Skip to content

[Precision Depth Alignment] fix precision for paddle.expm1 #75549

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Sep 28, 2025
Merged

[Precision Depth Alignment] fix precision for paddle.expm1 #75549

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
86a4662
accuracy_stable_expm1
zhengshengning Sep 26, 2025
bcf0c68
fix
zhengshengning Sep 26, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 15 additions & 3 deletions paddle/phi/kernels/funcs/activation_functor.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3798,20 +3798,31 @@ struct CudaExpm1Functor<double> : public BaseActivationFunctor<double> {
}
};

template <typename T>
__device__ __forceinline__ ComplexType<T> local_expm1(const ComplexType<T>& z) {
T x = z.real;
T y = z.imag;
T a = std::sin(y / 2);
T er = std::expm1(x) * std::cos(y) - T(2) * a * a;
T ei = std::exp(x) * std::sin(y);
return {er, ei};
}

template <typename T>
struct CudaExpm1Functor<ComplexType<T>>
: public BaseActivationFunctor<ComplexType<T>> {
__device__ __forceinline__ ComplexType<T> operator()(
const ComplexType<T> x) const {
return static_cast<ComplexType<T>>(Expm1<ComplexType<T>>()(x));
return static_cast<ComplexType<T>>(local_expm1(x));
}
};

template <typename T>
struct CudaExpm1GradFunctor : public BaseActivationFunctor<T> {
T one = static_cast<T>(1.0f);
// dx = dout * out
__device__ __forceinline__ T operator()(const T dout, const T out) const {
return dout * out + dout;
return dout * (out + one);
}

static constexpr ActBwdOpFwdDeps FwdDeps() {
Expand All @@ -3822,10 +3833,11 @@ struct CudaExpm1GradFunctor : public BaseActivationFunctor<T> {
template <typename T>
struct CudaExpm1GradFunctor<ComplexType<T>>
: public BaseActivationFunctor<ComplexType<T>> {
ComplexType<T> one = static_cast<ComplexType<T>>(1.0f);
// dx = dout * exp(x)
__device__ __forceinline__ ComplexType<T> operator()(
const ComplexType<T> dout, const ComplexType<T> out) const {
return static_cast<ComplexType<T>>(dout * conj(out) + dout);
return static_cast<ComplexType<T>>(dout * (conj(out) + one));
}

static constexpr ActBwdOpFwdDeps FwdDeps() {
Expand Down
Loading