From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 6189 invoked by alias); 7 Mar 2010 21:04:10 -0000 Received: (qmail 6176 invoked by uid 22791); 7 Mar 2010 21:04:09 -0000 X-SWARE-Spam-Status: No, hits=-1.8 required=5.0 tests=AWL,BAYES_00,SARE_MSGID_LONG40 X-Spam-Check-By: sourceware.org Received: from mail-wy0-f169.google.com (HELO mail-wy0-f169.google.com) (74.125.82.169) by sourceware.org (qpsmtpd/0.43rc1) with ESMTP; Sun, 07 Mar 2010 21:04:05 +0000 Received: by wyb29 with SMTP id 29so2812195wyb.0 for ; Sun, 07 Mar 2010 13:04:02 -0800 (PST) MIME-Version: 1.0 Received: by 10.216.176.212 with SMTP id b62mr2093565wem.179.1267995842466; Sun, 07 Mar 2010 13:04:02 -0800 (PST) In-Reply-To: <201003072028.o27KSrsI016094@glazunov.sibelius.xs4all.nl> References: <20100304180219.GA10826@intel.com> <20100306221634.GA21133@intel.com> <201003071416.o27EGPfu007140@glazunov.sibelius.xs4all.nl> <6dc9ffc81003070637q3e554ba4n2ee6053c2fd24511@mail.gmail.com> <6dc9ffc81003070831yf923b9bj83da56cb9c83a751@mail.gmail.com> <6dc9ffc81003070840x649dcc23qa088fddd69df7e54@mail.gmail.com> <201003072028.o27KSrsI016094@glazunov.sibelius.xs4all.nl> Date: Sun, 07 Mar 2010 21:04:00 -0000 Message-ID: <6dc9ffc81003071304m1b858d6fp3ca2b80364d4a473@mail.gmail.com> Subject: Re: PATCH: 0/6 [2nd try]: Add AVX support From: "H.J. Lu" To: Mark Kettenis Cc: gdb-patches@sourceware.org Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable X-IsSubscribed: yes Mailing-List: contact gdb-patches-help@sourceware.org; run by ezmlm Precedence: bulk List-Id: List-Subscribe: List-Archive: List-Post: List-Help: , Sender: gdb-patches-owner@sourceware.org X-SW-Source: 2010-03/txt/msg00282.txt.bz2 On Sun, Mar 7, 2010 at 12:28 PM, Mark Kettenis wr= ote: >> Date: Sun, 7 Mar 2010 08:40:10 -0800 >> From: "H.J. Lu" >> >> On Sun, Mar 7, 2010 at 8:31 AM, H.J. Lu wrote: >> > On Sun, Mar 7, 2010 at 6:37 AM, H.J. Lu wrote: >> >> On Sun, Mar 7, 2010 at 6:16 AM, Mark Kettenis wrote: >> >>>> Date: Sat, 6 Mar 2010 14:16:34 -0800 >> >>>> From: "H.J. Lu" >> >>>> >> >>>> AVX registers are saved and restored via the XSAVE extended state. = The >> >>>> extended control register 0 (the XFEATURE_ENABLED_MASK register), X= CR0, >> >>>> is used to determine which states, x87, SSE, AVX, ... are supported >> >>>> in the XSAVE extended state. =A0XCR0 can be read with the new "xget= bv" >> >>>> instruction. =A0The xstate_bv field at byte offset 512 in the XSAVE >> >>>> extended state indicates what states the current process is in. If >> >>>> the feature bit is cleared, the corresponding registers should be r= ead as >> >>>> 0. If we update a register, we should set the corresponding feature >> >>>> bit in the xstate_bv field. >> >>>> >> >>>> We added PTRACE_GETREGSET and PTRACE_SETREGSET to Linux kernel to >> >>>> fetch and store AVX registers with ptrace. Linux kernel also stores >> >>>> XCR0 at the first 8 bytes of the software usable bytes, starting at >> >>>> byte offset 464. >> >>>> >> >>>> There are total 6 patches to add AVX support for Linux. =A0They sup= port: >> >>>> >> >>>> 1. The upper 128bit YMM registers are added for AVX support. The up= per >> >>>> 128bit YMM registers are hidden from users. Gdb combines XMM regist= er, >> >>>> %xmmX, with 128bit YMM register, %ymmXh, and present the whole 256b= it >> >>>> YMM register, %ymmX, as pseudo register to users. >> >>>> 2. Backward compatible. If AVX isn't supported, SSE will be used. >> >>>> 3. Forward compatible. If new state beyond AVX is supported in >> >>>> the XSAVE extended state, only AVX state will be used. >> >>>> 4. Remote gdb protocol extension. GDB will send "x86=3Dxml" in qSup= ported >> >>>> request packet to indicate that GDB supports x86 XML target descipt= ion. >> >>>> The gdb stub will send x86 XML target desciption if it sees "x86=3D= xml" >> >>>> in qSupported request packet. >> >>>> >> >>>> One advantage of this approach is YMM registers are actually stored= as >> >>>> XMM registers and upper YMM registers in the XSAVE extended state. = =A0It >> >>>> is easy and natural to access them as %xmmX and %ymmXh internally. = =A0We >> >>>> just need to hide %ymmXh from users. >> >>>> >> >>>> To support AVX on other OSes, the following changes are needed: >> >>>> >> >>>> 1. Kernel support to get/set the XSAVE extended state. >> >>>> 2. Handle 8/16 upper YMM registers. >> >>>> 3. Provide target to_read_description to return SSE or AVX target >> >>>> description. >> >>>> 4. Update gdbarch_core_read_description to return SSE or AVX target >> >>>> description based on contents of core dump. >> >>> >> >>> Wait; there is something important missing here. =A0How are the new = %ymm >> >>> registers referred to in debug info? =A0The AMD64 SysV psABI defines= the >> >>> DWARF register Number Mapping, but the 0.99.4 draft copy I have >> >>> doesn't define any mappings for the %ymm registers. =A0What mapping = does >> >>> GCC use? >> >>> >> >> >> >> In gcc, XMM and YMM registers have the same register number. They map >> >> to be the same DWARF register with different sizes. =A0Since XMM and = YMM >> >> registers are caller-saved, they don't appear in unwind info. So, the= same >> >> DWARF register with different sizes for XMM/YMM registers isn't a pro= blem. >> >> >> >> >> > >> > Yes, there is a problem. amd64_dwarf_reg_to_regnum needs to map 256bit >> > register to YMM. How do other arches solve this? > > A possible solution here is to simply always map %xmmN onto %ymmN if > the target supports AVX. =A0This'll make "info address" say that a > 128-bit vector variable lives in %ymmN instead of %xmmN, but that > wouldn't really be a lie, would it? =A0The only problem with this > approach is that it will break cases where the debug info refers to a > variable living in consecutive %xmm (128-bit) registers using (only) > the register number of the first %xmm register. =A0This shouldn't happen > with DWARF2, but might happen with older debug formats like stabs. > Not necessarily a serious probem; at least nothing I care about still > uses stabs. > > Should be a simple matter of returning the %ymm pseudo register number > if tdep->num_ymm_regs > 0. Yes, it works. Thanks. --=20 H.J.