From patchwork Wed Apr 13 23:11:10 2011 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Aurelien Jarno X-Patchwork-Id: 91142 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Received: from lists.gnu.org (lists.gnu.org [140.186.70.17]) (using TLSv1 with cipher AES256-SHA (256/256 bits)) (Client did not present a certificate) by ozlabs.org (Postfix) with ESMTPS id B071EB6F0C for ; Thu, 14 Apr 2011 09:19:13 +1000 (EST) Received: from localhost ([::1]:38972 helo=lists2.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1QA9L5-0006xP-0Y for incoming@patchwork.ozlabs.org; Wed, 13 Apr 2011 19:19:11 -0400 Received: from eggs.gnu.org ([140.186.70.92]:57212) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1QA9Dk-0002XH-Ao for qemu-devel@nongnu.org; Wed, 13 Apr 2011 19:11:37 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1QA9Dh-0005FE-91 for qemu-devel@nongnu.org; Wed, 13 Apr 2011 19:11:36 -0400 Received: from hall.aurel32.net ([88.191.126.93]:56719) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1QA9Dg-0004yh-V0 for qemu-devel@nongnu.org; Wed, 13 Apr 2011 19:11:33 -0400 Received: from [2001:470:d4ed:0:5e26:aff:fe2b:6f5b] (helo=volta.aurel32.net) by hall.aurel32.net with esmtpsa (TLS1.0:RSA_AES_256_CBC_SHA1:32) (Exim 4.72) (envelope-from ) id 1QA9DX-0001i4-Lv; Thu, 14 Apr 2011 01:11:23 +0200 Received: from aurel32 by volta.aurel32.net with local (Exim 4.72) (envelope-from ) id 1QA9DR-00017t-G1; Thu, 14 Apr 2011 01:11:17 +0200 From: Aurelien Jarno To: qemu-devel@nongnu.org Date: Thu, 14 Apr 2011 01:11:10 +0200 Message-Id: <1302736274-2908-16-git-send-email-aurelien@aurel32.net> X-Mailer: git-send-email 1.7.2.3 In-Reply-To: <1302736274-2908-1-git-send-email-aurelien@aurel32.net> References: <1302736274-2908-1-git-send-email-aurelien@aurel32.net> X-detected-operating-system: by eggs.gnu.org: GNU/Linux 2.6 (newer, 3) X-Received-From: 88.191.126.93 Cc: Nathan Froyd , Alexander Graf , Aurelien Jarno Subject: [Qemu-devel] [PATCH v2 15/19] target-ppc: fix SPE comparison functions X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org Sender: qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org efstst*() functions are fast SPE funtions which do not take into account special values (infinites, NaN, etc.), while efscmp*() functions are IEEE754 compliant. Given that float32_*() functions are IEEE754 compliant, the efscmp*() functions are correctly implemented, while efstst*() are not. This patch reverse the implementation of this two groups of functions and fix the comments. It also use float32_eq() instead of float32_eq_quiet() as qNaNs should not be ignored. Cc: Alexander Graf Cc: Nathan Froyd Signed-off-by: Aurelien Jarno --- target-ppc/op_helper.c | 26 +++++++++++++------------- 1 files changed, 13 insertions(+), 13 deletions(-) v2: fix calls to efscmp*, removing an infinite loop diff --git a/target-ppc/op_helper.c b/target-ppc/op_helper.c index f645f57..9aa108e 100644 --- a/target-ppc/op_helper.c +++ b/target-ppc/op_helper.c @@ -3331,7 +3331,7 @@ HELPER_SPE_VECTOR_ARITH(fsmul); HELPER_SPE_VECTOR_ARITH(fsdiv); /* Single-precision floating-point comparisons */ -static inline uint32_t efststlt(uint32_t op1, uint32_t op2) +static inline uint32_t efscmplt(uint32_t op1, uint32_t op2) { CPU_FloatU u1, u2; u1.l = op1; @@ -3339,7 +3339,7 @@ static inline uint32_t efststlt(uint32_t op1, uint32_t op2) return float32_lt(u1.f, u2.f, &env->vec_status) ? 4 : 0; } -static inline uint32_t efststgt(uint32_t op1, uint32_t op2) +static inline uint32_t efscmpgt(uint32_t op1, uint32_t op2) { CPU_FloatU u1, u2; u1.l = op1; @@ -3347,30 +3347,30 @@ static inline uint32_t efststgt(uint32_t op1, uint32_t op2) return float32_le(u1.f, u2.f, &env->vec_status) ? 0 : 4; } -static inline uint32_t efststeq(uint32_t op1, uint32_t op2) +static inline uint32_t efscmpeq(uint32_t op1, uint32_t op2) { CPU_FloatU u1, u2; u1.l = op1; u2.l = op2; - return float32_eq_quiet(u1.f, u2.f, &env->vec_status) ? 4 : 0; + return float32_eq(u1.f, u2.f, &env->vec_status) ? 4 : 0; } -static inline uint32_t efscmplt(uint32_t op1, uint32_t op2) +static inline uint32_t efststlt(uint32_t op1, uint32_t op2) { - /* XXX: TODO: test special values (NaN, infinites, ...) */ - return efststlt(op1, op2); + /* XXX: TODO: ignore special values (NaN, infinites, ...) */ + return efscmplt(op1, op2); } -static inline uint32_t efscmpgt(uint32_t op1, uint32_t op2) +static inline uint32_t efststgt(uint32_t op1, uint32_t op2) { - /* XXX: TODO: test special values (NaN, infinites, ...) */ - return efststgt(op1, op2); + /* XXX: TODO: ignore special values (NaN, infinites, ...) */ + return efscmpgt(op1, op2); } -static inline uint32_t efscmpeq(uint32_t op1, uint32_t op2) +static inline uint32_t efststeq(uint32_t op1, uint32_t op2) { - /* XXX: TODO: test special values (NaN, infinites, ...) */ - return efststeq(op1, op2); + /* XXX: TODO: ignore special values (NaN, infinites, ...) */ + return efscmpeq(op1, op2); } #define HELPER_SINGLE_SPE_CMP(name) \