target/ppc: Implement xxblendvb/xxblendvh/xxblendvw/xxblendvd instructions

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Bruno Larsen (billionai) <bruno.larsen@eldorado.org.br>
Signed-off-by: Matheus Ferst <matheus.ferst@eldorado.org.br>
Message-Id: <20211104123719.323713-24-matheus.ferst@eldorado.org.br>
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>

target/ppc/helper.h

@@ -520,6 +520,10 @@ DEF_HELPER_4(xxpermr, void, env, vsr, vsr, vsr)
 DEF_HELPER_4(xxextractuw, void, env, vsr, vsr, i32)
 DEF_HELPER_4(xxinsertw, void, env, vsr, vsr, i32)
 DEF_HELPER_3(xvxsigsp, void, env, vsr, vsr)
+DEF_HELPER_5(XXBLENDVB, void, vsr, vsr, vsr, vsr, i32)
+DEF_HELPER_5(XXBLENDVH, void, vsr, vsr, vsr, vsr, i32)
+DEF_HELPER_5(XXBLENDVW, void, vsr, vsr, vsr, vsr, i32)
+DEF_HELPER_5(XXBLENDVD, void, vsr, vsr, vsr, vsr, i32)
 
 DEF_HELPER_2(efscfsi, i32, env, i32)
 DEF_HELPER_2(efscfui, i32, env, i32)

target/ppc/insn64.decode

@@ -44,6 +44,16 @@
                 ...... ..... ....  . ................ \
                 &8RR_D si=%8rr_si xt=%8rr_xt
 
+# Format XX4
+&XX4            xt xa xb xc
+%xx4_xt         0:1 21:5
+%xx4_xa         2:1 16:5
+%xx4_xb         1:1 11:5
+%xx4_xc         3:1  6:5
+@XX4            ........ ........ ........ ........ \
+                ...... ..... ..... ..... ..... .. .... \
+                &XX4 xt=%xx4_xt xa=%xx4_xa xb=%xx4_xb xc=%xx4_xc
+
 ### Fixed-Point Load Instructions
 
 PLBZ            000001 10 0--.-- .................. \
@@ -175,3 +185,12 @@ XXSPLTIW        000001 01 0000 -- -- ................ \
                 100000 ..... 0011 . ................    @8RR_D
 XXSPLTI32DX     000001 01 0000 -- -- ................ \
                 100000 ..... 000 .. ................    @8RR_D_IX
+
+XXBLENDVD       000001 01 0000 -- ------------------ \
+                100001 ..... ..... ..... ..... 11 ....  @XX4
+XXBLENDVW       000001 01 0000 -- ------------------ \
+                100001 ..... ..... ..... ..... 10 ....  @XX4
+XXBLENDVH       000001 01 0000 -- ------------------ \
+                100001 ..... ..... ..... ..... 01 ....  @XX4
+XXBLENDVB       000001 01 0000 -- ------------------ \
+                100001 ..... ..... ..... ..... 00 ....  @XX4

target/ppc/int_helper.c

@@ -1737,6 +1737,21 @@ void helper_xxinsertw(CPUPPCState *env, ppc_vsr_t *xt,
     *xt = t;
 }
 
+#define XXBLEND(name, sz) \
+void glue(helper_XXBLENDV, name)(ppc_avr_t *t, ppc_avr_t *a, ppc_avr_t *b,  \
+                                 ppc_avr_t *c, uint32_t desc)               \
+{                                                                           \
+    for (int i = 0; i < ARRAY_SIZE(t->glue(u, sz)); i++) {                  \
+        t->glue(u, sz)[i] = (c->glue(s, sz)[i] >> (sz - 1)) ?               \
+            b->glue(u, sz)[i] : a->glue(u, sz)[i];                          \
+    }                                                                       \
+}
+XXBLEND(B, 8)
+XXBLEND(H, 16)
+XXBLEND(W, 32)
+XXBLEND(D, 64)
+#undef XXBLEND
+
 #define VEXT_SIGNED(name, element, cast)                            \
 void helper_##name(ppc_avr_t *r, ppc_avr_t *b)                      \
 {                                                                   \

target/ppc/translate/vsx-impl.c.inc

@@ -2087,6 +2087,61 @@ TRANS64(PLXV, do_lstxv_PLS_D, false, false)
 TRANS64(PSTXVP, do_lstxv_PLS_D, true, true)
 TRANS64(PLXVP, do_lstxv_PLS_D, false, true)
 
+static void gen_xxblendv_vec(unsigned vece, TCGv_vec t, TCGv_vec a, TCGv_vec b,
+                             TCGv_vec c)
+{
+    TCGv_vec tmp = tcg_temp_new_vec_matching(c);
+    tcg_gen_sari_vec(vece, tmp, c, (8 << vece) - 1);
+    tcg_gen_bitsel_vec(vece, t, tmp, b, a);
+    tcg_temp_free_vec(tmp);
+}
+
+static bool do_xxblendv(DisasContext *ctx, arg_XX4 *a, unsigned vece)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_sari_vec, 0
+    };
+    static const GVecGen4 ops[4] = {
+        {
+            .fniv = gen_xxblendv_vec,
+            .fno = gen_helper_XXBLENDVB,
+            .opt_opc = vecop_list,
+            .vece = MO_8
+        },
+        {
+            .fniv = gen_xxblendv_vec,
+            .fno = gen_helper_XXBLENDVH,
+            .opt_opc = vecop_list,
+            .vece = MO_16
+        },
+        {
+            .fniv = gen_xxblendv_vec,
+            .fno = gen_helper_XXBLENDVW,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fniv = gen_xxblendv_vec,
+            .fno = gen_helper_XXBLENDVD,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        }
+    };
+
+    REQUIRE_VSX(ctx);
+
+    tcg_gen_gvec_4(vsr_full_offset(a->xt), vsr_full_offset(a->xa),
+                   vsr_full_offset(a->xb), vsr_full_offset(a->xc),
+                   16, 16, &ops[vece]);
+
+    return true;
+}
+
+TRANS(XXBLENDVB, do_xxblendv, MO_8)
+TRANS(XXBLENDVH, do_xxblendv, MO_16)
+TRANS(XXBLENDVW, do_xxblendv, MO_32)
+TRANS(XXBLENDVD, do_xxblendv, MO_64)
+
 #undef GEN_XX2FORM
 #undef GEN_XX3FORM
 #undef GEN_XX2IFORM