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, 2 insertions, 2 deletions

diff --git a/erts/emulator/beam/erl_gc.c b/erts/emulator/beam/erl_gc.c
index 8344c164fa..97a1ca915f 100644
--- a/erts/emulator/beam/erl_gc.c
+++ b/erts/emulator/beam/erl_gc.c
@@ -337,7 +337,7 @@ erts_heap_sizes(Process* p)
 
     for (i = num_heap_sizes-1; i >= 0; i--) {
 	n += 2;
-	if (!MY_IS_SSMALL(heap_sizes[i])) {
+	if (!IS_SSMALL(heap_sizes[i])) {
 	    big += BIG_UINT_HEAP_SIZE;
 	}
     }
@@ -352,7 +352,7 @@ erts_heap_sizes(Process* p)
 	Eterm num;
 	Sint sz = heap_sizes[i];
 
-	if (MY_IS_SSMALL(sz)) {
+	if (IS_SSMALL(sz)) {
 	    num = make_small(sz);
 	} else {
 	    num = uint_to_big(sz, bigp);