From 5a30b087c3a3c4435e680e6c61082d5432fa0ace Mon Sep 17 00:00:00 2001
From: MinetaS <skdty87@gmail.com>
Date: Wed, 25 Jan 2023 07:32:02 +0900
Subject: [PATCH] Expand statistics tools for engine development

This patch adds more debugging slots up to 32 per type and provide tools
to calculate standard deviation and Pearson's correlation coefficient.

However, due to slot being 0 at default, dbg_hit_on(c, b) has to be removed.

Initial idea from snicolet/Stockfish@d8ab604

closes https://github.com/official-stockfish/Stockfish/pull/4354

No functional change
---
 src/misc.cpp | 94 ++++++++++++++++++++++++++++++++++++++++++++++------
 src/misc.h   |  7 ++--
 2 files changed, 88 insertions(+), 13 deletions(-)

diff --git a/src/misc.cpp b/src/misc.cpp
index b651972b..7d848d32 100644
--- a/src/misc.cpp
+++ b/src/misc.cpp
@@ -41,6 +41,7 @@ typedef WORD(*fun5_t)();
 }
 #endif
 
+#include <cmath>
 #include <cstdlib>
 #include <fstream>
 #include <iomanip>
@@ -299,21 +300,94 @@ std::string compiler_info() {
 
 
 /// Debug functions used mainly to collect run-time statistics
-static std::atomic<int64_t> hits[2], means[2];
+constexpr int MaxDebugSlots = 32;
 
-void dbg_hit_on(bool b) { ++hits[0]; if (b) ++hits[1]; }
-void dbg_hit_on(bool c, bool b) { if (c) dbg_hit_on(b); }
-void dbg_mean_of(int v) { ++means[0]; means[1] += v; }
+namespace {
+
+template<size_t N>
+struct DebugInfo {
+    std::atomic<int64_t> data[N] = { 0 };
+
+    constexpr inline std::atomic<int64_t>& operator[](int index) { return data[index]; }
+};
+
+DebugInfo<2> hit[MaxDebugSlots];
+DebugInfo<2> mean[MaxDebugSlots];
+DebugInfo<3> stdev[MaxDebugSlots];
+DebugInfo<6> correl[MaxDebugSlots];
+
+}  // namespace
+
+void dbg_hit_on(bool cond, int slot) {
+
+    ++hit[slot][0];
+    if (cond)
+        ++hit[slot][1];
+}
+
+void dbg_mean_of(int64_t value, int slot) {
+
+    ++mean[slot][0];
+    mean[slot][1] += value;
+}
+
+void dbg_stdev_of(int64_t value, int slot) {
+
+    ++stdev[slot][0];
+    stdev[slot][1] += value;
+    stdev[slot][2] += value * value;
+}
+
+void dbg_correl_of(int64_t value1, int64_t value2, int slot) {
+
+    ++correl[slot][0];
+    correl[slot][1] += value1;
+    correl[slot][2] += value1 * value1;
+    correl[slot][3] += value2;
+    correl[slot][4] += value2 * value2;
+    correl[slot][5] += value1 * value2;
+}
 
 void dbg_print() {
 
-  if (hits[0])
-      cerr << "Total " << hits[0] << " Hits " << hits[1]
-           << " hit rate (%) " << 100 * hits[1] / hits[0] << endl;
+    int64_t n;
+    auto E   = [&n](int64_t x) { return double(x) / n; };
+    auto sqr = [](double x) { return x * x; };
 
-  if (means[0])
-      cerr << "Total " << means[0] << " Mean "
-           << (double)means[1] / means[0] << endl;
+    for (int i = 0; i < MaxDebugSlots; ++i)
+        if ((n = hit[i][0]))
+            std::cerr << "Hit #" << i
+                      << ": Total " << n << " Hits " << hit[i][1]
+                      << " Hit Rate (%) " << 100.0 * E(hit[i][1])
+                      << std::endl;
+
+    for (int i = 0; i < MaxDebugSlots; ++i)
+        if ((n = mean[i][0]))
+        {
+            std::cerr << "Mean #" << i
+                      << ": Total " << n << " Mean " << E(mean[i][1])
+                      << std::endl;
+        }
+
+    for (int i = 0; i < MaxDebugSlots; ++i)
+        if ((n = stdev[i][0]))
+        {
+            double r = sqrtl(E(stdev[i][2]) - sqr(E(stdev[i][1])));
+            std::cerr << "Stdev #" << i
+                      << ": Total " << n << " Stdev " << r
+                      << std::endl;
+        }
+
+    for (int i = 0; i < MaxDebugSlots; ++i)
+        if ((n = correl[i][0]))
+        {
+            double r = (E(correl[i][5]) - E(correl[i][1]) * E(correl[i][3]))
+                       / (  sqrtl(E(correl[i][2]) - sqr(E(correl[i][1])))
+                          * sqrtl(E(correl[i][4]) - sqr(E(correl[i][3]))));
+            std::cerr << "Correl. #" << i
+                      << ": Total " << n << " Coefficient " << r
+                      << std::endl;
+        }
 }
 
 
diff --git a/src/misc.h b/src/misc.h
index 4c1150f8..9761da8a 100644
--- a/src/misc.h
+++ b/src/misc.h
@@ -39,9 +39,10 @@ void std_aligned_free(void* ptr);
 void* aligned_large_pages_alloc(size_t size); // memory aligned by page size, min alignment: 4096 bytes
 void aligned_large_pages_free(void* mem); // nop if mem == nullptr
 
-void dbg_hit_on(bool b);
-void dbg_hit_on(bool c, bool b);
-void dbg_mean_of(int v);
+void dbg_hit_on(bool cond, int slot = 0);
+void dbg_mean_of(int64_t value, int slot = 0);
+void dbg_stdev_of(int64_t value, int slot = 0);
+void dbg_correl_of(int64_t value1, int64_t value2, int slot = 0);
 void dbg_print();
 
 typedef std::chrono::milliseconds::rep TimePoint; // A value in milliseconds
-- 
2.39.2