Avoid erts_cmp jump in atom, int and float comparisons

Given the function definition below:

    check(X) when X >= 0, X <= 20 -> true.

@nox has originally noticed that perfoming lt and ge
guard tests were performing slower than they should be.

Further investigation revealed that most of the cost
was in jumping to the erts_cmp function. This patch
brings the operations already inlined in erts_cmp
into the emulator, removing the jump cost.

After applying these changes, invoking the check/1
function defined above 30000 times with different
values from 0 to 20 has fallen from 367us to 213us
(measured as average of 3 runs). This is a
considerably improvement over Erlang 18 which takes
556us on average.

Floats have also dropped their time from 1126us
(on Erlang 18) to 613us.

1 files changed, 1 insertions, 1 deletions

diff --git a/erts/emulator/beam/atom.c b/erts/emulator/beam/atom.c
index fd2adac676..099c00bcf6 100644
--- a/erts/emulator/beam/atom.c
+++ b/erts/emulator/beam/atom.c
@@ -176,7 +176,7 @@ atom_alloc(Atom* tmpl)
 
     /*
      * Precompute ordinal value of first 3 bytes + 7 bits.
-     * This is used by utils.c:cmp_atoms().
+     * This is used by utils.c:erts_cmp_atoms().
      * We cannot use the full 32 bits of the first 4 bytes,
      * since we use the sign of the difference between two
      * ordinal values to represent their relative order.