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, 43 insertions, 48 deletions

diff --git a/src/bench/prevector.cpp b/src/bench/prevector.cpp
index 42b351a72d..a2dbefa54a 100644
--- a/src/bench/prevector.cpp
+++ b/src/bench/prevector.cpp
@@ -30,51 +30,44 @@ static_assert(IS_TRIVIALLY_CONSTRUCTIBLE<trivial_t>::value,
               "expected trivial_t to be trivially constructible");
 
 template <typename T>
-static void PrevectorDestructor(benchmark::State& state)
+static void PrevectorDestructor(benchmark::Bench& bench)
 {
-    while (state.KeepRunning()) {
-        for (auto x = 0; x < 1000; ++x) {
-            prevector<28, T> t0;
-            prevector<28, T> t1;
-            t0.resize(28);
-            t1.resize(29);
-        }
-    }
+    bench.batch(2).run([&] {
+        prevector<28, T> t0;
+        prevector<28, T> t1;
+        t0.resize(28);
+        t1.resize(29);
+    });
 }
 
 template <typename T>
-static void PrevectorClear(benchmark::State& state)
+static void PrevectorClear(benchmark::Bench& bench)
 {
-
-    while (state.KeepRunning()) {
-        for (auto x = 0; x < 1000; ++x) {
-            prevector<28, T> t0;
-            prevector<28, T> t1;
-            t0.resize(28);
-            t0.clear();
-            t1.resize(29);
-            t1.clear();
-        }
-    }
+    prevector<28, T> t0;
+    prevector<28, T> t1;
+    bench.batch(2).run([&] {
+        t0.resize(28);
+        t0.clear();
+        t1.resize(29);
+        t1.clear();
+    });
 }
 
 template <typename T>
-static void PrevectorResize(benchmark::State& state)
+static void PrevectorResize(benchmark::Bench& bench)
 {
-    while (state.KeepRunning()) {
-        prevector<28, T> t0;
-        prevector<28, T> t1;
-        for (auto x = 0; x < 1000; ++x) {
-            t0.resize(28);
-            t0.resize(0);
-            t1.resize(29);
-            t1.resize(0);
-        }
-    }
+    prevector<28, T> t0;
+    prevector<28, T> t1;
+    bench.batch(4).run([&] {
+        t0.resize(28);
+        t0.resize(0);
+        t1.resize(29);
+        t1.resize(0);
+    });
 }
 
 template <typename T>
-static void PrevectorDeserialize(benchmark::State& state)
+static void PrevectorDeserialize(benchmark::Bench& bench)
 {
     CDataStream s0(SER_NETWORK, 0);
     prevector<28, T> t0;
@@ -86,26 +79,28 @@ static void PrevectorDeserialize(benchmark::State& state)
     for (auto x = 0; x < 101; ++x) {
         s0 << t0;
     }
-    while (state.KeepRunning()) {
+    bench.batch(1000).run([&] {
         prevector<28, T> t1;
         for (auto x = 0; x < 1000; ++x) {
             s0 >> t1;
         }
         s0.Init(SER_NETWORK, 0);
-    }
+    });
 }
 
-#define PREVECTOR_TEST(name, nontrivops, trivops)                       \
-    static void Prevector ## name ## Nontrivial(benchmark::State& state) { \
-        Prevector ## name<nontrivial_t>(state);                         \
-    }                                                                   \
-    BENCHMARK(Prevector ## name ## Nontrivial, nontrivops);             \
-    static void Prevector ## name ## Trivial(benchmark::State& state) { \
-        Prevector ## name<trivial_t>(state);                            \
-    }                                                                   \
-    BENCHMARK(Prevector ## name ## Trivial, trivops);
+#define PREVECTOR_TEST(name)                                         \
+    static void Prevector##name##Nontrivial(benchmark::Bench& bench) \
+    {                                                                \
+        Prevector##name<nontrivial_t>(bench);                        \
+    }                                                                \
+    BENCHMARK(Prevector##name##Nontrivial);                          \
+    static void Prevector##name##Trivial(benchmark::Bench& bench)    \
+    {                                                                \
+        Prevector##name<trivial_t>(bench);                           \
+    }                                                                \
+    BENCHMARK(Prevector##name##Trivial);
 
-PREVECTOR_TEST(Clear, 28300, 88600)
-PREVECTOR_TEST(Destructor, 28800, 88900)
-PREVECTOR_TEST(Resize, 28900, 90300)
-PREVECTOR_TEST(Deserialize, 6800, 52000)
+PREVECTOR_TEST(Clear)
+PREVECTOR_TEST(Destructor)
+PREVECTOR_TEST(Resize)
+PREVECTOR_TEST(Deserialize)