For INDEX_op_bswap16_i64, use 64-bit instructions so that we can
easily provide the extension to 64-bits. Drop the special case,
previously used, where the input is already zero-extended -- the
minor code size savings is not worth the complication.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
tcg/s390/tcg-target.c.inc | 34 ++++++++++++++++++++++++++++------
1 file changed, 28 insertions(+), 6 deletions(-)
diff --git a/tcg/s390/tcg-target.c.inc b/tcg/s390/tcg-target.c.inc
index 5fe073f09a..b82cf19f09 100644
--- a/tcg/s390/tcg-target.c.inc
+++ b/tcg/s390/tcg-target.c.inc
@@ -1951,15 +1951,37 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
tgen_ext16u(s, TCG_TYPE_I32, args[0], args[1]);
break;
- OP_32_64(bswap16):
- /* The TCG bswap definition requires bits 0-47 already be zero.
- Thus we don't need the G-type insns to implement bswap16_i64. */
- tcg_out_insn(s, RRE, LRVR, args[0], args[1]);
- tcg_out_sh32(s, RS_SRL, args[0], TCG_REG_NONE, 16);
+ case INDEX_op_bswap16_i32:
+ a0 = args[0], a1 = args[1], a2 = args[2];
+ tcg_out_insn(s, RRE, LRVR, a0, a1);
+ if (a2 & TCG_BSWAP_OS) {
+ tcg_out_sh32(s, RS_SRA, a0, TCG_REG_NONE, 16);
+ } else {
+ tcg_out_sh32(s, RS_SRL, a0, TCG_REG_NONE, 16);
+ }
break;
- OP_32_64(bswap32):
+ case INDEX_op_bswap16_i64:
+ a0 = args[0], a1 = args[1], a2 = args[2];
+ tcg_out_insn(s, RRE, LRVGR, a0, a1);
+ if (a2 & TCG_BSWAP_OS) {
+ tcg_out_sh64(s, RSY_SRAG, a0, a0, TCG_REG_NONE, 48);
+ } else {
+ tcg_out_sh64(s, RSY_SRLG, a0, a0, TCG_REG_NONE, 48);
+ }
+ break;
+
+ case INDEX_op_bswap32_i32:
tcg_out_insn(s, RRE, LRVR, args[0], args[1]);
break;
+ case INDEX_op_bswap32_i64:
+ a0 = args[0], a1 = args[1], a2 = args[2];
+ tcg_out_insn(s, RRE, LRVR, a0, a1);
+ if (a2 & TCG_BSWAP_OS) {
+ tgen_ext32s(s, a0, a0);
+ } else if ((a2 & (TCG_BSWAP_IZ | TCG_BSWAP_OZ)) == TCG_BSWAP_OZ) {
+ tgen_ext32u(s, a0, a0);
+ }
+ break;
case INDEX_op_add2_i32:
if (const_args[4]) {
--
2.25.1