From patchwork Fri Oct 29 04:32:33 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Richard Henderson X-Patchwork-Id: 516379 Delivered-To: patch@linaro.org Received: by 2002:ad5:5208:0:0:0:0:0 with SMTP id p8csp388288iml; Thu, 28 Oct 2021 21:34:36 -0700 (PDT) X-Google-Smtp-Source: ABdhPJzHbxknM3iE0spld4FRq1eQJ/uE5AZJb75xT2RZcJm11AsoJ3lRMJqqtEMSGiMwu44gAeDM X-Received: by 2002:aca:3fd7:: with SMTP id m206mr11709092oia.162.1635482076396; Thu, 28 Oct 2021 21:34:36 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1635482076; cv=none; d=google.com; s=arc-20160816; b=i9aDINUCgAcSKXYnf4ZAuOfcMZR0vBaRDSNAxHKzzwSDmAwe8d0+KNx1siOd6YjgKr 3JdnKCnKr56G/wrGOeo0EJkAhy/isP5PKlC35NQzbltk7E1bRPPRO+7c7X44xV8JHQ/6 Zee0SQCFKfApbdoVAIhYz05x08nxMmOUFQEZM2idT54Uja0+QAlAmKh7RVaZHVMA5xGH o3yqkJEfvLACpzrZc45OIWuaunphYikByj1kh/PaOvFwA3B83C5i+Z0fpZMixeGb8IXm YJcqqJ8kyIl7UG0nHPXrM22tFNve/SXGHLweGngcYL8Kyg7CPdy4MUTW8Rdnx90js6dJ dJDA== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:cc: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=yA37LSgyZgUZ7Jnk9oYQugiaR4/N0x8exHl3zm53CZM=; b=OQalHtY30+561vvkFKwq+xHrewUFjAgcFRcflkpcoW0I8yzDR40D3WAzoRHWNtlswk ApMwu+QlHU0DfqzQRn+er2tW0BU/dxgjEeCJl+3HcC99v+ZYAj3BVIgWpUkBkX/GwYQN OtcxepPP1t6fbd66CTKN7Nt3sGdH7DGJQ66h7gmr4n7kc0Z5TZiXElE4GvWve0WsjGfl KdkMI0e0xZQbY+DjVy8mz7uq4+nGZ4ix0IA7w2kKZnrUwig+Re/GIZAitISx9RIvpk6w kCywqC4rD+bRZums/Cq1qclsjncD6OqtEGUcB/hJcIvrCjH/CF1HC7Xk+xv/PeM57d4n 2p5A== ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=Ta131xuL; 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 l14si6302592otb.144.2021.10.28.21.34.36 for (version=TLS1_2 cipher=ECDHE-ECDSA-CHACHA20-POLY1305 bits=256/256); Thu, 28 Oct 2021 21:34:36 -0700 (PDT) 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=Ta131xuL; 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]:41820 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1mgJb9-0003cC-LC for patch@linaro.org; Fri, 29 Oct 2021 00:34:35 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]:51016) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1mgJaE-0003ZM-AU for qemu-devel@nongnu.org; Fri, 29 Oct 2021 00:33:38 -0400 Received: from mail-pl1-x632.google.com ([2607:f8b0:4864:20::632]:42898) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1mgJaB-0007sq-Ky for qemu-devel@nongnu.org; Fri, 29 Oct 2021 00:33:37 -0400 Received: by mail-pl1-x632.google.com with SMTP id v16so5983343ple.9 for ; Thu, 28 Oct 2021 21:33:35 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; h=from:to:cc:subject:date:message-id:in-reply-to:references :mime-version:content-transfer-encoding; bh=yA37LSgyZgUZ7Jnk9oYQugiaR4/N0x8exHl3zm53CZM=; b=Ta131xuLNE+cUeWaciQvs6geeDOl3BoVnuAFj10oHfns9M3oLPAtnEY8ktmUk5gLts uZq2cUxo44Tjscr6+X4YJtA9WB+Blf2crTi2PYjltoZwIIfSlB70fMRUdZtCkbfRLUP3 jfg9UPlYMO/FBKaOUzFPf7E5W4dFEJN9iRwJTxVxy0lRe33XIsNQPfYPIn4f/+usy6kr niaiSbtkqOmRr/udcHfhJnsQGQe13tuGXtWb0K6iGg9fFUNn18uLfSWcr/R/MX5NIj4q Dl4FoeaNeFTGYZqL1Q9y0udZtoJbb76fSMFNyRCd2rEDvZa36oF3FDYGKU4fvepT6nL5 GUEA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references:mime-version:content-transfer-encoding; bh=yA37LSgyZgUZ7Jnk9oYQugiaR4/N0x8exHl3zm53CZM=; b=sZJJR6MPHopaqwlNJostkMG+UUQQTIXoZRueOleH7USGJO9ecBklsq9CZzegGegjV1 07kib9rmo2hyxezi3iWj+bH5uo1rOw4tRYpCmlSw5suKOCSNo727648ziiyy37nd8dko L6QXOiYYqPfFyDRauWiqkmr0njpVOHjswhqKTRHQ2sXztPc/rn0ZN3w1yd5M2f9TQ3qx FqKhcnl5hNy4Y5Q4qxsZ8n6qMn6UJ0QVjU+x33Boa3ywvhflIpCmY/v04xUgeXgaHesw obqbKdQcQnK6WyyOyT86sxbRhPxn37oVezxuD+V6L+DTRlF3nXMyyaTq4Xp6b4Ygf2JT HkTw== X-Gm-Message-State: AOAM532W7RStzliEux7JoyyM9/CuGipqTXFg3PPCMmDj+qN2CbZnO8/u K/q62zcvNLj5Gax5dysAQzOu+QcVfMWcXg== X-Received: by 2002:a17:90b:4d0b:: with SMTP id mw11mr9001559pjb.135.1635482014210; Thu, 28 Oct 2021 21:33:34 -0700 (PDT) Received: from localhost.localdomain (174-21-75-75.tukw.qwest.net. [174.21.75.75]) by smtp.gmail.com with ESMTPSA id i11sm4120257pgp.18.2021.10.28.21.33.33 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Thu, 28 Oct 2021 21:33:33 -0700 (PDT) From: Richard Henderson To: qemu-devel@nongnu.org Subject: [PULL v2 04/60] host-utils: add 128-bit quotient support to divu128/divs128 Date: Thu, 28 Oct 2021 21:32:33 -0700 Message-Id: <20211029043329.1518029-5-richard.henderson@linaro.org> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20211029043329.1518029-1-richard.henderson@linaro.org> References: <20211029043329.1518029-1-richard.henderson@linaro.org> MIME-Version: 1.0 Received-SPF: pass client-ip=2607:f8b0:4864:20::632; envelope-from=richard.henderson@linaro.org; helo=mail-pl1-x632.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: 2.1.23 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: Luis Pires Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: "Qemu-devel" From: Luis Pires These will be used to implement new decimal floating point instructions from Power ISA 3.1. The remainder is now returned directly by divu128/divs128, freeing up phigh to receive the high 64 bits of the quotient. Signed-off-by: Luis Pires Reviewed-by: Richard Henderson Message-Id: <20211025191154.350831-4-luis.pires@eldorado.org.br> Signed-off-by: Richard Henderson --- include/hw/clock.h | 6 +- include/qemu/host-utils.h | 20 ++++-- target/ppc/int_helper.c | 9 +-- util/host-utils.c | 133 +++++++++++++++++++++++++------------- 4 files changed, 108 insertions(+), 60 deletions(-) -- 2.25.1 diff --git a/include/hw/clock.h b/include/hw/clock.h index 7443e6c4ab..5c927cee7f 100644 --- a/include/hw/clock.h +++ b/include/hw/clock.h @@ -323,11 +323,7 @@ static inline uint64_t clock_ns_to_ticks(const Clock *clk, uint64_t ns) if (clk->period == 0) { return 0; } - /* - * BUG: when CONFIG_INT128 is not defined, the current implementation of - * divu128 does not return a valid truncated quotient, so the result will - * be wrong. - */ + divu128(&lo, &hi, clk->period); return lo; } diff --git a/include/qemu/host-utils.h b/include/qemu/host-utils.h index 08a17e16e5..a3a7ced78d 100644 --- a/include/qemu/host-utils.h +++ b/include/qemu/host-utils.h @@ -56,26 +56,32 @@ static inline uint64_t muldiv64(uint64_t a, uint32_t b, uint32_t c) return (__int128_t)a * b / c; } -static inline void divu128(uint64_t *plow, uint64_t *phigh, uint64_t divisor) +static inline uint64_t divu128(uint64_t *plow, uint64_t *phigh, + uint64_t divisor) { __uint128_t dividend = ((__uint128_t)*phigh << 64) | *plow; __uint128_t result = dividend / divisor; + *plow = result; - *phigh = dividend % divisor; + *phigh = result >> 64; + return dividend % divisor; } -static inline void divs128(int64_t *plow, int64_t *phigh, int64_t divisor) +static inline int64_t divs128(uint64_t *plow, int64_t *phigh, + int64_t divisor) { - __int128_t dividend = ((__int128_t)*phigh << 64) | (uint64_t)*plow; + __int128_t dividend = ((__int128_t)*phigh << 64) | *plow; __int128_t result = dividend / divisor; + *plow = result; - *phigh = dividend % divisor; + *phigh = result >> 64; + return dividend % divisor; } #else void muls64(uint64_t *plow, uint64_t *phigh, int64_t a, int64_t b); void mulu64(uint64_t *plow, uint64_t *phigh, uint64_t a, uint64_t b); -void divu128(uint64_t *plow, uint64_t *phigh, uint64_t divisor); -void divs128(int64_t *plow, int64_t *phigh, int64_t divisor); +uint64_t divu128(uint64_t *plow, uint64_t *phigh, uint64_t divisor); +int64_t divs128(uint64_t *plow, int64_t *phigh, int64_t divisor); static inline uint64_t muldiv64(uint64_t a, uint32_t b, uint32_t c) { diff --git a/target/ppc/int_helper.c b/target/ppc/int_helper.c index 510faf24cf..eeb7781a9e 100644 --- a/target/ppc/int_helper.c +++ b/target/ppc/int_helper.c @@ -120,7 +120,7 @@ uint64_t helper_divdeu(CPUPPCState *env, uint64_t ra, uint64_t rb, uint32_t oe) uint64_t helper_divde(CPUPPCState *env, uint64_t rau, uint64_t rbu, uint32_t oe) { - int64_t rt = 0; + uint64_t rt = 0; int64_t ra = (int64_t)rau; int64_t rb = (int64_t)rbu; int overflow = 0; @@ -2506,6 +2506,7 @@ uint32_t helper_bcdcfsq(ppc_avr_t *r, ppc_avr_t *b, uint32_t ps) int cr; uint64_t lo_value; uint64_t hi_value; + uint64_t rem; ppc_avr_t ret = { .u64 = { 0, 0 } }; if (b->VsrSD(0) < 0) { @@ -2541,10 +2542,10 @@ uint32_t helper_bcdcfsq(ppc_avr_t *r, ppc_avr_t *b, uint32_t ps) * In that case, we leave r unchanged. */ } else { - divu128(&lo_value, &hi_value, 1000000000000000ULL); + rem = divu128(&lo_value, &hi_value, 1000000000000000ULL); - for (i = 1; i < 16; hi_value /= 10, i++) { - bcd_put_digit(&ret, hi_value % 10, i); + for (i = 1; i < 16; rem /= 10, i++) { + bcd_put_digit(&ret, rem % 10, i); } for (; i < 32; lo_value /= 10, i++) { diff --git a/util/host-utils.c b/util/host-utils.c index 701a371843..bcc772b8ec 100644 --- a/util/host-utils.c +++ b/util/host-utils.c @@ -87,72 +87,117 @@ void muls64 (uint64_t *plow, uint64_t *phigh, int64_t a, int64_t b) } /* - * Unsigned 128-by-64 division. Returns quotient via plow and - * remainder via phigh. - * The result must fit in 64 bits (plow) - otherwise, the result - * is undefined. - * This function will cause a division by zero if passed a zero divisor. + * Unsigned 128-by-64 division. + * Returns the remainder. + * Returns quotient via plow and phigh. + * Also returns the remainder via the function return value. */ -void divu128(uint64_t *plow, uint64_t *phigh, uint64_t divisor) +uint64_t divu128(uint64_t *plow, uint64_t *phigh, uint64_t divisor) { uint64_t dhi = *phigh; uint64_t dlo = *plow; - unsigned i; - uint64_t carry = 0; + uint64_t rem, dhighest; + int sh; if (divisor == 0 || dhi == 0) { *plow = dlo / divisor; - *phigh = dlo % divisor; + *phigh = 0; + return dlo % divisor; } else { + sh = clz64(divisor); - for (i = 0; i < 64; i++) { - carry = dhi >> 63; - dhi = (dhi << 1) | (dlo >> 63); - if (carry || (dhi >= divisor)) { - dhi -= divisor; - carry = 1; - } else { - carry = 0; + if (dhi < divisor) { + if (sh != 0) { + /* normalize the divisor, shifting the dividend accordingly */ + divisor <<= sh; + dhi = (dhi << sh) | (dlo >> (64 - sh)); + dlo <<= sh; } - dlo = (dlo << 1) | carry; + + *phigh = 0; + *plow = udiv_qrnnd(&rem, dhi, dlo, divisor); + } else { + if (sh != 0) { + /* normalize the divisor, shifting the dividend accordingly */ + divisor <<= sh; + dhighest = dhi >> (64 - sh); + dhi = (dhi << sh) | (dlo >> (64 - sh)); + dlo <<= sh; + + *phigh = udiv_qrnnd(&dhi, dhighest, dhi, divisor); + } else { + /** + * dhi >= divisor + * Since the MSB of divisor is set (sh == 0), + * (dhi - divisor) < divisor + * + * Thus, the high part of the quotient is 1, and we can + * calculate the low part with a single call to udiv_qrnnd + * after subtracting divisor from dhi + */ + dhi -= divisor; + *phigh = 1; + } + + *plow = udiv_qrnnd(&rem, dhi, dlo, divisor); } - *plow = dlo; - *phigh = dhi; + /* + * since the dividend/divisor might have been normalized, + * the remainder might also have to be shifted back + */ + return rem >> sh; } } /* - * Signed 128-by-64 division. Returns quotient via plow and - * remainder via phigh. - * The result must fit in 64 bits (plow) - otherwise, the result - * is undefined. - * This function will cause a division by zero if passed a zero divisor. + * Signed 128-by-64 division. + * Returns quotient via plow and phigh. + * Also returns the remainder via the function return value. */ -void divs128(int64_t *plow, int64_t *phigh, int64_t divisor) +int64_t divs128(uint64_t *plow, int64_t *phigh, int64_t divisor) { - int sgn_dvdnd = *phigh < 0; - int sgn_divsr = divisor < 0; + bool neg_quotient = false, neg_remainder = false; + uint64_t unsig_hi = *phigh, unsig_lo = *plow; + uint64_t rem; - if (sgn_dvdnd) { - *plow = ~(*plow); - *phigh = ~(*phigh); - if (*plow == (int64_t)-1) { + if (*phigh < 0) { + neg_quotient = !neg_quotient; + neg_remainder = !neg_remainder; + + if (unsig_lo == 0) { + unsig_hi = -unsig_hi; + } else { + unsig_hi = ~unsig_hi; + unsig_lo = -unsig_lo; + } + } + + if (divisor < 0) { + neg_quotient = !neg_quotient; + + divisor = -divisor; + } + + rem = divu128(&unsig_lo, &unsig_hi, (uint64_t)divisor); + + if (neg_quotient) { + if (unsig_lo == 0) { + *phigh = -unsig_hi; *plow = 0; - (*phigh)++; - } else { - (*plow)++; - } + } else { + *phigh = ~unsig_hi; + *plow = -unsig_lo; + } + } else { + *phigh = unsig_hi; + *plow = unsig_lo; } - if (sgn_divsr) { - divisor = 0 - divisor; - } - - divu128((uint64_t *)plow, (uint64_t *)phigh, (uint64_t)divisor); - - if (sgn_dvdnd ^ sgn_divsr) { - *plow = 0 - *plow; + if (neg_remainder) { + return -rem; + } else { + return rem; } } #endif