Mercurial > hg > graal-compiler
diff src/share/vm/memory/padded.hpp @ 17754:d7070f371770
8035815: Cache-align and pad the from card cache
Summary: The from card cache is a very frequently accessed data structure. It is essentially a 2d array of per-region values, one row of values for every GC thread. Pad and align the data structure to avoid false sharing.
Reviewed-by: stefank
| author | tschatzl |
|---|---|
| date | Mon, 24 Mar 2014 15:30:30 +0100 |
| parents | 9766f73e770d |
| children | 5479cb006184 |
line wrap: on
line diff
--- a/src/share/vm/memory/padded.hpp Mon Mar 24 15:30:14 2014 +0100 +++ b/src/share/vm/memory/padded.hpp Mon Mar 24 15:30:30 2014 +0100 @@ -1,5 +1,5 @@ /* - * Copyright (c) 2013, Oracle and/or its affiliates. All rights reserved. + * Copyright (c) 2013, 2014, Oracle and/or its affiliates. All rights reserved. * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. * * This code is free software; you can redistribute it and/or modify it @@ -90,4 +90,15 @@ static PaddedEnd<T>* create_unfreeable(uint length); }; +// Helper class to create an array of references to arrays of primitive types +// Both the array of references and the data arrays are aligned to the given +// alignment. The allocated memory is zero-filled. +template <class T, MEMFLAGS flags, size_t alignment = DEFAULT_CACHE_LINE_SIZE> +class Padded2DArray { + public: + // Creates an aligned padded 2D array. + // The memory cannot be deleted since the raw memory chunk is not returned. + static T** create_unfreeable(uint rows, uint columns, size_t* allocation_size = NULL); +}; + #endif // SHARE_VM_MEMORY_PADDED_HPP