It is still a 64-bit OS code, but using 64-bit integer arguments for all functions.int64 refers to the default type of integer arguments expected by the FORTRAN library functions (all ACML functions are FORTRAN callable).The default integer size is INT*4, for 4 bytes, or 32-bits, or int32 (which is never really used as a descriptor).Int64 refers to using full 64-bit integers as the default integer size for fortran calls.int64 has no affect at all on the default type of floating point data and calling arguments.int64 also affects the C callable interface, which has to comprehend the proper size of integer variables. But if the array was larger than 2^32 numbers, then N must be stored in more than 32-bits.But acml-4-2-0-gfortran-64bit expects 32-bit integer values when integers are part of a function’s argument list.
Most applications will use the standard build (not int64). The user will often know if this is the case for gfortran because –fdefault-integer-8 is on the compile line for their fortran code.
Both of the named tgz files are 64-bit versions of ACML.
64-bit refers to the compiled code base: it’s compiled for 64-bit OS and 64-bit executable binary interface rules.
Note that there is no performance penalty for using the int64 version.
For instance there are two 64-bit gfortran downloads: acml-4-2-0-gfortran-64and acml-4-2-0-gfortran-64bit-int64
So what’s the difference, and when should the int64 version be used?