From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([208.118.235.92]:51458) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1TLsrK-0008D1-QU for qemu-devel@nongnu.org; Wed, 10 Oct 2012 05:45:48 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1TLsrE-00071N-GJ for qemu-devel@nongnu.org; Wed, 10 Oct 2012 05:45:46 -0400 Received: from hall.aurel32.net ([88.191.126.93]:44418) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1TLsrE-00071D-7Y for qemu-devel@nongnu.org; Wed, 10 Oct 2012 05:45:40 -0400 Date: Wed, 10 Oct 2012 11:45:32 +0200 From: Aurelien Jarno Message-ID: <20121010094532.GA25297@ohm.aurel32.net> References: <1349202750-16815-1-git-send-email-rth@twiddle.net> <1349202750-16815-8-git-send-email-rth@twiddle.net> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-15 Content-Disposition: inline In-Reply-To: <1349202750-16815-8-git-send-email-rth@twiddle.net> Subject: Re: [Qemu-devel] [PATCH 07/10] tcg: Do constant folding on double-word comparisons List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Richard Henderson Cc: qemu-devel@nongnu.org On Tue, Oct 02, 2012 at 11:32:27AM -0700, Richard Henderson wrote: > Signed-off-by: Richard Henderson > --- > tcg/optimize.c | 93 +++++++++++++++++++++++++++++++++++++++++++++------------- > 1 file changed, 72 insertions(+), 21 deletions(-) > > diff --git a/tcg/optimize.c b/tcg/optimize.c > index 38027dc..d9251e4 100644 > --- a/tcg/optimize.c > +++ b/tcg/optimize.c > @@ -398,6 +398,40 @@ static TCGArg do_constant_folding_cond(TCGOpcode op, TCGArg x, > } > } > > +/* Return 2 if the condition can't be simplified, and the result > + of the condition (0 or 1) if it can */ > +static TCGArg do_constant_folding_cond2(TCGArg *p1, TCGArg *p2, TCGCond c) > +{ > + TCGArg al = p1[0], ah = p1[1]; > + TCGArg bl = p2[0], bh = p2[1]; > + > + if (temps[bl].state == TCG_TEMP_CONST > + && temps[bh].state == TCG_TEMP_CONST) { > + uint64_t b = ((uint64_t)temps[bh].val << 32) | (uint32_t)temps[bl].val; > + > + if (temps[al].state == TCG_TEMP_CONST > + && temps[ah].state == TCG_TEMP_CONST) { > + uint64_t a; > + a = ((uint64_t)temps[ah].val << 32) | (uint32_t)temps[al].val; > + return do_constant_folding_cond_64(a, b, c); > + } > + if (b == 0) { > + switch (c) { > + case TCG_COND_LTU: > + return 0; > + case TCG_COND_GEU: > + return 1; > + default: > + break; > + } > + } > + } > + if (temps_are_copies(al, bl) && temps_are_copies(ah, bh)) { > + return do_constant_folding_cond_eq(c); > + } > + return 2; > +} > + > static bool swap_commutative(TCGArg dest, TCGArg *p1, TCGArg *p2) > { > TCGArg a1 = *p1, a2 = *p2; > @@ -763,43 +797,60 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr, > goto do_default; > > case INDEX_op_brcond2_i32: > - /* Simplify LT/GE comparisons vs zero to a single compare > - vs the high word of the input. */ > - if ((args[4] == TCG_COND_LT || args[4] == TCG_COND_GE) > - && temps[args[2]].state == TCG_TEMP_CONST > - && temps[args[3]].state == TCG_TEMP_CONST > - && temps[args[2]].val == 0 > - && temps[args[3]].val == 0) { > + tmp = do_constant_folding_cond2(&args[0], &args[2], args[4]); > + if (tmp != 2) { > + if (tmp) { > + memset(temps, 0, nb_temps * sizeof(struct tcg_temp_info)); > + gen_opc_buf[op_index] = INDEX_op_br; > + gen_args[0] = args[5]; > + gen_args += 1; > + } else { > + gen_opc_buf[op_index] = INDEX_op_nop; > + } > + } else if ((args[4] == TCG_COND_LT || args[4] == TCG_COND_GE) > + && temps[args[2]].state == TCG_TEMP_CONST > + && temps[args[3]].state == TCG_TEMP_CONST > + && temps[args[2]].val == 0 > + && temps[args[3]].val == 0) { > + /* Simplify LT/GE comparisons vs zero to a single compare > + vs the high word of the input. */ > + memset(temps, 0, nb_temps * sizeof(struct tcg_temp_info)); > gen_opc_buf[op_index] = INDEX_op_brcond_i32; > gen_args[0] = args[1]; > gen_args[1] = args[3]; > gen_args[2] = args[4]; > gen_args[3] = args[5]; > gen_args += 4; > - args += 6; > - memset(temps, 0, nb_temps * sizeof(struct tcg_temp_info)); > - break; > + } else { > + goto do_default; > } > - goto do_default; > + args += 6; > + break; > > case INDEX_op_setcond2_i32: > - /* Simplify LT/GE comparisons vs zero to a single compare > - vs the high word of the input. */ > - if ((args[5] == TCG_COND_LT || args[5] == TCG_COND_GE) > - && temps[args[3]].state == TCG_TEMP_CONST > - && temps[args[4]].state == TCG_TEMP_CONST > - && temps[args[3]].val == 0 > - && temps[args[4]].val == 0) { > + tmp = do_constant_folding_cond2(&args[1], &args[3], args[5]); > + if (tmp != 2) { > + gen_opc_buf[op_index] = INDEX_op_movi_i32; > + tcg_opt_gen_movi(gen_args, args[0], tmp); > + gen_args += 2; > + } else if ((args[5] == TCG_COND_LT || args[5] == TCG_COND_GE) > + && temps[args[3]].state == TCG_TEMP_CONST > + && temps[args[4]].state == TCG_TEMP_CONST > + && temps[args[3]].val == 0 > + && temps[args[4]].val == 0) { > + /* Simplify LT/GE comparisons vs zero to a single compare > + vs the high word of the input. */ > gen_opc_buf[op_index] = INDEX_op_setcond_i32; > gen_args[0] = args[0]; > gen_args[1] = args[2]; > gen_args[2] = args[4]; > gen_args[3] = args[5]; > gen_args += 4; > - args += 6; > - break; > + } else { > + goto do_default; > } > - goto do_default; > + args += 6; > + break; > > case INDEX_op_call: > nb_call_args = (args[0] >> 16) + (args[0] & 0xffff); Reviewed-by: Aurelien Jarno -- Aurelien Jarno GPG: 1024D/F1BCDB73 aurelien@aurel32.net http://www.aurel32.net