From patchwork Thu May 5 18:35:35 2011 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 1364 Return-Path: Delivered-To: unknown Received: from imap.gmail.com (74.125.159.109) by localhost6.localdomain6 with IMAP4-SSL; 08 Jun 2011 14:51:25 -0000 Delivered-To: patches@linaro.org Received: by 10.224.184.145 with SMTP id ck17cs110656qab; Thu, 5 May 2011 11:35:38 -0700 (PDT) Received: by 10.227.98.9 with SMTP id o9mr2858849wbn.25.1304620537490; Thu, 05 May 2011 11:35:37 -0700 (PDT) Received: from mnementh.archaic.org.uk (mnementh.archaic.org.uk [81.2.115.146]) by mx.google.com with ESMTPS id m10si6740929wbm.127.2011.05.05.11.35.36 (version=TLSv1/SSLv3 cipher=OTHER); Thu, 05 May 2011 11:35:37 -0700 (PDT) Received-SPF: pass (google.com: best guess record for domain of pm215@archaic.org.uk designates 81.2.115.146 as permitted sender) client-ip=81.2.115.146; Authentication-Results: mx.google.com; spf=pass (google.com: best guess record for domain of pm215@archaic.org.uk designates 81.2.115.146 as permitted sender) smtp.mail=pm215@archaic.org.uk Received: from pm215 by mnementh.archaic.org.uk with local (Exim 4.72) (envelope-from ) id 1QI3Oh-0007WK-40; Thu, 05 May 2011 19:35:35 +0100 From: Peter Maydell To: qemu-devel@nongnu.org Cc: patches@linaro.org Subject: [PATCH] target-arm: Fix VMLA, VMLS, VNMLS, VNMLA handling of NaNs Date: Thu, 5 May 2011 19:35:35 +0100 Message-Id: <1304620535-28885-1-git-send-email-peter.maydell@linaro.org> X-Mailer: git-send-email 1.7.2.5 Correct handling of NaNs for VFP VMLA, VMLS, VNMLS and VNMLA requires that we implement the set of negations and additions specified by the ARM ARM; plausible looking simplifications like turning (-A + B) into (B - A) or computing (A + B) rather than (B + A) result in selecting the wrong NaN or returning a NaN with the wrong sign bit. Signed-off-by: Peter Maydell --- target-arm/translate.c | 53 ++++++++++++++++++++++++++++++++++++----------- 1 files changed, 40 insertions(+), 13 deletions(-) diff --git a/target-arm/translate.c b/target-arm/translate.c index a1af436..3c38364 100644 --- a/target-arm/translate.c +++ b/target-arm/translate.c @@ -909,6 +909,26 @@ VFP_OP2(div) #undef VFP_OP2 +static inline void gen_vfp_F1_mul(int dp) +{ + /* Like gen_vfp_mul() but put result in F1 */ + if (dp) { + gen_helper_vfp_muld(cpu_F1d, cpu_F0d, cpu_F1d, cpu_env); + } else { + gen_helper_vfp_muls(cpu_F1s, cpu_F0s, cpu_F1s, cpu_env); + } +} + +static inline void gen_vfp_F1_neg(int dp) +{ + /* Like gen_vfp_neg() but put result in F1 */ + if (dp) { + gen_helper_vfp_negd(cpu_F1d, cpu_F0d); + } else { + gen_helper_vfp_negs(cpu_F1s, cpu_F0s); + } +} + static inline void gen_vfp_abs(int dp) { if (dp) @@ -3021,27 +3041,34 @@ static int disas_vfp_insn(CPUState * env, DisasContext *s, uint32_t insn) for (;;) { /* Perform the calculation. */ switch (op) { - case 0: /* mac: fd + (fn * fm) */ - gen_vfp_mul(dp); - gen_mov_F1_vreg(dp, rd); + case 0: /* VMLA: fd + (fn * fm) */ + /* Note that order of inputs to the add matters for NaNs */ + gen_vfp_F1_mul(dp); + gen_mov_F0_vreg(dp, rd); gen_vfp_add(dp); break; - case 1: /* nmac: fd - (fn * fm) */ + case 1: /* VMLS: fd + -(fn * fm) */ gen_vfp_mul(dp); - gen_vfp_neg(dp); - gen_mov_F1_vreg(dp, rd); + gen_vfp_F1_neg(dp); + gen_mov_F0_vreg(dp, rd); gen_vfp_add(dp); break; - case 2: /* msc: -fd + (fn * fm) */ - gen_vfp_mul(dp); - gen_mov_F1_vreg(dp, rd); - gen_vfp_sub(dp); + case 2: /* VNMLS: -fd + (fn * fm) */ + /* Note that it isn't valid to replace (-A + B) with (B - A) + * or similar plausible looking simplifications + * because this will give wrong results for NaNs. + */ + gen_vfp_F1_mul(dp); + gen_mov_F0_vreg(dp, rd); + gen_vfp_neg(dp); + gen_vfp_add(dp); break; - case 3: /* nmsc: -fd - (fn * fm) */ + case 3: /* VNMLA: -fd + -(fn * fm) */ gen_vfp_mul(dp); + gen_vfp_F1_neg(dp); + gen_mov_F0_vreg(dp, rd); gen_vfp_neg(dp); - gen_mov_F1_vreg(dp, rd); - gen_vfp_sub(dp); + gen_vfp_add(dp); break; case 4: /* mul: fn * fm */ gen_vfp_mul(dp);