tcg/s390x: Implement ctpop operation

There is an older form that produces per-byte results,
and a newer form that produces per-register results.

Reviewed-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

tcg/s390x/tcg-target.c.inc

@@ -206,6 +206,7 @@ typedef enum S390Opcode {
 
     RRFc_LOCR   = 0xb9f2,
     RRFc_LOCGR  = 0xb9e2,
+    RRFc_POPCNT = 0xb9e1,
 
     RR_AR       = 0x1a,
     RR_ALR      = 0x1e,
@@ -1435,6 +1436,32 @@ static void tgen_clz(TCGContext *s, TCGReg dest, TCGReg a1,
     tgen_movcond_int(s, TCG_TYPE_I64, dest, a2, a2const, TCG_REG_R0, 8, 2);
 }
 
+static void tgen_ctpop(TCGContext *s, TCGType type, TCGReg dest, TCGReg src)
+{
+    /* With MIE3, and bit 0 of m4 set, we get the complete result. */
+    if (HAVE_FACILITY(MISC_INSN_EXT3)) {
+        if (type == TCG_TYPE_I32) {
+            tgen_ext32u(s, dest, src);
+            src = dest;
+        }
+        tcg_out_insn(s, RRFc, POPCNT, dest, src, 8);
+        return;
+    }
+
+    /* Without MIE3, each byte gets the count of bits for the byte. */
+    tcg_out_insn(s, RRFc, POPCNT, dest, src, 0);
+
+    /* Multiply to sum each byte at the top of the word. */
+    if (type == TCG_TYPE_I32) {
+        tcg_out_insn(s, RIL, MSFI, dest, 0x01010101);
+        tcg_out_sh32(s, RS_SRL, dest, TCG_REG_NONE, 24);
+    } else {
+        tcg_out_movi(s, TCG_TYPE_I64, TCG_TMP0, 0x0101010101010101ull);
+        tcg_out_insn(s, RRE, MSGR, dest, TCG_TMP0);
+        tcg_out_sh64(s, RSY_SRLG, dest, dest, TCG_REG_NONE, 56);
+    }
+}
+
 static void tgen_deposit(TCGContext *s, TCGReg dest, TCGReg src,
                          int ofs, int len, int z)
 {
@@ -2584,6 +2611,13 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
         tgen_clz(s, args[0], args[1], args[2], const_args[2]);
         break;
 
+    case INDEX_op_ctpop_i32:
+        tgen_ctpop(s, TCG_TYPE_I32, args[0], args[1]);
+        break;
+    case INDEX_op_ctpop_i64:
+        tgen_ctpop(s, TCG_TYPE_I64, args[0], args[1]);
+        break;
+
     case INDEX_op_mb:
         /* The host memory model is quite strong, we simply need to
            serialize the instruction stream.  */
@@ -3146,6 +3180,8 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op)
     case INDEX_op_extu_i32_i64:
     case INDEX_op_extract_i32:
     case INDEX_op_extract_i64:
+    case INDEX_op_ctpop_i32:
+    case INDEX_op_ctpop_i64:
         return C_O1_I1(r, r);
 
     case INDEX_op_qemu_ld_i32:

tcg/s390x/tcg-target.h

@@ -91,7 +91,7 @@ extern uint64_t s390_facilities[3];
 #define TCG_TARGET_HAS_nor_i32        HAVE_FACILITY(MISC_INSN_EXT3)
 #define TCG_TARGET_HAS_clz_i32        0
 #define TCG_TARGET_HAS_ctz_i32        0
-#define TCG_TARGET_HAS_ctpop_i32      0
+#define TCG_TARGET_HAS_ctpop_i32      1
 #define TCG_TARGET_HAS_deposit_i32    1
 #define TCG_TARGET_HAS_extract_i32    1
 #define TCG_TARGET_HAS_sextract_i32   0
@@ -128,7 +128,7 @@ extern uint64_t s390_facilities[3];
 #define TCG_TARGET_HAS_nor_i64        HAVE_FACILITY(MISC_INSN_EXT3)
 #define TCG_TARGET_HAS_clz_i64        1
 #define TCG_TARGET_HAS_ctz_i64        0
-#define TCG_TARGET_HAS_ctpop_i64      0
+#define TCG_TARGET_HAS_ctpop_i64      1
 #define TCG_TARGET_HAS_deposit_i64    1
 #define TCG_TARGET_HAS_extract_i64    1
 #define TCG_TARGET_HAS_sextract_i64   0