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, 14 insertions, 17 deletions

diff --git a/src/bench/lockedpool.cpp b/src/bench/lockedpool.cpp
index 5d943810df..32b060a15a 100644
--- a/src/bench/lockedpool.cpp
+++ b/src/bench/lockedpool.cpp
@@ -9,10 +9,9 @@
 #include <vector>
 
 #define ASIZE 2048
-#define BITER 5000
 #define MSIZE 2048
 
-static void BenchLockedPool(benchmark::State& state)
+static void BenchLockedPool(benchmark::Bench& bench)
 {
     void *synth_base = reinterpret_cast<void*>(0x08000000);
     const size_t synth_size = 1024*1024;
@@ -22,24 +21,22 @@ static void BenchLockedPool(benchmark::State& state)
     for (int x=0; x<ASIZE; ++x)
         addr.push_back(nullptr);
     uint32_t s = 0x12345678;
-    while (state.KeepRunning()) {
-        for (int x=0; x<BITER; ++x) {
-            int idx = s & (addr.size()-1);
-            if (s & 0x80000000) {
-                b.free(addr[idx]);
-                addr[idx] = nullptr;
-            } else if(!addr[idx]) {
-                addr[idx] = b.alloc((s >> 16) & (MSIZE-1));
-            }
-            bool lsb = s & 1;
-            s >>= 1;
-            if (lsb)
-                s ^= 0xf00f00f0; // LFSR period 0xf7ffffe0
+    bench.run([&] {
+        int idx = s & (addr.size() - 1);
+        if (s & 0x80000000) {
+            b.free(addr[idx]);
+            addr[idx] = nullptr;
+        } else if (!addr[idx]) {
+            addr[idx] = b.alloc((s >> 16) & (MSIZE - 1));
         }
-    }
+        bool lsb = s & 1;
+        s >>= 1;
+        if (lsb)
+            s ^= 0xf00f00f0; // LFSR period 0xf7ffffe0
+    });
     for (void *ptr: addr)
         b.free(ptr);
     addr.clear();
 }
 
-BENCHMARK(BenchLockedPool, 1300);
+BENCHMARK(BenchLockedPool);