Tune up C-library stubs

Author: ckormanyos

ref_app/target/micros/xtensa_esp32_s3/startup/Std/StdLib.cpp

@@ -29,6 +29,108 @@
 
 extern "C" {
 
+typedef   signed long long DItype  __attribute__((mode (DI)));
+typedef unsigned long long UDItype __attribute__((mode (DI)));
+typedef unsigned int       USItype __attribute__((mode (SI)));
+
+extern int __builtin_clzll(unsigned long long);
+
+#define DWtype  DItype
+#define UDWtype UDItype
+#define UWtype  USItype
+
+UDWtype __udivdi3    (UDWtype n, UDWtype d);
+UDWtype __udivmoddi4 (UDWtype n, UDWtype d, UDWtype *rp);
+UDWtype __umoddi3    (UDWtype u, UDWtype v);
+
+UDWtype __udivdi3 (UDWtype n, UDWtype d)
+{
+  return __udivmoddi4 (n, d, (UDWtype *) 0);
+}
+
+UDWtype __umoddi3 (UDWtype u, UDWtype v)
+{
+  UDWtype w;
+
+  (void) __udivmoddi4 (u, v, &w);
+
+  return w;
+}
+
+UDWtype __udivmoddi4 (UDWtype n, UDWtype d, UDWtype *rp)
+{
+  UDWtype q = 0, r = n, y = d;
+  UWtype lz1, lz2, i, k;
+
+  // Implements align divisor shift dividend method. This algorithm
+  // aligns the divisor under the dividend and then perform number of
+  // test-subtract iterations which shift the dividend left. Number of
+  // iterations is k + 1 where k is the number of bit positions the
+  // divisor must be shifted left to align it under the dividend.
+  // quotient bits can be saved in the rightmost positions of the dividend
+  // as it shifts left on each test-subtract iteration.
+
+  if (y <= r)
+  {
+    lz1 = static_cast<USItype>(__builtin_clzll(static_cast<unsigned long long>(d)));
+    lz2 = static_cast<USItype>(__builtin_clzll(static_cast<unsigned long long>(n)));
+
+    k = lz1 - lz2;
+    y = (y << k);
+
+    // Dividend can exceed 2 ^ (width - 1) - 1 but still be less than the
+    // aligned divisor. Normal iteration can drops the high order bit
+    // of the dividend. Therefore, first test-subtract iteration is a
+    // special case, saving its quotient bit in a separate location and
+    // not shifting the dividend.
+
+    if (r >= y)
+    {
+      r = r - y;
+      q =  (1ULL << k);
+    }
+    
+    if (k > 0)
+    {
+      y = y >> 1;
+
+      // k additional iterations where k regular test subtract shift
+      // dividend iterations are done.
+
+      i = k;
+
+      do
+      {
+        if (r >= y)
+        {
+          r = ((r - y) << 1) + 1;
+        }
+        else
+        {
+          r =  (r << 1);
+        }
+
+        i = i - 1;
+      }
+      while (i != 0);
+
+      // First quotient bit is combined with the quotient bits resulting
+      // from the k regular iterations.
+
+      q = q + r;
+      r = r >> k;
+      q = q - (r << k);
+    }
+  }
+
+  if (rp)
+  {
+    *rp = r;
+  }
+
+  return q;
+}
+
 #if defined(__GNUC__)
 #pragma GCC diagnostic push
 #pragma GCC diagnostic ignored "-Wcast-align"