target/ppc: Move VPRTYB[WDQ] to decodetree and use gvec

Moved VPRTYBW and VPRTYBD to use gvec and both of them and VPRTYBQ to
decodetree. VPRTYBW and VPRTYBD now also use .fni4 and .fni8,
respectively.

vprtybw:
rept    loop    master             patch
8       12500   0,01198900         0,00703100 (-41.4%)
25      4000    0,01070100         0,00571400 (-46.6%)
100     1000    0,01123300         0,00678200 (-39.6%)
500     200     0,01601500         0,01535600 (-4.1%)
2500    40      0,03872900         0,05562100 (43.6%)
8000    12      0,10047000         0,16643000 (65.7%)

vprtybd:
rept    loop    master             patch
8       12500   0,00757700         0,00788100 (4.0%)
25      4000    0,00652500         0,00669600 (2.6%)
100     1000    0,00714400         0,00825400 (15.5%)
500     200     0,01211000         0,01903700 (57.2%)
2500    40      0,03483800         0,07021200 (101.5%)
8000    12      0,09591800         0,21036200 (119.3%)

vprtybq:
rept    loop    master             patch
8       12500   0,00675600         0,00667200 (-1.2%)
25      4000    0,00619400         0,00643200 (3.8%)
100     1000    0,00707100         0,00751100 (6.2%)
500     200     0,01199300         0,01342000 (11.9%)
2500    40      0,03490900         0,04092900 (17.2%)
8000    12      0,09588200         0,11465100 (19.6%)

I wasn't expecting such a performance lost in both VPRTYBD and VPRTYBQ,
I'm not sure if it's worth to move those instructions. Comparing the
assembly of the helper with the TCGop they are pretty similar, so
I'm not sure why vprtybd took so much more time.

Signed-off-by: Lucas Mateus Castro (alqotel) <lucas.araujo@eldorado.org.br>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20221019125040.48028-6-lucas.araujo@eldorado.org.br>
Signed-off-by: Daniel Henrique Barboza <danielhb413@gmail.com>

1 files changed, 65 insertions, 3 deletions

diff --git a/target/ppc/translate/vmx-impl.c.inc b/target/ppc/translate/vmx-impl.c.inc
index b9a9e83..cbb2a3e 100644
--- a/target/ppc/translate/vmx-impl.c.inc
+++ b/target/ppc/translate/vmx-impl.c.inc
@@ -1659,9 +1659,71 @@ GEN_VXFORM_NOA_ENV(vrfim, 5, 11);
 GEN_VXFORM_NOA_ENV(vrfin, 5, 8);
 GEN_VXFORM_NOA_ENV(vrfip, 5, 10);
 GEN_VXFORM_NOA_ENV(vrfiz, 5, 9);
-GEN_VXFORM_NOA(vprtybw, 1, 24);
-GEN_VXFORM_NOA(vprtybd, 1, 24);
-GEN_VXFORM_NOA(vprtybq, 1, 24);
+
+static void gen_vprtyb_vec(unsigned vece, TCGv_vec t, TCGv_vec b)
+{
+    int i;
+    TCGv_vec tmp = tcg_temp_new_vec_matching(b);
+    /* MO_32 is 2, so 2 iteractions for MO_32 and 3 for MO_64 */
+    for (i = 0; i < vece; i++) {
+        tcg_gen_shri_vec(vece, tmp, b, (4 << (vece - i)));
+        tcg_gen_xor_vec(vece, b, tmp, b);
+    }
+    tcg_gen_and_vec(vece, t, b, tcg_constant_vec_matching(t, vece, 1));
+    tcg_temp_free_vec(tmp);
+}
+
+/* vprtybw */
+static void gen_vprtyb_i32(TCGv_i32 t, TCGv_i32 b)
+{
+    tcg_gen_ctpop_i32(t, b);
+    tcg_gen_and_i32(t, t, tcg_constant_i32(1));
+}
+
+/* vprtybd */
+static void gen_vprtyb_i64(TCGv_i64 t, TCGv_i64 b)
+{
+    tcg_gen_ctpop_i64(t, b);
+    tcg_gen_and_i64(t, t, tcg_constant_i64(1));
+}
+
+static bool do_vx_vprtyb(DisasContext *ctx, arg_VX_tb *a, unsigned vece)
+{
+    static const TCGOpcode vecop_list[] = {
+        INDEX_op_shri_vec, 0
+    };
+
+    static const GVecGen2 op[] = {
+        {
+            .fniv = gen_vprtyb_vec,
+            .fni4 = gen_vprtyb_i32,
+            .opt_opc = vecop_list,
+            .vece = MO_32
+        },
+        {
+            .fniv = gen_vprtyb_vec,
+            .fni8 = gen_vprtyb_i64,
+            .opt_opc = vecop_list,
+            .vece = MO_64
+        },
+        {
+            .fno = gen_helper_VPRTYBQ,
+            .vece = MO_128
+        },
+    };
+
+    REQUIRE_INSNS_FLAGS2(ctx, ISA300);
+    REQUIRE_VECTOR(ctx);
+
+    tcg_gen_gvec_2(avr_full_offset(a->vrt), avr_full_offset(a->vrb),
+                   16, 16, &op[vece - MO_32]);
+
+    return true;
+}
+
+TRANS(VPRTYBW, do_vx_vprtyb, MO_32)
+TRANS(VPRTYBD, do_vx_vprtyb, MO_64)
+TRANS(VPRTYBQ, do_vx_vprtyb, MO_128)
 
 static void gen_vsplt(DisasContext *ctx, int vece)
 {