From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mail-wm1-f51.google.com (mail-wm1-f51.google.com [209.85.128.51]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 6A002217F29 for ; Mon, 3 Mar 2025 22:42:20 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.128.51 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1741041742; cv=none; b=s2ODYPiqvGTDF46LqtCdMbgMjmD70c+NOOl8KBXVIHWZ58JpxabSDpF86DfzmwWcpEpkTUTylGwACKhwGvZjLXiyagyPiTVsRJjHrhvS5P1RHPRfEPtxntyNdkecvSxqHtiG2X11czhAiT7iJ34McecNoABloIRq7EnwwhyzfLw= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1741041742; c=relaxed/simple; bh=3WcjziBYJ7UhydDwwC1yT484QDKIbhFIegMuTUZDvaY=; h=Date:From:To:Cc:Subject:Message-ID:In-Reply-To:References: MIME-Version:Content-Type; b=NgwFewlFVIAMmfGeXcHYgtywl9vl1a8PLznN9HLSmzSxwIE4+PFoOchz61yhAUJQIoAig/7PunSqEWM0MJ2IYKbVDGvMtxUWxFZpYll2ZsQGtVNS0PS/LnNg/0VQ3PByUHqOV9GHBiEVg1nDG8LRDL6RnrIoCwncjbACfxmPRoo= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com; spf=pass smtp.mailfrom=gmail.com; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b=acJpOq+q; arc=none smtp.client-ip=209.85.128.51 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=gmail.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b="acJpOq+q" Received: by mail-wm1-f51.google.com with SMTP id 5b1f17b1804b1-4398e3dfc66so45041135e9.0 for ; Mon, 03 Mar 2025 14:42:20 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20230601; t=1741041739; x=1741646539; darn=lists.linux.dev; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:subject:cc:to:from:date:from:to:cc:subject:date :message-id:reply-to; bh=IXvjaZuB8q7nUvxhvluaSegqkirhQmglnHumuP+7VuI=; b=acJpOq+qTs0HzYA4Mhln4QzerTpA0MCCXOEA70tiYYKkamcDHUQv6zEA9njFedQN9G TN4nbwcQ9xuiQJHCzbj5pjKwXvx9jJ7scGuScd9FtOWAtyEFiGbgbTmqf4b+kJAiZFdm q6q5y3TSXgoccgEPlOJym3DKdloM5DI+ZKzZjflEn4J8RLByxxBxgRknOM0ZO1rpL19p 1WH6KRtuJPxdl9ekqkO9OrlqpAmFH9YR3fKMpib5U/KQsYfvmBBI9ijczS1qK2W8mCmD GZxboM0phf2A7JIcVbfvSuXGQmaB44xpC1NUyy70e8pz/wQHf8sqKXKmHjEUR5kq+Si5 Pntw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1741041739; x=1741646539; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:subject:cc:to:from:date:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=IXvjaZuB8q7nUvxhvluaSegqkirhQmglnHumuP+7VuI=; b=tdv7Fmr713e1jtV+DmZciXxizJQhjeDNMpdSMI9vChhkZ2CfghkNWtUa9tTHo2AWA3 FIMkhTF9RVJHYgOZt+XYCu8FIHoZNeuEnXzv+3hfpiRh9J8ZYFV3eYZuZk3wNgzq3rhi VselRnQT8y9ziJT/RaBz3tDeMXTtmmKc8mR5O3wG2hhptOeWKi3HoOvKLUP4+Z5mAcXZ Xqip17dPmpFfIa0FtiB1nFzzHsb3wo91RZMnLxVlF4xercjnqjcQ2x2Bv6NqAKY8ZbYO UcaMpRelPu7u/bvzbqZ73GDUh9RGzNjCzs1FG9DFHTkbMj/YAp5Dn3xp/djRK6v3Ay6J K/3g== X-Forwarded-Encrypted: i=1; AJvYcCVib7l8f0uIqYQBmKXsH8k7D87bqkonhyfyxdD0aPZlw1O+BTdpYIscV+SkzWWhqDd0lSWT@lists.linux.dev X-Gm-Message-State: AOJu0YzGVVVCt+t/91ZNMpwk9AAqnHZchz9TRzTgwuvRMjfdt0a2k/Yp i6lKQfpbz2EekmtlBxfjqCq4mQEk+8TJSdWGG7YrxhdpJccixB15 X-Gm-Gg: ASbGncs+NB1zN7jDQi5yA4Zzc/5bnHRSsiSJEOKa29JONd+IvzY3oZIazuHCgurQTHE C4kRO+X12Qq/O6sfK6UX8ow9cYe8xA2giJMBmXJow63mOUO77oaA79dFY2DtVM+asUNbSwNKUXd uQwm8vOmwXiv3danI2ZSnmW8fRz4zDA14yhA3n+oMphmes3hxPw8TP9Hro0MdS8iIZ7yKdARgcd ab5tsxWdmvFSNsZy7Ayfuf2d8IbT3mDsJ3QUxCKNaBwCpJ0WQ5TxOaGYgPtTdj5wMwrozj/fIIR 94yiw/B2bYtF79/pLbovZIjyTRkR6LHOS8E7qI7IK/3i456MGO21JpSE/Pn/zLoxL9iJyfjfSpy N+KXatqs= X-Google-Smtp-Source: AGHT+IGz/4MMeNxI6FkfVAP1gBhWfV0TLINClFzpnGmKzbqTXvswWzt9UC98eYl7tiFXTNCznFca4g== X-Received: by 2002:a05:600c:4f51:b0:439:95b9:91fc with SMTP id 5b1f17b1804b1-43ba83f922cmr125458295e9.12.1741041738353; Mon, 03 Mar 2025 14:42:18 -0800 (PST) Received: from pumpkin (82-69-66-36.dsl.in-addr.zen.co.uk. [82.69.66.36]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-390e479609asm15518627f8f.2.2025.03.03.14.42.17 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Mon, 03 Mar 2025 14:42:17 -0800 (PST) Date: Mon, 3 Mar 2025 22:42:16 +0000 From: David Laight To: Bill Wendling Cc: Thomas Gleixner , Ingo Molnar , Borislav Petkov , Dave Hansen , "maintainer:X86 ARCHITECTURE (32-BIT AND 64-BIT)" , "H. Peter Anvin" , Eric Biggers , Ard Biesheuvel , Nathan Chancellor , Nick Desaulniers , Justin Stitt , LKML , linux-crypto@vger.kernel.org, clang-built-linux Subject: Re: [PATCH v2] x86/crc32: use builtins to improve code generation Message-ID: <20250303224216.30431b1d@pumpkin> In-Reply-To: References: <20250303201509.32f6f062@pumpkin> X-Mailer: Claws Mail 4.1.1 (GTK 3.24.38; arm-unknown-linux-gnueabihf) Precedence: bulk X-Mailing-List: llvm@lists.linux.dev List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable On Mon, 3 Mar 2025 12:27:21 -0800 Bill Wendling wrote: > On Mon, Mar 3, 2025 at 12:15=E2=80=AFPM David Laight > wrote: > > On Thu, 27 Feb 2025 15:47:03 -0800 > > Bill Wendling wrote: > > =20 > > > For both gcc and clang, crc32 builtins generate better code than the > > > inline asm. GCC improves, removing unneeded "mov" instructions. Clang > > > does the same and unrolls the loops. GCC has no changes on i386, but > > > Clang's code generation is vastly improved, due to Clang's "rm" > > > constraint issue. > > > > > > The number of cycles improved by ~0.1% for GCC and ~1% for Clang, whi= ch > > > is expected because of the "rm" issue. However, Clang's performance is > > > better than GCC's by ~1.5%, most likely due to loop unrolling. =20 > > > > How much does it unroll? > > How much you need depends on the latency of the crc32 instruction. > > The copy of Agner's tables I have gives it a latency of 3 on > > pretty much everything. > > If you can only do one chained crc instruction every three clocks > > it is hard to see how unrolling the loop will help. > > Intel cpu (since sandy bridge) will run a two clock loop. > > With three clocks to play with it should be easy (even for a compiler) > > to generate a loop with no extra clock stalls. > > > > Clearly if Clang decides to copy arguments to the stack an extra time > > that will kill things. But in this case you want the "m" constraint > > to directly read from the buffer (with a (reg,reg,8) addressing mode). > > =20 > Below is what Clang generates with the builtins. From what Eric said, > this code is only run for sizes <=3D 512 bytes? So maybe it's not super > important to micro-optimize this. I apologize, but my ability to > measure clock loops for x86 code isn't great. (I'm sure I lack the > requisite benchmarks, etc.) Jeepers - that is trashing the I-cache. Not to mention all the conditional branches at the bottom. Consider the basic loop: 1: crc32q (%rcx), %rbx addq $8, %rcx cmp %rcx, %rdx jne 1b The crc32 has latency 3 so it must take at least 3 clocks. Even naively the addq can be issued in the same clock as the crc32 and the cmp and jne in the following ones. Since the jne is predicted taken, the addq can be assumed to execute in the same clock as the jne. (The cmp+jne might also get merged into a single u-op) (I've done this with adc (for IP checksum), with two adc the loop takes two clocks even with the extra memory reads.) So that loop is likely to run limited by the three clock latency of crc32. Even the memory reads will happen with all the crc32 just waiting for the previous crc32 to finish. You can take an instruction out of the loop: 1: crc32q (%rcx,%rdx), %rbx addq $8, %rdx jne 1b but that may not be necessary, and (IIRC) gcc doesn't like letting you generate it. For buffers that aren't multiples of 8 bytes 'remember' that the crc of a byte depends on how far it is from the end of the buffer, and that initial zero bytes have no effect. So (provided the buffer is 8+ bytes long) read the first 8 bytes, shift right by the number of bytes needed to make the rest of the buffer a multip= le or 8 bytes (the same as reading from across the start of the buffer and mas= king the low bytes) then treat exactly the same as a buffer that is a multiple of 8 bytes long. Don't worry about misaligned reads, you lose less than one clock per cache line (that is with adc doing a read every clock). Actually measuring the performance is hard. You can use rdtsc because the clock speed will change when the cpu gets bus= y. There is a 'performance counter' that is actual clocks. While you can use the library functions to set it up, you need to just read= the register - the library overhead it too big. You also need the odd lfence. Having done that, and provided the buffer is in the L1 d-cache you can meas= ure the loop time in clocks and compare against the expected value. Once you've got 3 clocks per crc32 instruction it won't get any better, which is why the 'fast' code for big buffers does crc of 3+ buffers sections in parallel. David >=20 > -bw >=20 > .LBB1_9: # =3D>This Inner Loop Header: Dep= th=3D1 > movl %ebx, %ebx > crc32q (%rcx), %rbx > addq $8, %rcx > incq %rdi > cmpq %rdi, %rsi > jne .LBB1_9 > # %bb.10: > subq %rdi, %rax > jmp .LBB1_11 > .LBB1_7: > movq %r14, %rcx > .LBB1_11: > movq %r15, %rsi > andq $-8, %rsi > cmpq $7, %rdx > jb .LBB1_14 > # %bb.12: > xorl %edx, %edx > .LBB1_13: # =3D>This Inner Loop Header: Dep= th=3D1 > movl %ebx, %ebx > crc32q (%rcx,%rdx,8), %rbx > crc32q 8(%rcx,%rdx,8), %rbx > crc32q 16(%rcx,%rdx,8), %rbx > crc32q 24(%rcx,%rdx,8), %rbx > crc32q 32(%rcx,%rdx,8), %rbx > crc32q 40(%rcx,%rdx,8), %rbx > crc32q 48(%rcx,%rdx,8), %rbx > crc32q 56(%rcx,%rdx,8), %rbx > addq $8, %rdx > cmpq %rdx, %rax > jne .LBB1_13 > .LBB1_14: > addq %rsi, %r14 > .LBB1_15: > andq $7, %r15 > je .LBB1_23 > # %bb.16: > crc32b (%r14), %ebx > cmpl $1, %r15d > je .LBB1_23 > # %bb.17: > crc32b 1(%r14), %ebx > cmpl $2, %r15d > je .LBB1_23 > # %bb.18: > crc32b 2(%r14), %ebx > cmpl $3, %r15d > je .LBB1_23 > # %bb.19: > crc32b 3(%r14), %ebx > cmpl $4, %r15d > je .LBB1_23 > # %bb.20: > crc32b 4(%r14), %ebx > cmpl $5, %r15d > je .LBB1_23 > # %bb.21: > crc32b 5(%r14), %ebx > cmpl $6, %r15d > je .LBB1_23 > # %bb.22: > crc32b 6(%r14), %ebx > .LBB1_23: > movl %ebx, %eax > .LBB1_24: