aboutsummaryrefslogtreecommitdiffhomepage
path: root/Eigen
diff options
context:
space:
mode:
authorGravatar Christoph Hertzberg <chtz@informatik.uni-bremen.de>2018-10-01 16:51:04 +0000
committerGravatar Christoph Hertzberg <chtz@informatik.uni-bremen.de>2018-10-01 16:51:04 +0000
commit564ca71e392f580144a7ded4ac9e3700c848495e (patch)
tree7d5cafc2305816145c1f55f89effe0397f7ebc34 /Eigen
parent2088c0897f6ea7175d06de98fe04c71cd453a34d (diff)
parent94898488a6fe3096a7a44d0bb108e514f0e44699 (diff)
Merged in deven-amd/eigen/HIP_fixes (pull request PR-518)
PR with HIP specific fixes (for the eigen nightly regression failures in HIP mode)
Diffstat (limited to 'Eigen')
-rw-r--r--Eigen/src/Core/util/ConfigureVectorization.h6
-rw-r--r--Eigen/src/Core/util/Memory.h18
2 files changed, 19 insertions, 5 deletions
diff --git a/Eigen/src/Core/util/ConfigureVectorization.h b/Eigen/src/Core/util/ConfigureVectorization.h
index e75c7d89e..a2743624e 100644
--- a/Eigen/src/Core/util/ConfigureVectorization.h
+++ b/Eigen/src/Core/util/ConfigureVectorization.h
@@ -379,10 +379,12 @@
#include <cuda_fp16.h>
#endif
-#if defined(EIGEN_HIP_DEVICE_COMPILE)
-
+#if defined(EIGEN_HIPCC)
#define EIGEN_VECTORIZE_GPU
#include <hip/hip_vector_types.h>
+#endif
+
+#if defined(EIGEN_HIP_DEVICE_COMPILE)
#define EIGEN_HAS_HIP_FP16
#include <hip/hip_fp16.h>
diff --git a/Eigen/src/Core/util/Memory.h b/Eigen/src/Core/util/Memory.h
index 9dd2e0252..c624556c5 100644
--- a/Eigen/src/Core/util/Memory.h
+++ b/Eigen/src/Core/util/Memory.h
@@ -96,10 +96,16 @@ inline void throw_std_bad_alloc()
/** \internal Like malloc, but the returned pointer is guaranteed to be 16-byte aligned.
* Fast, but wastes 16 additional bytes of memory. Does not throw any exception.
*/
-inline void* handmade_aligned_malloc(std::size_t size, std::size_t alignment = EIGEN_DEFAULT_ALIGN_BYTES)
+EIGEN_DEVICE_FUNC inline void* handmade_aligned_malloc(std::size_t size, std::size_t alignment = EIGEN_DEFAULT_ALIGN_BYTES)
{
eigen_assert(alignment >= sizeof(void*) && (alignment & -alignment) == alignment && "Alignment must be at least sizeof(void*) and a power of 2");
+
+#if defined(EIGEN_HIP_DEVICE_COMPILE)
+ void *original = ::malloc(size+alignment);
+#else
void *original = std::malloc(size+alignment);
+#endif
+
if (original == 0) return 0;
void *aligned = reinterpret_cast<void*>((reinterpret_cast<std::size_t>(original) & ~(std::size_t(alignment-1))) + alignment);
*(reinterpret_cast<void**>(aligned) - 1) = original;
@@ -107,9 +113,15 @@ inline void* handmade_aligned_malloc(std::size_t size, std::size_t alignment = E
}
/** \internal Frees memory allocated with handmade_aligned_malloc */
-inline void handmade_aligned_free(void *ptr)
+EIGEN_DEVICE_FUNC inline void handmade_aligned_free(void *ptr)
{
- if (ptr) std::free(*(reinterpret_cast<void**>(ptr) - 1));
+ if (ptr) {
+#if defined(EIGEN_HIP_DEVICE_COMPILE)
+ ::free(*(reinterpret_cast<void**>(ptr) - 1));
+#else
+ std::free(*(reinterpret_cast<void**>(ptr) - 1));
+#endif
+ }
}
/** \internal