[PATCH v2 08/29] tcg/ppc: Split out tcg_out_bswap16

[Richard Henderson]

With the use of a suitable temporary, we can use the same
algorithm when src overlaps dst.  The result is the same
number of instructions either way.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 tcg/ppc/tcg-target.c.inc | 34 +++++++++++++++++++---------------
 1 file changed, 19 insertions(+), 15 deletions(-)

diff --git a/tcg/ppc/tcg-target.c.inc b/tcg/ppc/tcg-target.c.inc
index 50347182d7..ad46ce32ca 100644
--- a/tcg/ppc/tcg-target.c.inc
+++ b/tcg/ppc/tcg-target.c.inc
@@ -789,6 +789,24 @@ static inline void tcg_out_sari64(TCGContext *s, TCGReg 
dst, TCGReg src, int c)
     tcg_out32(s, SRADI | RA(dst) | RS(src) | SH(c & 0x1f) | ((c >> 4) & 2));
 }
 
+static void tcg_out_bswap16(TCGContext *s, TCGReg dst, TCGReg src)
+{
+    TCGReg tmp = dst == src ? TCG_REG_R0 : dst;
+
+    /*
+     * In the following,
+     *   dep(a, b, m) -> (a & ~m) | (b & m)
+     *
+     * Begin with:                              src = xxxxabcd
+     */
+    /* tmp = rol32(src, 24) & 0x000000ff            = 0000000c */
+    tcg_out_rlw(s, RLWINM, tmp, src, 24, 24, 31);
+    /* tmp = dep(tmp, rol32(src, 8), 0x0000ff00)    = 000000dc */
+    tcg_out_rlw(s, RLWIMI, tmp, src, 8, 16, 23);
+
+    tcg_out_mov(s, TCG_TYPE_REG, dst, tmp);
+}
+
 /* Emit a move into ret of arg, if it can be done in one insn.  */
 static bool tcg_out_movi_one(TCGContext *s, TCGReg ret, tcg_target_long arg)
 {
@@ -2779,21 +2797,7 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc,
 
     case INDEX_op_bswap16_i32:
     case INDEX_op_bswap16_i64:
-        a0 = args[0], a1 = args[1];
-        /* a1 = abcd */
-        if (a0 != a1) {
-            /* a0 = (a1 r<< 24) & 0xff # 000c */
-            tcg_out_rlw(s, RLWINM, a0, a1, 24, 24, 31);
-            /* a0 = (a0 & ~0xff00) | (a1 r<< 8) & 0xff00 # 00dc */
-            tcg_out_rlw(s, RLWIMI, a0, a1, 8, 16, 23);
-        } else {
-            /* r0 = (a1 r<< 8) & 0xff00 # 00d0 */
-            tcg_out_rlw(s, RLWINM, TCG_REG_R0, a1, 8, 16, 23);
-            /* a0 = (a1 r<< 24) & 0xff # 000c */
-            tcg_out_rlw(s, RLWINM, a0, a1, 24, 24, 31);
-            /* a0 = a0 | r0 # 00dc */
-            tcg_out32(s, OR | SAB(TCG_REG_R0, a0, a0));
-        }
+        tcg_out_bswap16(s, args[0], args[1]);
         break;
 
     case INDEX_op_bswap32_i32:
-- 
2.25.1