target/ppc: implement vcntmb[bhwd]

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Matheus Ferst <matheus.ferst@eldorado.org.br>
Message-Id: <20220225210936.1749575-18-matheus.ferst@eldorado.org.br>
Signed-off-by: Cédric Le Goater <clg@kaod.org>

diff --git a/target/ppc/insn32.decode b/target/ppc/insn32.decode
index b20f1eaa8e9c5056f987926790cafcb007549e7d..31a3c3b5084ccc848b6baf7d7d68c4ef9f4d21de 100644 (file)
--- a/target/ppc/insn32.decode
+++ b/target/ppc/insn32.decode
@@ -63,6 +63,9 @@
 &VX_bf          bf vra vrb
 @VX_bf          ...... bf:3 .. vra:5 vrb:5 ...........          &VX_bf
 
+&VX_mp          rt mp:bool vrb
+@VX_mp          ...... rt:5 .... mp:1 vrb:5 ...........         &VX_mp
+
 &VX_tb_rc       vrt vrb rc:bool
 @VX_tb_rc       ...... vrt:5 ..... vrb:5 rc:1 ..........        &VX_tb_rc
 
@@ -489,6 +492,11 @@ VEXTRACTWM      000100 ..... 01010 ..... 11001000010    @VX_tb
 VEXTRACTDM      000100 ..... 01011 ..... 11001000010    @VX_tb
 VEXTRACTQM      000100 ..... 01100 ..... 11001000010    @VX_tb
 
+VCNTMBB         000100 ..... 1100 . ..... 11001000010   @VX_mp
+VCNTMBH         000100 ..... 1101 . ..... 11001000010   @VX_mp
+VCNTMBW         000100 ..... 1110 . ..... 11001000010   @VX_mp
+VCNTMBD         000100 ..... 1111 . ..... 11001000010   @VX_mp
+
 ## Vector Multiply Instruction
 
 VMULESB         000100 ..... ..... ..... 01100001000    @VX

diff --git a/target/ppc/translate/vmx-impl.c.inc b/target/ppc/translate/vmx-impl.c.inc
index 4db5656669c7e85c40e19316119f034bd78e4f1d..e45bd194f430090c9f58085d34547c8d2f2b3db4 100644 (file)
--- a/target/ppc/translate/vmx-impl.c.inc
+++ b/target/ppc/translate/vmx-impl.c.inc
@@ -1910,6 +1910,38 @@ static bool trans_MTVSRBMI(DisasContext *ctx, arg_DX_b *a)
     return true;
 }
 
+static bool do_vcntmb(DisasContext *ctx, arg_VX_mp *a, int vece)
+{
+    TCGv_i64 rt, vrb, mask;
+    rt = tcg_const_i64(0);
+    vrb = tcg_temp_new_i64();
+    mask = tcg_constant_i64(dup_const(vece, 1ULL << ((8 << vece) - 1)));
+
+    for (int i = 0; i < 2; i++) {
+        get_avr64(vrb, a->vrb, i);
+        if (a->mp) {
+            tcg_gen_and_i64(vrb, mask, vrb);
+        } else {
+            tcg_gen_andc_i64(vrb, mask, vrb);
+        }
+        tcg_gen_ctpop_i64(vrb, vrb);
+        tcg_gen_add_i64(rt, rt, vrb);
+    }
+
+    tcg_gen_shli_i64(rt, rt, TARGET_LONG_BITS - 8 + vece);
+    tcg_gen_trunc_i64_tl(cpu_gpr[a->rt], rt);
+
+    tcg_temp_free_i64(vrb);
+    tcg_temp_free_i64(rt);
+
+    return true;
+}
+
+TRANS(VCNTMBB, do_vcntmb, MO_8)
+TRANS(VCNTMBH, do_vcntmb, MO_16)
+TRANS(VCNTMBW, do_vcntmb, MO_32)
+TRANS(VCNTMBD, do_vcntmb, MO_64)
+
 static bool do_vstri(DisasContext *ctx, arg_VX_tb_rc *a,
                      void (*gen_helper)(TCGv_i32, TCGv_ptr, TCGv_ptr))
 {