tcg: Introduce TYPE_CONST temporaries

These will hold a single constant for the duration of the TB.
They are hashed, so that each value has one temp across the TB.

Not used yet, this is all infrastructure.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

2 files changed, 188 insertions, 49 deletions

diff --git a/tcg/optimize.c b/tcg/optimize.c
index 433d2540f4..16b0aa7229 100644
--- a/tcg/optimize.c
+++ b/tcg/optimize.c
@@ -99,8 +99,17 @@ static void init_ts_info(TempOptInfo *infos,
         ts->state_ptr = ti;
         ti->next_copy = ts;
         ti->prev_copy = ts;
-        ti->is_const = false;
-        ti->mask = -1;
+        if (ts->kind == TEMP_CONST) {
+            ti->is_const = true;
+            ti->val = ti->mask = ts->val;
+            if (TCG_TARGET_REG_BITS > 32 && ts->type == TCG_TYPE_I32) {
+                /* High bits of a 32-bit quantity are garbage.  */
+                ti->mask |= ~0xffffffffull;
+            }
+        } else {
+            ti->is_const = false;
+            ti->mask = -1;
+        }
         set_bit(idx, temps_used->l);
     }
 }
diff --git a/tcg/tcg.c b/tcg/tcg.c
index 545dd2b0b2..802f0b8a32 100644
--- a/tcg/tcg.c
+++ b/tcg/tcg.c
@@ -1184,6 +1184,13 @@ void tcg_func_start(TCGContext *s)
     /* No temps have been previously allocated for size or locality.  */
     memset(s->free_temps, 0, sizeof(s->free_temps));
 
+    /* No constant temps have been previously allocated. */
+    for (int i = 0; i < TCG_TYPE_COUNT; ++i) {
+        if (s->const_table[i]) {
+            g_hash_table_remove_all(s->const_table[i]);
+        }
+    }
+
     s->nb_ops = 0;
     s->nb_labels = 0;
     s->current_frame_offset = s->frame_start;
@@ -1255,13 +1262,19 @@ TCGTemp *tcg_global_mem_new_internal(TCGType type, TCGv_ptr base,
     bigendian = 1;
 #endif
 
-    if (base_ts->kind != TEMP_FIXED) {
+    switch (base_ts->kind) {
+    case TEMP_FIXED:
+        break;
+    case TEMP_GLOBAL:
         /* We do not support double-indirect registers.  */
         tcg_debug_assert(!base_ts->indirect_reg);
         base_ts->indirect_base = 1;
         s->nb_indirects += (TCG_TARGET_REG_BITS == 32 && type == TCG_TYPE_I64
                             ? 2 : 1);
         indirect_reg = 1;
+        break;
+    default:
+        g_assert_not_reached();
     }
 
     if (TCG_TARGET_REG_BITS == 32 && type == TCG_TYPE_I64) {
@@ -1386,6 +1399,11 @@ void tcg_temp_free_internal(TCGTemp *ts)
     TCGContext *s = tcg_ctx;
     int k, idx;
 
+    /* In order to simplify users of tcg_constant_*, silently ignore free. */
+    if (ts->kind == TEMP_CONST) {
+        return;
+    }
+
 #if defined(CONFIG_DEBUG_TCG)
     s->temps_in_use--;
     if (s->temps_in_use < 0) {
@@ -1402,6 +1420,60 @@ void tcg_temp_free_internal(TCGTemp *ts)
     set_bit(idx, s->free_temps[k].l);
 }
 
+TCGTemp *tcg_constant_internal(TCGType type, int64_t val)
+{
+    TCGContext *s = tcg_ctx;
+    GHashTable *h = s->const_table[type];
+    TCGTemp *ts;
+
+    if (h == NULL) {
+        h = g_hash_table_new(g_int64_hash, g_int64_equal);
+        s->const_table[type] = h;
+    }
+
+    ts = g_hash_table_lookup(h, &val);
+    if (ts == NULL) {
+        ts = tcg_temp_alloc(s);
+
+        if (TCG_TARGET_REG_BITS == 32 && type == TCG_TYPE_I64) {
+            TCGTemp *ts2 = tcg_temp_alloc(s);
+
+            ts->base_type = TCG_TYPE_I64;
+            ts->type = TCG_TYPE_I32;
+            ts->kind = TEMP_CONST;
+            ts->temp_allocated = 1;
+            /*
+             * Retain the full value of the 64-bit constant in the low
+             * part, so that the hash table works.  Actual uses will
+             * truncate the value to the low part.
+             */
+            ts->val = val;
+
+            tcg_debug_assert(ts2 == ts + 1);
+            ts2->base_type = TCG_TYPE_I64;
+            ts2->type = TCG_TYPE_I32;
+            ts2->kind = TEMP_CONST;
+            ts2->temp_allocated = 1;
+            ts2->val = val >> 32;
+        } else {
+            ts->base_type = type;
+            ts->type = type;
+            ts->kind = TEMP_CONST;
+            ts->temp_allocated = 1;
+            ts->val = val;
+        }
+        g_hash_table_insert(h, &ts->val, ts);
+    }
+
+    return ts;
+}
+
+TCGv_vec tcg_constant_vec(TCGType type, unsigned vece, int64_t val)
+{
+    val = dup_const(vece, val);
+    return temp_tcgv_vec(tcg_constant_internal(type, val));
+}
+
 TCGv_i32 tcg_const_i32(int32_t val)
 {
     TCGv_i32 t0;
@@ -1937,6 +2009,9 @@ static void tcg_reg_alloc_start(TCGContext *s)
         TCGTempVal val = TEMP_VAL_MEM;
 
         switch (ts->kind) {
+        case TEMP_CONST:
+            val = TEMP_VAL_CONST;
+            break;
         case TEMP_FIXED:
             val = TEMP_VAL_REG;
             break;
@@ -1973,6 +2048,26 @@ static char *tcg_get_arg_str_ptr(TCGContext *s, char *buf, int buf_size,
     case TEMP_NORMAL:
         snprintf(buf, buf_size, "tmp%d", idx - s->nb_globals);
         break;
+    case TEMP_CONST:
+        switch (ts->type) {
+        case TCG_TYPE_I32:
+            snprintf(buf, buf_size, "$0x%x", (int32_t)ts->val);
+            break;
+#if TCG_TARGET_REG_BITS > 32
+        case TCG_TYPE_I64:
+            snprintf(buf, buf_size, "$0x%" PRIx64, ts->val);
+            break;
+#endif
+        case TCG_TYPE_V64:
+        case TCG_TYPE_V128:
+        case TCG_TYPE_V256:
+            snprintf(buf, buf_size, "v%d$0x%" PRIx64,
+                     64 << (ts->type - TCG_TYPE_V64), ts->val);
+            break;
+        default:
+            g_assert_not_reached();
+        }
+        break;
     }
     return buf;
 }
@@ -2574,6 +2669,7 @@ static void la_bb_end(TCGContext *s, int ng, int nt)
             state = TS_DEAD | TS_MEM;
             break;
         case TEMP_NORMAL:
+        case TEMP_CONST:
             state = TS_DEAD;
             break;
         default:
@@ -2608,14 +2704,24 @@ static void la_bb_sync(TCGContext *s, int ng, int nt)
     la_global_sync(s, ng);
 
     for (int i = ng; i < nt; ++i) {
-        if (s->temps[i].kind == TEMP_LOCAL) {
-            int state = s->temps[i].state;
-            s->temps[i].state = state | TS_MEM;
+        TCGTemp *ts = &s->temps[i];
+        int state;
+
+        switch (ts->kind) {
+        case TEMP_LOCAL:
+            state = ts->state;
+            ts->state = state | TS_MEM;
             if (state != TS_DEAD) {
                 continue;
             }
-        } else {
+            break;
+        case TEMP_NORMAL:
             s->temps[i].state = TS_DEAD;
+            break;
+        case TEMP_CONST:
+            continue;
+        default:
+            g_assert_not_reached();
         }
         la_reset_pref(&s->temps[i]);
     }
@@ -3254,15 +3360,28 @@ static void temp_load(TCGContext *, TCGTemp *, TCGRegSet, TCGRegSet, TCGRegSet);
    mark it free; otherwise mark it dead.  */
 static void temp_free_or_dead(TCGContext *s, TCGTemp *ts, int free_or_dead)
 {
-    if (temp_readonly(ts)) {
+    TCGTempVal new_type;
+
+    switch (ts->kind) {
+    case TEMP_FIXED:
         return;
+    case TEMP_GLOBAL:
+    case TEMP_LOCAL:
+        new_type = TEMP_VAL_MEM;
+        break;
+    case TEMP_NORMAL:
+        new_type = free_or_dead < 0 ? TEMP_VAL_MEM : TEMP_VAL_DEAD;
+        break;
+    case TEMP_CONST:
+        new_type = TEMP_VAL_CONST;
+        break;
+    default:
+        g_assert_not_reached();
     }
     if (ts->val_type == TEMP_VAL_REG) {
         s->reg_to_temp[ts->reg] = NULL;
     }
-    ts->val_type = (free_or_dead < 0
-                    || ts->kind != TEMP_NORMAL
-                    ? TEMP_VAL_MEM : TEMP_VAL_DEAD);
+    ts->val_type = new_type;
 }
 
 /* Mark a temporary as dead.  */
@@ -3278,10 +3397,7 @@ static inline void temp_dead(TCGContext *s, TCGTemp *ts)
 static void temp_sync(TCGContext *s, TCGTemp *ts, TCGRegSet allocated_regs,
                       TCGRegSet preferred_regs, int free_or_dead)
 {
-    if (temp_readonly(ts)) {
-        return;
-    }
-    if (!ts->mem_coherent) {
+    if (!temp_readonly(ts) && !ts->mem_coherent) {
         if (!ts->mem_allocated) {
             temp_allocate_frame(s, ts);
         }
@@ -3499,12 +3615,22 @@ static void tcg_reg_alloc_bb_end(TCGContext *s, TCGRegSet allocated_regs)
 
     for (i = s->nb_globals; i < s->nb_temps; i++) {
         TCGTemp *ts = &s->temps[i];
-        if (ts->kind == TEMP_LOCAL) {
+
+        switch (ts->kind) {
+        case TEMP_LOCAL:
             temp_save(s, ts, allocated_regs);
-        } else {
+            break;
+        case TEMP_NORMAL:
             /* The liveness analysis already ensures that temps are dead.
                Keep an tcg_debug_assert for safety. */
             tcg_debug_assert(ts->val_type == TEMP_VAL_DEAD);
+            break;
+        case TEMP_CONST:
+            /* Similarly, we should have freed any allocated register. */
+            tcg_debug_assert(ts->val_type == TEMP_VAL_CONST);
+            break;
+        default:
+            g_assert_not_reached();
         }
     }
 
@@ -3525,10 +3651,17 @@ static void tcg_reg_alloc_cbranch(TCGContext *s, TCGRegSet allocated_regs)
          * The liveness analysis already ensures that temps are dead.
          * Keep tcg_debug_asserts for safety.
          */
-        if (ts->kind == TEMP_LOCAL) {
+        switch (ts->kind) {
+        case TEMP_LOCAL:
             tcg_debug_assert(ts->val_type != TEMP_VAL_REG || ts->mem_coherent);
-        } else {
+            break;
+        case TEMP_NORMAL:
             tcg_debug_assert(ts->val_type == TEMP_VAL_DEAD);
+            break;
+        case TEMP_CONST:
+            break;
+        default:
+            g_assert_not_reached();
         }
     }
 }
@@ -3819,45 +3952,42 @@ static void tcg_reg_alloc_op(TCGContext *s, const TCGOp *op)
         i_preferred_regs = o_preferred_regs = 0;
         if (arg_ct->ialias) {
             o_preferred_regs = op->output_pref[arg_ct->alias_index];
-            if (ts->kind == TEMP_FIXED) {
-                /* if fixed register, we must allocate a new register
-                   if the alias is not the same register */
-                if (arg != op->args[arg_ct->alias_index]) {
-                    goto allocate_in_reg;
-                }
-            } else {
-                /* if the input is aliased to an output and if it is
-                   not dead after the instruction, we must allocate
-                   a new register and move it */
-                if (!IS_DEAD_ARG(i)) {
-                    goto allocate_in_reg;
-                }
 
-                /* check if the current register has already been allocated
-                   for another input aliased to an output */
-                if (ts->val_type == TEMP_VAL_REG) {
-                    int k2, i2;
-                    reg = ts->reg;
-                    for (k2 = 0 ; k2 < k ; k2++) {
-                        i2 = def->args_ct[nb_oargs + k2].sort_index;
-                        if (def->args_ct[i2].ialias && reg == new_args[i2]) {
-                            goto allocate_in_reg;
-                        }
+            /*
+             * If the input is readonly, then it cannot also be an
+             * output and aliased to itself.  If the input is not
+             * dead after the instruction, we must allocate a new
+             * register and move it.
+             */
+            if (temp_readonly(ts) || !IS_DEAD_ARG(i)) {
+                goto allocate_in_reg;
+            }
+
+            /*
+             * Check if the current register has already been allocated
+             * for another input aliased to an output.
+             */
+            if (ts->val_type == TEMP_VAL_REG) {
+                reg = ts->reg;
+                for (int k2 = 0; k2 < k; k2++) {
+                    int i2 = def->args_ct[nb_oargs + k2].sort_index;
+                    if (def->args_ct[i2].ialias && reg == new_args[i2]) {
+                        goto allocate_in_reg;
                     }
                 }
-                i_preferred_regs = o_preferred_regs;
             }
+            i_preferred_regs = o_preferred_regs;
         }
 
         temp_load(s, ts, arg_ct->regs, i_allocated_regs, i_preferred_regs);
         reg = ts->reg;
 
-        if (tcg_regset_test_reg(arg_ct->regs, reg)) {
-            /* nothing to do : the constraint is satisfied */
-        } else {
-        allocate_in_reg:
-            /* allocate a new register matching the constraint 
-               and move the temporary register into it */
+        if (!tcg_regset_test_reg(arg_ct->regs, reg)) {
+ allocate_in_reg:
+            /*
+             * Allocate a new register matching the constraint
+             * and move the temporary register into it.
+             */
             temp_load(s, ts, tcg_target_available_regs[ts->type],
                       i_allocated_regs, 0);
             reg = tcg_reg_alloc(s, arg_ct->regs, i_allocated_regs,