tcg/riscv: Improve setcond expansion

Split out a helper function, tcg_out_setcond_int, which does not
always produce the complete boolean result, but returns a set of
flags to do so.

Based on 21af16198425, the same improvement for loongarch64.

Acked-by: Alistair Francis <alistair.francis@wdc.com>
Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

1 files changed, 114 insertions, 36 deletions

diff --git a/tcg/riscv/tcg-target.c.inc b/tcg/riscv/tcg-target.c.inc
index 05ea9fe..db328dd 100644
--- a/tcg/riscv/tcg-target.c.inc
+++ b/tcg/riscv/tcg-target.c.inc
@@ -812,50 +812,128 @@ static void tcg_out_brcond(TCGContext *s, TCGCond cond, TCGReg arg1,
     tcg_out_opc_branch(s, op, arg1, arg2, 0);
 }
 
-static void tcg_out_setcond(TCGContext *s, TCGCond cond, TCGReg ret,
-                            TCGReg arg1, TCGReg arg2)
+#define SETCOND_INV    TCG_TARGET_NB_REGS
+#define SETCOND_NEZ    (SETCOND_INV << 1)
+#define SETCOND_FLAGS  (SETCOND_INV | SETCOND_NEZ)
+
+static int tcg_out_setcond_int(TCGContext *s, TCGCond cond, TCGReg ret,
+                               TCGReg arg1, tcg_target_long arg2, bool c2)
 {
+    int flags = 0;
+
     switch (cond) {
-    case TCG_COND_EQ:
-        tcg_out_opc_reg(s, OPC_SUB, ret, arg1, arg2);
-        tcg_out_opc_imm(s, OPC_SLTIU, ret, ret, 1);
-        break;
-    case TCG_COND_NE:
-        tcg_out_opc_reg(s, OPC_SUB, ret, arg1, arg2);
-        tcg_out_opc_reg(s, OPC_SLTU, ret, TCG_REG_ZERO, ret);
-        break;
-    case TCG_COND_LT:
-        tcg_out_opc_reg(s, OPC_SLT, ret, arg1, arg2);
+    case TCG_COND_EQ:    /* -> NE  */
+    case TCG_COND_GE:    /* -> LT  */
+    case TCG_COND_GEU:   /* -> LTU */
+    case TCG_COND_GT:    /* -> LE  */
+    case TCG_COND_GTU:   /* -> LEU */
+        cond = tcg_invert_cond(cond);
+        flags ^= SETCOND_INV;
         break;
-    case TCG_COND_GE:
-        tcg_out_opc_reg(s, OPC_SLT, ret, arg1, arg2);
-        tcg_out_opc_imm(s, OPC_XORI, ret, ret, 1);
+    default:
         break;
+    }
+
+    switch (cond) {
     case TCG_COND_LE:
-        tcg_out_opc_reg(s, OPC_SLT, ret, arg2, arg1);
-        tcg_out_opc_imm(s, OPC_XORI, ret, ret, 1);
-        break;
-    case TCG_COND_GT:
-        tcg_out_opc_reg(s, OPC_SLT, ret, arg2, arg1);
+    case TCG_COND_LEU:
+        /*
+         * If we have a constant input, the most efficient way to implement
+         * LE is by adding 1 and using LT.  Watch out for wrap around for LEU.
+         * We don't need to care for this for LE because the constant input
+         * is constrained to signed 12-bit, and 0x800 is representable in the
+         * temporary register.
+         */
+        if (c2) {
+            if (cond == TCG_COND_LEU) {
+                /* unsigned <= -1 is true */
+                if (arg2 == -1) {
+                    tcg_out_movi(s, TCG_TYPE_REG, ret, !(flags & SETCOND_INV));
+                    return ret;
+                }
+                cond = TCG_COND_LTU;
+            } else {
+                cond = TCG_COND_LT;
+            }
+            tcg_debug_assert(arg2 <= 0x7ff);
+            if (++arg2 == 0x800) {
+                tcg_out_movi(s, TCG_TYPE_REG, TCG_REG_TMP0, arg2);
+                arg2 = TCG_REG_TMP0;
+                c2 = false;
+            }
+        } else {
+            TCGReg tmp = arg2;
+            arg2 = arg1;
+            arg1 = tmp;
+            cond = tcg_swap_cond(cond);    /* LE -> GE */
+            cond = tcg_invert_cond(cond);  /* GE -> LT */
+            flags ^= SETCOND_INV;
+        }
         break;
-    case TCG_COND_LTU:
-        tcg_out_opc_reg(s, OPC_SLTU, ret, arg1, arg2);
+    default:
         break;
-    case TCG_COND_GEU:
-        tcg_out_opc_reg(s, OPC_SLTU, ret, arg1, arg2);
-        tcg_out_opc_imm(s, OPC_XORI, ret, ret, 1);
+    }
+
+    switch (cond) {
+    case TCG_COND_NE:
+        flags |= SETCOND_NEZ;
+        if (!c2) {
+            tcg_out_opc_reg(s, OPC_XOR, ret, arg1, arg2);
+        } else if (arg2 == 0) {
+            ret = arg1;
+        } else {
+            tcg_out_opc_imm(s, OPC_XORI, ret, arg1, arg2);
+        }
         break;
-    case TCG_COND_LEU:
-        tcg_out_opc_reg(s, OPC_SLTU, ret, arg2, arg1);
-        tcg_out_opc_imm(s, OPC_XORI, ret, ret, 1);
+
+    case TCG_COND_LT:
+        if (c2) {
+            tcg_out_opc_imm(s, OPC_SLTI, ret, arg1, arg2);
+        } else {
+            tcg_out_opc_reg(s, OPC_SLT, ret, arg1, arg2);
+        }
         break;
-    case TCG_COND_GTU:
-        tcg_out_opc_reg(s, OPC_SLTU, ret, arg2, arg1);
+
+    case TCG_COND_LTU:
+        if (c2) {
+            tcg_out_opc_imm(s, OPC_SLTIU, ret, arg1, arg2);
+        } else {
+            tcg_out_opc_reg(s, OPC_SLTU, ret, arg1, arg2);
+        }
         break;
+
     default:
-         g_assert_not_reached();
-         break;
-     }
+        g_assert_not_reached();
+    }
+
+    return ret | flags;
+}
+
+static void tcg_out_setcond(TCGContext *s, TCGCond cond, TCGReg ret,
+                            TCGReg arg1, tcg_target_long arg2, bool c2)
+{
+    int tmpflags = tcg_out_setcond_int(s, cond, ret, arg1, arg2, c2);
+
+    if (tmpflags != ret) {
+        TCGReg tmp = tmpflags & ~SETCOND_FLAGS;
+
+        switch (tmpflags & SETCOND_FLAGS) {
+        case SETCOND_INV:
+            /* Intermediate result is boolean: simply invert. */
+            tcg_out_opc_imm(s, OPC_XORI, ret, tmp, 1);
+            break;
+        case SETCOND_NEZ:
+            /* Intermediate result is zero/non-zero: test != 0. */
+            tcg_out_opc_reg(s, OPC_SLTU, ret, TCG_REG_ZERO, tmp);
+            break;
+        case SETCOND_NEZ | SETCOND_INV:
+            /* Intermediate result is zero/non-zero: test == 0. */
+            tcg_out_opc_imm(s, OPC_SLTIU, ret, tmp, 1);
+            break;
+        default:
+            g_assert_not_reached();
+        }
+    }
 }
 
 static void tcg_out_call_int(TCGContext *s, const tcg_insn_unit *arg, bool tail)
@@ -1542,7 +1620,7 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc,
 
     case INDEX_op_setcond_i32:
     case INDEX_op_setcond_i64:
-        tcg_out_setcond(s, args[3], a0, a1, a2);
+        tcg_out_setcond(s, args[3], a0, a1, a2, c2);
         break;
 
     case INDEX_op_qemu_ld_a32_i32:
@@ -1665,6 +1743,8 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op)
     case INDEX_op_and_i64:
     case INDEX_op_or_i64:
     case INDEX_op_xor_i64:
+    case INDEX_op_setcond_i32:
+    case INDEX_op_setcond_i64:
         return C_O1_I2(r, r, rI);
 
     case INDEX_op_andc_i32:
@@ -1686,7 +1766,6 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op)
     case INDEX_op_divu_i32:
     case INDEX_op_rem_i32:
     case INDEX_op_remu_i32:
-    case INDEX_op_setcond_i32:
     case INDEX_op_mul_i64:
     case INDEX_op_mulsh_i64:
     case INDEX_op_muluh_i64:
@@ -1694,7 +1773,6 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op)
     case INDEX_op_divu_i64:
     case INDEX_op_rem_i64:
     case INDEX_op_remu_i64:
-    case INDEX_op_setcond_i64:
         return C_O1_I2(r, rZ, rZ);
 
     case INDEX_op_shl_i32: