Cruz Cortés Nareli
Rivera Zamarripa Luis Alberto
Título A GPU parallel implementation of the RSA private operation
Tipo Congreso
Sub-tipo Memoria
Descripción 3rd Latin American Conference on High Performance Computing, CARLA 2016
Resumen The implementation of the RSA private operation tends to be expensive since its computationally complexity is cubic with respect to the bit-size of its private key. As a consequence, considerable effort has been put into optimizing this operation. In this work, we present a parallel implementation of the RSA private operation using the Single Instruction Multiple Thread (SIMT) threading model of Graphics Processor Unit (GPU) platforms. The underlying modular arithmetic is performed by means of the Residue Number System (RNS) representation. By combining these two approaches, we present a GPU software library that achieves high-speed timings for the RSA private operation when using 1024-, 2048- and 3072-bit secret keys.
Observaciones ; Communications in Computer and Information Science v. 697
Lugar Ciudad de México
País Mexico
No. de páginas 188-203
Vol. / Cap.
Inicio 2016-08-29
Fin 2016-09-02
ISBN/ISSN 9783319579719