tcg/s390x: Implement minimal vector operations

Implementing add, sub, and, or, xor as the minimal set.
This allows us to actually enable vectors in query_s390_facilities.

Reviewed-by: David Hildenbrand <[email protected]>
Signed-off-by: Richard Henderson <[email protected]>

Author: rth7680

tcg/s390x/tcg-target.c.inc

@@ -271,6 +271,14 @@ typedef enum S390Opcode {
     VRIc_VREP   = 0xe74d,
 
     VRRa_VLR    = 0xe756,
+    VRRc_VA     = 0xe7f3,
+    VRRc_VCEQ   = 0xe7f8,   /* we leave the m5 cs field 0 */
+    VRRc_VCH    = 0xe7fb,   /* " */
+    VRRc_VCHL   = 0xe7f9,   /* " */
+    VRRc_VN     = 0xe768,
+    VRRc_VO     = 0xe76a,
+    VRRc_VS     = 0xe7f7,
+    VRRc_VX     = 0xe76d,
     VRRf_VLVGP  = 0xe762,
 
     VRSb_VLVG   = 0xe722,
@@ -607,6 +615,17 @@ static void tcg_out_insn_VRRa(TCGContext *s, S390Opcode op,
     tcg_out32(s, (op & 0x00ff) | RXB(v1, v2, 0, 0) | (m3 << 12));
 }
 
+static void tcg_out_insn_VRRc(TCGContext *s, S390Opcode op,
+                              TCGReg v1, TCGReg v2, TCGReg v3, int m4)
+{
+    tcg_debug_assert(is_vector_reg(v1));
+    tcg_debug_assert(is_vector_reg(v2));
+    tcg_debug_assert(is_vector_reg(v3));
+    tcg_out16(s, (op & 0xff00) | ((v1 & 0xf) << 4) | (v2 & 0xf));
+    tcg_out16(s, v3 << 12);
+    tcg_out16(s, (op & 0x00ff) | RXB(v1, v2, v3, 0) | (m4 << 12));
+}
+
 static void tcg_out_insn_VRRf(TCGContext *s, S390Opcode op,
                               TCGReg v1, TCGReg r2, TCGReg r3)
 {
@@ -2636,18 +2655,145 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
                            unsigned vecl, unsigned vece,
                            const TCGArg *args, const int *const_args)
 {
-    g_assert_not_reached();
+    TCGType type = vecl + TCG_TYPE_V64;
+    TCGArg a0 = args[0], a1 = args[1], a2 = args[2];
+
+    switch (opc) {
+    case INDEX_op_ld_vec:
+        tcg_out_ld(s, type, a0, a1, a2);
+        break;
+    case INDEX_op_st_vec:
+        tcg_out_st(s, type, a0, a1, a2);
+        break;
+    case INDEX_op_dupm_vec:
+        tcg_out_dupm_vec(s, type, vece, a0, a1, a2);
+        break;
+
+    case INDEX_op_add_vec:
+        tcg_out_insn(s, VRRc, VA, a0, a1, a2, vece);
+        break;
+    case INDEX_op_sub_vec:
+        tcg_out_insn(s, VRRc, VS, a0, a1, a2, vece);
+        break;
+    case INDEX_op_and_vec:
+        tcg_out_insn(s, VRRc, VN, a0, a1, a2, 0);
+        break;
+    case INDEX_op_or_vec:
+        tcg_out_insn(s, VRRc, VO, a0, a1, a2, 0);
+        break;
+    case INDEX_op_xor_vec:
+        tcg_out_insn(s, VRRc, VX, a0, a1, a2, 0);
+        break;
+
+    case INDEX_op_cmp_vec:
+        switch ((TCGCond)args[3]) {
+        case TCG_COND_EQ:
+            tcg_out_insn(s, VRRc, VCEQ, a0, a1, a2, vece);
+            break;
+        case TCG_COND_GT:
+            tcg_out_insn(s, VRRc, VCH, a0, a1, a2, vece);
+            break;
+        case TCG_COND_GTU:
+            tcg_out_insn(s, VRRc, VCHL, a0, a1, a2, vece);
+            break;
+        default:
+            g_assert_not_reached();
+        }
+        break;
+
+    case INDEX_op_mov_vec:   /* Always emitted via tcg_out_mov.  */
+    case INDEX_op_dup_vec:   /* Always emitted via tcg_out_dup_vec.  */
+    default:
+        g_assert_not_reached();
+    }
 }
 
 int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece)
 {
-    return 0;
+    switch (opc) {
+    case INDEX_op_add_vec:
+    case INDEX_op_and_vec:
+    case INDEX_op_or_vec:
+    case INDEX_op_sub_vec:
+    case INDEX_op_xor_vec:
+        return 1;
+    case INDEX_op_cmp_vec:
+        return -1;
+    default:
+        return 0;
+    }
+}
+
+static bool expand_vec_cmp_noinv(TCGType type, unsigned vece, TCGv_vec v0,
+                                 TCGv_vec v1, TCGv_vec v2, TCGCond cond)
+{
+    bool need_swap = false, need_inv = false;
+
+    switch (cond) {
+    case TCG_COND_EQ:
+    case TCG_COND_GT:
+    case TCG_COND_GTU:
+        break;
+    case TCG_COND_NE:
+    case TCG_COND_LE:
+    case TCG_COND_LEU:
+        need_inv = true;
+        break;
+    case TCG_COND_LT:
+    case TCG_COND_LTU:
+        need_swap = true;
+        break;
+    case TCG_COND_GE:
+    case TCG_COND_GEU:
+        need_swap = need_inv = true;
+        break;
+    default:
+        g_assert_not_reached();
+    }
+
+    if (need_inv) {
+        cond = tcg_invert_cond(cond);
+    }
+    if (need_swap) {
+        TCGv_vec t1;
+        t1 = v1, v1 = v2, v2 = t1;
+        cond = tcg_swap_cond(cond);
+    }
+
+    vec_gen_4(INDEX_op_cmp_vec, type, vece, tcgv_vec_arg(v0),
+              tcgv_vec_arg(v1), tcgv_vec_arg(v2), cond);
+
+    return need_inv;
+}
+
+static void expand_vec_cmp(TCGType type, unsigned vece, TCGv_vec v0,
+                           TCGv_vec v1, TCGv_vec v2, TCGCond cond)
+{
+    if (expand_vec_cmp_noinv(type, vece, v0, v1, v2, cond)) {
+        tcg_gen_not_vec(vece, v0, v0);
+    }
 }
 
 void tcg_expand_vec_op(TCGOpcode opc, TCGType type, unsigned vece,
                        TCGArg a0, ...)
 {
-    g_assert_not_reached();
+    va_list va;
+    TCGv_vec v0, v1, v2;
+
+    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)));
+
+    switch (opc) {
+    case INDEX_op_cmp_vec:
+        expand_vec_cmp(type, vece, v0, v1, v2, va_arg(va, TCGArg));
+        break;
+
+    default:
+        g_assert_not_reached();
+    }
+    va_end(va);
 }
 
 static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op)
@@ -2839,7 +2985,7 @@ static void query_s390_facilities(void)
      * There is nothing else we currently care about in the 3rd word, so
      * disable VECTOR with one store.
      */
-    if (1 || !(hwcap & HWCAP_S390_VXRS)) {
+    if (!(hwcap & HWCAP_S390_VXRS)) {
         s390_facilities[2] = 0;
     }
 }