From patchwork Mon Feb 14 09:46:54 2011 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Christophe Lyon X-Patchwork-Id: 83052 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Received: from lists.gnu.org (lists.gnu.org [199.232.76.165]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (Client did not present a certificate) by ozlabs.org (Postfix) with ESMTPS id 77F83B7170 for ; Mon, 14 Feb 2011 20:48:22 +1100 (EST) Received: from localhost ([127.0.0.1]:42600 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.43) id 1Pov2Z-000794-Js for incoming@patchwork.ozlabs.org; Mon, 14 Feb 2011 04:48:19 -0500 Received: from [140.186.70.92] (port=37472 helo=eggs.gnu.org) by lists.gnu.org with esmtp (Exim 4.43) id 1Pov1I-0006GK-Mj for qemu-devel@nongnu.org; Mon, 14 Feb 2011 04:47:01 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1Pov1H-0000Eq-9C for qemu-devel@nongnu.org; Mon, 14 Feb 2011 04:47:00 -0500 Received: from eu1sys200aog106.obsmtp.com ([207.126.144.121]:57560) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1Pov1H-0000ER-0Z for qemu-devel@nongnu.org; Mon, 14 Feb 2011 04:46:59 -0500 Received: from source ([164.129.1.35]) (using TLSv1) by eu1sys200aob106.postini.com ([207.126.147.11]) with SMTP ID DSNKTVj6EFIyHchAe3Uv4ippwrXJ6h12STLD@postini.com; Mon, 14 Feb 2011 09:46:58 UTC Received: from zeta.dmz-eu.st.com (ns2.st.com [164.129.230.9]) by beta.dmz-eu.st.com (STMicroelectronics) with ESMTP id 8395412B for ; Mon, 14 Feb 2011 09:46:55 +0000 (GMT) Received: from Webmail-eu.st.com (safex1hubcas6.st.com [10.75.90.73]) by zeta.dmz-eu.st.com (STMicroelectronics) with ESMTP id 4DEB918D1 for ; Mon, 14 Feb 2011 09:46:55 +0000 (GMT) Received: from [164.129.122.40] (164.129.122.40) by webmail-eu.st.com (10.75.90.13) with Microsoft SMTP Server (TLS) id 8.2.234.1; Mon, 14 Feb 2011 10:46:54 +0100 Message-ID: <4D58FA0E.1040502@st.com> Date: Mon, 14 Feb 2011 10:46:54 +0100 From: Christophe Lyon User-Agent: Mozilla/5.0 (X11; U; Linux i686 (x86_64); en-US; rv:1.9.2.13) Gecko/20101207 Lightning/1.0b2 Thunderbird/3.1.7 MIME-Version: 1.0 To: "qemu-devel@nongnu.org" X-Enigmail-Version: 1.1.1 X-detected-operating-system: by eggs.gnu.org: GNU/Linux 2.6, seldom 2.4 (older, 4) X-Received-From: 207.126.144.121 Subject: [Qemu-devel] [PATCH] target-arm: fix support for vrecpe. X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: qemu-devel.nongnu.org List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org Errors-To: qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org Now use the same algorithm as described in the ARM ARM. Signed-off-by: Christophe Lyon --- target-arm/helper.c | 72 ++++++++++++++++++++++++++++++++++++++++++-------- 1 files changed, 60 insertions(+), 12 deletions(-) diff --git a/target-arm/helper.c b/target-arm/helper.c index 7f63a28..1ab5ae9 100644 --- a/target-arm/helper.c +++ b/target-arm/helper.c @@ -2687,13 +2687,53 @@ float32 HELPER(rsqrts_f32)(float32 a, float32 b, CPUState *env) /* NEON helpers. */ -/* TODO: The architecture specifies the value that the estimate functions - should return. We return the exact reciprocal/root instead. */ -float32 HELPER(recpe_f32)(float32 a, CPUState *env) +/* The algorithm that must be used to calculate the estimate + * is specified by the ARM ARM. + */ +static float64 recip_estimate(float64 a, CPUState *env) { float_status *s = &env->vfp.fp_status; - float32 one = int32_to_float32(1, s); - return float32_div(one, a, s); + float64 one = int64_to_float64(1, s); + /* q = (int)(a * 512.0) */ + float64 x512 = int64_to_float64(512, s); + float64 q = float64_mul(x512, a, s); + int64_t q_int = float64_to_int64_round_to_zero(q, s); + + /* r = 1.0 / (((double)q + 0.5) / 512.0) */ + q = int64_to_float64(q_int, s); + float64 half = float64_div(one, int64_to_float64(2, s), s); + q = float64_add(q, half, s); + q = float64_div(q, x512, s); + q = float64_div(one, q, s); + + /* s = (int)(256.0 * r + 0.5) */ + q = float64_mul(q, int64_to_float64(256, s), s); + q = float64_add(q, half, s); + q_int = float64_to_int64_round_to_zero(q, s); + + /* return (double)s / 256.0 */ + return float64_div(int64_to_float64(q_int, s), int64_to_float64(256, s), s); +} + +/* TODO: handle NaNs, zero and infinity as special input values. */ +float32 HELPER(recpe_f32)(float32 a, CPUState *env) +{ + float64 f64; + uint32_t val32; + + int result_exp; + + f64 = make_float64(((int64_t)0x3FE << 52) + | ((int64_t)(float32_val(a) & 0x7FFFFF) << 29)); + + result_exp = 253 - ((float32_val(a) & 0x7F800000) >> 23); + + f64 = recip_estimate(f64, env); + + val32 = (float32_val(a) & 0x80000000) + | ((result_exp & 0xFF) << 23) + | ((float64_val(f64) >> 29) & 0x7FFFFF); + return make_float32(val32); } float32 HELPER(rsqrte_f32)(float32 a, CPUState *env) @@ -2705,13 +2745,21 @@ float32 HELPER(rsqrte_f32)(float32 a, CPUState *env) uint32_t HELPER(recpe_u32)(uint32_t a, CPUState *env) { - float_status *s = &env->vfp.fp_status; - float32 tmp; - tmp = int32_to_float32(a, s); - tmp = float32_scalbn(tmp, -32, s); - tmp = helper_recpe_f32(tmp, env); - tmp = float32_scalbn(tmp, 31, s); - return float32_to_int32(tmp, s); + union { + int64_t i; + float64 f; + } dp_operand; + + if ((a & 0x80000000) == 0) { + return 0xFFFFFFFF; + } + + dp_operand.i = ((int64_t)0x3FE << 52) + | ((int64_t)(a & 0x7FFFFFFF) << 21); + + dp_operand.f = recip_estimate (dp_operand.f, env); + + return 0x80000000 | ((dp_operand.i >> 21) & 0x7FFFFFFF); } uint32_t HELPER(rsqrte_u32)(uint32_t a, CPUState *env)