Arrange operands of several opt_something insns so that jumps to
opt_send_without_block can be applied to them. This makes it
possible to eliminate CALL_SIMPLE_METHOD macro at all.  Results
in binary size of vm_exec_core to change from 27,008 bytes to
26,016 bytes on my machine. [close GH-1779]

Note however that PC can point somewhere non-instruction now.

-----------------------------------------------------------
benchmark results:
minimum results in each 3 measurements.
Execution time (sec)
name    before  after
so_ackermann     0.450  0.426
so_array         0.789  0.824
so_binary_trees  5.760  5.635
so_concatenate   3.594  3.508
so_count_words   0.211  0.196
so_exception     0.256  0.244
so_fannkuch      1.049  1.044
so_fasta         1.485  1.472
so_k_nucleotide  1.195  1.216
so_lists         0.517  0.513
so_mandelbrot    2.264  2.394
so_matrix        0.501  0.468
so_meteor_contest        2.987  2.912
so_nbody         1.307  1.289
so_nested_loop   0.908  0.925
so_nsieve        1.679  1.614
so_nsieve_bits   2.131  2.092
so_object        0.620  0.625
so_partial_sums  1.623  1.675
so_pidigits      1.135  1.190
so_random        0.357  0.321
so_reverse_complement    0.619  0.583
so_sieve         0.493  0.496
so_spectralnorm  1.749  1.737

Speedup ratio: compare with the result of `before' (greater is better)
name    after
so_ackermann    1.057
so_array        0.958
so_binary_trees 1.022
so_concatenate  1.024
so_count_words  1.077
so_exception    1.049
so_fannkuch     1.004
so_fasta        1.009
so_k_nucleotide 0.983
so_lists        1.007
so_mandelbrot   0.946
so_matrix       1.072
so_meteor_contest       1.026
so_nbody        1.013
so_nested_loop  0.982
so_nsieve       1.040
so_nsieve_bits  1.018
so_object       0.992
so_partial_sums 0.969
so_pidigits     0.954
so_random       1.111
so_reverse_complement   1.062
so_sieve        0.994
so_spectralnorm 1.007

git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@62089 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This commit is contained in:
shyouhei 2018-01-29 07:15:08 +00:00
Родитель 31ecd18f1a
Коммит c788fb4808
3 изменённых файлов: 16 добавлений и 31 удалений

Просмотреть файл

@ -2954,9 +2954,9 @@ insn_set_specialized_instruction(rb_iseq_t *iseq, INSN *iobj, int insn_id)
VALUE *old_operands = iobj->operands;
iobj->operand_size = 4;
iobj->operands = (VALUE *)compile_data_alloc(iseq, iobj->operand_size * sizeof(VALUE));
iobj->operands[0] = old_operands[0];
iobj->operands[0] = (VALUE)new_callinfo(iseq, idEq, 1, 0, NULL, FALSE);
iobj->operands[1] = Qfalse; /* CALL_CACHE */
iobj->operands[2] = (VALUE)new_callinfo(iseq, idEq, 1, 0, NULL, FALSE);
iobj->operands[2] = old_operands[0];
iobj->operands[3] = Qfalse; /* CALL_CACHE */
}
@ -6092,9 +6092,9 @@ iseq_compile_each0(rb_iseq_t *iseq, LINK_ANCHOR *const ret, const NODE *node, in
ISEQ_COMPILE_DATA(iseq)->option->specialized_instruction) {
VALUE str = freeze_literal(iseq, node->nd_args->nd_head->nd_lit);
CHECK(COMPILE(ret, "recv", node->nd_recv));
ADD_INSN3(ret, line, opt_aref_with,
ADD_INSN3(ret, line, opt_aref_with, str,
new_callinfo(iseq, idAREF, 1, 0, NULL, FALSE),
NULL/* CALL_CACHE */, str);
NULL/* CALL_CACHE */);
if (popped) {
ADD_INSN(ret, line, pop);
}
@ -7106,9 +7106,9 @@ iseq_compile_each0(rb_iseq_t *iseq, LINK_ANCHOR *const ret, const NODE *node, in
ADD_INSN(ret, line, swap);
ADD_INSN1(ret, line, topn, INT2FIX(1));
}
ADD_INSN3(ret, line, opt_aset_with,
ADD_INSN3(ret, line, opt_aset_with, str,
new_callinfo(iseq, idASET, 2, 0, NULL, FALSE),
NULL/* CALL_CACHE */, str);
NULL/* CALL_CACHE */);
ADD_INSN(ret, line, pop);
break;
}

Просмотреть файл

@ -1083,18 +1083,15 @@ opt_eq
/* optimized X!=Y. */
DEFINE_INSN
opt_neq
(CALL_INFO ci, CALL_CACHE cc, CALL_INFO ci_eq, CALL_CACHE cc_eq)
(CALL_INFO ci_eq, CALL_CACHE cc_eq, CALL_INFO ci, CALL_CACHE cc)
(VALUE recv, VALUE obj)
(VALUE val)
// attr bool handles_frame = true;
{
val = vm_opt_neq(ci, cc, ci_eq, cc_eq, recv, obj);
if (val == Qundef) {
/* other */
PUSH(recv);
PUSH(obj);
CALL_SIMPLE_METHOD(recv);
ADD_PC(2); /* !!! */
DISPATCH_ORIGINAL_INSN(opt_send_without_block);
}
}
@ -1199,10 +1196,9 @@ opt_aset
/* recv[str] = set */
DEFINE_INSN
opt_aset_with
(CALL_INFO ci, CALL_CACHE cc, VALUE key)
(VALUE key, CALL_INFO ci, CALL_CACHE cc)
(VALUE recv, VALUE val)
(VALUE val)
// attr bool handles_frame = true;
{
VALUE tmp = vm_opt_aset_with(recv, key, val);
@ -1210,29 +1206,26 @@ opt_aset_with
val = tmp;
}
else {
/* other */
PUSH(recv);
PUSH(rb_str_resurrect(key));
TOPN(0) = rb_str_resurrect(key);
PUSH(val);
CALL_SIMPLE_METHOD(recv);
ADD_PC(1); /* !!! */
DISPATCH_ORIGINAL_INSN(opt_send_without_block);
}
}
/* recv[str] */
DEFINE_INSN
opt_aref_with
(CALL_INFO ci, CALL_CACHE cc, VALUE key)
(VALUE key, CALL_INFO ci, CALL_CACHE cc)
(VALUE recv)
(VALUE val)
// attr bool handles_frame = true;
{
val = vm_opt_aref_with(recv, key);
if (val == Qundef) {
/* other */
PUSH(recv);
PUSH(rb_str_resurrect(key));
CALL_SIMPLE_METHOD(recv);
ADD_PC(1); /* !!! */
DISPATCH_ORIGINAL_INSN(opt_send_without_block);
}
}

Просмотреть файл

@ -194,14 +194,6 @@ enum vm_regan_acttype {
#define USE_IC_FOR_SPECIALIZED_METHOD 1
#endif
#define CALL_SIMPLE_METHOD(recv_) do { \
struct rb_calling_info calling; \
calling.block_handler = VM_BLOCK_HANDLER_NONE; \
calling.argc = ci->orig_argc; \
vm_search_method(ci, cc, calling.recv = (recv_)); \
CALL_METHOD(&calling, ci, cc); \
} while (0)
#define NEXT_CLASS_SERIAL() (++ruby_vm_class_serial)
#define GET_GLOBAL_METHOD_STATE() (ruby_vm_global_method_state)
#define INC_GLOBAL_METHOD_STATE() (++ruby_vm_global_method_state)