[mono][interp] Add SSA transformation and SSA based optimization

src/mono/browser/runtime/jiterpreter-trace-generator.ts

@@ -1098,18 +1098,6 @@ export function generateWasmBody(
                 break;
             }
 
-            case MintOpcode.MINT_NEWOBJ_VT_INLINED: {
-                const ret_size = getArgU16(ip, 3);
-                // memset (this_vt, 0, ret_size);
-                append_ldloca(builder, getArgU16(ip, 2), ret_size);
-                append_memset_dest(builder, 0, ret_size);
-                // LOCAL_VAR (ip [1], gpointer) = this_vt;
-                builder.local("pLocals");
-                append_ldloca(builder, getArgU16(ip, 2), ret_size);
-                append_stloc_tail(builder, getArgU16(ip, 1), WasmOpcode.i32_store);
-                break;
-            }
-
             case MintOpcode.MINT_NEWOBJ:
             case MintOpcode.MINT_NEWOBJ_VT:
             case MintOpcode.MINT_CALLVIRT_FAST:

src/mono/mono/mini/interp/interp-internals.h

@@ -275,6 +275,13 @@ typedef struct {
 typedef struct {
 	gint64 transform_time;
 	gint64 methods_transformed;
+	gint64 optimize_time;
+	gint64 ssa_compute_time;
+	gint64 ssa_compute_dominance_time;
+	gint64 ssa_compute_global_vars_time;
+	gint64 ssa_compute_pruned_liveness_time;
+	gint64 ssa_rename_vars_time;
+	gint64 optimize_bblocks_time;
 	gint64 cprop_time;
 	gint64 super_instructions_time;
 	gint32 emitted_instructions;

src/mono/mono/mini/interp/interp-intrins.c

@@ -16,7 +16,7 @@ rotate_left (guint32 value, int offset)
 }
 
 void
-interp_intrins_marvin_block (guint32 *pp0, guint32 *pp1)
+interp_intrins_marvin_block (guint32 *pp0, guint32 *pp1, guint32 *dest0, guint32 *dest1)
 {
 	// Marvin.Block
 	guint32 p0 = *pp0;
@@ -34,8 +34,8 @@ interp_intrins_marvin_block (guint32 *pp0, guint32 *pp1)
 	p0 += p1;
 	p1 = rotate_left (p1, 19);
 
-	*pp0 = p0;
-	*pp1 = p1;
+	*dest0 = p0;
+	*dest1 = p1;
 }
 
 guint32

src/mono/mono/mini/interp/interp-intrins.h

@@ -124,7 +124,7 @@ interp_intrins_popcount_i8 (guint64 val)
 #endif
 
 void
-interp_intrins_marvin_block (guint32 *pp0, guint32 *pp1);
+interp_intrins_marvin_block (guint32 *pp0, guint32 *pp1, guint32 *dest0, guint32 *dest1);
 
 guint32
 interp_intrins_ascii_chars_to_uppercase (guint32 val);

src/mono/mono/mini/interp/interp-simd.c

@@ -315,47 +315,15 @@ interp_v128_u2_widen_upper (gpointer res, gpointer v1)
 static void
 interp_v128_u1_narrow (gpointer res, gpointer v1, gpointer v2)
 {
-	guint8 *res_typed = (guint8*)res;
+	guint8 res_typed [SIZEOF_V128];
 	guint16 *v1_typed = (guint16*)v1;
 	guint16 *v2_typed = (guint16*)v2;
 
-	if (res != v2) {
-		res_typed [0] = v1_typed [0];
-		res_typed [1] = v1_typed [1];
-		res_typed [2] = v1_typed [2];
-		res_typed [3] = v1_typed [3];
-		res_typed [4] = v1_typed [4];
-		res_typed [5] = v1_typed [5];
-		res_typed [6] = v1_typed [6];
-		res_typed [7] = v1_typed [7];
-
-		res_typed [8] = v2_typed [0];
-		res_typed [9] = v2_typed [1];
-		res_typed [10] = v2_typed [2];
-		res_typed [11] = v2_typed [3];
-		res_typed [12] = v2_typed [4];
-		res_typed [13] = v2_typed [5];
-		res_typed [14] = v2_typed [6];
-		res_typed [15] = v2_typed [7];
-	} else {
-		res_typed [15] = v2_typed [7];
-		res_typed [14] = v2_typed [6];
-		res_typed [13] = v2_typed [5];
-		res_typed [12] = v2_typed [4];
-		res_typed [11] = v2_typed [3];
-		res_typed [10] = v2_typed [2];
-		res_typed [9] = v2_typed [1];
-		res_typed [8] = v2_typed [0];
-
-		res_typed [0] = v1_typed [0];
-		res_typed [1] = v1_typed [1];
-		res_typed [2] = v1_typed [2];
-		res_typed [3] = v1_typed [3];
-		res_typed [4] = v1_typed [4];
-		res_typed [5] = v1_typed [5];
-		res_typed [6] = v1_typed [6];
-		res_typed [7] = v1_typed [7];
-	}
+	for (int i = 0; i < 8; i++)
+		res_typed [i] = v1_typed [i];
+	for (int i = 0; i < 8; i++)
+		res_typed [i + 8] = v2_typed [i];
+	memcpy (res, res_typed, SIZEOF_V128);
 }
 
 // GreaterThan

src/mono/mono/mini/interp/interp.c

@@ -5786,15 +5786,6 @@ MINT_IN_CASE(MINT_BRTRUE_I8_SP) ZEROP_SP(gint64, !=); MINT_IN_BREAK;
 			cmethod = (InterpMethod*)frame->imethod->data_items [imethod_index];
 			goto jit_call;
 		}
-		MINT_IN_CASE(MINT_NEWOBJ_VT_INLINED) {
-			guint16 ret_size = ip [3];
-			gpointer this_vt = locals + ip [2];
-
-			memset (this_vt, 0, ret_size);
-			LOCAL_VAR (ip [1], gpointer) = this_vt;
-			ip += 4;
-			MINT_IN_BREAK;
-		}
 		MINT_IN_CASE(MINT_NEWOBJ_SLOW) {
 			guint32 const token = ip [3];
 			return_offset = ip [1];
@@ -5937,8 +5928,13 @@ MINT_IN_CASE(MINT_BRTRUE_I8_SP) ZEROP_SP(gint64, !=); MINT_IN_BREAK;
 			MINT_IN_BREAK;
 		}
 		MINT_IN_CASE(MINT_INTRINS_MARVIN_BLOCK) {
-			interp_intrins_marvin_block ((guint32*)(locals + ip [1]), (guint32*)(locals + ip [2]));
-			ip += 3;
+			guint32 *pp0 = (guint32*)(locals + ip [1]);
+			guint32 *pp1 = (guint32*)(locals + ip [2]);
+			guint32 *dest0 = (guint32*)(locals + ip [3]);
+			guint32 *dest1 = (guint32*)(locals + ip [4]);
+
+			interp_intrins_marvin_block (pp0, pp1, dest0, dest1);
+			ip += 5;
 			MINT_IN_BREAK;
 		}
 		MINT_IN_CASE(MINT_INTRINS_ASCII_CHARS_TO_UPPERCASE) {
@@ -7931,6 +7927,8 @@ interp_parse_options (const char *options)
 			else if (strncmp (arg, "jiterp", 6) == 0)
 				opt = INTERP_OPT_JITERPRETER;
 #endif
+			else if (strncmp (arg, "ssa", 3) == 0)
+				opt = INTERP_OPT_SSA;
 			else if (strncmp (arg, "all", 3) == 0)
 				opt = ~INTERP_OPT_NONE;
 
@@ -8682,19 +8680,6 @@ interp_cleanup (void)
 #endif
 }
 
-static void
-register_interp_stats (void)
-{
-	mono_counters_init ();
-	mono_counters_register ("Total transform time", MONO_COUNTER_INTERP | MONO_COUNTER_LONG | MONO_COUNTER_TIME, &mono_interp_stats.transform_time);
-	mono_counters_register ("Methods transformed", MONO_COUNTER_INTERP | MONO_COUNTER_LONG, &mono_interp_stats.methods_transformed);
-	mono_counters_register ("Total cprop time", MONO_COUNTER_INTERP | MONO_COUNTER_LONG | MONO_COUNTER_TIME, &mono_interp_stats.cprop_time);
-	mono_counters_register ("Total super instructions time", MONO_COUNTER_INTERP | MONO_COUNTER_LONG | MONO_COUNTER_TIME, &mono_interp_stats.super_instructions_time);
-	mono_counters_register ("Emitted instructions", MONO_COUNTER_INTERP | MONO_COUNTER_INT, &mono_interp_stats.emitted_instructions);
-	mono_counters_register ("Methods inlined", MONO_COUNTER_INTERP | MONO_COUNTER_INT, &mono_interp_stats.inlined_methods);
-	mono_counters_register ("Inline failures", MONO_COUNTER_INTERP | MONO_COUNTER_INT, &mono_interp_stats.inline_failures);
-}
-
 #undef MONO_EE_CALLBACK
 #define MONO_EE_CALLBACK(ret, name, sig) interp_ ## name,
 
@@ -8723,8 +8708,6 @@ mono_ee_interp_init (const char *opts)
 
 	mini_install_interp_callbacks (&mono_interp_callbacks);
 
-	register_interp_stats ();
-
 #ifdef HOST_WASI
 	debugger_enabled = mini_get_debug_options ()->mdb_optimizations;
 #endif

src/mono/mono/mini/interp/interp.h

@@ -41,7 +41,8 @@ enum {
 #if HOST_BROWSER
 	INTERP_OPT_JITERPRETER = 64,
 #endif
-	INTERP_OPT_DEFAULT = INTERP_OPT_INLINE | INTERP_OPT_CPROP | INTERP_OPT_SUPER_INSTRUCTIONS | INTERP_OPT_BBLOCKS | INTERP_OPT_TIERING | INTERP_OPT_SIMD
+	INTERP_OPT_SSA = 128,
+	INTERP_OPT_DEFAULT = INTERP_OPT_INLINE | INTERP_OPT_CPROP | INTERP_OPT_SUPER_INSTRUCTIONS | INTERP_OPT_BBLOCKS | INTERP_OPT_TIERING | INTERP_OPT_SIMD | INTERP_OPT_SSA
 #if HOST_BROWSER
 		| INTERP_OPT_JITERPRETER
 #endif

src/mono/mono/mini/interp/jiterpreter-opcode-values.h

@@ -135,7 +135,6 @@ OP(MINT_INTRINS_RUNTIMEHELPERS_OBJECT_HAS_COMPONENT_SIZE, HIGH)
 OP(MINT_INTRINS_ENUM_HASFLAG, HIGH)
 OP(MINT_INTRINS_ORDINAL_IGNORE_CASE_ASCII, HIGH)
 OP(MINT_NEWOBJ_INLINED, HIGH)
-OP(MINT_NEWOBJ_VT_INLINED, MASSIVE)
 OP(MINT_CPBLK, HIGH)
 OP(MINT_INITBLK, HIGH)
 OP(MINT_ROL_I4_IMM, HIGH)

src/mono/mono/mini/interp/mintops.def

@@ -363,7 +363,6 @@ OPDEF(MINT_NEWOBJ_STRING, "newobj_string", 4, 1, 1, MintOpMethodToken)
 OPDEF(MINT_NEWOBJ, "newobj", 5, 1, 1, MintOpMethodToken)
 OPDEF(MINT_NEWOBJ_INLINED, "newobj_inlined", 3, 1, 0, MintOpVTableToken)
 OPDEF(MINT_NEWOBJ_VT, "newobj_vt", 5, 1, 1, MintOpMethodToken)
-OPDEF(MINT_NEWOBJ_VT_INLINED, "newobj_vt_inlined", 4, 1, 1, MintOpShortInt)
 OPDEF(MINT_INITOBJ, "initobj", 3, 0, 1, MintOpShortInt)
 OPDEF(MINT_CASTCLASS, "castclass", 4, 1, 1, MintOpClassToken)
 OPDEF(MINT_ISINST, "isinst", 4, 1, 1, MintOpClassToken)
@@ -815,7 +814,8 @@ OPDEF(MINT_INTRINS_GET_TYPE, "intrins_get_type", 3, 1, 1, MintOpNoArgs)
 OPDEF(MINT_INTRINS_SPAN_CTOR, "intrins_span_ctor", 4, 1, 2, MintOpNoArgs)
 OPDEF(MINT_INTRINS_RUNTIMEHELPERS_OBJECT_HAS_COMPONENT_SIZE, "intrins_runtimehelpers_object_has_component_size", 3, 1, 1, MintOpNoArgs)
 OPDEF(MINT_INTRINS_CLEAR_WITH_REFERENCES, "intrin_clear_with_references", 3, 0, 2, MintOpNoArgs)
-OPDEF(MINT_INTRINS_MARVIN_BLOCK, "intrins_marvin_block", 3, 0, 2, MintOpNoArgs)
+// This actually has 2 dregs and 2 sregs. Dregs are displayed as the metadata
+OPDEF(MINT_INTRINS_MARVIN_BLOCK, "intrins_marvin_block", 5, 0, 2, MintOpTwoShorts)
 OPDEF(MINT_INTRINS_ASCII_CHARS_TO_UPPERCASE, "intrins_ascii_chars_to_uppercase", 3, 1, 1, MintOpNoArgs)
 OPDEF(MINT_INTRINS_MEMORYMARSHAL_GETARRAYDATAREF, "intrins_memorymarshal_getarraydataref", 3, 1, 1, MintOpNoArgs)
 OPDEF(MINT_INTRINS_ORDINAL_IGNORE_CASE_ASCII, "intrins_ordinal_ignore_case_ascii", 4, 1, 2, MintOpNoArgs)
@@ -834,12 +834,18 @@ OPDEF(MINT_TIER_MONITOR_JITERPRETER, "tier_monitor_jiterpreter", 4, 0, 0, MintOp
 
 IROPDEF(MINT_NOP, "nop", 1, 0, 0, MintOpNoArgs)
 IROPDEF(MINT_DEF, "def", 2, 1, 0, MintOpNoArgs)
+IROPDEF(MINT_DEF_ARG, "def_arg", 2, 1, 0, MintOpNoArgs)
+IROPDEF(MINT_DEF_TIER_VAR, "def_tier_var", 3, 1, 1, MintOpNoArgs)
 IROPDEF(MINT_IL_SEQ_POINT, "il_seq_point", 1, 0, 0, MintOpNoArgs)
 IROPDEF(MINT_DUMMY_USE, "dummy_use", 2, 0, 1, MintOpNoArgs)
 IROPDEF(MINT_TIER_PATCHPOINT_DATA, "tier_patchpoint_data", 2, 0, 0, MintOpShortInt)
 // These two opcodes are resolved to a normal MINT_MOV when emitting compacted instructions
 IROPDEF(MINT_MOV_SRC_OFF, "mov.src.off", 6, 1, 1, MintOpTwoShorts)
-IROPDEF(MINT_MOV_DST_OFF, "mov.dst.off", 6, 1, 1, MintOpTwoShorts)
+IROPDEF(MINT_MOV_DST_OFF, "mov.dst.off", 8, 1, 2, MintOpTwoShorts)
+IROPDEF(MINT_PHI, "phi", 2, 1, 0, MintOpNoArgs)
+IROPDEF(MINT_DEAD_PHI, "dead_phi", 1, 0, 0, MintOpNoArgs)
+IROPDEF(MINT_INTRINS_MARVIN_BLOCK_SSA1, "intrins_marvin_block_ssa1", 4, 1, 2, MintOpNoArgs)
+IROPDEF(MINT_INTRINS_MARVIN_BLOCK_SSA2, "intrins_marvin_block_ssa2", 4, 1, 2, MintOpNoArgs)
 
 #ifdef __DEFINED_IROPDEF__
 #undef IROPDEF

src/mono/mono/mini/interp/mintops.h

@@ -208,7 +208,8 @@ typedef enum {
 
 #define MINT_SWITCH_LEN(n) (4 + (n) * 2)
 
-#define MINT_IS_NOP(op) ((op) == MINT_NOP || (op) == MINT_DEF || (op) == MINT_DUMMY_USE || (op) == MINT_IL_SEQ_POINT)
+#define MINT_IS_NOP(op) ((op) == MINT_NOP || (op) == MINT_DEF || (op) == MINT_DEF_ARG || (op) == MINT_DUMMY_USE || (op) == MINT_IL_SEQ_POINT)
+#define MINT_IS_EMIT_NOP(op) ((op) == MINT_NOP || (op) == MINT_DEF || (op) == MINT_DEF_ARG || (op) == MINT_DEF_TIER_VAR || (op) == MINT_DUMMY_USE)
 #define MINT_IS_MOV(op) ((op) >= MINT_MOV_I4_I1 && (op) <= MINT_MOV_VT)
 #define MINT_IS_UNCONDITIONAL_BRANCH(op) ((op) >= MINT_BR && (op) <= MINT_CALL_HANDLER_S)
 #define MINT_IS_CONDITIONAL_BRANCH(op) ((op) >= MINT_BRFALSE_I4 && (op) <= MINT_BLT_UN_R8_S)
@@ -234,7 +235,7 @@ typedef enum {
 #define MINT_IS_RETURN(op) (((op) >= MINT_RET && (op) <= MINT_RET_U2) || (op) == MINT_RET_I4_IMM || (op) == MINT_RET_I8_IMM)
 
 // TODO Add more
-#define MINT_NO_SIDE_EFFECTS(op) (MINT_IS_MOV (op) || MINT_IS_LDC_I4 (op) || MINT_IS_LDC_I8 (op) || op == MINT_LDC_R4 || op == MINT_LDC_R8 || op == MINT_LDPTR || op == MINT_BOX)
+#define MINT_NO_SIDE_EFFECTS(op) (MINT_IS_MOV (op) || MINT_IS_LDC_I4 (op) || MINT_IS_LDC_I8 (op) || op == MINT_LDC_R4 || op == MINT_LDC_R8 || op == MINT_LDPTR || op == MINT_BOX || op == MINT_INITLOCAL)
 
 #define MINT_CALL_ARGS 2
 #define MINT_CALL_ARGS_SREG -2