[PATCH 4/8] tcg/loongarch64: Introduce tcg_out_addi

[Richard Henderson]

Adjust the constraints to allow any int32_t for immediate
addition.  Split immediate adds into addu16i + addi, which
covers quite a lot of the immediate space.  For the hole in
the middle, load the constant into TMP0 instead.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 tcg/loongarch64/tcg-target-con-set.h |  4 +-
 tcg/loongarch64/tcg-target-con-str.h |  2 +-
 tcg/loongarch64/tcg-target.c.inc     | 57 ++++++++++++++++++++++++----
 3 files changed, 53 insertions(+), 10 deletions(-)

diff --git a/tcg/loongarch64/tcg-target-con-set.h 
b/tcg/loongarch64/tcg-target-con-set.h
index 349c672687..7b5a7a3f5d 100644
--- a/tcg/loongarch64/tcg-target-con-set.h
+++ b/tcg/loongarch64/tcg-target-con-set.h
@@ -23,9 +23,11 @@ C_O1_I1(r, L)
 C_O1_I2(r, r, rC)
 C_O1_I2(r, r, ri)
 C_O1_I2(r, r, rI)
+C_O1_I2(r, r, rJ)
 C_O1_I2(r, r, rU)
 C_O1_I2(r, r, rW)
 C_O1_I2(r, r, rZ)
 C_O1_I2(r, 0, rZ)
-C_O1_I2(r, rZ, rN)
+C_O1_I2(r, rZ, ri)
+C_O1_I2(r, rZ, rJ)
 C_O1_I2(r, rZ, rZ)
diff --git a/tcg/loongarch64/tcg-target-con-str.h 
b/tcg/loongarch64/tcg-target-con-str.h
index c3986a4fd4..541ff47fa9 100644
--- a/tcg/loongarch64/tcg-target-con-str.h
+++ b/tcg/loongarch64/tcg-target-con-str.h
@@ -21,7 +21,7 @@ REGS('L', ALL_GENERAL_REGS & ~SOFTMMU_RESERVE_REGS)
  * CONST(letter, TCG_CT_CONST_* bit set)
  */
 CONST('I', TCG_CT_CONST_S12)
-CONST('N', TCG_CT_CONST_N12)
+CONST('J', TCG_CT_CONST_S32)
 CONST('U', TCG_CT_CONST_U12)
 CONST('Z', TCG_CT_CONST_ZERO)
 CONST('C', TCG_CT_CONST_C12)
diff --git a/tcg/loongarch64/tcg-target.c.inc b/tcg/loongarch64/tcg-target.c.inc
index b2350f2cc7..a477b1b96d 100644
--- a/tcg/loongarch64/tcg-target.c.inc
+++ b/tcg/loongarch64/tcg-target.c.inc
@@ -126,7 +126,7 @@ static const int tcg_target_call_oarg_regs[] = {
 
 #define TCG_CT_CONST_ZERO  0x100
 #define TCG_CT_CONST_S12   0x200
-#define TCG_CT_CONST_N12   0x400
+#define TCG_CT_CONST_S32   0x400
 #define TCG_CT_CONST_U12   0x800
 #define TCG_CT_CONST_C12   0x1000
 #define TCG_CT_CONST_WSZ   0x2000
@@ -161,7 +161,7 @@ static bool tcg_target_const_match(int64_t val, TCGType 
type, int ct)
     if ((ct & TCG_CT_CONST_S12) && val == sextreg(val, 0, 12)) {
         return true;
     }
-    if ((ct & TCG_CT_CONST_N12) && -val == sextreg(-val, 0, 12)) {
+    if ((ct & TCG_CT_CONST_S32) && val == (int32_t)val) {
         return true;
     }
     if ((ct & TCG_CT_CONST_U12) && val >= 0 && val <= 0xfff) {
@@ -378,6 +378,45 @@ static void tcg_out_movi(TCGContext *s, TCGType type, 
TCGReg rd,
     }
 }
 
+static void tcg_out_addi(TCGContext *s, TCGType type, TCGReg rd,
+                         TCGReg rs, tcg_target_long imm)
+{
+    tcg_target_long lo12 = sextreg(imm, 0, 12);
+    tcg_target_long hi16 = sextreg(imm - lo12, 16, 16);
+
+    /*
+     * Note that there's a hole in between hi16 and lo12:
+     *
+     *       3                   2                   1                   0
+     *     1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0
+     * ...+-------------------------------+-------+-----------------------+
+     *    |             hi16              |       |          lo12         |
+     * ...+-------------------------------+-------+-----------------------+
+     *
+     * For bits within that hole, it's more efficient to use LU12I and ADD.
+     */
+    if (imm == (hi16 << 16) + lo12) {
+        if (hi16) {
+            tcg_out_opc_addu16i_d(s, rd, rs, hi16);
+            rs = rd;
+        }
+        if (type == TCG_TYPE_I32) {
+            tcg_out_opc_addi_w(s, rd, rs, lo12);
+        } else if (lo12) {
+            tcg_out_opc_addi_d(s, rd, rs, lo12);
+        } else {
+            tcg_out_mov(s, type, rd, rs);
+        }
+    } else {
+        tcg_out_movi(s, type, TCG_REG_TMP0, imm);
+        if (type == TCG_TYPE_I32) {
+            tcg_out_opc_add_w(s, rd, rs, TCG_REG_TMP0);
+        } else {
+            tcg_out_opc_add_d(s, rd, rs, TCG_REG_TMP0);
+        }
+    }
+}
+
 static void tcg_out_ext8u(TCGContext *s, TCGReg ret, TCGReg arg)
 {
     tcg_out_opc_andi(s, ret, arg, 0xff);
@@ -1349,14 +1388,14 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc,
 
     case INDEX_op_add_i32:
         if (c2) {
-            tcg_out_opc_addi_w(s, a0, a1, a2);
+            tcg_out_addi(s, TCG_TYPE_I32, a0, a1, a2);
         } else {
             tcg_out_opc_add_w(s, a0, a1, a2);
         }
         break;
     case INDEX_op_add_i64:
         if (c2) {
-            tcg_out_opc_addi_d(s, a0, a1, a2);
+            tcg_out_addi(s, TCG_TYPE_I64, a0, a1, a2);
         } else {
             tcg_out_opc_add_d(s, a0, a1, a2);
         }
@@ -1364,14 +1403,14 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc,
 
     case INDEX_op_sub_i32:
         if (c2) {
-            tcg_out_opc_addi_w(s, a0, a1, -a2);
+            tcg_out_addi(s, TCG_TYPE_I32, a0, a1, -a2);
         } else {
             tcg_out_opc_sub_w(s, a0, a1, a2);
         }
         break;
     case INDEX_op_sub_i64:
         if (c2) {
-            tcg_out_opc_addi_d(s, a0, a1, -a2);
+            tcg_out_addi(s, TCG_TYPE_I64, a0, a1, -a2);
         } else {
             tcg_out_opc_sub_d(s, a0, a1, a2);
         }
@@ -1585,8 +1624,9 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode 
op)
         return C_O1_I2(r, r, ri);
 
     case INDEX_op_add_i32:
+        return C_O1_I2(r, r, ri);
     case INDEX_op_add_i64:
-        return C_O1_I2(r, r, rI);
+        return C_O1_I2(r, r, rJ);
 
     case INDEX_op_and_i32:
     case INDEX_op_and_i64:
@@ -1615,8 +1655,9 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode 
op)
         return C_O1_I2(r, 0, rZ);
 
     case INDEX_op_sub_i32:
+        return C_O1_I2(r, rZ, ri);
     case INDEX_op_sub_i64:
-        return C_O1_I2(r, rZ, rN);
+        return C_O1_I2(r, rZ, rJ);
 
     case INDEX_op_mul_i32:
     case INDEX_op_mul_i64:
-- 
2.34.1