Eliminate MY_IS_SSMALL()

For a long time, there has been the two macros IS_SSMALL() and
MY_IS_SSMALL() that do exactly the same thing.

There should only be one, and it should be called IS_SSMALL().

However, we must decide which implementation to use. When
MY_IS_SSMALL() was introduced a long time ago, it was the most
efficient. In a modern C compiler, there might not be any
difference.

To find out, I used the following small C program to examine
the code generation:

    #include <stdio.h>

    typedef unsigned int Uint32;
    typedef unsigned long Uint64;
    typedef long Sint;

    #define SWORD_CONSTANT(Const) Const##L
    #define SMALL_BITS	(64-4)
    #define MAX_SMALL	((SWORD_CONSTANT(1) << (SMALL_BITS-1))-1)
    #define MIN_SMALL	(-(SWORD_CONSTANT(1) << (SMALL_BITS-1)))

    #define MY_IS_SSMALL32(x) (((Uint32) ((((x)) >> (SMALL_BITS-1)) + 1)) < 2)
    #define MY_IS_SSMALL64(x) (((Uint64) ((((x)) >> (SMALL_BITS-1)) + 1)) < 2)
    #define MY_IS_SSMALL(x) (sizeof(x) == sizeof(Uint32) ? MY_IS_SSMALL32(x) : MY_IS_SSMALL64(x))

    #define IS_SSMALL(x)      (((x) >= MIN_SMALL) && ((x) <= MAX_SMALL))

    void original(Sint n)
    {
        if (IS_SSMALL(n)) {
            printf("yes\n");
        }
    }

    void enhanced(Sint n)
    {
        if (MY_IS_SSMALL(n)) {
            printf("yes\n");
        }
    }

gcc 7.2 produced the following code for the original() function:

.LC0:
  .string "yes"
original(long):
  movabs rax, 576460752303423488
  add rdi, rax
  movabs rax, 1152921504606846975
  cmp rdi, rax
  jbe .L4
  rep ret
.L4:
  mov edi, OFFSET FLAT:.LC0
  jmp puts

clang 5.0.0 produced the following code which is slightly better:

original(long):
  movabs rax, 576460752303423488
  add rax, rdi
  shr rax, 60
  jne .LBB0_1
  mov edi, .Lstr
  jmp puts # TAILCALL
.LBB0_1:
  ret
.Lstr:
  .asciz "yes"

However, in the context of beam_emu.c, clang could produce
similar to what gcc produced.

gcc 7.2 produced the following code when MY_IS_SSMALL() was used:

.LC0:
  .string "yes"
enhanced(long):
  sar rdi, 59
  add rdi, 1
  cmp rdi, 1
  jbe .L4
  rep ret
.L4:
  mov edi, OFFSET FLAT:.LC0
  jmp puts

clang produced similar code.

This code seems to be the cheapest. There are four instructions, and
there is no loading of huge integer constants.

1 files changed, 0 insertions, 1 deletions

diff --git a/erts/emulator/beam/erl_term.h b/erts/emulator/beam/erl_term.h
index 842802f8d9..6daf043117 100644
--- a/erts/emulator/beam/erl_term.h
+++ b/erts/emulator/beam/erl_term.h
@@ -270,7 +270,6 @@ _ET_DECLARE_CHECKED(Eterm*,list_val,Wterm)
 #define is_byte(x)	(((x) & ((~(Uint)0 << (_TAG_IMMED1_SIZE+8)) + _TAG_IMMED1_MASK)) == _TAG_IMMED1_SMALL)
 #define is_valid_bit_size(x) (((Sint)(x)) >= 0 && ((x) & 0x7F) == _TAG_IMMED1_SMALL)
 #define is_not_valid_bit_size(x) (!is_valid_bit_size((x)))
-#define MY_IS_SSMALL(x) (((Uint) ((((x)) >> (SMALL_BITS-1)) + 1)) < 2)
 #define _unchecked_unsigned_val(x)	((x) >> _TAG_IMMED1_SIZE)
 _ET_DECLARE_CHECKED(Uint,unsigned_val,Eterm)
 #define unsigned_val(x)	_ET_APPLY(unsigned_val,(x))