ARMv8 SHA256指令集测试

ARMv8指令集新增了crypto加密指令集,支持包括AES、SHA1、SHA256
SHA256指令集支持128bit的寄存器
1

PINE 64 aarch64环境下测试
速度对比:10000000次计算SHA256测试

CPU C CODE : time:14872734 ns

ARMv8 HW : time:1567756 ns

下面是aarch64下的部分汇编代码

    ld1       {v5.16b-v8.16b}, [x1], #64
    mov       v2.16b, v0.16b
    mov       v3.16b, v1.16b

    rev32     v5.16b, v5.16b
    rev32     v6.16b, v6.16b
    add       v9.4s, v5.4s, v16.4s
    rev32     v7.16b, v7.16b
    add       v10.4s, v6.4s, v17.4s
    mov       v4.16b, v2.16b
    sha256h   q2, q3, v9.4s
    sha256h2  q3, q4, v9.4s
    sha256su0 v5.4s, v6.4s
    rev32     v8.16b, v8.16b
    add       v9.4s, v7.4s, v18.4s
    mov       v4.16b, v2.16b
    sha256h   q2, q3, v10.4s
    sha256h2  q3, q4, v10.4s
    sha256su0 v6.4s, v7.4s
    sha256su1 v5.4s, v7.4s, v8.4s
    add       v10.4s, v8.4s, v19.4s
    mov       v4.16b, v2.16b
    sha256h   q2, q3, v9.4s
    sha256h2  q3, q4, v9.4s
    sha256su0 v7.4s, v8.4s
    sha256su1 v6.4s, v8.4s, v5.4s
    add       v9.4s, v5.4s, v20.4s
    mov       v4.16b, v2.16b
    sha256h   q2, q3, v10.4s
    sha256h2  q3, q4, v10.4s
    sha256su0 v8.4s, v5.4s


完整测试代码:github

发表回复

您的电子邮箱地址不会被公开。 必填项已用 * 标注