[Qemu-devel] [PATCH 17/25] tcg/ppc: Handle ctz and clz opcodes

[Richard Henderson]

Cc: address@hidden
Signed-off-by: Richard Henderson <address@hidden>
---
 tcg/ppc/tcg-target.h     |  8 +++----
 tcg/ppc/tcg-target.inc.c | 57 ++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 61 insertions(+), 4 deletions(-)

diff --git a/tcg/ppc/tcg-target.h b/tcg/ppc/tcg-target.h
index 698a599..442be63 100644
--- a/tcg/ppc/tcg-target.h
+++ b/tcg/ppc/tcg-target.h
@@ -68,8 +68,8 @@ typedef enum {
 #define TCG_TARGET_HAS_eqv_i32          1
 #define TCG_TARGET_HAS_nand_i32         1
 #define TCG_TARGET_HAS_nor_i32          1
-#define TCG_TARGET_HAS_clz_i32          0
-#define TCG_TARGET_HAS_ctz_i32          0
+#define TCG_TARGET_HAS_clz_i32          1
+#define TCG_TARGET_HAS_ctz_i32          1
 #define TCG_TARGET_HAS_deposit_i32      1
 #define TCG_TARGET_HAS_extract_i32      1
 #define TCG_TARGET_HAS_sextract_i32     0
@@ -103,8 +103,8 @@ typedef enum {
 #define TCG_TARGET_HAS_eqv_i64          1
 #define TCG_TARGET_HAS_nand_i64         1
 #define TCG_TARGET_HAS_nor_i64          1
-#define TCG_TARGET_HAS_clz_i64          0
-#define TCG_TARGET_HAS_ctz_i64          0
+#define TCG_TARGET_HAS_clz_i64          1
+#define TCG_TARGET_HAS_ctz_i64          1
 #define TCG_TARGET_HAS_deposit_i64      1
 #define TCG_TARGET_HAS_extract_i64      1
 #define TCG_TARGET_HAS_sextract_i64     0
diff --git a/tcg/ppc/tcg-target.inc.c b/tcg/ppc/tcg-target.inc.c
index 7ec54a2..bf147af 100644
--- a/tcg/ppc/tcg-target.inc.c
+++ b/tcg/ppc/tcg-target.inc.c
@@ -77,6 +77,7 @@
 #define TCG_CT_CONST_U32  0x800
 #define TCG_CT_CONST_ZERO 0x1000
 #define TCG_CT_CONST_MONE 0x2000
+#define TCG_CT_CONST_WSZ  0x4000
 
 static tcg_insn_unit *tb_ret_addr;
 
@@ -307,6 +308,9 @@ static int target_parse_constraint(TCGArgConstraint *ct, 
const char **pct_str)
     case 'U':
         ct->ct |= TCG_CT_CONST_U32;
         break;
+    case 'W':
+        ct->ct |= TCG_CT_CONST_WSZ;
+        break;
     case 'Z':
         ct->ct |= TCG_CT_CONST_ZERO;
         break;
@@ -345,6 +349,9 @@ static int tcg_target_const_match(tcg_target_long val, 
TCGType type,
         return 1;
     } else if ((ct & TCG_CT_CONST_MONE) && val == -1) {
         return 1;
+    } else if ((ct & TCG_CT_CONST_WSZ)
+               && val == (type == TCG_TYPE_I32 ? 32 : 64)) {
+        return 1;
     }
     return 0;
 }
@@ -449,6 +456,8 @@ static int tcg_target_const_match(tcg_target_long val, 
TCGType type,
 #define NOR    XO31(124)
 #define CNTLZW XO31( 26)
 #define CNTLZD XO31( 58)
+#define CNTTZW XO31(538)
+#define CNTTZD XO31(570)
 #define ANDC   XO31( 60)
 #define ORC    XO31(412)
 #define EQV    XO31(284)
@@ -1170,6 +1179,32 @@ static void tcg_out_movcond(TCGContext *s, TCGType type, 
TCGCond cond,
     }
 }
 
+static void tcg_out_cntxz(TCGContext *s, TCGType type, uint32_t opc,
+                          TCGArg a0, TCGArg a1, TCGArg a2, bool const_a2)
+{
+    if (const_a2 && a2 == (type == TCG_TYPE_I32 ? 32 : 64)) {
+        tcg_out32(s, opc | RA(a0) | RS(a1));
+    } else {
+        tcg_out_cmp(s, TCG_COND_EQ, a1, 0, 1, 7, type);
+        /* Note that the only other valid constant for a2 is 0.  */
+        if (HAVE_ISEL) {
+            tcg_out32(s, opc | RA(TCG_REG_R0) | RS(a1));
+            tcg_out32(s, tcg_to_isel[TCG_COND_EQ] | TAB(a0, a2, TCG_REG_R0));
+        } else if (!const_a2 && a0 == a2) {
+            tcg_out32(s, tcg_to_bc[TCG_COND_EQ] | 8);
+            tcg_out32(s, opc | RA(a0) | RS(a1));
+        } else {
+            tcg_out32(s, opc | RA(a0) | RS(a1));
+            tcg_out32(s, tcg_to_bc[TCG_COND_NE] | 8);
+            if (const_a2) {
+                tcg_out_movi(s, type, a0, 0);
+            } else {
+                tcg_out_mov(s, type, a0, a2);
+            }
+        }
+    }
+}
+
 static void tcg_out_cmp2(TCGContext *s, const TCGArg *args,
                          const int *const_args)
 {
@@ -2107,6 +2142,24 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc, 
const TCGArg *args,
         tcg_out32(s, NOR | SAB(args[1], args[0], args[2]));
         break;
 
+    case INDEX_op_clz_i32:
+        tcg_out_cntxz(s, TCG_TYPE_I32, CNTLZW, args[0], args[1],
+                      args[2], const_args[2]);
+        break;
+    case INDEX_op_ctz_i32:
+        tcg_out_cntxz(s, TCG_TYPE_I32, CNTTZW, args[0], args[1],
+                      args[2], const_args[2]);
+        break;
+
+    case INDEX_op_clz_i64:
+        tcg_out_cntxz(s, TCG_TYPE_I64, CNTLZD, args[0], args[1],
+                      args[2], const_args[2]);
+        break;
+    case INDEX_op_ctz_i64:
+        tcg_out_cntxz(s, TCG_TYPE_I64, CNTTZD, args[0], args[1],
+                      args[2], const_args[2]);
+        break;
+
     case INDEX_op_mul_i32:
         a0 = args[0], a1 = args[1], a2 = args[2];
         if (const_args[2]) {
@@ -2519,6 +2572,8 @@ static const TCGTargetOpDef ppc_op_defs[] = {
     { INDEX_op_eqv_i32, { "r", "r", "ri" } },
     { INDEX_op_nand_i32, { "r", "r", "r" } },
     { INDEX_op_nor_i32, { "r", "r", "r" } },
+    { INDEX_op_clz_i32, { "r", "r", "rZW" } },
+    { INDEX_op_ctz_i32, { "r", "r", "rZW" } },
 
     { INDEX_op_shl_i32, { "r", "r", "ri" } },
     { INDEX_op_shr_i32, { "r", "r", "ri" } },
@@ -2567,6 +2622,8 @@ static const TCGTargetOpDef ppc_op_defs[] = {
     { INDEX_op_eqv_i64, { "r", "r", "r" } },
     { INDEX_op_nand_i64, { "r", "r", "r" } },
     { INDEX_op_nor_i64, { "r", "r", "r" } },
+    { INDEX_op_clz_i64, { "r", "r", "rZW" } },
+    { INDEX_op_ctz_i64, { "r", "r", "rZW" } },
 
     { INDEX_op_shl_i64, { "r", "r", "ri" } },
     { INDEX_op_shr_i64, { "r", "r", "ri" } },
-- 
2.7.4