From 96658acafd9ade24d00526e46cc073ed8fcf2111 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Sat, 5 Aug 2023 15:51:30 -0700 Subject: [PATCH] tcg/i386: Clear dest first in tcg_out_setcond if possible Using XOR first is both smaller and more efficient, though cannot be applied if it clobbers an input. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson --- tcg/i386/tcg-target.c.inc | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/tcg/i386/tcg-target.c.inc b/tcg/i386/tcg-target.c.inc index 4d7b745a52..3f3c114efd 100644 --- a/tcg/i386/tcg-target.c.inc +++ b/tcg/i386/tcg-target.c.inc @@ -1532,6 +1532,7 @@ static void tcg_out_setcond(TCGContext *s, int rexw, TCGCond cond, int const_arg2) { bool inv = false; + bool cleared; switch (cond) { case TCG_COND_NE: @@ -1581,9 +1582,23 @@ static void tcg_out_setcond(TCGContext *s, int rexw, TCGCond cond, break; } + /* + * If dest does not overlap the inputs, clearing it first is preferred. + * The XOR breaks any false dependency for the low-byte write to dest, + * and is also one byte smaller than MOVZBL. + */ + cleared = false; + if (dest != arg1 && (const_arg2 || dest != arg2)) { + tgen_arithr(s, ARITH_XOR, dest, dest); + cleared = true; + } + tcg_out_cmp(s, arg1, arg2, const_arg2, rexw); tcg_out_modrm(s, OPC_SETCC | tcg_cond_to_jcc[cond], 0, dest); - tcg_out_ext8u(s, dest, dest); + + if (!cleared) { + tcg_out_ext8u(s, dest, dest); + } } #if TCG_TARGET_REG_BITS == 32 -- 2.11.0