From patchwork Fri Sep 21 19:43:15 2012 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Aurelien Jarno X-Patchwork-Id: 185912 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Received: from lists.gnu.org (lists.gnu.org [208.118.235.17]) (using TLSv1 with cipher AES256-SHA (256/256 bits)) (Client did not present a certificate) by ozlabs.org (Postfix) with ESMTPS id C8F532C0086 for ; Sat, 22 Sep 2012 06:29:52 +1000 (EST) Received: from localhost ([::1]:46661 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1TF99n-0002FC-Sb for incoming@patchwork.ozlabs.org; Fri, 21 Sep 2012 15:44:59 -0400 Received: from eggs.gnu.org ([208.118.235.92]:59085) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1TF98k-00084R-H3 for qemu-devel@nongnu.org; Fri, 21 Sep 2012 15:43:57 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1TF98g-0002l7-V8 for qemu-devel@nongnu.org; Fri, 21 Sep 2012 15:43:54 -0400 Received: from hall.aurel32.net ([88.191.126.93]:43254) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1TF98g-0002ju-KK for qemu-devel@nongnu.org; Fri, 21 Sep 2012 15:43:50 -0400 Received: from [2001:470:d4ed:1:2db:dfff:fe14:52d] (helo=ohm.aurel32.net) by hall.aurel32.net with esmtpsa (TLS1.0:DHE_RSA_AES_128_CBC_SHA1:16) (Exim 4.72) (envelope-from ) id 1TF98f-0005jy-5l; Fri, 21 Sep 2012 21:43:49 +0200 Received: from aurel32 by ohm.aurel32.net with local (Exim 4.80) (envelope-from ) id 1TF98d-0002Ln-Ci; Fri, 21 Sep 2012 21:43:47 +0200 From: Aurelien Jarno To: qemu-devel@nongnu.org Date: Fri, 21 Sep 2012 21:43:15 +0200 Message-Id: <1348256598-8146-8-git-send-email-aurelien@aurel32.net> X-Mailer: git-send-email 1.7.10.4 In-Reply-To: <1348256598-8146-1-git-send-email-aurelien@aurel32.net> References: <1348256598-8146-1-git-send-email-aurelien@aurel32.net> X-detected-operating-system: by eggs.gnu.org: GNU/Linux 2.6 (newer, 3) X-Received-From: 88.191.126.93 Cc: Aurelien Jarno Subject: [Qemu-devel] [PATCH v2 07/10] tcg/optimize: further optimize brcond/movcond/setcond X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org Sender: qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org When both argument of brcond/movcond/setcond are the same or when one of the two values is a constant equal to zero, it's possible to do further optimizations. Signed-off-by: Aurelien Jarno --- tcg/optimize.c | 127 +++++++++++++++++++++++++++++++++----------------------- 1 file changed, 76 insertions(+), 51 deletions(-) diff --git a/tcg/optimize.c b/tcg/optimize.c index ceea644..abe016a 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -292,58 +292,88 @@ static TCGArg do_constant_folding(TCGOpcode op, TCGArg x, TCGArg y) return res; } +/* 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_cond(TCGOpcode op, TCGArg x, TCGArg y, TCGCond c) { - switch (op_bits(op)) { - case 32: + if (temps[x].state == TCG_TEMP_CONST && temps[y].state == TCG_TEMP_CONST) { + switch (op_bits(op)) { + case 32: + switch (c) { + case TCG_COND_EQ: + return (uint32_t)temps[x].val == (uint32_t)temps[y].val; + case TCG_COND_NE: + return (uint32_t)temps[x].val != (uint32_t)temps[y].val; + case TCG_COND_LT: + return (int32_t)temps[x].val < (int32_t)temps[y].val; + case TCG_COND_GE: + return (int32_t)temps[x].val >= (int32_t)temps[y].val; + case TCG_COND_LE: + return (int32_t)temps[x].val <= (int32_t)temps[y].val; + case TCG_COND_GT: + return (int32_t)temps[x].val > (int32_t)temps[y].val; + case TCG_COND_LTU: + return (uint32_t)temps[x].val < (uint32_t)temps[y].val; + case TCG_COND_GEU: + return (uint32_t)temps[x].val >= (uint32_t)temps[y].val; + case TCG_COND_LEU: + return (uint32_t)temps[x].val <= (uint32_t)temps[y].val; + case TCG_COND_GTU: + return (uint32_t)temps[x].val > (uint32_t)temps[y].val; + } + break; + case 64: + switch (c) { + case TCG_COND_EQ: + return (uint64_t)temps[x].val == (uint64_t)temps[y].val; + case TCG_COND_NE: + return (uint64_t)temps[x].val != (uint64_t)temps[y].val; + case TCG_COND_LT: + return (int64_t)temps[x].val < (int64_t)temps[y].val; + case TCG_COND_GE: + return (int64_t)temps[x].val >= (int64_t)temps[y].val; + case TCG_COND_LE: + return (int64_t)temps[x].val <= (int64_t)temps[y].val; + case TCG_COND_GT: + return (int64_t)temps[x].val > (int64_t)temps[y].val; + case TCG_COND_LTU: + return (uint64_t)temps[x].val < (uint64_t)temps[y].val; + case TCG_COND_GEU: + return (uint64_t)temps[x].val >= (uint64_t)temps[y].val; + case TCG_COND_LEU: + return (uint64_t)temps[x].val <= (uint64_t)temps[y].val; + case TCG_COND_GTU: + return (uint64_t)temps[x].val > (uint64_t)temps[y].val; + } + break; + } + } else if (temps_are_copies(x, y)) { switch (c) { - case TCG_COND_EQ: - return (uint32_t)x == (uint32_t)y; - case TCG_COND_NE: - return (uint32_t)x != (uint32_t)y; - case TCG_COND_LT: - return (int32_t)x < (int32_t)y; - case TCG_COND_GE: - return (int32_t)x >= (int32_t)y; - case TCG_COND_LE: - return (int32_t)x <= (int32_t)y; case TCG_COND_GT: - return (int32_t)x > (int32_t)y; case TCG_COND_LTU: - return (uint32_t)x < (uint32_t)y; - case TCG_COND_GEU: - return (uint32_t)x >= (uint32_t)y; - case TCG_COND_LEU: - return (uint32_t)x <= (uint32_t)y; + case TCG_COND_LT: case TCG_COND_GTU: - return (uint32_t)x > (uint32_t)y; - } - break; - case 64: - switch (c) { - case TCG_COND_EQ: - return (uint64_t)x == (uint64_t)y; case TCG_COND_NE: - return (uint64_t)x != (uint64_t)y; - case TCG_COND_LT: - return (int64_t)x < (int64_t)y; + return 0; case TCG_COND_GE: - return (int64_t)x >= (int64_t)y; + case TCG_COND_GEU: case TCG_COND_LE: - return (int64_t)x <= (int64_t)y; - case TCG_COND_GT: - return (int64_t)x > (int64_t)y; + case TCG_COND_LEU: + case TCG_COND_EQ: + return 1; + } + } else if (temps[y].state == TCG_TEMP_CONST && temps[y].val == 0) { + switch (c) { case TCG_COND_LTU: - return (uint64_t)x < (uint64_t)y; + return 0; case TCG_COND_GEU: - return (uint64_t)x >= (uint64_t)y; - case TCG_COND_LEU: - return (uint64_t)x <= (uint64_t)y; - case TCG_COND_GTU: - return (uint64_t)x > (uint64_t)y; + return 1; + default: + return 2; } - break; + } else { + return 2; } fprintf(stderr, @@ -636,11 +666,9 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr, args += 3; break; CASE_OP_32_64(setcond): - if (temps[args[1]].state == TCG_TEMP_CONST - && temps[args[2]].state == TCG_TEMP_CONST) { + tmp = do_constant_folding_cond(op, args[1], args[2], args[3]); + if (tmp != 2) { gen_opc_buf[op_index] = op_to_movi(op); - tmp = do_constant_folding_cond(op, temps[args[1]].val, - temps[args[2]].val, args[3]); tcg_opt_gen_movi(gen_args, args[0], tmp); gen_args += 2; } else { @@ -654,10 +682,9 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr, args += 4; break; CASE_OP_32_64(brcond): - if (temps[args[0]].state == TCG_TEMP_CONST - && temps[args[1]].state == TCG_TEMP_CONST) { - if (do_constant_folding_cond(op, temps[args[0]].val, - temps[args[1]].val, args[2])) { + tmp = do_constant_folding_cond(op, args[0], args[1], args[2]); + 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[3]; @@ -677,10 +704,8 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr, args += 4; break; CASE_OP_32_64(movcond): - if (temps[args[1]].state == TCG_TEMP_CONST - && temps[args[2]].state == TCG_TEMP_CONST) { - tmp = do_constant_folding_cond(op, temps[args[1]].val, - temps[args[2]].val, args[5]); + tmp = do_constant_folding_cond(op, args[1], args[2], args[5]); + if (tmp != 2) { if (temps_are_copies(args[0], args[4-tmp])) { gen_opc_buf[op_index] = INDEX_op_nop; } else if (temps[args[4-tmp]].state == TCG_TEMP_CONST) {