
(FPCore (s u) :precision binary32 (* s (log (/ 1.0 (- 1.0 (* 4.0 u))))))
float code(float s, float u) {
return s * logf((1.0f / (1.0f - (4.0f * u))));
}
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
function code(s, u) return Float32(s * log(Float32(Float32(1.0) / Float32(Float32(1.0) - Float32(Float32(4.0) * u))))) end
function tmp = code(s, u) tmp = s * log((single(1.0) / (single(1.0) - (single(4.0) * u)))); end
\begin{array}{l}
\\
s \cdot \log \left(\frac{1}{1 - 4 \cdot u}\right)
\end{array}
Sampling outcomes in binary32 precision:
Herbie found 3 alternatives:
| Alternative | Accuracy | Speedup |
|---|
(FPCore (s u) :precision binary32 (* s (log (/ 1.0 (- 1.0 (* 4.0 u))))))
float code(float s, float u) {
return s * logf((1.0f / (1.0f - (4.0f * u))));
}
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
function code(s, u) return Float32(s * log(Float32(Float32(1.0) / Float32(Float32(1.0) - Float32(Float32(4.0) * u))))) end
function tmp = code(s, u) tmp = s * log((single(1.0) / (single(1.0) - (single(4.0) * u)))); end
\begin{array}{l}
\\
s \cdot \log \left(\frac{1}{1 - 4 \cdot u}\right)
\end{array}
(FPCore (s u) :precision binary32 (let* ((t_0 (- 1.0 (* 4.0 u)))) (if (<= t_0 0.9997000098228455) (* s (log (/ 1.0 t_0))) (* (* 4.0 u) s))))
float code(float s, float u) {
float t_0 = 1.0f - (4.0f * u);
float tmp;
if (t_0 <= 0.9997000098228455f) {
tmp = s * logf((1.0f / t_0));
} else {
tmp = (4.0f * u) * s;
}
return tmp;
}
real(4) function code(s, u)
real(4), intent (in) :: s
real(4), intent (in) :: u
real(4) :: t_0
real(4) :: tmp
t_0 = 1.0e0 - (4.0e0 * u)
if (t_0 <= 0.9997000098228455e0) then
tmp = s * log((1.0e0 / t_0))
else
tmp = (4.0e0 * u) * s
end if
code = tmp
end function
function code(s, u) t_0 = Float32(Float32(1.0) - Float32(Float32(4.0) * u)) tmp = Float32(0.0) if (t_0 <= Float32(0.9997000098228455)) tmp = Float32(s * log(Float32(Float32(1.0) / t_0))); else tmp = Float32(Float32(Float32(4.0) * u) * s); end return tmp end
function tmp_2 = code(s, u) t_0 = single(1.0) - (single(4.0) * u); tmp = single(0.0); if (t_0 <= single(0.9997000098228455)) tmp = s * log((single(1.0) / t_0)); else tmp = (single(4.0) * u) * s; end tmp_2 = tmp; end
\begin{array}{l}
\\
\begin{array}{l}
t_0 := 1 - 4 \cdot u\\
\mathbf{if}\;t\_0 \leq 0.9997000098228455:\\
\;\;\;\;s \cdot \log \left(\frac{1}{t\_0}\right)\\
\mathbf{else}:\\
\;\;\;\;\left(4 \cdot u\right) \cdot s\\
\end{array}
\end{array}
if (-.f32 #s(literal 1 binary32) (*.f32 #s(literal 4 binary32) u)) < 0.99970001Initial program 86.8%
if 0.99970001 < (-.f32 #s(literal 1 binary32) (*.f32 #s(literal 4 binary32) u)) Initial program 44.1%
Taylor expanded in u around 0
lower-*.f3290.7
Applied rewrites90.7%
Final simplification89.4%
(FPCore (s u) :precision binary32 (* (* 4.0 u) s))
float code(float s, float u) {
return (4.0f * u) * s;
}
real(4) function code(s, u)
real(4), intent (in) :: s
real(4), intent (in) :: u
code = (4.0e0 * u) * s
end function
function code(s, u) return Float32(Float32(Float32(4.0) * u) * s) end
function tmp = code(s, u) tmp = (single(4.0) * u) * s; end
\begin{array}{l}
\\
\left(4 \cdot u\right) \cdot s
\end{array}
Initial program 58.3%
Taylor expanded in u around 0
lower-*.f3276.4
Applied rewrites76.4%
Final simplification76.4%
(FPCore (s u) :precision binary32 (* 4.0 (* u s)))
float code(float s, float u) {
return 4.0f * (u * s);
}
real(4) function code(s, u)
real(4), intent (in) :: s
real(4), intent (in) :: u
code = 4.0e0 * (u * s)
end function
function code(s, u) return Float32(Float32(4.0) * Float32(u * s)) end
function tmp = code(s, u) tmp = single(4.0) * (u * s); end
\begin{array}{l}
\\
4 \cdot \left(u \cdot s\right)
\end{array}
Initial program 58.3%
Taylor expanded in u around 0
lower-*.f32N/A
*-commutativeN/A
lower-*.f3276.1
Applied rewrites76.1%
herbie shell --seed 2024216
(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))))))