diff mbox series

[v2,34/36] tcg/ppc: Implement INDEX_op_rot[lr]v_vec

Message ID 20200422011722.13287-35-richard.henderson@linaro.org
State New
Headers show
Series tcg 5.1 omnibus patch set | expand

Commit Message

Richard Henderson April 22, 2020, 1:17 a.m. UTC 
We already had support for rotlv, using a target-specific opcode;
convert to use the generic opcode.  Handle rotrv via simple negation.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

---
 tcg/ppc/tcg-target.h     |  2 +-
 tcg/ppc/tcg-target.opc.h |  1 -
 tcg/ppc/tcg-target.inc.c | 23 +++++++++++++++++++----
 3 files changed, 20 insertions(+), 6 deletions(-)

-- 
2.20.1
diff mbox series

Patch

diff --git a/tcg/ppc/tcg-target.h b/tcg/ppc/tcg-target.h
index 4a17aebc5a..be5b2901c3 100644
--- a/tcg/ppc/tcg-target.h
+++ b/tcg/ppc/tcg-target.h
@@ -163,7 +163,7 @@  extern bool have_vsx;
 #define TCG_TARGET_HAS_abs_vec          0
 #define TCG_TARGET_HAS_roti_vec         0
 #define TCG_TARGET_HAS_rots_vec         0
-#define TCG_TARGET_HAS_rotv_vec         0
+#define TCG_TARGET_HAS_rotv_vec         1
 #define TCG_TARGET_HAS_shi_vec          0
 #define TCG_TARGET_HAS_shs_vec          0
 #define TCG_TARGET_HAS_shv_vec          1
diff --git a/tcg/ppc/tcg-target.opc.h b/tcg/ppc/tcg-target.opc.h
index 1373f77e82..db514403c3 100644
--- a/tcg/ppc/tcg-target.opc.h
+++ b/tcg/ppc/tcg-target.opc.h
@@ -30,4 +30,3 @@  DEF(ppc_msum_vec, 1, 3, 0, IMPLVEC)
 DEF(ppc_muleu_vec, 1, 2, 0, IMPLVEC)
 DEF(ppc_mulou_vec, 1, 2, 0, IMPLVEC)
 DEF(ppc_pkum_vec, 1, 2, 0, IMPLVEC)
-DEF(ppc_rotl_vec, 1, 2, 0, IMPLVEC)
diff --git a/tcg/ppc/tcg-target.inc.c b/tcg/ppc/tcg-target.inc.c
index 3333b55766..3f9690418f 100644
--- a/tcg/ppc/tcg-target.inc.c
+++ b/tcg/ppc/tcg-target.inc.c
@@ -2988,6 +2988,7 @@  int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece)
     case INDEX_op_shlv_vec:
     case INDEX_op_shrv_vec:
     case INDEX_op_sarv_vec:
+    case INDEX_op_rotlv_vec:
         return vece <= MO_32 || have_isa_2_07;
     case INDEX_op_ssadd_vec:
     case INDEX_op_sssub_vec:
@@ -2998,6 +2999,7 @@  int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece)
     case INDEX_op_shli_vec:
     case INDEX_op_shri_vec:
     case INDEX_op_sari_vec:
+    case INDEX_op_rotli_vec:
         return vece <= MO_32 || have_isa_2_07 ? -1 : 0;
     case INDEX_op_neg_vec:
         return vece >= MO_32 && have_isa_3_00;
@@ -3012,6 +3014,8 @@  int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece)
         return 0;
     case INDEX_op_bitsel_vec:
         return have_vsx;
+    case INDEX_op_rotrv_vec:
+        return -1;
     default:
         return 0;
     }
@@ -3294,7 +3298,7 @@  static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
     case INDEX_op_ppc_pkum_vec:
         insn = pkum_op[vece];
         break;
-    case INDEX_op_ppc_rotl_vec:
+    case INDEX_op_rotlv_vec:
         insn = rotl_op[vece];
         break;
     case INDEX_op_ppc_msum_vec:
@@ -3401,7 +3405,7 @@  static void expand_vec_mul(TCGType type, unsigned vece, TCGv_vec v0,
         t3 = tcg_temp_new_vec(type);
         t4 = tcg_temp_new_vec(type);
         tcg_gen_dupi_vec(MO_8, t4, -16);
-        vec_gen_3(INDEX_op_ppc_rotl_vec, type, MO_32, tcgv_vec_arg(t1),
+        vec_gen_3(INDEX_op_rotlv_vec, type, MO_32, tcgv_vec_arg(t1),
                   tcgv_vec_arg(v2), tcgv_vec_arg(t4));
         vec_gen_3(INDEX_op_ppc_mulou_vec, type, MO_16, tcgv_vec_arg(t2),
                   tcgv_vec_arg(v1), tcgv_vec_arg(v2));
@@ -3426,7 +3430,7 @@  void tcg_expand_vec_op(TCGOpcode opc, TCGType type, unsigned vece,
                        TCGArg a0, ...)
 {
     va_list va;
-    TCGv_vec v0, v1, v2;
+    TCGv_vec v0, v1, v2, t0;
     TCGArg a2;
 
     va_start(va, a0);
@@ -3444,6 +3448,9 @@  void tcg_expand_vec_op(TCGOpcode opc, TCGType type, unsigned vece,
     case INDEX_op_sari_vec:
         expand_vec_shi(type, vece, v0, v1, a2, INDEX_op_sarv_vec);
         break;
+    case INDEX_op_rotli_vec:
+        expand_vec_shi(type, vece, v0, v1, a2, INDEX_op_rotlv_vec);
+        break;
     case INDEX_op_cmp_vec:
         v2 = temp_tcgv_vec(arg_temp(a2));
         expand_vec_cmp(type, vece, v0, v1, v2, va_arg(va, TCGArg));
@@ -3452,6 +3459,13 @@  void tcg_expand_vec_op(TCGOpcode opc, TCGType type, unsigned vece,
         v2 = temp_tcgv_vec(arg_temp(a2));
         expand_vec_mul(type, vece, v0, v1, v2);
         break;
+    case INDEX_op_rotlv_vec:
+        v2 = temp_tcgv_vec(arg_temp(a2));
+        t0 = tcg_temp_new_vec(type);
+        tcg_gen_neg_vec(vece, t0, v2);
+        tcg_gen_rotlv_vec(vece, v0, v1, t0);
+        tcg_temp_free_vec(t0);
+        break;
     default:
         g_assert_not_reached();
     }
@@ -3656,12 +3670,13 @@  static const TCGTargetOpDef *tcg_target_op_def(TCGOpcode op)
     case INDEX_op_shlv_vec:
     case INDEX_op_shrv_vec:
     case INDEX_op_sarv_vec:
+    case INDEX_op_rotlv_vec:
+    case INDEX_op_rotrv_vec:
     case INDEX_op_ppc_mrgh_vec:
     case INDEX_op_ppc_mrgl_vec:
     case INDEX_op_ppc_muleu_vec:
     case INDEX_op_ppc_mulou_vec:
     case INDEX_op_ppc_pkum_vec:
-    case INDEX_op_ppc_rotl_vec:
     case INDEX_op_dup2_vec:
         return &v_v_v;
     case INDEX_op_not_vec: