devtools/eigen
1
0
Fork 0
mirror of https://gitlab.com/libeigen/eigen.git synced 2026-04-10 11:34:33 +08:00
Code Issues Packages Projects Releases Wiki Activity

Enable equality comparisons on GPU.

Browse Source 
Since `std::equal_to::operator()` is not a device function, it
fails on GPU.  On my device, I seem to get a silent crash in the
kernel (no reported error, but the kernel does not complete).

Replacing this with a portable version enables comparisons on device.

Addresses #2292 - would need to be cherry-picked.  The 3.3 branch
also requires adding `EIGEN_DEVICE_FUNC` in `BooleanRedux.h` to get
fully working.


(cherry picked from commit 7880f10526)
This commit is contained in:
Antonio Sanchez
2021-07-20 13:53:41 -07:00
committed by Rasmus Munk Larsen
parent 7adc1545b4
commit 3dc42eeaec
3 changed files with 41 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
Eigen/src/Core/functors/StlFunctors.h
View File

@@ -12,6 +12,28 @@
namespace Eigen {
// Portable replacements for certain functors.
namespace numext {
template<typename T = void>
struct equal_to {
typedef bool result_type;
EIGEN_DEVICE_FUNC bool operator()(const T& lhs, const T& rhs) const {
return lhs == rhs;
}
};
template<typename T = void>
struct not_equal_to {
typedef bool result_type;
EIGEN_DEVICE_FUNC bool operator()(const T& lhs, const T& rhs) const {
return lhs != rhs;
}
};
}
namespace internal {
// default functor traits for STL functors:
@@ -68,10 +90,18 @@ template<typename T>
struct functor_traits<std::equal_to<T> >
{ enum { Cost = 1, PacketAccess = false }; };
template<typename T>
struct functor_traits<numext::equal_to<T> >
: functor_traits<std::equal_to<T> > {};
template<typename T>
struct functor_traits<std::not_equal_to<T> >
{ enum { Cost = 1, PacketAccess = false }; };
template<typename T>
struct functor_traits<numext::not_equal_to<T> >
: functor_traits<std::not_equal_to<T> > {};
#if (EIGEN_COMP_CXXVER < 11)
// std::binder* are deprecated since c++11 and will be removed in c++17
template<typename T>