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.
bug #1548
The macro EIGEN_IDEAL_MAX_ALIGN_BYTES is being incorrectly set to 32
on AVX512 builds. It should be set to 64. In the current code it is
only set to 64 if the macro EIGEN_VECTORIZE_AVX512 is defined. This
macro does get defined in AVX512 builds in Core, but only after Macros.h,
the file that defines EIGEN_IDEAL_MAX_ALIGN_BYTES, has been included.
This commit fixes the issue by setting EIGEN_IDEAL_MAX_ALIGN_BYTES to
64 if __AVX512F__ is defined.
Author: George Burgess IV <gbiv@google.com>
Date: Thu Mar 1 11:20:24 2018 -0800
Prefer `::operator new` to `new`
The C++ standard allows compilers much flexibility with `new`
expressions, including eliding them entirely
(https://godbolt.org/g/yS6i91). However, calls to `operator new` are
required to be treated like opaque function calls.
Since we're calling `new` for side-effects other than allocating heap
memory, we should prefer the less flexible version.
Signed-off-by: George Burgess IV <gbiv@google.com>
Only include the indexed view methods when the compiler supports the code.
This makes it possible to use Eigen again in complex code bases such as TensorFlow and older compilers such as gcc 4.8
The problem was that is "sparse" is not const, then sparse.diagonal() must have the
LValueBit flag meaning that sparse.diagonal().coeff(i) must returns a const reference,
const Scalar&. However, sparse::coeff() cannot returns a reference for a non-existing
zero coefficient. The trick is to return a reference to a local member of
evaluator<SparseMatrix>.
