Adding support for using Eigen in HIP kernels.

This commit enables the use of Eigen on HIP kernels / AMD GPUs. Support has been added along the same lines as what already exists for using Eigen in CUDA kernels / NVidia GPUs.

Application code needs to explicitly define EIGEN_USE_HIP when using Eigen in HIP kernels. This is because some of the CUDA headers get picked up by default during Eigen compile (irrespective of whether or not the underlying compiler is CUDACC/NVCC, for e.g. Eigen/src/Core/arch/CUDA/Half.h). In order to maintain this behavior, the EIGEN_USE_HIP macro is used to switch to using the HIP version of those header files (see Eigen/Core and unsupported/Eigen/CXX11/Tensor)


Use the "-DEIGEN_TEST_HIP" cmake option to enable the HIP specific unit tests.

1 files changed, 6 insertions, 2 deletions

diff --git a/Eigen/src/Core/GenericPacketMath.h b/Eigen/src/Core/GenericPacketMath.h
index 888a3f7ea..0903c3a6e 100644
--- a/Eigen/src/Core/GenericPacketMath.h
+++ b/Eigen/src/Core/GenericPacketMath.h
@@ -299,7 +299,11 @@ template<typename Scalar, typename Packet> EIGEN_DEVICE_FUNC inline void pstoreu
  { pstore(to, from); }
 
 /** \internal tries to do cache prefetching of \a addr */
-template<typename Scalar> EIGEN_DEVICE_FUNC inline void prefetch(const Scalar* addr)
+template<typename Scalar>
+  #if !defined(EIGEN_HIPCC)
+  EIGEN_DEVICE_FUNC
+  #endif
+  inline void prefetch(const Scalar* addr)
 {
 #ifdef EIGEN_CUDA_ARCH
 #if defined(__LP64__)
@@ -528,7 +532,7 @@ inline void palign(PacketType& first, const PacketType& second)
 ***************************************************************************/
 
 // Eigen+CUDA does not support complexes.
-#ifndef EIGEN_CUDACC
+#if !defined(EIGEN_CUDACC) && !defined(EIGEN_HIPCC)
 
 template<> inline std::complex<float> pmul(const std::complex<float>& a, const std::complex<float>& b)
 { return std::complex<float>(real(a)*real(b) - imag(a)*imag(b), imag(a)*real(b) + real(a)*imag(b)); }