[PATCH v6 09/30] tcg/loongarch64: Implement tcg_out_mov and tcg_out_movi

[WANG Xuerui <git@xen0n.name>]

Signed-off-by: WANG Xuerui <git@xen0n.name>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
 tcg/loongarch64/tcg-target.c.inc | 137 +++++++++++++++++++++++++++++++
 1 file changed, 137 insertions(+)

diff --git a/tcg/loongarch64/tcg-target.c.inc b/tcg/loongarch64/tcg-target.c.inc
index f12955723d..4487851b5e 100644
--- a/tcg/loongarch64/tcg-target.c.inc
+++ b/tcg/loongarch64/tcg-target.c.inc
@@ -247,6 +247,141 @@ static void tcg_out_mb(TCGContext *s, TCGArg a0)
     tcg_out_opc_dbar(s, 0);
 }
 
+static bool tcg_out_mov(TCGContext *s, TCGType type, TCGReg ret, TCGReg arg)
+{
+    if (ret == arg) {
+        return true;
+    }
+    switch (type) {
+    case TCG_TYPE_I32:
+    case TCG_TYPE_I64:
+        /*
+         * Conventional register-register move used in LoongArch is
+         * `or dst, src, zero`.
+         */
+        tcg_out_opc_or(s, ret, arg, TCG_REG_ZERO);
+        break;
+    default:
+        g_assert_not_reached();
+    }
+    return true;
+}
+
+static bool imm_part_needs_loading(bool high_bits_are_ones,
+                                   tcg_target_long part)
+{
+    if (high_bits_are_ones) {
+        return part != -1;
+    } else {
+        return part != 0;
+    }
+}
+
+/* Loads a 32-bit immediate into rd, sign-extended.  */
+static void tcg_out_movi_i32(TCGContext *s, TCGReg rd, int32_t val)
+{
+    tcg_target_long lo = sextreg(val, 0, 12);
+    tcg_target_long hi12 = sextreg(val, 12, 20);
+
+    /* Single-instruction cases.  */
+    if (lo == val) {
+        /* val fits in simm12: addi.w rd, zero, val */
+        tcg_out_opc_addi_w(s, rd, TCG_REG_ZERO, val);
+        return;
+    }
+    if (0x800 <= val && val <= 0xfff) {
+        /* val fits in uimm12: ori rd, zero, val */
+        tcg_out_opc_ori(s, rd, TCG_REG_ZERO, val);
+        return;
+    }
+
+    /* High bits must be set; load with lu12i.w + optional ori.  */
+    tcg_out_opc_lu12i_w(s, rd, hi12);
+    if (lo != 0) {
+        tcg_out_opc_ori(s, rd, rd, lo & 0xfff);
+    }
+}
+
+static void tcg_out_movi(TCGContext *s, TCGType type, TCGReg rd,
+                         tcg_target_long val)
+{
+    /*
+     * LoongArch conventionally loads 64-bit immediates in at most 4 steps,
+     * with dedicated instructions for filling the respective bitfields
+     * below:
+     *
+     *        6                   5                   4               3
+     *  3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2
+     * +-----------------------+---------------------------------------+...
+     * |          hi52         |                  hi32                 |
+     * +-----------------------+---------------------------------------+...
+     *       3                   2                   1
+     *     1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0
+     * ...+-------------------------------------+-------------------------+
+     *    |                 hi12                |            lo           |
+     * ...+-------------------------------------+-------------------------+
+     *
+     * Check if val belong to one of the several fast cases, before falling
+     * back to the slow path.
+     */
+
+    intptr_t pc_offset;
+    tcg_target_long val_lo, val_hi, pc_hi, offset_hi;
+    tcg_target_long hi32, hi52;
+    bool rd_high_bits_are_ones;
+
+    /* Value fits in signed i32.  */
+    if (type == TCG_TYPE_I32 || val == (int32_t)val) {
+        tcg_out_movi_i32(s, rd, val);
+        return;
+    }
+
+    /* PC-relative cases.  */
+    pc_offset = tcg_pcrel_diff(s, (void *)val);
+    if (pc_offset == sextreg(pc_offset, 0, 22) && (pc_offset & 3) == 0) {
+        /* Single pcaddu2i.  */
+        tcg_out_opc_pcaddu2i(s, rd, pc_offset >> 2);
+        return;
+    }
+
+    if (pc_offset == (int32_t)pc_offset) {
+        /* Offset within 32 bits; load with pcalau12i + ori.  */
+        val_lo = sextreg(val, 0, 12);
+        val_hi = val >> 12;
+        pc_hi = (val - pc_offset) >> 12;
+        offset_hi = val_hi - pc_hi;
+
+        tcg_debug_assert(offset_hi == sextreg(offset_hi, 0, 20));
+        tcg_out_opc_pcalau12i(s, rd, offset_hi);
+        if (val_lo != 0) {
+            tcg_out_opc_ori(s, rd, rd, val_lo & 0xfff);
+        }
+        return;
+    }
+
+    hi32 = sextreg(val, 32, 20);
+    hi52 = sextreg(val, 52, 12);
+
+    /* Single cu52i.d case.  */
+    if (ctz64(val) >= 52) {
+        tcg_out_opc_cu52i_d(s, rd, TCG_REG_ZERO, hi52);
+        return;
+    }
+
+    /* Slow path.  Initialize the low 32 bits, then concat high bits.  */
+    tcg_out_movi_i32(s, rd, val);
+    rd_high_bits_are_ones = (int32_t)val < 0;
+
+    if (imm_part_needs_loading(rd_high_bits_are_ones, hi32)) {
+        tcg_out_opc_cu32i_d(s, rd, hi32);
+        rd_high_bits_are_ones = hi32 < 0;
+    }
+
+    if (imm_part_needs_loading(rd_high_bits_are_ones, hi52)) {
+        tcg_out_opc_cu52i_d(s, rd, rd, hi52);
+    }
+}
+
 /*
  * Entry-points
  */
@@ -262,6 +397,8 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc,
         tcg_out_mb(s, a0);
         break;
 
+    case INDEX_op_mov_i32:  /* Always emitted via tcg_out_mov.  */
+    case INDEX_op_mov_i64:
     default:
         g_assert_not_reached();
     }
-- 
2.33.0