tcg/ppc: Support vector shift by immediate

For Altivec, this is done via vector shift by vector,
and loading the immediate into a register.

Tested-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk>
Reviewed-by: Aleksandar Markovic <amarkovic@wavecomp.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Aleksandar Markovic <amarkovic@wavecomp.com>

2 files changed, 57 insertions, 3 deletions

diff --git a/tcg/ppc/tcg-target.h b/tcg/ppc/tcg-target.h
index 3ebbbfa..ffb2269 100644
--- a/tcg/ppc/tcg-target.h
+++ b/tcg/ppc/tcg-target.h
@@ -160,7 +160,7 @@ extern bool have_altivec;
 #define TCG_TARGET_HAS_abs_vec          0
 #define TCG_TARGET_HAS_shi_vec          0
 #define TCG_TARGET_HAS_shs_vec          0
-#define TCG_TARGET_HAS_shv_vec          0
+#define TCG_TARGET_HAS_shv_vec          1
 #define TCG_TARGET_HAS_cmp_vec          1
 #define TCG_TARGET_HAS_mul_vec          0
 #define TCG_TARGET_HAS_sat_vec          1
diff --git a/tcg/ppc/tcg-target.inc.c b/tcg/ppc/tcg-target.inc.c
index a116520..a9264ec 100644
--- a/tcg/ppc/tcg-target.inc.c
+++ b/tcg/ppc/tcg-target.inc.c
@@ -514,6 +514,16 @@ static int tcg_target_const_match(tcg_target_long val, TCGType type,
 #define VCMPGTUH   VX4(582)
 #define VCMPGTUW   VX4(646)
 
+#define VSLB       VX4(260)
+#define VSLH       VX4(324)
+#define VSLW       VX4(388)
+#define VSRB       VX4(516)
+#define VSRH       VX4(580)
+#define VSRW       VX4(644)
+#define VSRAB      VX4(772)
+#define VSRAH      VX4(836)
+#define VSRAW      VX4(900)
+
 #define VAND       VX4(1028)
 #define VANDC      VX4(1092)
 #define VNOR       VX4(1284)
@@ -2860,8 +2870,14 @@ int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece)
     case INDEX_op_sssub_vec:
     case INDEX_op_usadd_vec:
     case INDEX_op_ussub_vec:
+    case INDEX_op_shlv_vec:
+    case INDEX_op_shrv_vec:
+    case INDEX_op_sarv_vec:
         return vece <= MO_32;
     case INDEX_op_cmp_vec:
+    case INDEX_op_shli_vec:
+    case INDEX_op_shri_vec:
+    case INDEX_op_sari_vec:
         return vece <= MO_32 ? -1 : 0;
     default:
         return 0;
@@ -2968,7 +2984,10 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
         umin_op[4] = { VMINUB, VMINUH, VMINUW, 0 },
         smin_op[4] = { VMINSB, VMINSH, VMINSW, 0 },
         umax_op[4] = { VMAXUB, VMAXUH, VMAXUW, 0 },
-        smax_op[4] = { VMAXSB, VMAXSH, VMAXSW, 0 };
+        smax_op[4] = { VMAXSB, VMAXSH, VMAXSW, 0 },
+        shlv_op[4] = { VSLB, VSLH, VSLW, 0 },
+        shrv_op[4] = { VSRB, VSRH, VSRW, 0 },
+        sarv_op[4] = { VSRAB, VSRAH, VSRAW, 0 };
 
     TCGType type = vecl + TCG_TYPE_V64;
     TCGArg a0 = args[0], a1 = args[1], a2 = args[2];
@@ -3015,6 +3034,15 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
     case INDEX_op_umax_vec:
         insn = umax_op[vece];
         break;
+    case INDEX_op_shlv_vec:
+        insn = shlv_op[vece];
+        break;
+    case INDEX_op_shrv_vec:
+        insn = shrv_op[vece];
+        break;
+    case INDEX_op_sarv_vec:
+        insn = sarv_op[vece];
+        break;
     case INDEX_op_and_vec:
         insn = VAND;
         break;
@@ -3059,6 +3087,18 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
     tcg_out32(s, insn | VRT(a0) | VRA(a1) | VRB(a2));
 }
 
+static void expand_vec_shi(TCGType type, unsigned vece, TCGv_vec v0,
+                           TCGv_vec v1, TCGArg imm, TCGOpcode opci)
+{
+    TCGv_vec t1 = tcg_temp_new_vec(type);
+
+    /* Splat w/bytes for xxspltib.  */
+    tcg_gen_dupi_vec(MO_8, t1, imm & ((8 << vece) - 1));
+    vec_gen_3(opci, type, vece, tcgv_vec_arg(v0),
+              tcgv_vec_arg(v1), tcgv_vec_arg(t1));
+    tcg_temp_free_vec(t1);
+}
+
 static void expand_vec_cmp(TCGType type, unsigned vece, TCGv_vec v0,
                            TCGv_vec v1, TCGv_vec v2, TCGCond cond)
 {
@@ -3110,14 +3150,25 @@ void tcg_expand_vec_op(TCGOpcode opc, TCGType type, unsigned vece,
 {
     va_list va;
     TCGv_vec v0, v1, v2;
+    TCGArg a2;
 
     va_start(va, a0);
     v0 = temp_tcgv_vec(arg_temp(a0));
     v1 = temp_tcgv_vec(arg_temp(va_arg(va, TCGArg)));
-    v2 = temp_tcgv_vec(arg_temp(va_arg(va, TCGArg)));
+    a2 = va_arg(va, TCGArg);
 
     switch (opc) {
+    case INDEX_op_shli_vec:
+        expand_vec_shi(type, vece, v0, v1, a2, INDEX_op_shlv_vec);
+        break;
+    case INDEX_op_shri_vec:
+        expand_vec_shi(type, vece, v0, v1, a2, INDEX_op_shrv_vec);
+        break;
+    case INDEX_op_sari_vec:
+        expand_vec_shi(type, vece, v0, v1, a2, INDEX_op_sarv_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));
         break;
     default:
@@ -3317,6 +3368,9 @@ static const TCGTargetOpDef *tcg_target_op_def(TCGOpcode op)
     case INDEX_op_smin_vec:
     case INDEX_op_umax_vec:
     case INDEX_op_umin_vec:
+    case INDEX_op_shlv_vec:
+    case INDEX_op_shrv_vec:
+    case INDEX_op_sarv_vec:
         return &v_v_v;
     case INDEX_op_not_vec:
     case INDEX_op_dup_vec: