[PATCH v3 16/16] tcg/mips: Try three insns with shift and add in tcg_out_movi

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

These sequences are inexpensive to test.  Maxing out at three insns
results in the same space as a load plus the constant pool entry.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 tcg/mips/tcg-target.c.inc | 44 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 44 insertions(+)

diff --git a/tcg/mips/tcg-target.c.inc b/tcg/mips/tcg-target.c.inc
index 27a23662c8..92f324de68 100644
--- a/tcg/mips/tcg-target.c.inc
+++ b/tcg/mips/tcg-target.c.inc
@@ -583,6 +583,7 @@ static void tcg_out_movi_int(TCGContext *s, TCGType type, TCGReg ret,
                              tcg_target_long arg, TCGReg tbreg)
 {
     tcg_target_long tmp;
+    int sh, lo;
 
     if (TCG_TARGET_REG_BITS == 64 && type == TCG_TYPE_I32) {
         arg = (int32_t)arg;
@@ -605,6 +606,49 @@ static void tcg_out_movi_int(TCGContext *s, TCGType type, TCGReg ret,
         return;
     }
 
+    /*
+     * Load bitmasks with a right-shift.  This is good for things
+     * like 0x0fff_ffff_ffff_fff0: ADDUI r,0xff00 + DSRL r,r,4.
+     * or similarly using LUI.  For this to work, bit 31 must be set.
+     */
+    if (arg > 0 && (int32_t)arg < 0) {
+        sh = clz64(arg);
+        if (tcg_out_movi_one(s, ret, arg << sh)) {
+            tcg_out_dsrl(s, ret, ret, sh);
+            return;
+        }
+    }
+
+    /*
+     * Load slightly larger constants using left-shift.
+     * Limit this sequence to 3 insns to avoid too much expansion.
+     */
+    sh = ctz64(arg);
+    if (sh && tcg_out_movi_two(s, ret, arg >> sh)) {
+        tcg_out_dsll(s, ret, ret, sh);
+        return;
+    }
+
+    /*
+     * Load slightly larger constants using left-shift and add/or.
+     * Prefer addi with a negative immediate when that would produce
+     * a larger shift.  For this to work, bits 15 and 16 must be set.
+     */
+    lo = arg & 0xffff;
+    if (lo) {
+        if ((arg & 0x18000) == 0x18000) {
+            lo = (int16_t)arg;
+        }
+        tmp = arg - lo;
+        sh = ctz64(tmp);
+        tmp >>= sh;
+        if (tcg_out_movi_one(s, ret, tmp)) {
+            tcg_out_dsll(s, ret, ret, sh);
+            tcg_out_opc_imm(s, lo < 0 ? OPC_DADDIU : OPC_ORI, ret, ret, lo);
+            return;
+        }
+    }
+
     /* Otherwise, put 64-bit constants into the constant pool. */
     tcg_out_movi_pool(s, ret, arg, tbreg);
 }
-- 
2.25.1