left(u, 64, 21.333333333333332\right), -u, 8\right)}, 4\right)\right) \]
14. Add Preprocessing

Alternative 3: 93.8% accurate, 3.1× speedup

Math

\[\begin{array}{l} \\ \left(s \cdot u\right) \cdot \frac{1}{\mathsf{fma}\left(u, \mathsf{fma}\left(u, \mathsf{fma}\left(u, -0.6666666666666666, -0.3333333333333333\right), -0.5\right), 0.25\right)} \end{array} \]

FPCore

(FPCore (s u)
 :precision binary32
 (*
  (* s u)
  (/
   1.0
   (fma u (fma u (fma u -0.6666666666666666 -0.3333333333333333) -0.5) 0.25))))

C

float code(float s, float u) {
	return (s * u) * (1.0f / fmaf(u, fmaf(u, fmaf(u, -0.6666666666666666f, -0.3333333333333333f), -0.5f), 0.25f));
}

Julia

function code(s, u)
	return Float32(Float32(s * u) * Float32(Float32(1.0) / fma(u, fma(u, fma(u, Float32(-0.6666666666666666), Float32(-0.3333333333333333)), Float32(-0.5)), Float32(0.25))))
end

Derivation

1. Initial program 63.8%

   \[s \cdot \log \left(\frac{1}{1 - 4 \cdot u}\right) \]
2. Add Preprocessing

3. Taylor expanded in u around 0

   \[\leadsto \color{blue}{u \cdot \left(4 \cdot s + u \cdot \left(8 \cdot s + u \cdot \left(\frac{64}{3} \cdot s + 64 \cdot \left(s \cdot u\right)\right)\right)\right)} \]

5. Applied rewrites 90.5%

   \[\leadsto \color{blue}{\left(u \cdot s\right) \cdot \mathsf{fma}\left(u, \mathsf{fma}\left(u, \mathsf{fma}\left(u, 64, 21.333333333333332\right), 8\right), 4\right)} \]
6. Step-by-step derivation

7. Applied rewrites 90.5%

   \[\leadsto \left(u \cdot s\right) \cdot \frac{1}{\color{blue}{\frac{1}{\mathsf{fma}\left(u, \mathsf{fma}\left(u, \mathsf{fma}\left(u, 64, 21.333333333333332\right), 8\right), 4\right)}}} \]

8. Taylor expanded in u around 0

   \[\leadsto \left(u \cdot s\right) \cdot \frac{1}{\frac{1}{4} + \color{blue}{u \cdot \left(u \cdot \left(\frac{-2}{3} \cdot u - \frac{1}{3}\right) - \frac{1}{2}\right)}} \]
9. Step-by-step derivation

10. Applied rewrites 92.0%

    \[\leadsto \left(u \cdot s\right) \cdot \frac{1}{\mathsf{fma}\left(u, \color{blue}{\mathsf{fma}\left(u, \mathsf{fma}\left(u, -0.6666666666666666, -0.3333333333333333\right), -0.5\right)}, 0.25\right)} \]

11. Final simplification 92.0%

    \[\leadsto \left(s \cdot u\right) \cdot \frac{1}{\mathsf{fma}\left(u, \mathsf{fma}\left(u, \mathsf{fma}\left(u, -0.6666666666666666, -0.3333333333333333\right), -0.5\right), 0.25\right)} \]
12. Add Preprocessing

Alternative 4: 93.6% accurate, 3.2× speedup

Math

\[\begin{array}{l} \\ \mathsf{fma}\left(4 \cdot u, s, u \cdot \left(s \cdot \left(u \cdot \mathsf{fma}\left(u, \mathsf{fma}\left(u, 64, 21.333333333333332\right), 8\right)\right)\right)\right) \end{array} \]

FPCore

(FPCore (s u)
 :precision binary32
 (fma
  (* 4.0 u)
  s
  (* u (* s (* u (fma u (fma u 64.0 21.333333333333332) 8.0))))))

C

float code(float s, float u) {
	return fmaf((4.0f * u), s, (u * (s * (u * fmaf(u, fmaf(u, 64.0f, 21.333333333333332f), 8.0f)))));
}

Julia

function code(s, u)
	return fma(Float32(Float32(4.0) * u), s, Float32(u * Float32(s * Float32(u * fma(u, fma(u, Float32(64.0), Float32(21.333333333333332)), Float32(8.0))))))
end

Derivation

1. Initial program 63.8%

   \[s \cdot \log \left(\frac{1}{1 - 4 \cdot u}\right) \]
2. Add Preprocessing

3. Taylor expanded in u around 0

   \[\leadsto \color{blue}{u \cdot \left(4 \cdot s + u \cdot \left(8 \cdot s + u \cdot \left(\frac{64}{3} \cdot s + 64 \cdot \left(s \cdot u\right)\right)\right)\right)} \]

5. Applied rewrites 90.5%

   \[\leadsto \color{blue}{\left(u \cdot s\right) \cdot \mathsf{fma}\left(u, \mathsf{fma}\left(u, \mathsf{fma}\left(u, 64, 21.333333333333332\right), 8\right), 4\right)} \]
6. Step-by-step derivation

7. Applied rewrites 90.5%

   \[\leadsto \left(u \cdot s\right) \cdot \frac{1}{\color{blue}{\frac{1}{\mathsf{fma}\left(u, \mathsf{fma}\left(u, \mathsf{fma}\left(u, 64, 21.333333333333332\right), 8\right), 4\right)}}} \]

9. Applied rewrites 91.4%

   \[\leadsto \mathsf{fma}\left(u \cdot 4, \color{blue}{s}, u \cdot \left(s \cdot \left(u \cdot \mathsf{fma}\left(u, \mathsf{fma}\left(u, 64, 21.333333333333332\right), 8\right)\right)\right)\right) \]

10. Final simplification 91.4%

    \[\leadsto \mathsf{fma}\left(4 \cdot u, s, u \cdot \left(s \cdot \left(u \cdot \mathsf{fma}\left(u, \mathsf{fma}\left(u, 64, 21.333333333333332\right), 8\right)\right)\right)\right) \]
11. Add Preprocessing

Alternative 5: 93.5% accurate, 3.2× speedup

Math

\[\begin{array}{l} \\ \mathsf{fma}\left(4 \cdot u, s, \mathsf{fma}\left(u, \mathsf{fma}\left(u, 64, 21.333333333333332\right), 8\right) \cdot \left(u \cdot \left(s \cdot u\right)\right)\right) \end{array} \]

FPCore

(FPCore (s u)
 :precision binary32
 (fma
  (* 4.0 u)
  s
  (* (fma u (fma u 64.0 21.333333333333332) 8.0) (* u (* s u)))))

C

float code(float s, float u) {
	return fmaf((4.0f * u), s, (fmaf(u, fmaf(u, 64.0f, 21.333333333333332f), 8.0f) * (u * (s * u))));
}

Julia

function code(s, u)
	return fma(Float32(Float32(4.0) * u), s, Float32(fma(u, fma(u, Float32(64.0), Float32(21.333333333333332)), Float32(8.0)) * Float32(u * Float32(s * u))))
end

Derivation

1. Initial program 63.8%

   \[s \cdot \log \left(\frac{1}{1 - 4 \cdot u}\right) \]
2. Add Preprocessing

3. Taylor expanded in u around 0

   \[\leadsto \color{blue}{u \cdot \left(4 \cdot s + u \cdot \left(8 \cdot s + u \cdot \left(\frac{64}{3} \cdot s + 64 \cdot \left(s \cdot u\right)\right)\right)\right)} \]

5. Applied rewrites 90.5%

   \[\leadsto \color{blue}{\left(u \cdot s\right) \cdot \mathsf{fma}\left(u, \mathsf{fma}\left(u, \mathsf{fma}\left(u, 64, 21.333333333333332\right), 8\right), 4\right)} \]
6. Step-by-step derivation

7. Applied rewrites 91.3%

   \[\leadsto \mathsf{fma}\left(4 \cdot u, \color{blue}{s}, \mathsf{fma}\left(u, \mathsf{fma}\left(u, 64, 21.333333333333332\right), 8\right) \cdot \left(u \cdot \left(s \cdot u\right)\right)\right) \]
8. Add Preprocessing

Alternative 6: 93.2% accurate, 3.7× speedup

Math

\[\begin{array}{l} \\ s \cdot \mathsf{fma}\left(\mathsf{fma}\left(u, \mathsf{fma}\left(u, 64, 21.333333333333332\right), 8\right), u \cdot u, 4 \cdot u\right) \end{array} \]

FPCore

(FPCore (s u)
 :precision binary32
 (* s (fma (fma u (fma u 64.0 21.333333333333332) 8.0) (* u u) (* 4.0 u))))

C

float code(float s, float u) {
	return s * fmaf(fmaf(u, fmaf(u, 64.0f, 21.333333333333332f), 8.0f), (u * u), (4.0f * u));
}

Julia

function code(s, u)
	return Float32(s * fma(fma(u, fma(u, Float32(64.0), Float32(21.333333333333332)), Float32(8.0)), Float32(u * u), Float32(Float32(4.0) * u)))
end

Derivation

1. Initial program 63.8%

   \[s \cdot \log \left(\frac{1}{1 - 4 \cdot u}\right) \]
2. Add Preprocessing

4. Applied rewrites 63.2%

   \[\leadsto s \cdot \log \left(\frac{1}{\color{blue}{\frac{-\left(u \cdot \left(u \cdot 16\right) - 1\right)}{\mathsf{fma}\left(4, u, 1\right)}}}\right) \]

5. Taylor expanded in u around 0

   \[\leadsto s \cdot \color{blue}{\left(u \cdot \left(4 + u \cdot \left(8 + u \cdot \left(\frac{64}{3} + 64 \cdot u\right)\right)\right)\right)} \]
6. Step-by-step derivation

   1. lower-*.f32 N/A

      \[\leadsto s \cdot \color{blue}{\left(u \cdot \left(4 + u \cdot \left(8 + u \cdot \left(\frac{64}{3} + 64 \cdot u\right)\right)\right)\right)} \]

   2. +-commutative N/A

      \[\leadsto s \cdot \left(u \cdot \color{blue}{\left(u \cdot \left(8 + u \cdot \left(\frac{64}{3} + 64 \cdot u\right)\right) + 4\right)}\right) \]

   3. lower-fma.f32 N/A

      \[\leadsto s \cdot \left(u \cdot \color{blue}{\mathsf{fma}\left(u, 8 + u \cdot \left(\frac{64}{3} + 64 \cdot u\right), 4\right)}\right) \]

   4. +-commutative N/A

      \[\leadsto s \cdot \left(u \cdot \mathsf{fma}\left(u, \color{blue}{u \cdot \left(\frac{64}{3} + 64 \cdot u\right) + 8}, 4\right)\right) \]

   5. metadata-eval N/A

      \[\leadsto s \cdot \left(u \cdot \mathsf{fma}\left(u, u \cdot \left(\color{blue}{\frac{64}{3} \cdot 1} + 64 \cdot u\right) + 8, 4\right)\right) \]

   6. lft-mult-inverse N/A

      \[\leadsto s \cdot \left(u \cdot \mathsf{fma}\left(u, u \cdot \left(\frac{64}{3} \cdot \color{blue}{\left(\frac{1}{u} \cdot u\right)} + 64 \cdot u\right) + 8, 4\right)\right) \]

   7. associate-*l* N/A

      \[\leadsto s \cdot \left(u \cdot \mathsf{fma}\left(u, u \cdot \left(\color{blue}{\left(\frac{64}{3} \cdot \frac{1}{u}\right) \cdot u} + 64 \cdot u\right) + 8, 4\right)\right) \]

   8. distribute-rgt-in N/A

      \[\leadsto s \cdot \left(u \cdot \mathsf{fma}\left(u, u \cdot \color{blue}{\left(u \cdot \left(\frac{64}{3} \cdot \frac{1}{u} + 64\right)\right)} + 8, 4\right)\right) \]

   9. +-commutative N/A

      \[\leadsto s \cdot \left(u \cdot \mathsf{fma}\left(u, u \cdot \left(u \cdot \color{blue}{\left(64 + \frac{64}{3} \cdot \frac{1}{u}\right)}\right) + 8, 4\right)\right) \]

   10. lower-fma.f32 N/A

       \[\leadsto s \cdot \left(u \cdot \mathsf{fma}\left(u, \color{blue}{\mathsf{fma}\left(u, u \cdot \left(64 + \frac{64}{3} \cdot \frac{1}{u}\right), 8\right)}, 4\right)\right) \]

   11. distribute-rgt-in N/A

       \[\leadsto s \cdot \left(u \cdot \mathsf{fma}\left(u, \mathsf{fma}\left(u, \color{blue}{64 \cdot u + \left(\frac{64}{3} \cdot \frac{1}{u}\right) \cdot u}, 8\right), 4\right)\right) \]

   12. *-commutative N/A

       \[\leadsto s \cdot \left(u \cdot \mathsf{fma}\left(u, \mathsf{fma}\left(u, \color{blue}{u \cdot 64} + \left(\frac{64}{3} \cdot \frac{1}{u}\right) \cdot u, 8\right), 4\right)\right) \]

   13. associate-*l* N/A

       \[\leadsto s \cdot \left(u \cdot \mathsf{fma}\left(u, \mathsf{fma}\left(u, u \cdot 64 + \color{blue}{\frac{64}{3} \cdot \left(\frac{1}{u} \cdot u\right)}, 8\right), 4\right)\right) \]

   14. lft-mult-inverse N/A

       \[\leadsto s \cdot \left(u \cdot \mathsf{fma}\left(u, \mathsf{fma}\left(u, u \cdot 64 + \frac{64}{3} \cdot \color{blue}{1}, 8\right), 4\right)\right) \]

   15. metadata-eval N/A

       \[\leadsto s \cdot \left(u \cdot \mathsf{fma}\left(u, \mathsf{fma}\left(u, u \cdot 64 + \color{blue}{\frac{64}{3}}, 8\right), 4\right)\right) \]

   16. lower-fma.f32 90.7

       \[\leadsto s \cdot \left(u \cdot \mathsf{fma}\left(u, \mathsf{fma}\left(u, \color{blue}{\mathsf{fma}\left(u, 64, 21.333333333333332\right)}, 8\right), 4\right)\right) \]

7. Applied rewrites 90.7%

   \[\leadsto s \cdot \color{blue}{\left(u \cdot \mathsf{fma}\left(u, \mathsf{fma}\left(u, \mathsf{fma}\left(u, 64, 21.333333333333332\right), 8\right), 4\right)\right)} \]
8. Step-by-step derivation

9. Applied rewrites 91.1%

   \[\leadsto s \cdot \mathsf{fma}\left(\mathsf{fma}\left(u, \mathsf{fma}\left(u, 64, 21.333333333333332\right), 8\right), \color{blue}{u \cdot u}, u \cdot 4\right) \]

10. Final simplification 91.1%

    \[\leadsto s \cdot \mathsf{fma}\left(\mathsf{fma}\left(u, \mathsf{fma}\left(u, 64, 21.333333333333332\right), 8\right), u \cdot u, 4 \cdot u\right) \]
11. Add Preprocessing

Alternative 7: 92.9% accurate, 4.3× speedup

Math

\[\begin{array}{l} \\ u \cdot \left(s \cdot \mathsf{fma}\left(u, \mathsf{fma}\left(u, \mathsf{fma}\left(u, 64, 21.333333333333332\right), 8\right), 4\right)\right) \end{array} \]

FPCore

(FPCore (s u)
 :precision binary32
 (* u (* s (fma u (fma u (fma u 64.0 21.333333333333332) 8.0) 4.0))))

C

float code(float s, float u) {
	return u * (s * fmaf(u, fmaf(u, fmaf(u, 64.0f, 21.333333333333332f), 8.0f), 4.0f));
}

Julia

function code(s, u)
	return Float32(u * Float32(s * fma(u, fma(u, fma(u, Float32(64.0), Float32(21.333333333333332)), Float32(8.0)), Float32(4.0))))
end

Derivation

1. Initial program 63.8%

   \[s \cdot \log \left(\frac{1}{1 - 4 \cdot u}\right) \]
2. Add Preprocessing

3. Taylor expanded in u around 0

   \[\leadsto \color{blue}{u \cdot \left(4 \cdot s + u \cdot \left(8 \cdot s + u \cdot \left(\frac{64}{3} \cdot s + 64 \cdot \left(s \cdot u\right)\right)\right)\right)} \]

5. Applied rewrites 90.5%

   \[\leadsto \color{blue}{\left(u \cdot s\right) \cdot \mathsf{fma}\left(u, \mathsf{fma}\left(u, \mathsf{fma}\left(u, 64, 21.333333333333332\right), 8\right), 4\right)} \]
6. Step-by-step derivation

7. Applied rewrites 90.8%

   \[\leadsto \left(s \cdot \mathsf{fma}\left(u, \mathsf{fma}\left(u, \mathsf{fma}\left(u, 64, 21.333333333333332\right), 8\right), 4\right)\right) \cdot \color{blue}{u} \]

8. Final simplification 90.8%

   \[\leadsto u \cdot \left(s \cdot \mathsf{fma}\left(u, \mathsf{fma}\left(u, \mathsf{fma}\left(u, 64, 21.333333333333332\right), 8\right), 4\right)\right) \]
9. Add Preprocessing

Alternative 8: 91.1% accurate, 4.5× speedup

Math

\[\begin{array}{l} \\ u \cdot \mathsf{fma}\left(u, s \cdot \mathsf{fma}\left(u, 21.333333333333332, 8\right), s \cdot 4\right) \end{array} \]

FPCore

(FPCore (s u)
 :precision binary32
 (* u (fma u (* s (fma u 21.333333333333332 8.0)) (* s 4.0))))

C

float code(float s, float u) {
	return u * fmaf(u, (s * fmaf(u, 21.333333333333332f, 8.0f)), (s * 4.0f));
}

Julia

function code(s, u)
	return Float32(u * fma(u, Float32(s * fma(u, Float32(21.333333333333332), Float32(8.0))), Float32(s * Float32(4.0))))
end

Derivation

1. Initial program 63.8%

   \[s \cdot \log \left(\frac{1}{1 - 4 \cdot u}\right) \]
2. Add Preprocessing

4. Applied rewrites 63.2%

   \[\leadsto s \cdot \log \left(\frac{1}{\color{blue}{\frac{-\left(u \cdot \left(u \cdot 16\right) - 1\right)}{\mathsf{fma}\left(4, u, 1\right)}}}\right) \]

5. Taylor expanded in u around 0

   \[\leadsto s \cdot \color{blue}{\left(4 \cdot u\right)} \]
6. Step-by-step derivation

   1. lower-*.f32 71.6

      \[\leadsto s \cdot \color{blue}{\left(4 \cdot u\right)} \]

7. Applied rewrites 71.6%

   \[\leadsto s \cdot \color{blue}{\left(4 \cdot u\right)} \]

8. Taylor expanded in u around 0

   \[\leadsto \color{blue}{u \cdot \left(4 \cdot s + u \cdot \left(8 \cdot s + \frac{64}{3} \cdot \left(s \cdot u\right)\right)\right)} \]
9. Step-by-step derivation

   1. lower-*.f32 N/A

      \[\leadsto \color{blue}{u \cdot \left(4 \cdot s + u \cdot \left(8 \cdot s + \frac{64}{3} \cdot \left(s \cdot u\right)\right)\right)} \]

   2. +-commutative N/A

      \[\leadsto u \cdot \color{blue}{\left(u \cdot \left(8 \cdot s + \frac{64}{3} \cdot \left(s \cdot u\right)\right) + 4 \cdot s\right)} \]

   3. lower-fma.f32 N/A

      \[\leadsto u \cdot \color{blue}{\mathsf{fma}\left(u, 8 \cdot s + \frac{64}{3} \cdot \left(s \cdot u\right), 4 \cdot s\right)} \]

   4. *-commutative N/A

      \[\leadsto u \cdot \mathsf{fma}\left(u, \color{blue}{s \cdot 8} + \frac{64}{3} \cdot \left(s \cdot u\right), 4 \cdot s\right) \]

   5. *-commutative N/A

      \[\leadsto u \cdot \mathsf{fma}\left(u, s \cdot 8 + \color{blue}{\left(s \cdot u\right) \cdot \frac{64}{3}}, 4 \cdot s\right) \]

   6. associate-*l* N/A

      \[\leadsto u \cdot \mathsf{fma}\left(u, s \cdot 8 + \color{blue}{s \cdot \left(u \cdot \frac{64}{3}\right)}, 4 \cdot s\right) \]

   7. *-commutative N/A

      \[\leadsto u \cdot \mathsf{fma}\left(u, s \cdot 8 + s \cdot \color{blue}{\left(\frac{64}{3} \cdot u\right)}, 4 \cdot s\right) \]

   8. distribute-lft-out N/A

      \[\leadsto u \cdot \mathsf{fma}\left(u, \color{blue}{s \cdot \left(8 + \frac{64}{3} \cdot u\right)}, 4 \cdot s\right) \]

   9. lower-*.f32 N/A

      \[\leadsto u \cdot \mathsf{fma}\left(u, \color{blue}{s \cdot \left(8 + \frac{64}{3} \cdot u\right)}, 4 \cdot s\right) \]

   10. +-commutative N/A

       \[\leadsto u \cdot \mathsf{fma}\left(u, s \cdot \color{blue}{\left(\frac{64}{3} \cdot u + 8\right)}, 4 \cdot s\right) \]

   11. *-commutative N/A

       \[\leadsto u \cdot \mathsf{fma}\left(u, s \cdot \left(\color{blue}{u \cdot \frac{64}{3}} + 8\right), 4 \cdot s\right) \]

   12. lower-fma.f32 N/A

       \[\leadsto u \cdot \mathsf{fma}\left(u, s \cdot \color{blue}{\mathsf{fma}\left(u, \frac{64}{3}, 8\right)}, 4 \cdot s\right) \]

   13. lower-*.f32 88.5

       \[\leadsto u \cdot \mathsf{fma}\left(u, s \cdot \mathsf{fma}\left(u, 21.333333333333332, 8\right), \color{blue}{4 \cdot s}\right) \]

10. Applied rewrites 88.5%

    \[\leadsto \color{blue}{u \cdot \mathsf{fma}\left(u, s \cdot \mathsf{fma}\left(u, 21.333333333333332, 8\right), 4 \cdot s\right)} \]

11. Final simplification 88.5%

    \[\leadsto u \cdot \mathsf{fma}\left(u, s \cdot \mathsf{fma}\left(u, 21.333333333333332, 8\right), s \cdot 4\right) \]
12. Add Preprocessing

Alternative 9: 90.8% accurate, 5.4× speedup

Math

\[\begin{array}{l} \\ u \cdot \left(s \cdot \mathsf{fma}\left(u, \mathsf{fma}\left(u, 21.333333333333332, 8\right), 4\right)\right) \end{array} \]

FPCore

(FPCore (s u)
 :precision binary32
 (* u (* s (fma u (fma u 21.333333333333332 8.0) 4.0))))

C

float code(float s, float u) {
	return u * (s * fmaf(u, fmaf(u, 21.333333333333332f, 8.0f), 4.0f));
}

Julia

function code(s, u)
	return Float32(u * Float32(s * fma(u, fma(u, Float32(21.333333333333332), Float32(8.0)), Float32(4.0))))
end

Derivation

1. Initial program 63.8%

   \[s \cdot \log \left(\frac{1}{1 - 4 \cdot u}\right) \]
2. Add Preprocessing

4. Applied rewrites 63.2%

   \[\leadsto s \cdot \log \left(\frac{1}{\color{blue}{\frac{-\left(u \cdot \left(u \cdot 16\right) - 1\right)}{\mathsf{fma}\left(4, u, 1\right)}}}\right) \]

5. Taylor expanded in u around 0

   \[\leadsto \color{blue}{u \cdot \left(4 \cdot s + u \cdot \left(8 \cdot s + \frac{64}{3} \cdot \left(s \cdot u\right)\right)\right)} \]

7. Applied rewrites 88.2%

   \[\leadsto \color{blue}{u \cdot \left(s \cdot \mathsf{fma}\left(u, \mathsf{fma}\left(u, 21.333333333333332, 8\right), 4\right)\right)} \]
8. Add Preprocessing

Alternative 10: 90.5% accurate, 5.4× speedup

Math

\[\begin{array}{l} \\ \left(s \cdot u\right) \cdot \mathsf{fma}\left(u, \mathsf{fma}\left(u, 21.333333333333332, 8\right), 4\right) \end{array} \]

FPCore

(FPCore (s u)
 :precision binary32
 (* (* s u) (fma u (fma u 21.333333333333332 8.0) 4.0)))

C

float code(float s, float u) {
	return (s * u) * fmaf(u, fmaf(u, 21.333333333333332f, 8.0f), 4.0f);
}

Julia

function code(s, u)
	return Float32(Float32(s * u) * fma(u, fma(u, Float32(21.333333333333332), Float32(8.0)), Float32(4.0)))
end

Derivation

1. Initial program 63.8%

   \[s \cdot \log \left(\frac{1}{1 - 4 \cdot u}\right) \]
2. Add Preprocessing

3. Taylor expanded in u around 0

   \[\leadsto \color{blue}{u \cdot \left(4 \cdot s + u \cdot \left(8 \cdot s + \frac{64}{3} \cdot \left(s \cdot u\right)\right)\right)} \]
4. Step-by-step derivation

   1. distribute-rgt-in N/A

      \[\leadsto u \cdot \left(4 \cdot s + \color{blue}{\left(\left(8 \cdot s\right) \cdot u + \left(\frac{64}{3} \cdot \left(s \cdot u\right)\right) \cdot u\right)}\right) \]

   2. associate-*r* N/A

      \[\leadsto u \cdot \left(4 \cdot s + \left(\color{blue}{8 \cdot \left(s \cdot u\right)} + \left(\frac{64}{3} \cdot \left(s \cdot u\right)\right) \cdot u\right)\right) \]

   3. associate-+r+ N/A

      \[\leadsto u \cdot \color{blue}{\left(\left(4 \cdot s + 8 \cdot \left(s \cdot u\right)\right) + \left(\frac{64}{3} \cdot \left(s \cdot u\right)\right) \cdot u\right)} \]

   4. *-commutative N/A

      \[\leadsto u \cdot \left(\left(4 \cdot s + 8 \cdot \left(s \cdot u\right)\right) + \color{blue}{u \cdot \left(\frac{64}{3} \cdot \left(s \cdot u\right)\right)}\right) \]

   5. distribute-lft-in N/A

      \[\leadsto \color{blue}{u \cdot \left(4 \cdot s + 8 \cdot \left(s \cdot u\right)\right) + u \cdot \left(u \cdot \left(\frac{64}{3} \cdot \left(s \cdot u\right)\right)\right)} \]

   6. distribute-rgt-in N/A

      \[\leadsto \color{blue}{\left(\left(4 \cdot s\right) \cdot u + \left(8 \cdot \left(s \cdot u\right)\right) \cdot u\right)} + u \cdot \left(u \cdot \left(\frac{64}{3} \cdot \left(s \cdot u\right)\right)\right) \]

   7. associate-*r* N/A

      \[\leadsto \left(\color{blue}{4 \cdot \left(s \cdot u\right)} + \left(8 \cdot \left(s \cdot u\right)\right) \cdot u\right) + u \cdot \left(u \cdot \left(\frac{64}{3} \cdot \left(s \cdot u\right)\right)\right) \]

   8. *-commutative N/A

      \[\leadsto \left(\color{blue}{\left(s \cdot u\right) \cdot 4} + \left(8 \cdot \left(s \cdot u\right)\right) \cdot u\right) + u \cdot \left(u \cdot \left(\frac{64}{3} \cdot \left(s \cdot u\right)\right)\right) \]

   9. *-commutative N/A

      \[\leadsto \left(\left(s \cdot u\right) \cdot 4 + \color{blue}{\left(\left(s \cdot u\right) \cdot 8\right)} \cdot u\right) + u \cdot \left(u \cdot \left(\frac{64}{3} \cdot \left(s \cdot u\right)\right)\right) \]

   10. associate-*l* N/A

       \[\leadsto \left(\left(s \cdot u\right) \cdot 4 + \color{blue}{\left(s \cdot u\right) \cdot \left(8 \cdot u\right)}\right) + u \cdot \left(u \cdot \left(\frac{64}{3} \cdot \left(s \cdot u\right)\right)\right) \]

   11. distribute-lft-out N/A

       \[\leadsto \color{blue}{\left(s \cdot u\right) \cdot \left(4 + 8 \cdot u\right)} + u \cdot \left(u \cdot \left(\frac{64}{3} \cdot \left(s \cdot u\right)\right)\right) \]

   12. *-commutative N/A

       \[\leadsto \color{blue}{\left(4 + 8 \cdot u\right) \cdot \left(s \cdot u\right)} + u \cdot \left(u \cdot \left(\frac{64}{3} \cdot \left(s \cdot u\right)\right)\right) \]

   13. associate-*r* N/A

       \[\leadsto \left(4 + 8 \cdot u\right) \cdot \left(s \cdot u\right) + u \cdot \color{blue}{\left(\left(u \cdot \frac{64}{3}\right) \cdot \left(s \cdot u\right)\right)} \]

   14. *-commutative N/A

       \[\leadsto \left(4 + 8 \cdot u\right) \cdot \left(s \cdot u\right) + u \cdot \left(\color{blue}{\left(\frac{64}{3} \cdot u\right)} \cdot \left(s \cdot u\right)\right) \]

   15. associate-*r* N/A

       \[\leadsto \left(4 + 8 \cdot u\right) \cdot \left(s \cdot u\right) + \color{blue}{\left(u \cdot \left(\frac{64}{3} \cdot u\right)\right) \cdot \left(s \cdot u\right)} \]

   16. distribute-rgt-in N/A

       \[\leadsto \color{blue}{\left(s \cdot u\right) \cdot \left(\left(4 + 8 \cdot u\right) + u \cdot \left(\frac{64}{3} \cdot u\right)\right)} \]

5. Applied rewrites 87.9%

   \[\leadsto \color{blue}{\left(u \cdot s\right) \cdot \mathsf{fma}\left(u, \mathsf{fma}\left(u, 21.333333333333332, 8\right), 4\right)} \]

6. Final simplification 87.9%

   \[\leadsto \left(s \cdot u\right) \cdot \mathsf{fma}\left(u, \mathsf{fma}\left(u, 21.333333333333332, 8\right), 4\right) \]
7. Add Preprocessing

Alternative 11: 86.7% accurate, 5.7× speedup

Math

\[\begin{array}{l} \\ u \cdot \mathsf{fma}\left(u, s \cdot 8, s \cdot 4\right) \end{array} \]

FPCore

(FPCore (s u) :precision binary32 (* u (fma u (* s 8.0) (* s 4.0))))

C

float code(float s, float u) {
	return u * fmaf(u, (s * 8.0f), (s * 4.0f));
}

Julia

function code(s, u)
	return Float32(u * fma(u, Float32(s * Float32(8.0)), Float32(s * Float32(4.0))))
end

Derivation

1. Initial program 63.8%

   \[s \cdot \log \left(\frac{1}{1 - 4 \cdot u}\right) \]
2. Add Preprocessing

4. Applied rewrites 63.2%

   \[\leadsto s \cdot \log \left(\frac{1}{\color{blue}{\frac{-\left(u \cdot \left(u \cdot 16\right) - 1\right)}{\mathsf{fma}\left(4, u, 1\right)}}}\right) \]

5. Taylor expanded in u around 0

   \[\leadsto s \cdot \color{blue}{\left(4 \cdot u\right)} \]
6. Step-by-step derivation

   1. lower-*.f32 71.6

      \[\leadsto s \cdot \color{blue}{\left(4 \cdot u\right)} \]

7. Applied rewrites 71.6%

   \[\leadsto s \cdot \color{blue}{\left(4 \cdot u\right)} \]

8. Taylor expanded in u around 0

   \[\leadsto \color{blue}{u \cdot \left(4 \cdot s + u \cdot \left(8 \cdot s + \frac{64}{3} \cdot \left(s \cdot u\right)\right)\right)} \]
9. Step-by-step derivation

   1. lower-*.f32 N/A

      \[\leadsto \color{blue}{u \cdot \left(4 \cdot s + u \cdot \left(8 \cdot s + \frac{64}{3} \cdot \left(s \cdot u\right)\right)\right)} \]

   2. +-commutative N/A

      \[\leadsto u \cdot \color{blue}{\left(u \cdot \left(8 \cdot s + \frac{64}{3} \cdot \left(s \cdot u\right)\right) + 4 \cdot s\right)} \]

   3. lower-fma.f32 N/A

      \[\leadsto u \cdot \color{blue}{\mathsf{fma}\left(u, 8 \cdot s + \frac{64}{3} \cdot \left(s \cdot u\right), 4 \cdot s\right)} \]

   4. *-commutative N/A

      \[\leadsto u \cdot \mathsf{fma}\left(u, \color{blue}{s \cdot 8} + \frac{64}{3} \cdot \left(s \cdot u\right), 4 \cdot s\right) \]

   5. *-commutative N/A

      \[\leadsto u \cdot \mathsf{fma}\left(u, s \cdot 8 + \color{blue}{\left(s \cdot u\right) \cdot \frac{64}{3}}, 4 \cdot s\right) \]

   6. associate-*l* N/A

      \[\leadsto u \cdot \mathsf{fma}\left(u, s \cdot 8 + \color{blue}{s \cdot \left(u \cdot \frac{64}{3}\right)}, 4 \cdot s\right) \]

   7. *-commutative N/A

      \[\leadsto u \cdot \mathsf{fma}\left(u, s \cdot 8 + s \cdot \color{blue}{\left(\frac{64}{3} \cdot u\right)}, 4 \cdot s\right) \]

   8. distribute-lft-out N/A

      \[\leadsto u \cdot \mathsf{fma}\left(u, \color{blue}{s \cdot \left(8 + \frac{64}{3} \cdot u\right)}, 4 \cdot s\right) \]

   9. lower-*.f32 N/A

      \[\leadsto u \cdot \mathsf{fma}\left(u, \color{blue}{s \cdot \left(8 + \frac{64}{3} \cdot u\right)}, 4 \cdot s\right) \]

   10. +-commutative N/A

       \[\leadsto u \cdot \mathsf{fma}\left(u, s \cdot \color{blue}{\left(\frac{64}{3} \cdot u + 8\right)}, 4 \cdot s\right) \]

   11. *-commutative N/A

       \[\leadsto u \cdot \mathsf{fma}\left(u, s \cdot \left(\color{blue}{u \cdot \frac{64}{3}} + 8\right), 4 \cdot s\right) \]

   12. lower-fma.f32 N/A

       \[\leadsto u \cdot \mathsf{fma}\left(u, s \cdot \color{blue}{\mathsf{fma}\left(u, \frac{64}{3}, 8\right)}, 4 \cdot s\right) \]

   13. lower-*.f32 88.5

       \[\leadsto u \cdot \mathsf{fma}\left(u, s \cdot \mathsf{fma}\left(u, 21.333333333333332, 8\right), \color{blue}{4 \cdot s}\right) \]

10. Applied rewrites 88.5%

    \[\leadsto \color{blue}{u \cdot \mathsf{fma}\left(u, s \cdot \mathsf{fma}\left(u, 21.333333333333332, 8\right), 4 \cdot s\right)} \]

11. Taylor expanded in u around 0

    \[\leadsto u \cdot \mathsf{fma}\left(u, 8 \cdot \color{blue}{s}, 4 \cdot s\right) \]
12. Step-by-step derivation

13. Applied rewrites 84.0%

    \[\leadsto u \cdot \mathsf{fma}\left(u, s \cdot \color{blue}{8}, 4 \cdot s\right) \]

14. Final simplification 84.0%

    \[\leadsto u \cdot \mathsf{fma}\left(u, s \cdot 8, s \cdot 4\right) \]
15. Add Preprocessing

Alternative 12: 86.6% accurate, 7.4× speedup

Math

\[\begin{array}{l} \\ u \cdot \left(s \cdot \mathsf{fma}\left(u, 8, 4\right)\right) \end{array} \]

FPCore

(FPCore (s u) :precision binary32 (* u (* s (fma u 8.0 4.0))))

C

float code(float s, float u) {
	return u * (s * fmaf(u, 8.0f, 4.0f));
}

Julia

function code(s, u)
	return Float32(u * Float32(s * fma(u, Float32(8.0), Float32(4.0))))
end

Derivation

1. Initial program 63.8%

   \[s \cdot \log \left(\frac{1}{1 - 4 \cdot u}\right) \]
2. Add Preprocessing

4. Applied rewrites 63.2%

   \[\leadsto s \cdot \log \left(\frac{1}{\color{blue}{\frac{-\left(u \cdot \left(u \cdot 16\right) - 1\right)}{\mathsf{fma}\left(4, u, 1\right)}}}\right) \]

5. Taylor expanded in u around 0

   \[\leadsto s \cdot \color{blue}{\left(4 \cdot u\right)} \]
6. Step-by-step derivation

   1. lower-*.f32 71.6

      \[\leadsto s \cdot \color{blue}{\left(4 \cdot u\right)} \]

7. Applied rewrites 71.6%

   \[\leadsto s \cdot \color{blue}{\left(4 \cdot u\right)} \]

8. Taylor expanded in u around 0

   \[\leadsto \color{blue}{u \cdot \left(4 \cdot s + 8 \cdot \left(s \cdot u\right)\right)} \]
9. Step-by-step derivation

   1. lower-*.f32 N/A

      \[\leadsto \color{blue}{u \cdot \left(4 \cdot s + 8 \cdot \left(s \cdot u\right)\right)} \]

   2. *-commutative N/A

      \[\leadsto u \cdot \left(4 \cdot s + 8 \cdot \color{blue}{\left(u \cdot s\right)}\right) \]

   3. associate-*r* N/A

      \[\leadsto u \cdot \left(4 \cdot s + \color{blue}{\left(8 \cdot u\right) \cdot s}\right) \]

   4. distribute-rgt-out N/A

      \[\leadsto u \cdot \color{blue}{\left(s \cdot \left(4 + 8 \cdot u\right)\right)} \]

   5. lower-*.f32 N/A

      \[\leadsto u \cdot \color{blue}{\left(s \cdot \left(4 + 8 \cdot u\right)\right)} \]

   6. +-commutative N/A

      \[\leadsto u \cdot \left(s \cdot \color{blue}{\left(8 \cdot u + 4\right)}\right) \]

   7. *-commutative N/A

      \[\leadsto u \cdot \left(s \cdot \left(\color{blue}{u \cdot 8} + 4\right)\right) \]

   8. lower-fma.f32 83.7

      \[\leadsto u \cdot \left(s \cdot \color{blue}{\mathsf{fma}\left(u, 8, 4\right)}\right) \]

10. Applied rewrites 83.7%

    \[\leadsto \color{blue}{u \cdot \left(s \cdot \mathsf{fma}\left(u, 8, 4\right)\right)} \]
11. Add Preprocessing

Alternative 13: 86.3% accurate, 7.4× speedup

Math

\[\begin{array}{l} \\ \left(s \cdot u\right) \cdot \mathsf{fma}\left(u, 8, 4\right) \end{array} \]

FPCore

(FPCore (s u) :precision binary32 (* (* s u) (fma u 8.0 4.0)))

C

float code(float s, float u) {
	return (s * u) * fmaf(u, 8.0f, 4.0f);
}

Julia

function code(s, u)
	return Float32(Float32(s * u) * fma(u, Float32(8.0), Float32(4.0)))
end

Derivation

1. Initial program 63.8%

   \[s \cdot \log \left(\frac{1}{1 - 4 \cdot u}\right) \]
2. Add Preprocessing

3. Taylor expanded in u around 0

   \[\leadsto \color{blue}{u \cdot \left(4 \cdot s + 8 \cdot \left(s \cdot u\right)\right)} \]
4. Step-by-step derivation

   1. distribute-rgt-in N/A

      \[\leadsto \color{blue}{\left(4 \cdot s\right) \cdot u + \left(8 \cdot \left(s \cdot u\right)\right) \cdot u} \]

   2. associate-*r* N/A

      \[\leadsto \color{blue}{4 \cdot \left(s \cdot u\right)} + \left(8 \cdot \left(s \cdot u\right)\right) \cdot u \]

   3. *-commutative N/A

      \[\leadsto \color{blue}{\left(s \cdot u\right) \cdot 4} + \left(8 \cdot \left(s \cdot u\right)\right) \cdot u \]

   4. *-commutative N/A

      \[\leadsto \left(s \cdot u\right) \cdot 4 + \color{blue}{\left(\left(s \cdot u\right) \cdot 8\right)} \cdot u \]

   5. associate-*l* N/A

      \[\leadsto \left(s \cdot u\right) \cdot 4 + \color{blue}{\left(s \cdot u\right) \cdot \left(8 \cdot u\right)} \]

   6. distribute-lft-out N/A

      \[\leadsto \color{blue}{\left(s \cdot u\right) \cdot \left(4 + 8 \cdot u\right)} \]

   7. *-commutative N/A

      \[\leadsto \color{blue}{\left(4 + 8 \cdot u\right) \cdot \left(s \cdot u\right)} \]

   8. lower-*.f32 N/A

      \[\leadsto \color{blue}{\left(4 + 8 \cdot u\right) \cdot \left(s \cdot u\right)} \]

   9. +-commutative N/A

      \[\leadsto \color{blue}{\left(8 \cdot u + 4\right)} \cdot \left(s \cdot u\right) \]

   10. *-commutative N/A

       \[\leadsto \left(\color{blue}{u \cdot 8} + 4\right) \cdot \left(s \cdot u\right) \]

   11. lower-fma.f32 N/A

       \[\leadsto \color{blue}{\mathsf{fma}\left(u, 8, 4\right)} \cdot \left(s \cdot u\right) \]

   12. *-commutative N/A

       \[\leadsto \mathsf{fma}\left(u, 8, 4\right) \cdot \color{blue}{\left(u \cdot s\right)} \]

   13. lower-*.f32 83.3

       \[\leadsto \mathsf{fma}\left(u, 8, 4\right) \cdot \color{blue}{\left(u \cdot s\right)} \]

5. Applied rewrites 83.3%

   \[\leadsto \color{blue}{\mathsf{fma}\left(u, 8, 4\right) \cdot \left(u \cdot s\right)} \]

6. Final simplification 83.3%

   \[\leadsto \left(s \cdot u\right) \cdot \mathsf{fma}\left(u, 8, 4\right) \]
7. Add Preprocessing

Alternative 14: 73.7% accurate, 11.4× speedup

Math

\[\begin{array}{l} \\ s \cdot \left(4 \cdot u\right) \end{array} \]

FPCore

(FPCore (s u) :precision binary32 (* s (* 4.0 u)))

C

float code(float s, float u) {
	return s * (4.0f * u);
}

Fortran

real(4) function code(s, u)
    real(4), intent (in) :: s
    real(4), intent (in) :: u
    code = s * (4.0e0 * u)
end function

Julia

function code(s, u)
	return Float32(s * Float32(Float32(4.0) * u))
end

MATLAB

function tmp = code(s, u)
	tmp = s * (single(4.0) * u);
end

Derivation

1. Initial program 63.8%

   \[s \cdot \log \left(\frac{1}{1 - 4 \cdot u}\right) \]
2. Add Preprocessing

3. Taylor expanded in u around 0

   \[\leadsto s \cdot \color{blue}{\left(4 \cdot u\right)} \]
4. Step-by-step derivation

   1. lower-*.f32 71.6

      \[\leadsto s \cdot \color{blue}{\left(4 \cdot u\right)} \]

5. Applied rewrites 71.6%

   \[\leadsto s \cdot \color{blue}{\left(4 \cdot u\right)} \]
6. Add Preprocessing

Alternative 15: 73.5% accurate, 11.4× speedup

Math

\[\begin{array}{l} \\ 4 \cdot \left(s \cdot u\right) \end{array} \]

FPCore

(FPCore (s u) :precision binary32 (* 4.0 (* s u)))

C

float code(float s, float u) {
	return 4.0f * (s * u);
}

Fortran

real(4) function code(s, u)
    real(4), intent (in) :: s
    real(4), intent (in) :: u
    code = 4.0e0 * (s * u)
end function

Julia

function code(s, u)
	return Float32(Float32(4.0) * Float32(s * u))
end

MATLAB

function tmp = code(s, u)
	tmp = single(4.0) * (s * u);
end

Derivation

1. Initial program 63.8%

   \[s \cdot \log \left(\frac{1}{1 - 4 \cdot u}\right) \]
2. Add Preprocessing

3. Taylor expanded in u around 0

   \[\leadsto \color{blue}{4 \cdot \left(s \cdot u\right)} \]
4. Step-by-step derivation

   1. lower-*.f32 N/A

      \[\leadsto \color{blue}{4 \cdot \left(s \cdot u\right)} \]

   2. *-commutative N/A

      \[\leadsto 4 \cdot \color{blue}{\left(u \cdot s\right)} \]

   3. lower-*.f32 71.3

      \[\leadsto 4 \cdot \color{blue}{\left(u \cdot s\right)} \]

5. Applied rewrites 71.3%

   \[\leadsto \color{blue}{4 \cdot \left(u \cdot s\right)} \]

6. Final simplification 71.3%

   \[\leadsto 4 \cdot \left(s \cdot u\right) \]
7. Add Preprocessing

Reproduce

herbie shell --seed 2024222 
(FPCore (s u)
  :name "Disney BSSRDF, sample scattering profile, lower"
  :precision binary32
  :pre (and (and (<= 0.0 s) (<= s 256.0)) (and (<= 2.328306437e-10 u) (<= u 0.25)))
  (* s (log (/ 1.0 (- 1.0 (* 4.0 u))))))