From 1f106544fd87fd12566c8c5e12251067e2bc9f78 Mon Sep 17 00:00:00 2001
From: Richard Henderson <richard.henderson@linaro.org>
Date: Fri, 6 Sep 2024 12:22:41 -0700
Subject: [PATCH] tcg/optimize: Optimize cmp_vec and cmpsel_vec

Place immediate values second in the comparison.
Place destination matches first in the true/false values.
All of this mirrors what we do for integer setcond and movcond.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 tcg/optimize.c | 36 ++++++++++++++++++++++++++++++++++++
 1 file changed, 36 insertions(+)

diff --git a/tcg/optimize.c b/tcg/optimize.c
index cf311790e0..f11f576fd4 100644
--- a/tcg/optimize.c
+++ b/tcg/optimize.c
@@ -2422,6 +2422,36 @@ static bool fold_setcond2(OptContext *ctx, TCGOp *op)
     return tcg_opt_gen_movi(ctx, op, op->args[0], i);
 }
 
+static bool fold_cmp_vec(OptContext *ctx, TCGOp *op)
+{
+    /* Canonicalize the comparison to put immediate second. */
+    if (swap_commutative(NO_DEST, &op->args[1], &op->args[2])) {
+        op->args[3] = tcg_swap_cond(op->args[3]);
+    }
+    return false;
+}
+
+static bool fold_cmpsel_vec(OptContext *ctx, TCGOp *op)
+{
+    /* If true and false values are the same, eliminate the cmp. */
+    if (args_are_copies(op->args[3], op->args[4])) {
+        return tcg_opt_gen_mov(ctx, op, op->args[0], op->args[3]);
+    }
+
+    /* Canonicalize the comparison to put immediate second. */
+    if (swap_commutative(NO_DEST, &op->args[1], &op->args[2])) {
+        op->args[5] = tcg_swap_cond(op->args[5]);
+    }
+    /*
+     * Canonicalize the "false" input reg to match the destination,
+     * so that the tcg backend can implement "move if true".
+     */
+    if (swap_commutative(op->args[0], &op->args[4], &op->args[3])) {
+        op->args[5] = tcg_invert_cond(op->args[5]);
+    }
+    return false;
+}
+
 static bool fold_sextract(OptContext *ctx, TCGOp *op)
 {
     uint64_t z_mask, s_mask, s_mask_old;
@@ -2928,6 +2958,12 @@ void tcg_optimize(TCGContext *s)
         case INDEX_op_setcond2_i32:
             done = fold_setcond2(&ctx, op);
             break;
+        case INDEX_op_cmp_vec:
+            done = fold_cmp_vec(&ctx, op);
+            break;
+        case INDEX_op_cmpsel_vec:
+            done = fold_cmpsel_vec(&ctx, op);
+            break;
         CASE_OP_32_64(sextract):
             done = fold_sextract(&ctx, op);
             break;