在 Visual Studio 2017 中计算 AES/CCM 的时间加密

我正在使用库 Crypto++ 5.6.5 和 Visual Studio 2017.

I am using the library Crypto++ 5.6.5 and Visual Studio 2017.

如何计算 AES-CCM 的加密时间?

How can I calculate the encryption time for AES-CCM?

推荐答案

我想知道如何计算 AES-CCM 的加密时间.

I would like to know how to calculate the encryption time for AES-CCM.

Crypto++ wiki 提供了一篇文章基准.它提供了许多有关库性能、吞吐量计算方式的详细信息,甚至还引用了测量实际吞吐量的源代码.信不信由你,对 clock 的简单调用就可以很好地测量批量加密.另请参阅基准 |时间循环在同一篇维基文章中.

The Crypto++ wiki provides an article Benchmarks. It provides a lot of details regarding library performance, how throughput is calculated, and it even references the source code where the actual throughput is measured. Believe it or not, a simple call to clock works just fine to measure bulk encryption. Also see Benchmarks | Timing Loop in the same wiki article.

要对 AES/CCM 进行基准测试,请执行以下操作.它基于 Crypto++ 基准测试代码,但它使用 ThreadUserTimer 而不是直接调用 clock.ThreadUserTimer 适用于所有操作系统和所有版本的 C++.

To benchmark AES/CCM, do something like the following. It is based on the Crypto++ benchmarking code, but it uses a ThreadUserTimer instead of a direct call to clock. ThreadUserTimer works across all OSes and all versions of C++.

您需要在 cpuFreq 上拨入您的处理器速度.您应该还运行./Governor.sh perf 将 CPU 从空闲或 C 级睡眠状态移动,但你不能,因为它是一个 Linux 脚本.您可以在 TestScript/ 文件夹中找到它.

You need to dial-in your processor speed at cpuFreq. You should also run ./governor.sh perf to move the CPU from an idle or C-level sleep state, but you can't because it is a Linux script. You can find it in the TestScript/ folder.

#include "cryptlib.h"
#include "secblock.h"
#include "hrtimer.h"
#include "osrng.h"
#include "modes.h"
#include "aes.h"
#include "ccm.h"
#include <iostream>

const double runTimeInSeconds = 3.0;
const double cpuFreq = 2.7*1000*1000*1000;

int main(int argc, char* argv[])
{
    using namespace CryptoPP;
    AutoSeededRandomPool prng;

    SecByteBlock key(16);
    prng.GenerateBlock(key, key.size());

    CCM<AES>::Encryption cipher;
    cipher.SetKeyWithIV(key, key.size(), key);

    const int BUF_SIZE=RoundUpToMultipleOf(2048U,
        dynamic_cast<StreamTransformation&>(cipher).OptimalBlockSize());

    AlignedSecByteBlock buf(BUF_SIZE);
    prng.GenerateBlock(buf, BUF_SIZE);

    double elapsedTimeInSeconds;
    unsigned long i=0, blocks=1;

    ThreadUserTimer timer;
    timer.StartTimer();

    do
    {
        blocks *= 2;
        for (; i<blocks; i++)
            cipher.ProcessString(buf, BUF_SIZE);
        elapsedTimeInSeconds = timer.ElapsedTimeAsDouble();
    }
    while (elapsedTimeInSeconds < runTimeInSeconds);

    const double bytes = static_cast<double>(BUF_SIZE) * blocks;
    const double ghz = cpuFreq / 1000 / 1000 / 1000;
    const double mbs = bytes / 1024 / 1024 / elapsedTimeInSeconds;
    const double cpb = elapsedTimeInSeconds * cpuFreq / bytes;

    std::cout << cipher.AlgorithmName() << " benchmarks..." << std::endl;
    std::cout << "  " << ghz << " GHz cpu frequency" << std::endl;
    std::cout << "  " << cpb << " cycles per byte (cpb)" << std::endl;
    std::cout << "  " << mbs << " MiB per second (MiB)" << std::endl;
    // std::cout << "  " << elapsedTimeInSeconds << " seconds passed" << std::endl;
    // std::cout << "  " << (word64) bytes << " bytes processed"  << std::endl;

    return 0;
}

在 2.7 GHz 的 Core i5-6400 上运行结果:

Running it on a Core i5-6400 at 2.7 GHz results in:

$ g++ bench.cxx ./libcryptopp.a -o bench.exe
$ ./bench.exe
AES/CCM benchmarks...
  2.7 GHz cpu frequency
  3.00491 cycles per byte (cpb)
  856.904 MiB per second (MiB)

<小时>

通常您使用 CTR 模式对库进行基准测试.例如,所有 SUPERCOP 基准测试都是使用该模式执行的.您可以通过包含 "modes.h" 来切换到 CTR 模式,然后:


Usually you benchmark a library with CTR mode. For example, all of the SUPERCOP benchmarks are performed using the mode. You can switch to CTR mode by including "modes.h", and then:

CTR_Mode<AES>::Encryption cipher;
cipher.SetKeyWithIV(key, key.size(), key);

最后,同样的测试使用CTR模式:

Finally, the same test using CTR mode:

$ ./bench.exe
AES/CTR benchmarks...
  2.7 GHz cpu frequency
  0.568922 cycles per byte (cpb)
  4525.97 MiB per second (MiB)

相关文章