[PULL 15/31] tcg/loongarch64: Implement clz/ctz ops

[Richard Henderson <richard.henderson@linaro.org>]

From: WANG Xuerui <git@xen0n.name>

Signed-off-by: WANG Xuerui <git@xen0n.name>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20211221054105.178795-16-git@xen0n.name>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 tcg/loongarch64/tcg-target-con-set.h |  1 +
 tcg/loongarch64/tcg-target.h         |  8 +++---
 tcg/loongarch64/tcg-target.c.inc     | 42 ++++++++++++++++++++++++++++
 3 files changed, 47 insertions(+), 4 deletions(-)

diff --git a/tcg/loongarch64/tcg-target-con-set.h b/tcg/loongarch64/tcg-target-con-set.h
index d958183020..2975e03127 100644
--- a/tcg/loongarch64/tcg-target-con-set.h
+++ b/tcg/loongarch64/tcg-target-con-set.h
@@ -18,4 +18,5 @@ C_O0_I1(r)
 C_O1_I1(r, r)
 C_O1_I2(r, r, rC)
 C_O1_I2(r, r, rU)
+C_O1_I2(r, r, rW)
 C_O1_I2(r, 0, rZ)
diff --git a/tcg/loongarch64/tcg-target.h b/tcg/loongarch64/tcg-target.h
index 5303001653..2fd2745b63 100644
--- a/tcg/loongarch64/tcg-target.h
+++ b/tcg/loongarch64/tcg-target.h
@@ -120,8 +120,8 @@ typedef enum {
 #define TCG_TARGET_HAS_eqv_i32          0
 #define TCG_TARGET_HAS_nand_i32         0
 #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_ctpop_i32        0
 #define TCG_TARGET_HAS_direct_jump      0
 #define TCG_TARGET_HAS_brcond2          0
@@ -156,8 +156,8 @@ typedef enum {
 #define TCG_TARGET_HAS_eqv_i64          0
 #define TCG_TARGET_HAS_nand_i64         0
 #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_ctpop_i64        0
 #define TCG_TARGET_HAS_add2_i64         0
 #define TCG_TARGET_HAS_sub2_i64         0
diff --git a/tcg/loongarch64/tcg-target.c.inc b/tcg/loongarch64/tcg-target.c.inc
index 3b056dd358..39df2885b5 100644
--- a/tcg/loongarch64/tcg-target.c.inc
+++ b/tcg/loongarch64/tcg-target.c.inc
@@ -412,6 +412,28 @@ static void tcg_out_ext32s(TCGContext *s, TCGReg ret, TCGReg arg)
     tcg_out_opc_addi_w(s, ret, arg, 0);
 }
 
+static void tcg_out_clzctz(TCGContext *s, LoongArchInsn opc,
+                           TCGReg a0, TCGReg a1, TCGReg a2,
+                           bool c2, bool is_32bit)
+{
+    if (c2) {
+        /*
+         * Fast path: semantics already satisfied due to constraint and
+         * insn behavior, single instruction is enough.
+         */
+        tcg_debug_assert(a2 == (is_32bit ? 32 : 64));
+        /* all clz/ctz insns belong to DJ-format */
+        tcg_out32(s, encode_dj_insn(opc, a0, a1));
+        return;
+    }
+
+    tcg_out32(s, encode_dj_insn(opc, TCG_REG_TMP0, a1));
+    /* a0 = a1 ? REG_TMP0 : a2 */
+    tcg_out_opc_maskeqz(s, TCG_REG_TMP0, TCG_REG_TMP0, a1);
+    tcg_out_opc_masknez(s, a0, a2, a1);
+    tcg_out_opc_or(s, a0, TCG_REG_TMP0, a0);
+}
+
 /*
  * Entry-points
  */
@@ -572,6 +594,20 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc,
         tcg_out_opc_revb_d(s, a0, a1);
         break;
 
+    case INDEX_op_clz_i32:
+        tcg_out_clzctz(s, OPC_CLZ_W, a0, a1, a2, c2, true);
+        break;
+    case INDEX_op_clz_i64:
+        tcg_out_clzctz(s, OPC_CLZ_D, a0, a1, a2, c2, false);
+        break;
+
+    case INDEX_op_ctz_i32:
+        tcg_out_clzctz(s, OPC_CTZ_W, a0, a1, a2, c2, true);
+        break;
+    case INDEX_op_ctz_i64:
+        tcg_out_clzctz(s, OPC_CTZ_D, a0, a1, a2, c2, false);
+        break;
+
     case INDEX_op_mov_i32:  /* Always emitted via tcg_out_mov.  */
     case INDEX_op_mov_i64:
     default:
@@ -632,6 +668,12 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op)
         /* LoongArch reg-imm bitops have their imms ZERO-extended */
         return C_O1_I2(r, r, rU);
 
+    case INDEX_op_clz_i32:
+    case INDEX_op_clz_i64:
+    case INDEX_op_ctz_i32:
+    case INDEX_op_ctz_i64:
+        return C_O1_I2(r, r, rW);
+
     case INDEX_op_deposit_i32:
     case INDEX_op_deposit_i64:
         /* Must deposit into the same register as input */
-- 
2.25.1