Mercurial > hg > graal-compiler
diff src/share/vm/memory/padded.hpp @ 17760:5479cb006184
8036860: Pad and cache-align the BiasedMappedArray
Summary: Pad and cache-align BiasedMappedArray instances by default to avoid performance variability problems due to false sharing, as instances of this data structures are typically used for performance sensitive code.
Reviewed-by: brutisso, stefank
author | tschatzl |
---|---|
date | Mon, 24 Mar 2014 15:31:00 +0100 |
parents | d7070f371770 |
children |
line wrap: on
line diff
--- a/src/share/vm/memory/padded.hpp Mon Mar 24 15:30:56 2014 +0100 +++ b/src/share/vm/memory/padded.hpp Mon Mar 24 15:31:00 2014 +0100 @@ -101,4 +101,12 @@ static T** create_unfreeable(uint rows, uint columns, size_t* allocation_size = NULL); }; +// Helper class to create an array of T objects. The array as a whole will +// start at a multiple of alignment and its size will be aligned to alignment. +template <class T, MEMFLAGS flags, size_t alignment = DEFAULT_CACHE_LINE_SIZE> +class PaddedPrimitiveArray { + public: + static T* create_unfreeable(size_t length); +}; + #endif // SHARE_VM_MEMORY_PADDED_HPP