From nobody Tue Oct 28 02:06:22 2025 Delivered-To: importer@patchew.org Received-SPF: pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) client-ip=208.118.235.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Authentication-Results: mx.zohomail.com; spf=pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org Return-Path: Received: from lists.gnu.org (lists.gnu.org [208.118.235.17]) by mx.zohomail.com with SMTPS id 1522128989241960.9704239628279; Mon, 26 Mar 2018 22:36:29 -0700 (PDT) Received: from localhost ([::1]:60490 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1f0hHU-0000Kg-SE for importer@patchew.org; Tue, 27 Mar 2018 01:36:24 -0400 Received: from eggs.gnu.org ([2001:4830:134:3::10]:35790) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1f0hFI-0007P7-7e for qemu-devel@nongnu.org; Tue, 27 Mar 2018 01:34:10 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1f0hFD-0005MV-TC for qemu-devel@nongnu.org; Tue, 27 Mar 2018 01:34:08 -0400 Received: from out5-smtp.messagingengine.com ([66.111.4.29]:40295) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1f0hFD-0005M1-Oc for qemu-devel@nongnu.org; Tue, 27 Mar 2018 01:34:03 -0400 Received: from compute4.internal (compute4.nyi.internal [10.202.2.44]) by mailout.nyi.internal (Postfix) with ESMTP id 67BAF21665; Tue, 27 Mar 2018 01:34:03 -0400 (EDT) Received: from mailfrontend2 ([10.202.2.163]) by compute4.internal (MEProxy); Tue, 27 Mar 2018 01:34:03 -0400 Received: from localhost (flamenco.cs.columbia.edu [128.59.20.216]) by mail.messagingengine.com (Postfix) with ESMTPA id 225631025C; Tue, 27 Mar 2018 01:34:03 -0400 (EDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=braap.org; h=cc :date:from:in-reply-to:message-id:references:subject:to :x-me-sender:x-me-sender:x-sasl-enc; s=mesmtp; bh=4yRX2NUogHvayH JHedIeKwsrlJBYLN/89LXKTj/l8+4=; b=oP45DmF0vYA6K38zC6y69eH05TaIl2 fGG+jjOsNpIlVl1fIMu+HXuHgNJxaXreOTrhORDgWw1thXWFWBkNh3t4yfKYrMhA Dnl2X1d7H/5WZxIxNtXb7RBYtAlzjwus6pvhSiULAwxchaRtWi3dgVBKeqHAmtjL G9dP2azjbw3qc= DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d= messagingengine.com; h=cc:date:from:in-reply-to:message-id :references:subject:to:x-me-sender:x-me-sender:x-sasl-enc; s= fm2; bh=4yRX2NUogHvayHJHedIeKwsrlJBYLN/89LXKTj/l8+4=; b=hLzpbvY5 3S2er+QmCH/A/MpVuC1nnVPqUleEVsBzejO3dTOpANCzvUjfJel/7hcoeKmzCp6f 1Z4TDbTv8OhsI/HafIOPAzd59dIB0k2ZnZepEuObPeKDGBHXhmFmSv6cXNrGZ4CJ 9oy9woHbDgP3OxbL+pVjyJgTy718DOx1vb/hPaKY0XEZgHw7eiwwj2uXIZAElwwa elU1KakCRJDpJitoQrYePcgavA6ouGKCgus/7OIjmx2A5rgs1rbxEa/19C+DWw8r CvH18QTV8BCDt5sqJLdN3sz9UXpt+ZkiUYN7k6rS1IXqBlktCo+fCX7rXmuBdwPP 9jHTqkWlfE8e5w== X-ME-Sender: From: "Emilio G. Cota" To: qemu-devel@nongnu.org Date: Tue, 27 Mar 2018 01:33:55 -0400 Message-Id: <1522128840-498-10-git-send-email-cota@braap.org> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1522128840-498-1-git-send-email-cota@braap.org> References: <1522128840-498-1-git-send-email-cota@braap.org> X-detected-operating-system: by eggs.gnu.org: GNU/Linux 2.2.x-3.x [generic] [fuzzy] X-Received-From: 66.111.4.29 Subject: [Qemu-devel] [PATCH v2 09/14] hardfloat: support float32/64 multiplication 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: Peter Maydell , Mark Cave-Ayland , Richard Henderson , Laurent Vivier , Paolo Bonzini , =?UTF-8?q?Alex=20Benn=C3=A9e?= , Aurelien Jarno Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" X-ZohoMail: RSF_0 Z_629925259 SPT_0 Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Performance results for fp-bench run under aarch64-linux-user on an Intel(R) Core(TM) i7-4790K CPU @ 4.00GHz host: - before: mul-single: 88.37 MFlops mul-double: 85.55 MFlops - after: mul-single: 115.06 MFlops mul-double: 124.67 MFlops - w/ both using float32/64_is_normal etc.: mul-single: 113.49 MFlops mul-double: 113.46 MFlops - w/ both using fpclassify etc.: mul-single: 105.70 MFlops mul-double: 127.69 MFlops Signed-off-by: Emilio G. Cota --- fpu/softfloat.c | 77 +++++++++++++++++++++++++++++++++++++++++++++++++++++= +--- 1 file changed, 73 insertions(+), 4 deletions(-) diff --git a/fpu/softfloat.c b/fpu/softfloat.c index e0ab0ca..9739a86 100644 --- a/fpu/softfloat.c +++ b/fpu/softfloat.c @@ -1044,8 +1044,8 @@ float16 __attribute__((flatten)) float16_mul(float16 = a, float16 b, return float16_round_pack_canonical(pr, status); } =20 -float32 __attribute__((flatten)) float32_mul(float32 a, float32 b, - float_status *status) +static float32 __attribute__((flatten, noinline)) +soft_float32_mul(float32 a, float32 b, float_status *status) { FloatParts pa =3D float32_unpack_canonical(a, status); FloatParts pb =3D float32_unpack_canonical(b, status); @@ -1054,8 +1054,8 @@ float32 __attribute__((flatten)) float32_mul(float32 = a, float32 b, return float32_round_pack_canonical(pr, status); } =20 -float64 __attribute__((flatten)) float64_mul(float64 a, float64 b, - float_status *status) +static float64 __attribute__((flatten, noinline)) +soft_float64_mul(float64 a, float64 b, float_status *status) { FloatParts pa =3D float64_unpack_canonical(a, status); FloatParts pb =3D float64_unpack_canonical(b, status); @@ -1064,6 +1064,75 @@ float64 __attribute__((flatten)) float64_mul(float64= a, float64 b, return float64_round_pack_canonical(pr, status); } =20 +#define GEN_FPU_MUL(name, soft_t, host_t, host_abs_func, min_normal) \ + soft_t name(soft_t a, soft_t b, float_status *s) \ + { \ + soft_t ## _input_flush2(&a, &b, s); \ + if (likely((soft_t ## _is_normal(a) || soft_t ## _is_zero(a)) && \ + (soft_t ## _is_normal(b) || soft_t ## _is_zero(b)) && \ + s->float_exception_flags & float_flag_inexact && \ + s->float_rounding_mode =3D=3D float_round_nearest_even)= ) { \ + if (soft_t ## _is_zero(a) || soft_t ## _is_zero(b)) { \ + bool signbit =3D soft_t ## _is_neg(a) ^ soft_t ## _is_neg(= b); \ + \ + return soft_t ## _set_sign(soft_t ## _zero, signbit); \ + } else { \ + host_t ha =3D soft_t ## _to_ ## host_t(a); \ + host_t hb =3D soft_t ## _to_ ## host_t(b); \ + host_t hr =3D ha * hb; \ + soft_t r =3D host_t ## _to_ ## soft_t(hr); \ + \ + if (unlikely(soft_t ## _is_infinity(r))) { \ + s->float_exception_flags |=3D float_flag_overflow; \ + } else if (unlikely(host_abs_func(hr) <=3D min_normal)) { \ + goto soft; \ + } \ + return r; \ + } \ + } \ + soft: \ + return soft_ ## soft_t ## _mul(a, b, s); \ + } + +GEN_FPU_MUL(float32_mul, float32, float, fabsf, FLT_MIN) +#undef GEN_FPU_MUL + +#define GEN_FPU_MUL(name, soft_t, host_t, host_abs_func, min_normal) \ + soft_t name(soft_t a, soft_t b, float_status *s) \ + { \ + host_t ha, hb; \ + \ + soft_t ## _input_flush2(&a, &b, s); \ + ha =3D soft_t ## _to_ ## host_t(a); \ + hb =3D soft_t ## _to_ ## host_t(b); \ + if (likely((fpclassify(ha) =3D=3D FP_NORMAL || = \ + fpclassify(ha) =3D=3D FP_ZERO) && = \ + (fpclassify(hb) =3D=3D FP_NORMAL || = \ + fpclassify(hb) =3D=3D FP_ZERO) && = \ + s->float_exception_flags & float_flag_inexact && \ + s->float_rounding_mode =3D=3D float_round_nearest_even)= ) { \ + if (soft_t ## _is_zero(a) || soft_t ## _is_zero(b)) { \ + bool signbit =3D soft_t ## _is_neg(a) ^ soft_t ## _is_neg(= b); \ + \ + return soft_t ## _set_sign(soft_t ## _zero, signbit); \ + } else { \ + host_t hr =3D ha * hb; \ + \ + if (unlikely(isinf(hr))) { \ + s->float_exception_flags |=3D float_flag_overflow; \ + } else if (unlikely(host_abs_func(hr) <=3D min_normal)) { \ + goto soft; \ + } \ + return host_t ## _to_ ## soft_t(hr); \ + } \ + } \ + soft: \ + return soft_ ## soft_t ## _mul(a, b, s); \ + } + +GEN_FPU_MUL(float64_mul, float64, double, fabs, DBL_MIN) +#undef GEN_FPU_MUL + /* * Returns the result of multiplying the floating-point values `a' and * `b' then adding 'c', with no intermediate rounding step after the --=20 2.7.4