From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mailman by lists.gnu.org with tmda-scanned (Exim 4.43) id 1FshBc-0005tM-Nb for qemu-devel@nongnu.org; Tue, 20 Jun 2006 10:26:36 -0400 Received: from exim by lists.gnu.org with spam-scanned (Exim 4.43) id 1FshBb-0005pw-2S for qemu-devel@nongnu.org; Tue, 20 Jun 2006 10:26:36 -0400 Received: from [199.232.76.173] (helo=monty-python.gnu.org) by lists.gnu.org with esmtp (Exim 4.43) id 1FshBa-0005pQ-OJ for qemu-devel@nongnu.org; Tue, 20 Jun 2006 10:26:34 -0400 Received: from [217.10.32.16] (helo=comtv.ru) by monty-python.gnu.org with esmtp (Exim 4.52) id 1FshM8-0008Qj-4f for qemu-devel@nongnu.org; Tue, 20 Jun 2006 10:37:28 -0400 Received: from av1474.oops ([10.0.66.9] verified) by comtv.ru (CommuniGate Pro SMTP 4.1.8) with ESMTP id 157234130 for qemu-devel@nongnu.org; Tue, 20 Jun 2006 18:26:33 +0400 Date: Tue, 20 Jun 2006 18:26:50 +0400 (MSD) From: malc Subject: Re: [Qemu-devel] cvttps2dq, movdq2q, movq2dq incorrect behaviour In-Reply-To: <200606201248.36106.jseward@acm.org> Message-ID: References: <200606201154.40985.jseward@acm.org> <200606201248.36106.jseward@acm.org> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed Reply-To: qemu-devel@nongnu.org List-Id: qemu-devel.nongnu.org List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: qemu-devel@nongnu.org On Tue, 20 Jun 2006, Julian Seward wrote: >> As for cvttps2dq i ran it with interpreter which uses outdated(i.e. non >> soft-float) conversion routines and it passed, so my guess would be that >> this is float32_to_int32_round_to_zero vs (int32_t) cast issue. > > I had a feeling this is a garbage-in-memory (or regs, or somewhere) > problem. Reason is that the wrong results kept changing as I cut > the full test program down to just the small one I posted. Can you > try on a vanilla build of i386-softmmu from cvs? soft-float was a red herring, translate.c is at fault here (interpreter does not use it, hence behaved correctly) translate.c:3009 if (b1 >= 2 && ((b >= 0x50 && b <= 0x5f) || b == 0xc2)) { /* specific case for SSE single instructions */ if (b1 == 2) { /* 32 bit access */ gen_op_ld_T0_A0[OT_LONG + s->mem_index](); gen_op_movl_env_T0(offsetof(CPUX86State,xmm_t0.XMM_L(0))); } else { /* 64 bit access */ gen_ldq_env_A0[s->mem_index >> 2](offsetof(CPUX86State,xmm_t0.XMM_D(0))); } } else { gen_ldo_env_A0[s->mem_index >> 2](op2_offset); } cvttps2dq is 0x5b(b=0x5b) with repn prefix (b1=2) the above code is optimized a bit more than it should have been, as it loads only 4 bytes into xmm_t0 instead of 16. -- mailto:malc@pulsesoft.com