منابع مشابه
Compiler Controlled Register Stack Management for the Intel
Intel Itanium processors were designed with an on chip register stack engine (RSE) in order to reduce the overhead related to procedure call boundaries. The RSE automatically preserves values stored in stacked registers across procedure invocations. This architecture model significantly reduces the amount of spill code necessary to maintain an application’s state, which in turn reduces memory t...
متن کاملOffload Compiler Runtime for the Intel® Xeon Phi Coprocessor
The Intel® Xeon PhiTM coprocessor platform enables offload of computation from a host processor to a coprocessor that is a fully-functional Intel® Architecture CPU. This paper presents the C/C++ and Fortran compiler offload runtime for that coprocessor. The paper addresses why offload to a coprocessor is useful, how it is specified, and what the conditions for the profitability of offload are. ...
متن کاملSMLNJ: Intel x86 back end Compiler Controlled Memory
This note describes the code generation algorithm used for the Intel x86, introduced in version 110.16. The standard Chaitin graph coloring register allocation cannot be used directly for machines with few registers, as all temporaries wind up being spilled, making for a poor allocation[Cha82]. Thus, for the x86, the conceptual model of the architecture has been extended with a set of memory lo...
متن کاملAn Overview of the Intel® IA-64 Compiler
The IA-64 architecture is designed with a unique combination of rich features so that it overcomes the limitations of traditional architectures and provides performance scalability for the future. The IA-64 features expose new opportunities for the compiler to optimize applications. We have incorporated into the Intel IA-64 compiler the key technology necessary to exploit these new optimization...
متن کاملExploring the Use of Hyper-Threading Technology for Multimedia Applications with Intel® OpenMP* Compiler
Processors with Hyper-Threading technology can improve the performance of applications by permitting a single processor to process data as if it were two processors by executing instructions from different threads in parallel rather than serially. However, the potential performance improvement can be only obtained if an application is multithreaded by parallelization techniques. This paper pres...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: The Journal of The Institute of Image Information and Television Engineers
سال: 2011
ISSN: 1342-6907,1881-6908
DOI: 10.3169/itej.65.1304