[PATCH v4 40/51] tcg/optimize: Expand fold_addsub2_i32 to 64-bit ops

[Richard Henderson <richard.henderson@linaro.org>]

Rename to fold_addsub2.
Use Int128 to implement the wider operation.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 tcg/optimize.c | 65 ++++++++++++++++++++++++++++++++++----------------
 1 file changed, 44 insertions(+), 21 deletions(-)

diff --git a/tcg/optimize.c b/tcg/optimize.c
index 7597655a43..6189637dd8 100644
--- a/tcg/optimize.c
+++ b/tcg/optimize.c
@@ -24,6 +24,7 @@
  */
 
 #include "qemu/osdep.h"
+#include "qemu/int128.h"
 #include "tcg/tcg-op.h"
 #include "tcg-internal.h"
 
@@ -838,37 +839,59 @@ static bool fold_add(OptContext *ctx, TCGOp *op)
     return false;
 }
 
-static bool fold_addsub2_i32(OptContext *ctx, TCGOp *op, bool add)
+static bool fold_addsub2(OptContext *ctx, TCGOp *op, bool add)
 {
     if (arg_is_const(op->args[2]) && arg_is_const(op->args[3]) &&
         arg_is_const(op->args[4]) && arg_is_const(op->args[5])) {
-        uint32_t al = arg_info(op->args[2])->val;
-        uint32_t ah = arg_info(op->args[3])->val;
-        uint32_t bl = arg_info(op->args[4])->val;
-        uint32_t bh = arg_info(op->args[5])->val;
-        uint64_t a = ((uint64_t)ah << 32) | al;
-        uint64_t b = ((uint64_t)bh << 32) | bl;
+        uint64_t al = arg_info(op->args[2])->val;
+        uint64_t ah = arg_info(op->args[3])->val;
+        uint64_t bl = arg_info(op->args[4])->val;
+        uint64_t bh = arg_info(op->args[5])->val;
         TCGArg rl, rh;
-        TCGOp *op2 = tcg_op_insert_before(ctx->tcg, op, INDEX_op_mov_i32);
+        TCGOp *op2;
 
-        if (add) {
-            a += b;
+        if (ctx->type == TCG_TYPE_I32) {
+            uint64_t a = deposit64(al, 32, 32, ah);
+            uint64_t b = deposit64(bl, 32, 32, bh);
+
+            if (add) {
+                a += b;
+            } else {
+                a -= b;
+            }
+
+            al = sextract64(a, 0, 32);
+            ah = sextract64(a, 32, 32);
         } else {
-            a -= b;
+            Int128 a = int128_make128(al, ah);
+            Int128 b = int128_make128(bl, bh);
+
+            if (add) {
+                a = int128_add(a, b);
+            } else {
+                a = int128_sub(a, b);
+            }
+
+            al = int128_getlo(a);
+            ah = int128_gethi(a);
         }
 
         rl = op->args[0];
         rh = op->args[1];
-        tcg_opt_gen_movi(ctx, op, rl, (int32_t)a);
-        tcg_opt_gen_movi(ctx, op2, rh, (int32_t)(a >> 32));
+
+        /* The proper opcode is supplied by tcg_opt_gen_mov. */
+        op2 = tcg_op_insert_before(ctx->tcg, op, 0);
+
+        tcg_opt_gen_movi(ctx, op, rl, al);
+        tcg_opt_gen_movi(ctx, op2, rh, ah);
         return true;
     }
     return false;
 }
 
-static bool fold_add2_i32(OptContext *ctx, TCGOp *op)
+static bool fold_add2(OptContext *ctx, TCGOp *op)
 {
-    return fold_addsub2_i32(ctx, op, true);
+    return fold_addsub2(ctx, op, true);
 }
 
 static bool fold_and(OptContext *ctx, TCGOp *op)
@@ -1725,9 +1748,9 @@ static bool fold_sub(OptContext *ctx, TCGOp *op)
     return false;
 }
 
-static bool fold_sub2_i32(OptContext *ctx, TCGOp *op)
+static bool fold_sub2(OptContext *ctx, TCGOp *op)
 {
-    return fold_addsub2_i32(ctx, op, false);
+    return fold_addsub2(ctx, op, false);
 }
 
 static bool fold_tcg_ld(OptContext *ctx, TCGOp *op)
@@ -1873,8 +1896,8 @@ void tcg_optimize(TCGContext *s)
         CASE_OP_32_64_VEC(add):
             done = fold_add(&ctx, op);
             break;
-        case INDEX_op_add2_i32:
-            done = fold_add2_i32(&ctx, op);
+        CASE_OP_32_64(add2):
+            done = fold_add2(&ctx, op);
             break;
         CASE_OP_32_64_VEC(and):
             done = fold_and(&ctx, op);
@@ -2011,8 +2034,8 @@ void tcg_optimize(TCGContext *s)
         CASE_OP_32_64_VEC(sub):
             done = fold_sub(&ctx, op);
             break;
-        case INDEX_op_sub2_i32:
-            done = fold_sub2_i32(&ctx, op);
+        CASE_OP_32_64(sub2):
+            done = fold_sub2(&ctx, op);
             break;
         CASE_OP_32_64_VEC(xor):
             done = fold_xor(&ctx, op);
-- 
2.25.1