UNIFIED AES-SMS4-CAMELLIA SYMMETRIC KEY BLOCK CIPHER ACCELERATION

    公开(公告)号:US20190386815A1

    公开(公告)日:2019-12-19

    申请号:US16010206

    申请日:2018-06-15

    申请人: Intel Corporation

    IPC分类号: H04L9/06 G09C1/00 G06F7/72

    摘要: Disclosed embodiments relate to a unified Advanced Encryption Standard (AES), SMS4, and Camellia (CML) accelerator. In one example, a processor includes fetch circuitry to fetch a cipher instruction specifying an opcode, a datum, and a key, the opcode to specify one of three cryptographic modes and an operation, decode circuitry to decode the fetched cipher instruction, and execution circuitry to respond to the decoded cipher instruction by performing the operation using a selected one of three block ciphers corresponding to the specified cryptographic mode and a unified cipher datapath shared by the three block ciphers, the unified cipher datapath comprising a plurality of hybrid substitution boxes (Sboxes) to perform Galois Field (GF) multiplications and inverse computations, wherein the unified cipher datapath is to implement an eighth-order polynomial isomorphically equivalent to each polynomial used by the three block ciphers by calculating and then combining two fourth-order polynomials.

    VARIABLE FORMAT, VARIABLE SPARSITY MATRIX MULTIPLICATION INSTRUCTION

    公开(公告)号:US20200334038A1

    公开(公告)日:2020-10-22

    申请号:US16921838

    申请日:2020-07-06

    申请人: Intel Corporation

    摘要: Disclosed embodiments relate to a variable format, variable sparsity matrix multiplication (VFVSMM) instruction. In one example, a processor includes fetch and decode circuitry to fetch and decode a VFVSMM instruction specifying locations of A, B, and C matrices having (M×K), (K×N), and (M×N) elements, respectively, execution circuitry, responsive to the decoded VFVSMM instruction, to: route each row of the specified A matrix, staggering subsequent rows, into corresponding rows of a (M×N) processing array, and route each column of the specified B matrix, staggering subsequent columns, into corresponding columns of the processing array, wherein each of the processing units is to generate K products of A-matrix elements and matching B-matrix elements having a same row address as a column address of the A-matrix element, and to accumulate each generated product with a corresponding C-matrix element.

    HYBRID AES-SMS4 HARDWARE ACCELERATOR
    5.
    发明申请

    公开(公告)号:US20180062829A1

    公开(公告)日:2018-03-01

    申请号:US15252741

    申请日:2016-08-31

    申请人: Intel Corporation

    IPC分类号: H04L9/06

    摘要: A hybrid AES-SMS4 hardware accelerator is described. A System on Chip implementing a hybrid AES-SMS4 hardware accelerator may include a processor core and a single hardware accelerator coupled to the processor core, the single hardware accelerator to encrypt or decrypt data. The single hardware accelerator may include a first block cipher to encrypt or decrypt the data according to a first encryption algorithm and a second block cipher to encrypt or decrypt the data according to a second encryption algorithm. The accelerator may further include a combined substitution box (Sbox) coupled to the first block cipher and the second block cipher, the combined Sbox comprising logic to perform Galois Field (GF) multiplications and inverse computations, wherein the inverse computations are common to the first block cipher and the second block cipher.