From patchwork Fri Dec 30 00:01:53 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Richard Henderson X-Patchwork-Id: 637841 Delivered-To: patch@linaro.org Received: by 2002:a17:522:c983:b0:460:3032:e3c4 with SMTP id kr3csp3181274pvb; Thu, 29 Dec 2022 16:14:39 -0800 (PST) X-Google-Smtp-Source: AMrXdXt9eO1ca1qOkqpo7S57RhAhacevgUYv2l5f+U2rLkidrWPeb3TU9a2XgcuFlJY14EDoeani X-Received: by 2002:a05:6214:5709:b0:4c6:e1ba:b1a with SMTP id lt9-20020a056214570900b004c6e1ba0b1amr42657897qvb.10.1672359279373; Thu, 29 Dec 2022 16:14:39 -0800 (PST) ARC-Seal: i=1; a=rsa-sha256; t=1672359279; cv=none; d=google.com; s=arc-20160816; b=Hi1R22fpUt6jDCKqNnXqRGqtCWLZsOMg/kyDwGRlr+ifxvLSclL2HecxKS2OL5SwfB QDDEiX2Yy71Y+D0sBxPtAtoydRXvyqpjcHruBfYj2eA21JluFl+gpAZuR3UxVxxzH+7f 1gR9PQHGhDswSc7DmA4JZSTpfvJ13qNUbS1gEvo4dAwdelafmN9AIRJaMHTw4iHVzWHO K6+0VocFHJcpslovwL+Lm+ZYD47RPcTfkkZuafod+Jqkgpsd7t4PdDajpWd6gWyXlzgg JAyarHkxe8Fb6XxCuOnI0TfatUGxjgU42LVG7bq7L+p3ih1fmB8Lbfr+aqq4TzLVhrAS 7x5w== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:content-transfer-encoding :mime-version:references:in-reply-to:message-id:date:subject:to:from :dkim-signature; bh=/ZnmrQYh5lPqNDd6nIjEmLxLWOodOPTCOD2Tnh7/rwM=; b=1AYLFWVoa+YPqdFJBoNqnrzBK0MiOZSNkz2WD5zKLtMoWHVvkMXCwBf/S3aScYgbbC LCLKVaVTwoqhwp+RuHshPyQIIQvi44MEnaPLlVAiXzqIEdxdZDGiUw+b1vUuJ1kZB376 T6OcwtXbP7nX+f9Ju0OVE4ZsFVqGptyBM0LhgPEqaAZYoJb4vIH5GpN25DBrGG09vn5K niTEoplK/xXIMMIzJTOdmC3/tyoiqC5CUK+Or6nbMPXA1W/jYAdLlLDfr7WJfC6C6ipo b7de+d6HwALl228nzjgC7dJNwZDAoMckgNbBrcQ8eYSN/X6Gm+MzxGa/yU8ZGBj0fh5u sU2A== ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=giZQeO5x; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id i16-20020a05620a075000b006fc8359140esi8625356qki.352.2022.12.29.16.14.39 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Thu, 29 Dec 2022 16:14:39 -0800 (PST) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=giZQeO5x; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1pB2rH-00036S-0r; Thu, 29 Dec 2022 19:02:47 -0500 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1pB2rE-00034M-Jk for qemu-devel@nongnu.org; Thu, 29 Dec 2022 19:02:44 -0500 Received: from mail-pl1-x62e.google.com ([2607:f8b0:4864:20::62e]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1pB2rB-0002iQ-Uc for qemu-devel@nongnu.org; Thu, 29 Dec 2022 19:02:44 -0500 Received: by mail-pl1-x62e.google.com with SMTP id u7so20339260plq.11 for ; Thu, 29 Dec 2022 16:02:41 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:from:to:cc:subject:date:message-id :reply-to; bh=/ZnmrQYh5lPqNDd6nIjEmLxLWOodOPTCOD2Tnh7/rwM=; b=giZQeO5x+7z4sOc/sAdhcHKrYQlBmF4eA/4atOAwDoQzvZ9VwoWRIITq/0TvsK4WdV my+/6jhMNIMdoW94RBAaFF2NoUIc+gNo2ejeo7hAOaF2mSZB2jMe2dYtNQwfBbljI012 tCQ2p69bv8dxv4Mgk1yDUTbgCWdCl2U/YH/LhlZp0UU0VDYLpWjd8LGGr6mzj4Dxd8Uk 6unoQXJxNGq3RwfzxBQlfsC/c4z9iufw1j0ttXNylWKfPhabbsY8zaKlyEtGK2hqMJ2m 9E3J+Vk2/sdT92PK1LGWU0nIK1MhIqzduFjqYSAG9AgLAz/qo7aIZ/bTr7k8rceqrq/Y YHXw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=/ZnmrQYh5lPqNDd6nIjEmLxLWOodOPTCOD2Tnh7/rwM=; b=JrUs+YKGdJlLEvX413a1CW9S8qNbmEX5a4Yj/lz2MtbNjhuqJZiT87/dWkkRCB84Tv tbuBqPkBGK791qm+utGlxxa4OrrEt44d4pRyKGioS2Zcik5toRV6+ruNz4NqmGeJ6/uq IOyvA9EdI2BY+32V27itIq0L3mkCPKMLHX2rwaUfj4HI7IleTM8CMs0bMIC0g1UeQKQO v0rqoypI2xXeFNTlNOWOM7nAf/gYeX9wSLeyzc53Bg8ODNMsAdjwEm+9vdMrlZg+OqM6 +rnefzpwssc8MguWjYGHZVxE/hn8OLEPRy49UKomr7etYaUTpS5TYEz9ZE22ENO9cN6R bihQ== X-Gm-Message-State: AFqh2kqWBZvkqerUcs/q4HOfrimbmqQDyC/Jpy6QHKEFX+TbvOImUkNe t4zjYA93s3uaUpyvDI2lxLZl+hmhcWV5SJdD X-Received: by 2002:a17:902:a984:b0:192:9a7d:c38a with SMTP id bh4-20020a170902a98400b001929a7dc38amr5642832plb.9.1672358560228; Thu, 29 Dec 2022 16:02:40 -0800 (PST) Received: from stoup.. (76-14-210-194.or.wavecable.com. [76.14.210.194]) by smtp.gmail.com with ESMTPSA id j14-20020a170903028e00b00192849e1d0asm7343953plr.116.2022.12.29.16.02.39 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Thu, 29 Dec 2022 16:02:39 -0800 (PST) From: Richard Henderson To: qemu-devel@nongnu.org Subject: [PULL 19/47] tcg: Introduce paired register allocation Date: Thu, 29 Dec 2022 16:01:53 -0800 Message-Id: <20221230000221.2764875-20-richard.henderson@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20221230000221.2764875-1-richard.henderson@linaro.org> References: <20221230000221.2764875-1-richard.henderson@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2607:f8b0:4864:20::62e; envelope-from=richard.henderson@linaro.org; helo=mail-pl1-x62e.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: qemu-devel-bounces+patch=linaro.org@nongnu.org There are several instances where we need to be able to allocate a pair of registers to related inputs/outputs. Add 'p' and 'm' register constraints for this, in order to be able to allocate the even/odd register first or second. Signed-off-by: Richard Henderson --- include/tcg/tcg.h | 2 + tcg/tcg.c | 419 ++++++++++++++++++++++++++++++++++++++++------ 2 files changed, 373 insertions(+), 48 deletions(-) diff --git a/include/tcg/tcg.h b/include/tcg/tcg.h index d84bae6e3f..5c2254ce9f 100644 --- a/include/tcg/tcg.h +++ b/include/tcg/tcg.h @@ -951,6 +951,8 @@ typedef struct TCGArgConstraint { unsigned ct : 16; unsigned alias_index : 4; unsigned sort_index : 4; + unsigned pair_index : 4; + unsigned pair : 2; /* 0: none, 1: first, 2: second, 3: second alias */ bool oalias : 1; bool ialias : 1; bool newreg : 1; diff --git a/tcg/tcg.c b/tcg/tcg.c index 92141bd79a..e7570ecb4a 100644 --- a/tcg/tcg.c +++ b/tcg/tcg.c @@ -1969,15 +1969,32 @@ static void tcg_dump_ops(TCGContext *s, FILE *f, bool have_prefs) static int get_constraint_priority(const TCGOpDef *def, int k) { const TCGArgConstraint *arg_ct = &def->args_ct[k]; - int n; + int n = ctpop64(arg_ct->regs); - if (arg_ct->oalias) { - /* an alias is equivalent to a single register */ - n = 1; - } else { - n = ctpop64(arg_ct->regs); + /* + * Sort constraints of a single register first, which includes output + * aliases (which must exactly match the input already allocated). + */ + if (n == 1 || arg_ct->oalias) { + return INT_MAX; } - return TCG_TARGET_NB_REGS - n + 1; + + /* + * Sort register pairs next, first then second immediately after. + * Arbitrarily sort multiple pairs by the index of the first reg; + * there shouldn't be many pairs. + */ + switch (arg_ct->pair) { + case 1: + case 3: + return (k + 1) * 2; + case 2: + return (arg_ct->pair_index + 1) * 2 - 1; + } + + /* Finally, sort by decreasing register count. */ + assert(n > 1); + return -n; } /* sort from highest priority to lowest */ @@ -2012,7 +2029,8 @@ static void process_op_defs(TCGContext *s) for (op = 0; op < NB_OPS; op++) { TCGOpDef *def = &tcg_op_defs[op]; const TCGTargetOpDef *tdefs; - int i, o, nb_args; + bool saw_alias_pair = false; + int i, o, i2, o2, nb_args; if (def->flags & TCG_OPF_NOT_PRESENT) { continue; @@ -2053,6 +2071,9 @@ static void process_op_defs(TCGContext *s) /* The input sets ialias. */ def->args_ct[i].ialias = 1; def->args_ct[i].alias_index = o; + if (def->args_ct[i].pair) { + saw_alias_pair = true; + } tcg_debug_assert(ct_str[1] == '\0'); continue; @@ -2061,6 +2082,38 @@ static void process_op_defs(TCGContext *s) def->args_ct[i].newreg = true; ct_str++; break; + + case 'p': /* plus */ + /* Allocate to the register after the previous. */ + tcg_debug_assert(i > (input_p ? def->nb_oargs : 0)); + o = i - 1; + tcg_debug_assert(!def->args_ct[o].pair); + tcg_debug_assert(!def->args_ct[o].ct); + def->args_ct[i] = (TCGArgConstraint){ + .pair = 2, + .pair_index = o, + .regs = def->args_ct[o].regs << 1, + }; + def->args_ct[o].pair = 1; + def->args_ct[o].pair_index = i; + tcg_debug_assert(ct_str[1] == '\0'); + continue; + + case 'm': /* minus */ + /* Allocate to the register before the previous. */ + tcg_debug_assert(i > (input_p ? def->nb_oargs : 0)); + o = i - 1; + tcg_debug_assert(!def->args_ct[o].pair); + tcg_debug_assert(!def->args_ct[o].ct); + def->args_ct[i] = (TCGArgConstraint){ + .pair = 1, + .pair_index = o, + .regs = def->args_ct[o].regs >> 1, + }; + def->args_ct[o].pair = 2; + def->args_ct[o].pair_index = i; + tcg_debug_assert(ct_str[1] == '\0'); + continue; } do { @@ -2084,6 +2137,8 @@ static void process_op_defs(TCGContext *s) default: case '0' ... '9': case '&': + case 'p': + case 'm': /* Typo in TCGTargetOpDef constraint. */ g_assert_not_reached(); } @@ -2093,6 +2148,79 @@ static void process_op_defs(TCGContext *s) /* TCGTargetOpDef entry with too much information? */ tcg_debug_assert(i == TCG_MAX_OP_ARGS || tdefs->args_ct_str[i] == NULL); + /* + * Fix up output pairs that are aliased with inputs. + * When we created the alias, we copied pair from the output. + * There are three cases: + * (1a) Pairs of inputs alias pairs of outputs. + * (1b) One input aliases the first of a pair of outputs. + * (2) One input aliases the second of a pair of outputs. + * + * Case 1a is handled by making sure that the pair_index'es are + * properly updated so that they appear the same as a pair of inputs. + * + * Case 1b is handled by setting the pair_index of the input to + * itself, simply so it doesn't point to an unrelated argument. + * Since we don't encounter the "second" during the input allocation + * phase, nothing happens with the second half of the input pair. + * + * Case 2 is handled by setting the second input to pair=3, the + * first output to pair=3, and the pair_index'es to match. + */ + if (saw_alias_pair) { + for (i = def->nb_oargs; i < nb_args; i++) { + /* + * Since [0-9pm] must be alone in the constraint string, + * the only way they can both be set is if the pair comes + * from the output alias. + */ + if (!def->args_ct[i].ialias) { + continue; + } + switch (def->args_ct[i].pair) { + case 0: + break; + case 1: + o = def->args_ct[i].alias_index; + o2 = def->args_ct[o].pair_index; + tcg_debug_assert(def->args_ct[o].pair == 1); + tcg_debug_assert(def->args_ct[o2].pair == 2); + if (def->args_ct[o2].oalias) { + /* Case 1a */ + i2 = def->args_ct[o2].alias_index; + tcg_debug_assert(def->args_ct[i2].pair == 2); + def->args_ct[i2].pair_index = i; + def->args_ct[i].pair_index = i2; + } else { + /* Case 1b */ + def->args_ct[i].pair_index = i; + } + break; + case 2: + o = def->args_ct[i].alias_index; + o2 = def->args_ct[o].pair_index; + tcg_debug_assert(def->args_ct[o].pair == 2); + tcg_debug_assert(def->args_ct[o2].pair == 1); + if (def->args_ct[o2].oalias) { + /* Case 1a */ + i2 = def->args_ct[o2].alias_index; + tcg_debug_assert(def->args_ct[i2].pair == 1); + def->args_ct[i2].pair_index = i; + def->args_ct[i].pair_index = i2; + } else { + /* Case 2 */ + def->args_ct[i].pair = 3; + def->args_ct[o2].pair = 3; + def->args_ct[i].pair_index = o2; + def->args_ct[o2].pair_index = i; + } + break; + default: + g_assert_not_reached(); + } + } + } + /* sort the constraints (XXX: this is just an heuristic) */ sort_constraints(def, 0, def->nb_oargs); sort_constraints(def, def->nb_oargs, def->nb_iargs); @@ -3141,6 +3269,52 @@ static TCGReg tcg_reg_alloc(TCGContext *s, TCGRegSet required_regs, tcg_abort(); } +static TCGReg tcg_reg_alloc_pair(TCGContext *s, TCGRegSet required_regs, + TCGRegSet allocated_regs, + TCGRegSet preferred_regs, bool rev) +{ + int i, j, k, fmin, n = ARRAY_SIZE(tcg_target_reg_alloc_order); + TCGRegSet reg_ct[2]; + const int *order; + + /* Ensure that if I is not in allocated_regs, I+1 is not either. */ + reg_ct[1] = required_regs & ~(allocated_regs | (allocated_regs >> 1)); + tcg_debug_assert(reg_ct[1] != 0); + reg_ct[0] = reg_ct[1] & preferred_regs; + + order = rev ? indirect_reg_alloc_order : tcg_target_reg_alloc_order; + + /* + * Skip the preferred_regs option if it cannot be satisfied, + * or if the preference made no difference. + */ + k = reg_ct[0] == 0 || reg_ct[0] == reg_ct[1]; + + /* + * Minimize the number of flushes by looking for 2 free registers first, + * then a single flush, then two flushes. + */ + for (fmin = 2; fmin >= 0; fmin--) { + for (j = k; j < 2; j++) { + TCGRegSet set = reg_ct[j]; + + for (i = 0; i < n; i++) { + TCGReg reg = order[i]; + + if (tcg_regset_test_reg(set, reg)) { + int f = !s->reg_to_temp[reg] + !s->reg_to_temp[reg + 1]; + if (f >= fmin) { + tcg_reg_free(s, reg, allocated_regs); + tcg_reg_free(s, reg + 1, allocated_regs); + return reg; + } + } + } + } + } + tcg_abort(); +} + /* Make sure the temporary is in a register. If needed, allocate the register from DESIRED while avoiding ALLOCATED. */ static void temp_load(TCGContext *s, TCGTemp *ts, TCGRegSet desired_regs, @@ -3550,8 +3724,10 @@ static void tcg_reg_alloc_op(TCGContext *s, const TCGOp *op) /* satisfy input constraints */ for (k = 0; k < nb_iargs; k++) { - TCGRegSet i_preferred_regs; - bool allocate_new_reg; + TCGRegSet i_preferred_regs, i_required_regs; + bool allocate_new_reg, copyto_new_reg; + TCGTemp *ts2; + int i1, i2; i = def->args_ct[nb_oargs + k].sort_index; arg = op->args[i]; @@ -3568,43 +3744,159 @@ static void tcg_reg_alloc_op(TCGContext *s, const TCGOp *op) reg = ts->reg; i_preferred_regs = 0; + i_required_regs = arg_ct->regs; allocate_new_reg = false; + copyto_new_reg = false; - if (arg_ct->ialias) { + switch (arg_ct->pair) { + case 0: /* not paired */ + if (arg_ct->ialias) { + i_preferred_regs = op->output_pref[arg_ct->alias_index]; + + /* + * If the input is not dead after the instruction, + * we must allocate a new register and move it. + */ + if (!IS_DEAD_ARG(i)) { + allocate_new_reg = true; + } else if (ts->val_type == TEMP_VAL_REG) { + /* + * Check if the current register has already been + * allocated for another input. + */ + allocate_new_reg = + tcg_regset_test_reg(i_allocated_regs, reg); + } + } + if (!allocate_new_reg) { + temp_load(s, ts, i_required_regs, i_allocated_regs, + i_preferred_regs); + reg = ts->reg; + allocate_new_reg = !tcg_regset_test_reg(i_required_regs, reg); + } + if (allocate_new_reg) { + /* + * Allocate a new register matching the constraint + * and move the temporary register into it. + */ + temp_load(s, ts, tcg_target_available_regs[ts->type], + i_allocated_regs, 0); + reg = tcg_reg_alloc(s, i_required_regs, i_allocated_regs, + i_preferred_regs, ts->indirect_base); + copyto_new_reg = true; + } + break; + + case 1: + /* First of an input pair; if i1 == i2, the second is an output. */ + i1 = i; + i2 = arg_ct->pair_index; + ts2 = i1 != i2 ? arg_temp(op->args[i2]) : NULL; + + /* + * It is easier to default to allocating a new pair + * and to identify a few cases where it's not required. + */ + if (arg_ct->ialias) { + i_preferred_regs = op->output_pref[arg_ct->alias_index]; + if (IS_DEAD_ARG(i1) && + IS_DEAD_ARG(i2) && + ts->val_type == TEMP_VAL_REG && + ts->reg < TCG_TARGET_NB_REGS - 1 && + tcg_regset_test_reg(i_required_regs, reg) && + !tcg_regset_test_reg(i_allocated_regs, reg) && + !tcg_regset_test_reg(i_allocated_regs, reg + 1) && + (ts2 + ? ts2->val_type == TEMP_VAL_REG && + ts2->reg == reg + 1 + : s->reg_to_temp[reg + 1] == NULL)) { + break; + } + } else { + /* Without aliasing, the pair must also be an input. */ + tcg_debug_assert(ts2); + if (ts->val_type == TEMP_VAL_REG && + ts2->val_type == TEMP_VAL_REG && + ts2->reg == reg + 1 && + tcg_regset_test_reg(i_required_regs, reg)) { + break; + } + } + reg = tcg_reg_alloc_pair(s, i_required_regs, i_allocated_regs, + 0, ts->indirect_base); + goto do_pair; + + case 2: /* pair second */ + reg = new_args[arg_ct->pair_index] + 1; + goto do_pair; + + case 3: /* ialias with second output, no first input */ + tcg_debug_assert(arg_ct->ialias); i_preferred_regs = op->output_pref[arg_ct->alias_index]; - /* - * If the input is readonly, then it cannot also be an - * output and aliased to itself. If the input is not - * dead after the instruction, we must allocate a new - * register and move it. - */ - if (temp_readonly(ts) || !IS_DEAD_ARG(i)) { - allocate_new_reg = true; - } else if (ts->val_type == TEMP_VAL_REG) { - /* - * Check if the current register has already been - * allocated for another input. - */ - allocate_new_reg = tcg_regset_test_reg(i_allocated_regs, reg); + if (IS_DEAD_ARG(i) && + ts->val_type == TEMP_VAL_REG && + reg > 0 && + s->reg_to_temp[reg - 1] == NULL && + tcg_regset_test_reg(i_required_regs, reg) && + !tcg_regset_test_reg(i_allocated_regs, reg) && + !tcg_regset_test_reg(i_allocated_regs, reg - 1)) { + tcg_regset_set_reg(i_allocated_regs, reg - 1); + break; } - } + reg = tcg_reg_alloc_pair(s, i_required_regs >> 1, + i_allocated_regs, 0, + ts->indirect_base); + tcg_regset_set_reg(i_allocated_regs, reg); + reg += 1; + goto do_pair; - if (!allocate_new_reg) { - temp_load(s, ts, arg_ct->regs, i_allocated_regs, i_preferred_regs); - reg = ts->reg; - allocate_new_reg = !tcg_regset_test_reg(arg_ct->regs, reg); - } - - if (allocate_new_reg) { + do_pair: /* - * Allocate a new register matching the constraint - * and move the temporary register into it. + * If an aliased input is not dead after the instruction, + * we must allocate a new register and move it. */ - temp_load(s, ts, tcg_target_available_regs[ts->type], - i_allocated_regs, 0); - reg = tcg_reg_alloc(s, arg_ct->regs, i_allocated_regs, - i_preferred_regs, ts->indirect_base); + if (arg_ct->ialias && !IS_DEAD_ARG(i)) { + TCGRegSet t_allocated_regs = i_allocated_regs; + + /* + * Because of the alias, and the continued life, make sure + * that the temp is somewhere *other* than the reg pair, + * and we get a copy in reg. + */ + tcg_regset_set_reg(t_allocated_regs, reg); + tcg_regset_set_reg(t_allocated_regs, reg + 1); + if (ts->val_type == TEMP_VAL_REG && ts->reg == reg) { + /* If ts was already in reg, copy it somewhere else. */ + TCGReg nr; + bool ok; + + tcg_debug_assert(ts->kind != TEMP_FIXED); + nr = tcg_reg_alloc(s, tcg_target_available_regs[ts->type], + t_allocated_regs, 0, ts->indirect_base); + ok = tcg_out_mov(s, ts->type, nr, reg); + tcg_debug_assert(ok); + + set_temp_val_reg(s, ts, nr); + } else { + temp_load(s, ts, tcg_target_available_regs[ts->type], + t_allocated_regs, 0); + copyto_new_reg = true; + } + } else { + /* Preferably allocate to reg, otherwise copy. */ + i_required_regs = (TCGRegSet)1 << reg; + temp_load(s, ts, i_required_regs, i_allocated_regs, + i_preferred_regs); + copyto_new_reg = ts->reg != reg; + } + break; + + default: + g_assert_not_reached(); + } + + if (copyto_new_reg) { if (!tcg_out_mov(s, ts->type, reg, ts->reg)) { /* * Cross register class move not supported. Sync the @@ -3656,15 +3948,46 @@ static void tcg_reg_alloc_op(TCGContext *s, const TCGOp *op) /* ENV should not be modified. */ tcg_debug_assert(!temp_readonly(ts)); - if (arg_ct->oalias && !const_args[arg_ct->alias_index]) { - reg = new_args[arg_ct->alias_index]; - } else if (arg_ct->newreg) { - reg = tcg_reg_alloc(s, arg_ct->regs, - i_allocated_regs | o_allocated_regs, - op->output_pref[k], ts->indirect_base); - } else { - reg = tcg_reg_alloc(s, arg_ct->regs, o_allocated_regs, - op->output_pref[k], ts->indirect_base); + switch (arg_ct->pair) { + case 0: /* not paired */ + if (arg_ct->oalias && !const_args[arg_ct->alias_index]) { + reg = new_args[arg_ct->alias_index]; + } else if (arg_ct->newreg) { + reg = tcg_reg_alloc(s, arg_ct->regs, + i_allocated_regs | o_allocated_regs, + op->output_pref[k], ts->indirect_base); + } else { + reg = tcg_reg_alloc(s, arg_ct->regs, o_allocated_regs, + op->output_pref[k], ts->indirect_base); + } + break; + + case 1: /* first of pair */ + tcg_debug_assert(!arg_ct->newreg); + if (arg_ct->oalias) { + reg = new_args[arg_ct->alias_index]; + break; + } + reg = tcg_reg_alloc_pair(s, arg_ct->regs, o_allocated_regs, + op->output_pref[k], ts->indirect_base); + break; + + case 2: /* second of pair */ + tcg_debug_assert(!arg_ct->newreg); + if (arg_ct->oalias) { + reg = new_args[arg_ct->alias_index]; + } else { + reg = new_args[arg_ct->pair_index] + 1; + } + break; + + case 3: /* first of pair, aliasing with a second input */ + tcg_debug_assert(!arg_ct->newreg); + reg = new_args[arg_ct->pair_index] - 1; + break; + + default: + g_assert_not_reached(); } tcg_regset_set_reg(o_allocated_regs, reg); set_temp_val_reg(s, ts, reg);