[PATCH v4 41/51] tcg/optimize: Sink commutative operand swapping into fold functions

[Richard Henderson]

Most of these are handled by creating a fold_const2_commutative
to handle all of the binary operators.  The rest were already
handled on a case-by-case basis in the switch, and have their
own fold function in which to place the call.

We now have only one major switch on TCGOpcode.

Introduce NO_DEST and a block comment for swap_commutative in
order to make the handling of brcond and movcond opcodes cleaner.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 tcg/optimize.c | 141 ++++++++++++++++++++++++-------------------------
 1 file changed, 69 insertions(+), 72 deletions(-)

diff --git a/tcg/optimize.c b/tcg/optimize.c
index 6189637dd8..b72a01910a 100644
--- a/tcg/optimize.c
+++ b/tcg/optimize.c
@@ -577,6 +577,19 @@ static int do_constant_folding_cond2(TCGArg *p1, TCGArg 
*p2, TCGCond c)
     return -1;
 }
 
+/**
+ * swap_commutative:
+ * @dest: TCGArg of the destination argument, or NO_DEST.
+ * @p1: first paired argument
+ * @p2: second paired argument
+ *
+ * If *@p1 is a constant and *@p2 is not, swap.
+ * If *@p2 matches @dest, swap.
+ * Return true if a swap was performed.
+ */
+
+#define NO_DEST  temp_arg(NULL)
+
 static bool swap_commutative(TCGArg dest, TCGArg *p1, TCGArg *p2)
 {
     TCGArg a1 = *p1, a2 = *p2;
@@ -696,6 +709,12 @@ static bool fold_const2(OptContext *ctx, TCGOp *op)
     return false;
 }
 
+static bool fold_const2_commutative(OptContext *ctx, TCGOp *op)
+{
+    swap_commutative(op->args[0], &op->args[1], &op->args[2]);
+    return fold_const2(ctx, op);
+}
+
 static bool fold_masks(OptContext *ctx, TCGOp *op)
 {
     uint64_t a_mask = ctx->a_mask;
@@ -832,7 +851,7 @@ static bool fold_xx_to_x(OptContext *ctx, TCGOp *op)
 
 static bool fold_add(OptContext *ctx, TCGOp *op)
 {
-    if (fold_const2(ctx, op) ||
+    if (fold_const2_commutative(ctx, op) ||
         fold_xi_to_x(ctx, op, 0)) {
         return true;
     }
@@ -891,6 +910,9 @@ static bool fold_addsub2(OptContext *ctx, TCGOp *op, bool 
add)
 
 static bool fold_add2(OptContext *ctx, TCGOp *op)
 {
+    swap_commutative(op->args[0], &op->args[2], &op->args[4]);
+    swap_commutative(op->args[1], &op->args[3], &op->args[5]);
+
     return fold_addsub2(ctx, op, true);
 }
 
@@ -898,7 +920,7 @@ static bool fold_and(OptContext *ctx, TCGOp *op)
 {
     uint64_t z1, z2;
 
-    if (fold_const2(ctx, op) ||
+    if (fold_const2_commutative(ctx, op) ||
         fold_xi_to_i(ctx, op, 0) ||
         fold_xi_to_x(ctx, op, -1) ||
         fold_xx_to_x(ctx, op)) {
@@ -950,8 +972,13 @@ static bool fold_andc(OptContext *ctx, TCGOp *op)
 static bool fold_brcond(OptContext *ctx, TCGOp *op)
 {
     TCGCond cond = op->args[2];
-    int i = do_constant_folding_cond(ctx->type, op->args[0], op->args[1], 
cond);
+    int i;
 
+    if (swap_commutative(NO_DEST, &op->args[0], &op->args[1])) {
+        op->args[2] = cond = tcg_swap_cond(cond);
+    }
+
+    i = do_constant_folding_cond(ctx->type, op->args[0], op->args[1], cond);
     if (i == 0) {
         tcg_op_remove(ctx->tcg, op);
         return true;
@@ -966,10 +993,14 @@ static bool fold_brcond(OptContext *ctx, TCGOp *op)
 static bool fold_brcond2(OptContext *ctx, TCGOp *op)
 {
     TCGCond cond = op->args[4];
-    int i = do_constant_folding_cond2(&op->args[0], &op->args[2], cond);
     TCGArg label = op->args[5];
-    int inv = 0;
+    int i, inv = 0;
 
+    if (swap_commutative2(&op->args[0], &op->args[2])) {
+        op->args[4] = cond = tcg_swap_cond(cond);
+    }
+
+    i = do_constant_folding_cond2(&op->args[0], &op->args[2], cond);
     if (i >= 0) {
         goto do_brcond_const;
     }
@@ -1219,7 +1250,7 @@ static bool fold_dup2(OptContext *ctx, TCGOp *op)
 
 static bool fold_eqv(OptContext *ctx, TCGOp *op)
 {
-    if (fold_const2(ctx, op) ||
+    if (fold_const2_commutative(ctx, op) ||
         fold_xi_to_x(ctx, op, -1) ||
         fold_xi_to_not(ctx, op, 0)) {
         return true;
@@ -1381,8 +1412,20 @@ static bool fold_mov(OptContext *ctx, TCGOp *op)
 static bool fold_movcond(OptContext *ctx, TCGOp *op)
 {
     TCGCond cond = op->args[5];
-    int i = do_constant_folding_cond(ctx->type, op->args[1], op->args[2], 
cond);
+    int i;
 
+    if (swap_commutative(NO_DEST, &op->args[1], &op->args[2])) {
+        op->args[5] = cond = tcg_swap_cond(cond);
+    }
+    /*
+     * Canonicalize the "false" input reg to match the destination reg so
+     * that the tcg backend can implement a "move if true" operation.
+     */
+    if (swap_commutative(op->args[0], &op->args[4], &op->args[3])) {
+        op->args[5] = cond = tcg_invert_cond(cond);
+    }
+
+    i = do_constant_folding_cond(ctx->type, op->args[1], op->args[2], cond);
     if (i >= 0) {
         return tcg_opt_gen_mov(ctx, op, op->args[0], op->args[4 - i]);
     }
@@ -1428,7 +1471,7 @@ static bool fold_mul(OptContext *ctx, TCGOp *op)
 
 static bool fold_mul_highpart(OptContext *ctx, TCGOp *op)
 {
-    if (fold_const2(ctx, op) ||
+    if (fold_const2_commutative(ctx, op) ||
         fold_xi_to_i(ctx, op, 0)) {
         return true;
     }
@@ -1437,6 +1480,8 @@ static bool fold_mul_highpart(OptContext *ctx, TCGOp *op)
 
 static bool fold_multiply2(OptContext *ctx, TCGOp *op)
 {
+    swap_commutative(op->args[0], &op->args[2], &op->args[3]);
+
     if (arg_is_const(op->args[2]) && arg_is_const(op->args[3])) {
         uint64_t a = arg_info(op->args[2])->val;
         uint64_t b = arg_info(op->args[3])->val;
@@ -1480,7 +1525,7 @@ static bool fold_multiply2(OptContext *ctx, TCGOp *op)
 
 static bool fold_nand(OptContext *ctx, TCGOp *op)
 {
-    if (fold_const2(ctx, op) ||
+    if (fold_const2_commutative(ctx, op) ||
         fold_xi_to_not(ctx, op, -1)) {
         return true;
     }
@@ -1509,7 +1554,7 @@ static bool fold_neg(OptContext *ctx, TCGOp *op)
 
 static bool fold_nor(OptContext *ctx, TCGOp *op)
 {
-    if (fold_const2(ctx, op) ||
+    if (fold_const2_commutative(ctx, op) ||
         fold_xi_to_not(ctx, op, 0)) {
         return true;
     }
@@ -1529,7 +1574,7 @@ static bool fold_not(OptContext *ctx, TCGOp *op)
 
 static bool fold_or(OptContext *ctx, TCGOp *op)
 {
-    if (fold_const2(ctx, op) ||
+    if (fold_const2_commutative(ctx, op) ||
         fold_xi_to_x(ctx, op, 0) ||
         fold_xx_to_x(ctx, op)) {
         return true;
@@ -1581,8 +1626,13 @@ static bool fold_remainder(OptContext *ctx, TCGOp *op)
 static bool fold_setcond(OptContext *ctx, TCGOp *op)
 {
     TCGCond cond = op->args[3];
-    int i = do_constant_folding_cond(ctx->type, op->args[1], op->args[2], 
cond);
+    int i;
 
+    if (swap_commutative(op->args[0], &op->args[1], &op->args[2])) {
+        op->args[3] = cond = tcg_swap_cond(cond);
+    }
+
+    i = do_constant_folding_cond(ctx->type, op->args[1], op->args[2], cond);
     if (i >= 0) {
         return tcg_opt_gen_movi(ctx, op, op->args[0], i);
     }
@@ -1594,9 +1644,13 @@ static bool fold_setcond(OptContext *ctx, TCGOp *op)
 static bool fold_setcond2(OptContext *ctx, TCGOp *op)
 {
     TCGCond cond = op->args[5];
-    int i = do_constant_folding_cond2(&op->args[1], &op->args[3], cond);
-    int inv = 0;
+    int i, inv = 0;
 
+    if (swap_commutative2(&op->args[1], &op->args[3])) {
+        op->args[5] = cond = tcg_swap_cond(cond);
+    }
+
+    i = do_constant_folding_cond2(&op->args[1], &op->args[3], cond);
     if (i >= 0) {
         goto do_setcond_const;
     }
@@ -1774,7 +1828,7 @@ static bool fold_tcg_ld(OptContext *ctx, TCGOp *op)
 
 static bool fold_xor(OptContext *ctx, TCGOp *op)
 {
-    if (fold_const2(ctx, op) ||
+    if (fold_const2_commutative(ctx, op) ||
         fold_xx_to_i(ctx, op, 0) ||
         fold_xi_to_x(ctx, op, 0) ||
         fold_xi_to_not(ctx, op, -1)) {
@@ -1827,63 +1881,6 @@ void tcg_optimize(TCGContext *s)
             ctx.type = TCG_TYPE_I32;
         }
 
-        /* For commutative operations make constant second argument */
-        switch (opc) {
-        CASE_OP_32_64_VEC(add):
-        CASE_OP_32_64_VEC(mul):
-        CASE_OP_32_64_VEC(and):
-        CASE_OP_32_64_VEC(or):
-        CASE_OP_32_64_VEC(xor):
-        CASE_OP_32_64(eqv):
-        CASE_OP_32_64(nand):
-        CASE_OP_32_64(nor):
-        CASE_OP_32_64(muluh):
-        CASE_OP_32_64(mulsh):
-            swap_commutative(op->args[0], &op->args[1], &op->args[2]);
-            break;
-        CASE_OP_32_64(brcond):
-            if (swap_commutative(-1, &op->args[0], &op->args[1])) {
-                op->args[2] = tcg_swap_cond(op->args[2]);
-            }
-            break;
-        CASE_OP_32_64(setcond):
-            if (swap_commutative(op->args[0], &op->args[1], &op->args[2])) {
-                op->args[3] = tcg_swap_cond(op->args[3]);
-            }
-            break;
-        CASE_OP_32_64(movcond):
-            if (swap_commutative(-1, &op->args[1], &op->args[2])) {
-                op->args[5] = tcg_swap_cond(op->args[5]);
-            }
-            /* For movcond, we canonicalize the "false" input reg to match
-               the destination reg so that the tcg backend can implement
-               a "move if true" operation.  */
-            if (swap_commutative(op->args[0], &op->args[4], &op->args[3])) {
-                op->args[5] = tcg_invert_cond(op->args[5]);
-            }
-            break;
-        CASE_OP_32_64(add2):
-            swap_commutative(op->args[0], &op->args[2], &op->args[4]);
-            swap_commutative(op->args[1], &op->args[3], &op->args[5]);
-            break;
-        CASE_OP_32_64(mulu2):
-        CASE_OP_32_64(muls2):
-            swap_commutative(op->args[0], &op->args[2], &op->args[3]);
-            break;
-        case INDEX_op_brcond2_i32:
-            if (swap_commutative2(&op->args[0], &op->args[2])) {
-                op->args[4] = tcg_swap_cond(op->args[4]);
-            }
-            break;
-        case INDEX_op_setcond2_i32:
-            if (swap_commutative2(&op->args[1], &op->args[3])) {
-                op->args[5] = tcg_swap_cond(op->args[5]);
-            }
-            break;
-        default:
-            break;
-        }
-
         /* Assume all bits affected, and no bits known zero. */
         ctx.a_mask = -1;
         ctx.z_mask = -1;
-- 
2.25.1