target/arm: Improve REV32

For the sf version, we are performing two 32-bit bswaps
in either half of the register.  This is equivalent to
performing one 64-bit bswap followed by a rotate.

For the non-sf version, we can remove TCG_BSWAP_IZ
and the preceding zero-extension.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

1 files changed, 4 insertions, 13 deletions

diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
index f2641a3..304fd3d 100644
--- a/target/arm/translate-a64.c
+++ b/target/arm/translate-a64.c
@@ -5430,22 +5430,13 @@ static void handle_rev32(DisasContext *s, unsigned int sf,
                          unsigned int rn, unsigned int rd)
 {
     TCGv_i64 tcg_rd = cpu_reg(s, rd);
+    TCGv_i64 tcg_rn = cpu_reg(s, rn);
 
     if (sf) {
-        TCGv_i64 tcg_tmp = tcg_temp_new_i64();
-        TCGv_i64 tcg_rn = read_cpu_reg(s, rn, sf);
-
-        /* bswap32_i64 requires zero high word */
-        tcg_gen_ext32u_i64(tcg_tmp, tcg_rn);
-        tcg_gen_bswap32_i64(tcg_rd, tcg_tmp, TCG_BSWAP_IZ | TCG_BSWAP_OZ);
-        tcg_gen_shri_i64(tcg_tmp, tcg_rn, 32);
-        tcg_gen_bswap32_i64(tcg_tmp, tcg_tmp, TCG_BSWAP_IZ | TCG_BSWAP_OZ);
-        tcg_gen_concat32_i64(tcg_rd, tcg_rd, tcg_tmp);
-
-        tcg_temp_free_i64(tcg_tmp);
+        tcg_gen_bswap64_i64(tcg_rd, tcg_rn);
+        tcg_gen_rotri_i64(tcg_rd, tcg_rd, 32);
     } else {
-        tcg_gen_ext32u_i64(tcg_rd, cpu_reg(s, rn));
-        tcg_gen_bswap32_i64(tcg_rd, tcg_rd, TCG_BSWAP_IZ | TCG_BSWAP_OZ);
+        tcg_gen_bswap32_i64(tcg_rd, tcg_rn, TCG_BSWAP_OZ);
     }
 }