From patchwork Wed Feb 21 11:05:22 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: =?utf-8?q?Alex_Benn=C3=A9e?= X-Patchwork-Id: 129037 Delivered-To: patch@linaro.org Received: by 10.46.124.24 with SMTP id x24csp509071ljc; Wed, 21 Feb 2018 03:26:51 -0800 (PST) X-Google-Smtp-Source: AH8x226UXlr+CbeJtth52ul3k5MynGGe8w+nJDApp87iPVU8zNDtClwqFsiZgERN2Qi/xlLHPmMC X-Received: by 2002:a25:d146:: with SMTP id i67-v6mr1930129ybg.495.1519212411613; Wed, 21 Feb 2018 03:26:51 -0800 (PST) ARC-Seal: i=1; a=rsa-sha256; t=1519212411; cv=none; d=google.com; s=arc-20160816; b=Gty3SbGDxvTXmPjFhAYo+kIDDwh1dz87OpUklPHYqhysaXqa+lPFsPZVHC+QLIZ7lz BRLI02xj4EQwa/8kfIaHNT5mH4U/vg7HRgCUHF/IwoIpSHoMYC34zd3+S5YUvPapFjB2 H10JOjC+Wuseq/XgcKkB4+noTEfZeBvxwDTynU+k06Zg0rPcHyPp62zyIDWxEOB8WLMc iJ8j9/hLmwBiZK3O/9fCS9KfSBGiYTtzs/iYmA1muC990fYq+c99PuqV0zwJmQW71y/D nivdY8LF5aIudzTNsb7NvSMhf2fCLRyXEDLJoOQ9PvamM3FIeRlxhz9RROVKSG5aIAKi zDlA== 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:subject :content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:to:from:dkim-signature:arc-authentication-results; bh=yn69zVGmuNidSJ9HxRcTZD6IcAUFa/6Ul7HJQ+7g54s=; b=CL7kU56f3gxSxXv/pqfVq16WNDnVotcd3hpIAvM4eeCnDTlaZ9ylQ/WeBwK1Jnsl5m pCuvSK3Yc7dszTn89tlbnqRDrG2DTCg8mBiDKK09sc+cq2qVs+/2J6JLAa/pCBmu5y8s q1r9lBjV+gNZUaT0EWXoV6I7k6CrZfYqRjYvP2n5Rx3HoU0Tmh1fnYhFApeAEqb2msYs DYtR86a6R53gHYGGl+P2NMKQ143PPCWXvS1NCYH26vSb8TJm3r3AgPYzGLI0wXYUXtzh 6c86J/w48WhhXD1vHBWRZOBABzPKpdTnegVCuUqPOUJmJ/cy5kDOXbkE7NUf3t7EePHQ YCbQ== ARC-Authentication-Results: i=1; mx.google.com; dkim=fail header.i=@linaro.org header.s=google header.b=hBWxKtss; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 2001:4830:134:3::11 as permitted sender) smtp.mailfrom=qemu-devel-bounces+patch=linaro.org@nongnu.org; dmarc=fail (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [2001:4830:134:3::11]) by mx.google.com with ESMTPS id r196si2205271ybc.582.2018.02.21.03.26.51 for (version=TLS1 cipher=AES128-SHA bits=128/128); Wed, 21 Feb 2018 03:26:51 -0800 (PST) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 2001:4830:134:3::11 as permitted sender) client-ip=2001:4830:134:3::11; Authentication-Results: mx.google.com; dkim=fail header.i=@linaro.org header.s=google header.b=hBWxKtss; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 2001:4830:134:3::11 as permitted sender) smtp.mailfrom=qemu-devel-bounces+patch=linaro.org@nongnu.org; dmarc=fail (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([::1]:60166 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1eoSXz-0003sJ-0G for patch@linaro.org; Wed, 21 Feb 2018 06:26:51 -0500 Received: from eggs.gnu.org ([2001:4830:134:3::10]:37316) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1eoSK5-000160-Mt for qemu-devel@nongnu.org; Wed, 21 Feb 2018 06:12:31 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1eoSK3-0002LZ-Oa for qemu-devel@nongnu.org; Wed, 21 Feb 2018 06:12:29 -0500 Received: from mail-wr0-x242.google.com ([2a00:1450:400c:c0c::242]:40457) by eggs.gnu.org with esmtps (TLS1.0:RSA_AES_128_CBC_SHA1:16) (Exim 4.71) (envelope-from ) id 1eoSK3-0002L7-Fs for qemu-devel@nongnu.org; Wed, 21 Feb 2018 06:12:27 -0500 Received: by mail-wr0-x242.google.com with SMTP id o76so3326904wrb.7 for ; Wed, 21 Feb 2018 03:12:27 -0800 (PST) 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=yn69zVGmuNidSJ9HxRcTZD6IcAUFa/6Ul7HJQ+7g54s=; b=hBWxKtsssuHQGHM57DH3DkrROPfSJAIHmFChZ6CH+jxt8DPlRJ6oAdwKB9D8YNNgyi IPzZ5iHw3hX7jl+Iwj3rXGfitcC2uBfNXmrltL/BbMAsXMT/dTsLXiUG/LEDQSYCi205 MmyG5Ap6q+Fhd9GEeDYRbM6NuLbabdxMWaRfQ= X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references:mime-version:content-transfer-encoding; bh=yn69zVGmuNidSJ9HxRcTZD6IcAUFa/6Ul7HJQ+7g54s=; b=NO/ey8aD1O4heYK+CewTCyTxgUTvWKLm6hKtBYU1z5/vRrZ69zLlqUQztYEkEnRznu 6vBlChuw4UvU9D+hXkZ+Z23apWRkHHPSNs0eAsvYKG90ZAkGZ4HoAGmyd0Lu7M6k38px P22ZnH3lw66IrtVzs/aPWwL034aIz97xoc+1HfSj5QT1iLYdLr4IIssdWR7hkEXqXmZW wl7qJm0wTbCQUyYCl2/jHzDJfwneGYig9x0n/4UZ4HV/unpy2HctkAlxtkMN2RT6Rdy2 1ojA0qtAwD4M5ylxmbrgVVmJyEk22Zc2I6GgP/1cOVjSgXekGkcrzRhEDbTTV2F66WGm Hm+w== X-Gm-Message-State: APf1xPAyx6Nym/BLP5QlQIuFa+9SRNnVLtpwtDrFReSWxBM+NtNPLc/j dTtFX7NAqBSdY6rwdYNgh5/mcg== X-Received: by 10.223.166.135 with SMTP id t7mr2659642wrc.260.1519211546353; Wed, 21 Feb 2018 03:12:26 -0800 (PST) Received: from zen.linaro.local ([81.128.185.34]) by smtp.gmail.com with ESMTPSA id n24sm30580073wmi.21.2018.02.21.03.12.21 (version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Wed, 21 Feb 2018 03:12:24 -0800 (PST) Received: from zen.linaroharston (localhost [127.0.0.1]) by zen.linaro.local (Postfix) with ESMTP id E5CE43E0CEF; Wed, 21 Feb 2018 11:05:24 +0000 (GMT) From: =?utf-8?q?Alex_Benn=C3=A9e?= To: peter.maydell@linaro.org Date: Wed, 21 Feb 2018 11:05:22 +0000 Message-Id: <20180221110523.859-23-alex.bennee@linaro.org> X-Mailer: git-send-email 2.15.1 In-Reply-To: <20180221110523.859-1-alex.bennee@linaro.org> References: <20180221110523.859-1-alex.bennee@linaro.org> MIME-Version: 1.0 X-detected-operating-system: by eggs.gnu.org: Genre and OS details not recognized. X-Received-From: 2a00:1450:400c:c0c::242 Subject: [Qemu-devel] [PULL 22/22] fpu/softfloat: re-factor sqrt X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.21 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: =?utf-8?q?Alex_Benn=C3=A9e?= , qemu-devel@nongnu.org, Aurelien Jarno Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: "Qemu-devel" This is a little bit of a departure from softfloat's original approach as we skip the estimate step in favour of a straight iteration. There is a minor optimisation to avoid calculating more bits of precision than we need however this still brings a performance drop, especially for float64 operations. Suggested-by: Richard Henderson Signed-off-by: Alex Bennée Reviewed-by: Peter Maydell Reviewed-by: Richard Henderson -- 2.15.1 diff --git a/fpu/softfloat.c b/fpu/softfloat.c index 4bc425d7e4..e7fb0d357a 100644 --- a/fpu/softfloat.c +++ b/fpu/softfloat.c @@ -1896,6 +1896,102 @@ float64 float64_scalbn(float64 a, int n, float_status *status) return float64_round_pack_canonical(pr, status); } +/* + * Square Root + * + * The old softfloat code did an approximation step before zeroing in + * on the final result. However for simpleness we just compute the + * square root by iterating down from the implicit bit to enough extra + * bits to ensure we get a correctly rounded result. + * + * This does mean however the calculation is slower than before, + * especially for 64 bit floats. + */ + +static FloatParts sqrt_float(FloatParts a, float_status *s, const FloatFmt *p) +{ + uint64_t a_frac, r_frac, s_frac; + int bit, last_bit; + + if (is_nan(a.cls)) { + return return_nan(a, s); + } + if (a.cls == float_class_zero) { + return a; /* sqrt(+-0) = +-0 */ + } + if (a.sign) { + s->float_exception_flags |= float_flag_invalid; + a.cls = float_class_dnan; + return a; + } + if (a.cls == float_class_inf) { + return a; /* sqrt(+inf) = +inf */ + } + + assert(a.cls == float_class_normal); + + /* We need two overflow bits at the top. Adding room for that is a + * right shift. If the exponent is odd, we can discard the low bit + * by multiplying the fraction by 2; that's a left shift. Combine + * those and we shift right if the exponent is even. + */ + a_frac = a.frac; + if (!(a.exp & 1)) { + a_frac >>= 1; + } + a.exp >>= 1; + + /* Bit-by-bit computation of sqrt. */ + r_frac = 0; + s_frac = 0; + + /* Iterate from implicit bit down to the 3 extra bits to compute a + * properly rounded result. Remember we've inserted one more bit + * at the top, so these positions are one less. + */ + bit = DECOMPOSED_BINARY_POINT - 1; + last_bit = MAX(p->frac_shift - 4, 0); + do { + uint64_t q = 1ULL << bit; + uint64_t t_frac = s_frac + q; + if (t_frac <= a_frac) { + s_frac = t_frac + q; + a_frac -= t_frac; + r_frac += q; + } + a_frac <<= 1; + } while (--bit >= last_bit); + + /* Undo the right shift done above. If there is any remaining + * fraction, the result is inexact. Set the sticky bit. + */ + a.frac = (r_frac << 1) + (a_frac != 0); + + return a; +} + +float16 __attribute__((flatten)) float16_sqrt(float16 a, float_status *status) +{ + FloatParts pa = float16_unpack_canonical(a, status); + FloatParts pr = sqrt_float(pa, status, &float16_params); + return float16_round_pack_canonical(pr, status); +} + +float32 __attribute__((flatten)) float32_sqrt(float32 a, float_status *status) +{ + FloatParts pa = float32_unpack_canonical(a, status); + FloatParts pr = sqrt_float(pa, status, &float32_params); + return float32_round_pack_canonical(pr, status); +} + +float64 __attribute__((flatten)) float64_sqrt(float64 a, float_status *status) +{ + FloatParts pa = float64_unpack_canonical(a, status); + FloatParts pr = sqrt_float(pa, status, &float64_params); + return float64_round_pack_canonical(pr, status); +} + + /*---------------------------------------------------------------------------- | Takes a 64-bit fixed-point value `absZ' with binary point between bits 6 | and 7, and returns the properly rounded 32-bit integer corresponding to the @@ -3303,62 +3399,6 @@ float32 float32_rem(float32 a, float32 b, float_status *status) } -/*---------------------------------------------------------------------------- -| Returns the square root of the single-precision floating-point value `a'. -| The operation is performed according to the IEC/IEEE Standard for Binary -| Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -float32 float32_sqrt(float32 a, float_status *status) -{ - flag aSign; - int aExp, zExp; - uint32_t aSig, zSig; - uint64_t rem, term; - a = float32_squash_input_denormal(a, status); - - aSig = extractFloat32Frac( a ); - aExp = extractFloat32Exp( a ); - aSign = extractFloat32Sign( a ); - if ( aExp == 0xFF ) { - if (aSig) { - return propagateFloat32NaN(a, float32_zero, status); - } - if ( ! aSign ) return a; - float_raise(float_flag_invalid, status); - return float32_default_nan(status); - } - if ( aSign ) { - if ( ( aExp | aSig ) == 0 ) return a; - float_raise(float_flag_invalid, status); - return float32_default_nan(status); - } - if ( aExp == 0 ) { - if ( aSig == 0 ) return float32_zero; - normalizeFloat32Subnormal( aSig, &aExp, &aSig ); - } - zExp = ( ( aExp - 0x7F )>>1 ) + 0x7E; - aSig = ( aSig | 0x00800000 )<<8; - zSig = estimateSqrt32( aExp, aSig ) + 2; - if ( ( zSig & 0x7F ) <= 5 ) { - if ( zSig < 2 ) { - zSig = 0x7FFFFFFF; - goto roundAndPack; - } - aSig >>= aExp & 1; - term = ( (uint64_t) zSig ) * zSig; - rem = ( ( (uint64_t) aSig )<<32 ) - term; - while ( (int64_t) rem < 0 ) { - --zSig; - rem += ( ( (uint64_t) zSig )<<1 ) | 1; - } - zSig |= ( rem != 0 ); - } - shift32RightJamming( zSig, 1, &zSig ); - roundAndPack: - return roundAndPackFloat32(0, zExp, zSig, status); - -} /*---------------------------------------------------------------------------- | Returns the binary exponential of the single-precision floating-point value @@ -4202,61 +4242,6 @@ float64 float64_rem(float64 a, float64 b, float_status *status) } - -/*---------------------------------------------------------------------------- -| Returns the square root of the double-precision floating-point value `a'. -| The operation is performed according to the IEC/IEEE Standard for Binary -| Floating-Point Arithmetic. -*----------------------------------------------------------------------------*/ - -float64 float64_sqrt(float64 a, float_status *status) -{ - flag aSign; - int aExp, zExp; - uint64_t aSig, zSig, doubleZSig; - uint64_t rem0, rem1, term0, term1; - a = float64_squash_input_denormal(a, status); - - aSig = extractFloat64Frac( a ); - aExp = extractFloat64Exp( a ); - aSign = extractFloat64Sign( a ); - if ( aExp == 0x7FF ) { - if (aSig) { - return propagateFloat64NaN(a, a, status); - } - if ( ! aSign ) return a; - float_raise(float_flag_invalid, status); - return float64_default_nan(status); - } - if ( aSign ) { - if ( ( aExp | aSig ) == 0 ) return a; - float_raise(float_flag_invalid, status); - return float64_default_nan(status); - } - if ( aExp == 0 ) { - if ( aSig == 0 ) return float64_zero; - normalizeFloat64Subnormal( aSig, &aExp, &aSig ); - } - zExp = ( ( aExp - 0x3FF )>>1 ) + 0x3FE; - aSig |= LIT64( 0x0010000000000000 ); - zSig = estimateSqrt32( aExp, aSig>>21 ); - aSig <<= 9 - ( aExp & 1 ); - zSig = estimateDiv128To64( aSig, 0, zSig<<32 ) + ( zSig<<30 ); - if ( ( zSig & 0x1FF ) <= 5 ) { - doubleZSig = zSig<<1; - mul64To128( zSig, zSig, &term0, &term1 ); - sub128( aSig, 0, term0, term1, &rem0, &rem1 ); - while ( (int64_t) rem0 < 0 ) { - --zSig; - doubleZSig -= 2; - add128( rem0, rem1, zSig>>63, doubleZSig | 1, &rem0, &rem1 ); - } - zSig |= ( ( rem0 | rem1 ) != 0 ); - } - return roundAndPackFloat64(0, zExp, zSig, status); - -} - /*---------------------------------------------------------------------------- | Returns the binary log of the double-precision floating-point value `a'. | The operation is performed according to the IEC/IEEE Standard for Binary diff --git a/include/fpu/softfloat.h b/include/fpu/softfloat.h index cebe37b716..9b7b5e34e2 100644 --- a/include/fpu/softfloat.h +++ b/include/fpu/softfloat.h @@ -251,6 +251,7 @@ float16 float16_minnum(float16, float16, float_status *status); float16 float16_maxnum(float16, float16, float_status *status); float16 float16_minnummag(float16, float16, float_status *status); float16 float16_maxnummag(float16, float16, float_status *status); +float16 float16_sqrt(float16, float_status *status); int float16_compare(float16, float16, float_status *status); int float16_compare_quiet(float16, float16, float_status *status);