target/arm: optimize aarch32 rev16

Use the same mask to avoid having to load two different constants, as
suggested by Richard Henderson.

Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Reviewed-by: Richard Henderson <rth@twiddle.net>
Message-Id: <20170516230159.4195-2-aurelien@aurel32.net>
Signed-off-by: Richard Henderson <rth@twiddle.net>

diff --git a/target/arm/translate.c b/target/arm/translate.c
index e27736ce5b716cb39282a98db9bc71f454f7899e..d3003ae0d8a6c38815102f3be6a86810b5d54f60 100644 (file)
--- a/target/arm/translate.c
+++ b/target/arm/translate.c
@@ -343,11 +343,13 @@ static void gen_smul_dual(TCGv_i32 a, TCGv_i32 b)
 static void gen_rev16(TCGv_i32 var)
 {
     TCGv_i32 tmp = tcg_temp_new_i32();
+    TCGv_i32 mask = tcg_const_i32(0x00ff00ff);
     tcg_gen_shri_i32(tmp, var, 8);
-    tcg_gen_andi_i32(tmp, tmp, 0x00ff00ff);
+    tcg_gen_and_i32(tmp, tmp, mask);
+    tcg_gen_and_i32(var, var, mask);
     tcg_gen_shli_i32(var, var, 8);
-    tcg_gen_andi_i32(var, var, 0xff00ff00);
     tcg_gen_or_i32(var, var, tmp);
+    tcg_temp_free_i32(mask);
     tcg_temp_free_i32(tmp);
 }