[PATCH] D14053: Optimize StringTableBuilder

[Rafael Espíndola via llvm-commits]

> -O0
> real    0m0.455s
> real    0m0.430s (5.5% faster)
>
> -O3
> real    0m0.487s
> real    0m0.452s (7.2% faster)

Nice!

> +static void qsort(StringPair **Begin, StringPair **End, int Pos) {
> +  if (End - Begin < 2)
> +    return;
> +
> +  // Safeguard for pathetic input.
> +  if (Pos > 10000)
> +    return;

We get here if two strings have a lot of characters in common, right?
This if then avoids running out of stack.

> +  // Partition items. Items in [Begin, P) are less than the pivot, [P, Q)
> +  // are the same as the pivot, and [Q, End) are greater than the pivot.

We are actually sorting the other way, no? Things larger than the
pivot go to be start of the array.

> +  int Pivot = charTailAt(*Begin, Pos);
> +  StringPair **P = Begin;
> +  StringPair **Q = End;
> +  for (StringPair **R = Begin + 1; R < Q;) {
> +    int C = charTailAt(*R, Pos);
> +    if (C > Pivot)
> +      std::swap(*P++, *R++);
> +    else if (C < Pivot)
> +      std::swap(*--Q, *R);
> +    else
> +      R++;
>    }
> -  return SizeB - SizeA;
> +  qsort(Begin, P, Pos);
> +  if (Pivot != -1)
> +    qsort(P, Q, Pos + 1);

This is the recursive call that can causes us to run out of stack. If
you write this as

qsort(Begin, P, Pos);
qsort(Q, End, Pos);
if (Pivot != -1)
 loop back to stort P, Q, Pos + 1.

We should be able to remove the earlier check for Pos being too large.

Thanks you so much for ding this, it should help MC too!

Cheers,
Rafael