Merge #18011: Replace current benchmarking framework with nanobench

78c312c983255e15fc274de2368a2ec13ce81cbf Replace current benchmarking framework with nanobench (Martin Ankerl)

Pull request description:

  Replace current benchmarking framework with nanobench

  This replaces the current benchmarking framework with nanobench [1], an
  MIT licensed single-header benchmarking library, of which I am the
  autor. This has in my opinion several advantages, especially on Linux:

  * fast: Running all benchmarks takes ~6 seconds instead of 4m13s on
    an Intel i7-8700 CPU @ 3.20GHz.

  * accurate: I ran e.g. the benchmark for SipHash_32b 10 times and
    calculate standard deviation / mean = coefficient of variation:

    * 0.57% CV for old benchmarking framework
    * 0.20% CV for nanobench

    So the benchmark results with nanobench seem to vary less than with
    the old framework.

  * It automatically determines runtime based on clock precision, no need
    to specify number of evaluations.

  * measure instructions, cycles, branches, instructions per cycle,
    branch misses (only Linux, when performance counters are available)

  * output in markdown table format.

  * Warn about unstable environment (frequency scaling, turbo, ...)

  * For better profiling, it is possible to set the environment variable
    NANOBENCH_ENDLESS to force endless running of a particular benchmark
    without the need to recompile. This makes it to e.g. run "perf top"
    and look at hotspots.

  Here is an example copy & pasted from the terminal output:

  |             ns/byte |              byte/s |    err% |        ins/byte |        cyc/byte |    IPC |       bra/byte |   miss% |     total | benchmark
  |--------------------:|--------------------:|--------:|----------------:|----------------:|-------:|---------------:|--------:|----------:|:----------
  |                2.52 |      396,529,415.94 |    0.6% |           25.42 |            8.02 |  3.169 |           0.06 |    0.0% |      0.03 | `bench/crypto_hash.cpp RIPEMD160`
  |                1.87 |      535,161,444.83 |    0.3% |           21.36 |            5.95 |  3.589 |           0.06 |    0.0% |      0.02 | `bench/crypto_hash.cpp SHA1`
  |                3.22 |      310,344,174.79 |    1.1% |           36.80 |           10.22 |  3.601 |           0.09 |    0.0% |      0.04 | `bench/crypto_hash.cpp SHA256`
  |                2.01 |      496,375,796.23 |    0.0% |           18.72 |            6.43 |  2.911 |           0.01 |    1.0% |      0.00 | `bench/crypto_hash.cpp SHA256D64_1024`
  |                7.23 |      138,263,519.35 |    0.1% |           82.66 |           23.11 |  3.577 |           1.63 |    0.1% |      0.00 | `bench/crypto_hash.cpp SHA256_32b`
  |                3.04 |      328,780,166.40 |    0.3% |           35.82 |            9.69 |  3.696 |           0.03 |    0.0% |      0.03 | `bench/crypto_hash.cpp SHA512`

  [1] https://github.com/martinus/nanobench

ACKs for top commit:
  laanwj:
    ACK 78c312c983255e15fc274de2368a2ec13ce81cbf

Tree-SHA512: 9e18770b18b6f95a7d0105a4a5497d31cf4eb5efe6574f4482f6f1b4c88d7e0946b9a4a1e9e8e6ecbf41a3f2d7571240677dcb45af29a6f0584e89b25f32e49e

1 files changed, 36 insertions, 32 deletions

diff --git a/src/bench/crypto_hash.cpp b/src/bench/crypto_hash.cpp
index ddcef5121e..36be86bcc8 100644
--- a/src/bench/crypto_hash.cpp
+++ b/src/bench/crypto_hash.cpp
@@ -16,88 +16,92 @@
 /* Number of bytes to hash per iteration */
 static const uint64_t BUFFER_SIZE = 1000*1000;
 
-static void RIPEMD160(benchmark::State& state)
+static void RIPEMD160(benchmark::Bench& bench)
 {
     uint8_t hash[CRIPEMD160::OUTPUT_SIZE];
     std::vector<uint8_t> in(BUFFER_SIZE,0);
-    while (state.KeepRunning())
+    bench.batch(in.size()).unit("byte").run([&] {
         CRIPEMD160().Write(in.data(), in.size()).Finalize(hash);
+    });
 }
 
-static void SHA1(benchmark::State& state)
+static void SHA1(benchmark::Bench& bench)
 {
     uint8_t hash[CSHA1::OUTPUT_SIZE];
     std::vector<uint8_t> in(BUFFER_SIZE,0);
-    while (state.KeepRunning())
+    bench.batch(in.size()).unit("byte").run([&] {
         CSHA1().Write(in.data(), in.size()).Finalize(hash);
+    });
 }
 
-static void SHA256(benchmark::State& state)
+static void SHA256(benchmark::Bench& bench)
 {
     uint8_t hash[CSHA256::OUTPUT_SIZE];
     std::vector<uint8_t> in(BUFFER_SIZE,0);
-    while (state.KeepRunning())
+    bench.batch(in.size()).unit("byte").run([&] {
         CSHA256().Write(in.data(), in.size()).Finalize(hash);
+    });
 }
 
-static void SHA256_32b(benchmark::State& state)
+static void SHA256_32b(benchmark::Bench& bench)
 {
     std::vector<uint8_t> in(32,0);
-    while (state.KeepRunning()) {
+    bench.batch(in.size()).unit("byte").run([&] {
         CSHA256()
             .Write(in.data(), in.size())
             .Finalize(in.data());
-    }
+    });
 }
 
-static void SHA256D64_1024(benchmark::State& state)
+static void SHA256D64_1024(benchmark::Bench& bench)
 {
     std::vector<uint8_t> in(64 * 1024, 0);
-    while (state.KeepRunning()) {
+    bench.batch(in.size()).unit("byte").run([&] {
         SHA256D64(in.data(), in.data(), 1024);
-    }
+    });
 }
 
-static void SHA512(benchmark::State& state)
+static void SHA512(benchmark::Bench& bench)
 {
     uint8_t hash[CSHA512::OUTPUT_SIZE];
     std::vector<uint8_t> in(BUFFER_SIZE,0);
-    while (state.KeepRunning())
+    bench.batch(in.size()).unit("byte").run([&] {
         CSHA512().Write(in.data(), in.size()).Finalize(hash);
+    });
 }
 
-static void SipHash_32b(benchmark::State& state)
+static void SipHash_32b(benchmark::Bench& bench)
 {
     uint256 x;
     uint64_t k1 = 0;
-    while (state.KeepRunning()) {
+    bench.run([&] {
         *((uint64_t*)x.begin()) = SipHashUint256(0, ++k1, x);
-    }
+    });
 }
 
-static void FastRandom_32bit(benchmark::State& state)
+static void FastRandom_32bit(benchmark::Bench& bench)
 {
     FastRandomContext rng(true);
-    while (state.KeepRunning()) {
+    bench.run([&] {
         rng.rand32();
-    }
+    });
 }
 
-static void FastRandom_1bit(benchmark::State& state)
+static void FastRandom_1bit(benchmark::Bench& bench)
 {
     FastRandomContext rng(true);
-    while (state.KeepRunning()) {
+    bench.run([&] {
         rng.randbool();
-    }
+    });
 }
 
-BENCHMARK(RIPEMD160, 440);
-BENCHMARK(SHA1, 570);
-BENCHMARK(SHA256, 340);
-BENCHMARK(SHA512, 330);
+BENCHMARK(RIPEMD160);
+BENCHMARK(SHA1);
+BENCHMARK(SHA256);
+BENCHMARK(SHA512);
 
-BENCHMARK(SHA256_32b, 4700 * 1000);
-BENCHMARK(SipHash_32b, 40 * 1000 * 1000);
-BENCHMARK(SHA256D64_1024, 7400);
-BENCHMARK(FastRandom_32bit, 110 * 1000 * 1000);
-BENCHMARK(FastRandom_1bit, 440 * 1000 * 1000);
+BENCHMARK(SHA256_32b);
+BENCHMARK(SipHash_32b);
+BENCHMARK(SHA256D64_1024);
+BENCHMARK(FastRandom_32bit);
+BENCHMARK(FastRandom_1bit);