The tcg uses tgen_arithi(ARITH_AND) during fast CPU TLB lookups,
which e.g. translates to:

0x7ff5b011556a:  48 81 e6 00 f0 ff ff     andq     $0xfffffffffffff000, %rsi

In case the upper 48 bits are all set, the shorter sequence to operate
on the lower 16 bits of the target reg (si) can be used, which will then
be a 2 bytes shorter instruction sequence:

0x7f4488097b31:  66 81 e6 00 f0           andw     $0xf000, %si

Signed-off-by: Helge Deller <del...@gmx.de>
---
 tcg/i386/tcg-target.c.inc | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/tcg/i386/tcg-target.c.inc b/tcg/i386/tcg-target.c.inc
index 77482da070..1cb9759c9e 100644
--- a/tcg/i386/tcg-target.c.inc
+++ b/tcg/i386/tcg-target.c.inc
@@ -1342,6 +1342,13 @@ static void tgen_arithi(TCGContext *s, int c, int r0,
                 /* AND with no high bits set can use a 32-bit operation.  */
                 rexw = 0;
             }
+            if ((val & 0xffffffffffff0000) == 0xffffffffffff0000) {
+                /* mask lower 16 bits on 16-bit register */
+                tcg_out8(s, 0x66);
+                tcg_out_modrm(s, OPC_ARITH_EvIz, c, r0);
+                tcg_out16(s, val);
+                return;
+            }
         }
         if (val == 0xffu && (r0 < 4 || TCG_TARGET_REG_BITS == 64)) {
             tcg_out_ext8u(s, r0, r0);
--
2.41.0


Reply via email to