From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-ej1-x62d.google.com (mail-ej1-x62d.google.com [IPv6:2a00:1450:4864:20::62d]) by sourceware.org (Postfix) with ESMTPS id B9AF43858C74 for ; Thu, 8 Sep 2022 19:03:26 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.1 sourceware.org B9AF43858C74 Authentication-Results: sourceware.org; dmarc=pass (p=none dis=none) header.from=gmail.com Authentication-Results: sourceware.org; spf=pass smtp.mailfrom=gmail.com Received: by mail-ej1-x62d.google.com with SMTP id v16so578655ejr.10 for ; Thu, 08 Sep 2022 12:03:26 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20210112; h=message-id:from:cc:to:subject:content-transfer-encoding :mime-version:references:in-reply-to:user-agent:date:from:to:cc :subject:date; bh=fke9TWyv2STCi7AZou5gLlr/hi/nKrzIUV7lvLfWy/s=; b=BE3ZylS5NupfNU2Mr7JrcWDWwRt7h6LossGnM1OofEgZYiqDAi+XVgrfoAwThXO6pd MbNhiMyrlFQ9yeVU2uQkcNx82HwZvvzMgZiysqVNtrFj/P1h46QBxMNDk1jrikPekSeH K+4KKSrXt7qFcIk4m3JKsJeOVeKjaZSl9pgUWZeQDdVgIS4gZVRXo69awOlJBObPZuIk jDJpzgygffQ8TB2KhA7DAJ6jvPYYo2P2Okru8vOpS0hrbKcL5Eyq+LXDAxIlMvQu0BJY Q20peNIxchSuk7rvfViRm10jEQxVa3IG+eCu3phkYeXfnLhKem0EyZLWXYNdwbi7Qc+a rj3w== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=message-id:from:cc:to:subject:content-transfer-encoding :mime-version:references:in-reply-to:user-agent:date :x-gm-message-state:from:to:cc:subject:date; bh=fke9TWyv2STCi7AZou5gLlr/hi/nKrzIUV7lvLfWy/s=; b=8E3icWGz85dQ0UcRipMcHj+9AWSxXyrXLHh6lnmXx1UnXSIcMSDur+N3Mp0tVgsmZA QsEIPn5M6vqmkjxg0W/eY/gHgdumYTwQ+4aTM1/AmVUncWf9adRlUFRhjB+I52UiegbL aYmzFPgIsqwD2qYnr3I3wKsDKFMqe81xb2Nghk2CUMo80ax/kbVW4YfCKYhf89v+I8kX wPbxgXI5gr0agh5Rl1juHnTYF7XKrd2flzWb8uk6H7dxACXjVDSqhu0J0qxjLZePJaQO Oj1fKQM+YxOp46JzjTMPO0eWpeFyMq0g7SUzKPkIIAFm9MLSzxKpM4tiSkooIq6N7ibe xAXg== X-Gm-Message-State: ACgBeo185MYpzBQw5uGyy390DOq9ImGYE4paztuhnG5jsBzYGnhewM2b rfJYYkGCOSlPqItmh6j4sq8= X-Google-Smtp-Source: AA6agR6sTQpTdU+Q6/0DlKlwlBc4FIN15+19shgwbPU81kwseKSt1DNa6Ah78rhaDdJ7+P23cHy7Mw== X-Received: by 2002:a17:907:a06b:b0:73d:dde9:75a7 with SMTP id ia11-20020a170907a06b00b0073ddde975a7mr7231812ejc.52.1662663805287; Thu, 08 Sep 2022 12:03:25 -0700 (PDT) Received: from [192.168.1.105] (92.40.182.234.threembb.co.uk. [92.40.182.234]) by smtp.gmail.com with ESMTPSA id ky2-20020a170907778200b007794a742094sm257461ejc.111.2022.09.08.12.03.24 (version=TLS1_2 cipher=ECDHE-ECDSA-AES128-GCM-SHA256 bits=128/128); Thu, 08 Sep 2022 12:03:24 -0700 (PDT) Date: Thu, 08 Sep 2022 20:03:19 +0100 User-Agent: XryptoMail for Android In-Reply-To: References: <20220908182530.118842-1-ghostmansd@gmail.com> MIME-Version: 1.0 Content-Type: multipart/alternative; boundary=----21ZR6WVA6XDC5RW3Y6QUQQ9UASNA0E Content-Transfer-Encoding: 7bit Subject: Re: [PATCH] ppc/svp64: support svshape2 instruction To: Dmitry Selyutin ,binutils@sourceware.org CC: Alan Modra From: lkcl Message-ID: X-Spam-Status: No, score=2.3 required=5.0 tests=BAYES_00,DKIM_SIGNED,DKIM_VALID,DKIM_VALID_AU,DKIM_VALID_EF,FREEMAIL_FROM,HTML_MESSAGE,RCVD_IN_ABUSEAT,RCVD_IN_BARRACUDACENTRAL,RCVD_IN_DNSWL_NONE,SPF_HELO_NONE,SPF_PASS,TXREP,T_SCC_BODY_TEXT_LINE autolearn=no autolearn_force=no version=3.4.6 X-Spam-Level: ** X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on server2.sourceware.org List-Id: ------21ZR6WVA6XDC5RW3Y6QUQQ9UASNA0E Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable On September 8, 2022 7:34:32 PM GMT+01:00, Dmitry Selyutin wrote: > This is a tricky part. svshape2 shares some of its bits with svshape; > we reserve 0b1000 and 0b1001 values from svshape for svshape2. (background): in hardware all 16 combinations are sent to the exact same unit. the slightly different Form (SVM2 vs SVM because the opcode args are different bitwidths) is for the convenience of the assembly writer. (further background): svshape is insanely powerful, the sort of thing i revered in supercomputers from the 90s. it provides Matrix "Structure Packing" schedules, DCT/FFT, Parallel Reduction, it's pretty mental. all in-place: no more loop-unrolling, no more transpose copying of regs. l. ------21ZR6WVA6XDC5RW3Y6QUQQ9UASNA0E--