py/compile: De-duplicate constant objects in module's constant table.

The recent rework of bytecode made all constants global with respect to the
module (previously, each function had its own constant table).  That means
the constant table for a module is shared among all functions/methods/etc
within the module.

This commit add support to the compiler to de-duplicate constants in this
module constant table.  So if a constant is used more than once -- eg 1.0
or (None, None) -- then the same object is reused for all instances.

For example, if there is code like `print(1.0, 1.0)` then the parser will
create two independent constants 1.0 and 1.0.  The compiler will then (with
this commit) notice they are the same and only put one of them in the
constant table.  The bytecode will then reuse that constant twice in the
print expression.  That allows the second 1.0 to be reclaimed by the GC,
also means the constant table has one less entry so saves a word.

Signed-off-by: Damien George <damien@micropython.org>

1 files changed, 8 insertions, 6 deletions

diff --git a/py/emitnative.c b/py/emitnative.c
index ddc0b5b97..3507d6621 100644
--- a/py/emitnative.c
+++ b/py/emitnative.c
@@ -99,7 +99,6 @@
 #define OFFSETOF_OBJ_FUN_BC_BYTECODE (offsetof(mp_obj_fun_bc_t, bytecode) / sizeof(uintptr_t))
 #define OFFSETOF_MODULE_CONTEXT_OBJ_TABLE (offsetof(mp_module_context_t, constants.obj_table) / sizeof(uintptr_t))
 #define OFFSETOF_MODULE_CONTEXT_GLOBALS (offsetof(mp_module_context_t, module.globals) / sizeof(uintptr_t))
-#define INDEX_OF_MP_FUN_TABLE_IN_CONST_TABLE (0)
 
 // If not already defined, set parent args to same as child call registers
 #ifndef REG_PARENT_RET
@@ -406,6 +405,8 @@ STATIC void emit_native_start_pass(emit_t *emit, pass_kind_t pass, scope_t *scop
         emit->code_state_start = SIZEOF_NLR_BUF;
     }
 
+    size_t fun_table_off = mp_emit_common_use_const_obj(emit->emit_common, MP_OBJ_FROM_PTR(&mp_fun_table));
+
     if (emit->do_viper_types) {
         // Work out size of state (locals plus stack)
         // n_state counts all stack and locals, even those in registers
@@ -443,7 +444,7 @@ STATIC void emit_native_start_pass(emit_t *emit, pass_kind_t pass, scope_t *scop
         // Load REG_FUN_TABLE with a pointer to mp_fun_table, found in the const_table
         ASM_LOAD_REG_REG_OFFSET(emit->as, REG_FUN_TABLE, REG_PARENT_ARG_1, OFFSETOF_OBJ_FUN_BC_CONTEXT);
         ASM_LOAD_REG_REG_OFFSET(emit->as, REG_FUN_TABLE, REG_FUN_TABLE, OFFSETOF_MODULE_CONTEXT_OBJ_TABLE);
-        ASM_LOAD_REG_REG_OFFSET(emit->as, REG_FUN_TABLE, REG_FUN_TABLE, INDEX_OF_MP_FUN_TABLE_IN_CONST_TABLE);
+        ASM_LOAD_REG_REG_OFFSET(emit->as, REG_FUN_TABLE, REG_FUN_TABLE, fun_table_off);
 
         // Store function object (passed as first arg) to stack if needed
         if (NEED_FUN_OBJ(emit)) {
@@ -520,7 +521,7 @@ STATIC void emit_native_start_pass(emit_t *emit, pass_kind_t pass, scope_t *scop
             ASM_LOAD_REG_REG_OFFSET(emit->as, REG_TEMP0, REG_GENERATOR_STATE, LOCAL_IDX_FUN_OBJ(emit));
             ASM_LOAD_REG_REG_OFFSET(emit->as, REG_TEMP0, REG_TEMP0, OFFSETOF_OBJ_FUN_BC_CONTEXT);
             ASM_LOAD_REG_REG_OFFSET(emit->as, REG_TEMP0, REG_TEMP0, OFFSETOF_MODULE_CONTEXT_OBJ_TABLE);
-            ASM_LOAD_REG_REG_OFFSET(emit->as, REG_FUN_TABLE, REG_TEMP0, INDEX_OF_MP_FUN_TABLE_IN_CONST_TABLE);
+            ASM_LOAD_REG_REG_OFFSET(emit->as, REG_FUN_TABLE, REG_TEMP0, fun_table_off);
         } else {
             // The locals and stack start after the code_state structure
             emit->stack_start = emit->code_state_start + SIZEOF_CODE_STATE;
@@ -540,7 +541,7 @@ STATIC void emit_native_start_pass(emit_t *emit, pass_kind_t pass, scope_t *scop
             // Load REG_FUN_TABLE with a pointer to mp_fun_table, found in the const_table
             ASM_LOAD_REG_REG_OFFSET(emit->as, REG_FUN_TABLE, REG_PARENT_ARG_1, OFFSETOF_OBJ_FUN_BC_CONTEXT);
             ASM_LOAD_REG_REG_OFFSET(emit->as, REG_FUN_TABLE, REG_FUN_TABLE, OFFSETOF_MODULE_CONTEXT_OBJ_TABLE);
-            ASM_LOAD_REG_REG_OFFSET(emit->as, REG_FUN_TABLE, REG_FUN_TABLE, INDEX_OF_MP_FUN_TABLE_IN_CONST_TABLE);
+            ASM_LOAD_REG_REG_OFFSET(emit->as, REG_FUN_TABLE, REG_FUN_TABLE, fun_table_off);
 
             // Set code_state.fun_bc
             ASM_MOV_LOCAL_REG(emit->as, LOCAL_IDX_FUN_OBJ(emit), REG_PARENT_ARG_1);
@@ -1105,7 +1106,7 @@ STATIC exc_stack_entry_t *emit_native_pop_exc_stack(emit_t *emit) {
 }
 
 STATIC void emit_load_reg_with_object(emit_t *emit, int reg, mp_obj_t obj) {
-    size_t table_off = mp_emit_common_alloc_const_obj(emit->emit_common, obj);
+    size_t table_off = mp_emit_common_use_const_obj(emit->emit_common, obj);
     emit_native_mov_reg_state(emit, REG_TEMP0, LOCAL_IDX_FUN_OBJ(emit));
     ASM_LOAD_REG_REG_OFFSET(emit->as, REG_TEMP0, REG_TEMP0, OFFSETOF_OBJ_FUN_BC_CONTEXT);
     ASM_LOAD_REG_REG_OFFSET(emit->as, REG_TEMP0, REG_TEMP0, OFFSETOF_MODULE_CONTEXT_OBJ_TABLE);
@@ -1211,10 +1212,11 @@ STATIC void emit_native_global_exc_entry(emit_t *emit) {
             emit_native_label_assign(emit, global_except_label);
             #if N_NLR_SETJMP
             // Reload REG_FUN_TABLE, since it may be clobbered by longjmp
+            size_t fun_table_off = mp_emit_common_use_const_obj(emit->emit_common, MP_OBJ_FROM_PTR(&mp_fun_table));
             emit_native_mov_reg_state(emit, REG_LOCAL_1, LOCAL_IDX_FUN_OBJ(emit));
             ASM_LOAD_REG_REG_OFFSET(emit->as, REG_LOCAL_1, REG_LOCAL_1, OFFSETOF_OBJ_FUN_BC_CONTEXT);
             ASM_LOAD_REG_REG_OFFSET(emit->as, REG_LOCAL_1, REG_LOCAL_1, OFFSETOF_MODULE_CONTEXT_OBJ_TABLE);
-            ASM_LOAD_REG_REG_OFFSET(emit->as, REG_FUN_TABLE, REG_LOCAL_1, emit->scope->num_pos_args + emit->scope->num_kwonly_args);
+            ASM_LOAD_REG_REG_OFFSET(emit->as, REG_FUN_TABLE, REG_LOCAL_1, fun_table_off);
             #endif
             ASM_MOV_REG_LOCAL(emit->as, REG_LOCAL_1, LOCAL_IDX_EXC_HANDLER_PC(emit));
             ASM_JUMP_IF_REG_NONZERO(emit->as, REG_LOCAL_1, nlr_label, false);