From dev-return-107-archive-asf-public=cust-asf.ponee.io@tvm.apache.org Thu Apr 4 16:51:32 2019 Return-Path: X-Original-To: archive-asf-public@cust-asf.ponee.io Delivered-To: archive-asf-public@cust-asf.ponee.io Received: from mail.apache.org (hermes.apache.org [140.211.11.3]) by mx-eu-01.ponee.io (Postfix) with SMTP id 18C4418064C for ; Thu, 4 Apr 2019 18:51:31 +0200 (CEST) Received: (qmail 44650 invoked by uid 500); 4 Apr 2019 16:51:31 -0000 Mailing-List: contact dev-help@tvm.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: dev@tvm.apache.org Delivered-To: mailing list dev@tvm.apache.org Received: (qmail 44637 invoked by uid 99); 4 Apr 2019 16:51:30 -0000 Received: from pnap-us-west-generic-nat.apache.org (HELO spamd1-us-west.apache.org) (209.188.14.142) by apache.org (qpsmtpd/0.29) with ESMTP; Thu, 04 Apr 2019 16:51:30 +0000 Received: from localhost (localhost [127.0.0.1]) by spamd1-us-west.apache.org (ASF Mail Server at spamd1-us-west.apache.org) with ESMTP id 17015C869C for ; Thu, 4 Apr 2019 16:51:30 +0000 (UTC) X-Virus-Scanned: Debian amavisd-new at spamd1-us-west.apache.org X-Spam-Flag: NO X-Spam-Score: 0.9 X-Spam-Level: X-Spam-Status: No, score=0.9 tagged_above=-999 required=6.31 tests=[DKIMWL_WL_MED=-0.001, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, HEADER_FROM_DIFFERENT_DOMAINS=0.001, HTML_MESSAGE=2, MAILING_LIST_MULTI=-1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_PASS=-0.001, URIBL_BLOCKED=0.001] autolearn=disabled Authentication-Results: spamd1-us-west.apache.org (amavisd-new); dkim=pass (1024-bit key) header.d=discuss.tvm.ai header.b=B9EDMXm1; dkim=pass (1024-bit key) header.d=elasticemail.com header.b=gm+u+JJr Received: from mx1-lw-us.apache.org ([10.40.0.8]) by localhost (spamd1-us-west.apache.org [10.40.0.7]) (amavisd-new, port 10024) with ESMTP id iWZh8kgpgqdv for ; Thu, 4 Apr 2019 16:51:27 +0000 (UTC) Received: from mail-ed1-f44.google.com (mail-ed1-f44.google.com [209.85.208.44]) by mx1-lw-us.apache.org (ASF Mail Server at mx1-lw-us.apache.org) with ESMTPS id 713D361237 for ; Thu, 4 Apr 2019 16:51:27 +0000 (UTC) Received: by mail-ed1-f44.google.com with SMTP id m16so2837673edd.12 for ; Thu, 04 Apr 2019 09:51:27 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:delivered-to:dkim-signature:dkim-signature:from :date:subject:message-id:reply-to:sender:to:feedback-id:in-reply-to :references:list-unsubscribe:auto-submitted:precedence:list-id :list-archive:mime-version; bh=8Vxqxco1uz8FgaxtZmbJjZoCbNNBEtbd+wUWVVLtZ9Q=; b=OsOsUvJPGVXq7qoYmDmGlyvm/HQOe2sgt1L//cdiTnF3FxVl9kFpfZu8bCI9z8Z9om TXet5JuISx0z65BE3nOTnRqlzpBSJex2crf9aRe207M1v4CERUqOLgnFddv6+fYgbMXF AM3JKqteJfu6dUu67vpjOij0mefTJyES4sc0K97sHLiBA5rUEMClQNL2/J0P+MzK6tQ6 3bXPdZdpMANmPXdinUpPcCsj+C85jDgA0spOMepMJqNd7fZPvRa57wjV4vWZZ6Ai5JWl jqimHaICa49ThKRFKrwjlK4I9hAVgTPsROY7wqJ0OVqDVbswF66tkbDcGN3foVCZH/11 SW/w== X-Gm-Message-State: APjAAAV4BoDs9YamupYx6CAZxk8VgogqzcZDMWLnw+OsGvGbAhsOp+9k Hu+5NESnVcFNkKvRPKKrW/O5AD4sMhfuQSONKH5TcuyHcPhxPRk= X-Received: by 2002:a50:b309:: with SMTP id q9mr4470798edd.91.1554396686234; Thu, 04 Apr 2019 09:51:26 -0700 (PDT) X-Forwarded-To: dev@tvm.apache.org X-Forwarded-For: tvm.archiver@gmail.com dev@tvm.apache.org Delivered-To: tvm.archiver@gmail.com Received: by 2002:a50:cf4b:0:0:0:0:0 with SMTP id d11csp1820788edk; Thu, 4 Apr 2019 09:51:25 -0700 (PDT) X-Google-Smtp-Source: APXvYqwawUqBN/MU0omMJq/C7yjJG+sxlFzOcB1Ej43yMvAWTDwM9O0fTvpQKhs0gTq+qt6sYiM+ X-Received: by 2002:adf:b6a4:: with SMTP id j36mr4764561wre.55.1554396685009; Thu, 04 Apr 2019 09:51:25 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1554396685; cv=none; d=google.com; s=arc-20160816; b=S77SichEB/kd7GbZCsWJlmvpufq619W7ydqeeNWRF7B/IqEauUk5Z23XtQqhA2/nXA uqyPSP12ooeHHUaXaJe1Ofey1sfGFC6R8DKVgk+7upEsTNgnGgpCqVXspBSPeqz/J84w GSgXFFR6WH6tldqdceQHOJpaSvAdLVOR79sxS3wUzrg3EXfm+RWpiBwQng0lqExLZOwu F9Wh45bnxQ3kW1/MN8T5WwkJkbCRAtLj9IgLLsX7SjLoqz0yTs2L1lEey+iUkgoxt/Wp R5aJwx1+OP1DnbE4fv+ZiLAqcUkujBQ5laSomycRyRkiRP79E5qSauQ0YjFEhWszcGcI UiHQ== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=mime-version:list-archive:list-id:precedence:auto-submitted :list-unsubscribe:references:in-reply-to:feedback-id:to:sender :reply-to:message-id:subject:date:from:dkim-signature:dkim-signature; bh=8Vxqxco1uz8FgaxtZmbJjZoCbNNBEtbd+wUWVVLtZ9Q=; b=02+4jtQlFjL/RzYEUSQVqo95uQ+RtoOfBwoy/nK2X4N2tcpGKLThgQshRo0szVtCrr 4+FgkIqxqn1GdaarCbwPsmsvX3SefQPhDlt1ckztNZWzfdIIZB/rJc2iRov4+5yvk67E wU9KZ4qn71HIcBUW7J981xdOe6xLXUar/X6BUg5m1UqZ/XrpZLjy3ibTqejYQVw8OTnG CFONMzoniXWiT65RFEJXP89IzkHc6qwfoeE6ltdAfzvvOkS+JAyknaLEeP0pwzROv16M FrwJosYKcDBwhUsspNEv3awkhnGpVgftUNyivmHRno0zFpCZ1uCCxrV8N7ysYWJ6f+te AOKw== ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@discuss.tvm.ai header.s=api header.b=B9EDMXm1; dkim=pass header.i=@elasticemail.com header.s=api header.b=gm+u+JJr; spf=neutral (google.com: 96.45.68.82 is neither permitted nor denied by best guess record for domain of noreply@discuss.tvm.ai) smtp.mailfrom=noreply@discuss.tvm.ai Received: from f82.mxout.mta4.net (f82.mxout.mta4.net. [96.45.68.82]) by mx.google.com with ESMTPS id v128si12411807wmf.99.2019.04.04.09.51.24 for (version=TLS1_2 cipher=ECDHE-RSA-AES128-SHA bits=128/128); Thu, 04 Apr 2019 09:51:24 -0700 (PDT) Received-SPF: neutral (google.com: 96.45.68.82 is neither permitted nor denied by best guess record for domain of noreply@discuss.tvm.ai) client-ip=96.45.68.82; Authentication-Results: mx.google.com; dkim=pass header.i=@discuss.tvm.ai header.s=api header.b=B9EDMXm1; dkim=pass header.i=@elasticemail.com header.s=api header.b=gm+u+JJr; spf=neutral (google.com: 96.45.68.82 is neither permitted nor denied by best guess record for domain of noreply@discuss.tvm.ai) smtp.mailfrom=noreply@discuss.tvm.ai DKIM-Signature: v=1; a=rsa-sha256; d=discuss.tvm.ai; s=api; c=relaxed/simple; t=1554396680; h=from:date:subject:reply-to:to:list-unsubscribe:mime-version; bh=CFNOzBI7CKw9G+CMGiwWKKf8wfr2Mofj+1fJ4EwkbF4=; b=B9EDMXm1nXaF8dnRQI288Vir0yhawflEyHGdM200ketQ4cAvEy99qYZKao12pD4BcXEzuCGTyLB Y+XEI4icRr81ufsI5TY8/y8LGeJ8HeiLnl3UCNsND3J5c1bOkvMVix6SToOkHwRq4mgQrCZo553zC Z5RuSoahkjzzvF9msWs= DKIM-Signature: v=1; a=rsa-sha256; d=elasticemail.com; s=api; c=relaxed/simple; t=1554396680; h=from:date:subject:reply-to:to:list-unsubscribe; bh=CFNOzBI7CKw9G+CMGiwWKKf8wfr2Mofj+1fJ4EwkbF4=; b=gm+u+JJrV/bFb2xt98GzpOn3o+fLPg+sIGdeKxglPpJ/fUAr+IUWMKl9pAfNgS1ZGCd6QWpyLfH Svw7IW7oBA1soJ51TQ/RUJaFvTdK9ixDw0bnRJZMa9wJf/XfojyeRxsiOvIfx1ogUkCwr64hX7qjj ao6oVFX1pj0U8b982J0= From: tqchen via TVM Discuss Date: Thu, 04 Apr 2019 16:51:03 +0000 Subject: [TVM Discuss] [Development] Google lasted work: MLIR Primer Message-Id: <4u766mq9fax9.oFfzY6AgreTn0Y-vgk1jfw2@tracking.discuss.tvm.ai> Reply-To: tqchen via TVM Discuss Sender: tqchen via TVM Discuss To: tvm.archiver@gmail.com X-Msg-EID: oFfzY6AgreTn0Y-vgk1jfw2 Feedback-ID: qz0r3x:-4pr9lq2h:ElasticEmailFBL In-Reply-To: References: X-Auto-Response-Suppress: All Auto-Submitted: auto-generated List-Archive: https://discuss.tvm.ai/t/google-lasted-work-mlir-primer/1721 MIME-Version: 1.0 Content-Type: multipart/alternative; boundary="=-eZCfC0TT5ByaBsCMb/0hORCMxANphPQj23WKzA==" --=-eZCfC0TT5ByaBsCMb/0hORCMxANphPQj23WKzA== Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: 7bit Good comments. I would like to separate the answer in two parts, and this is an updated view after I take look at the MLIR's codebase. ## Interpretation of MLIR's Vision I think what you answered reflects MLIR's vision. Make the abstract class of IR and derive dialects. But not necessarily provide specific pass for the dialect, so if X-IR is a dialect of MLIR, then there are dialect specific passes that is needed in the pass. Polyhedral dialect is a dialect in MLIR. In the current case, the polyhedral IR is part of the mlir codebase, which gives the view of "native", but non-the-less it is a dialect just like the other automatic optimization dialect. The fact that it is part of the native code base does give an opinionated view of what what automatic optimization should be like in MLIR ecosystem. I think it is still very much an open problem, TVM has done a lot in this direction, and we can collectively innovate on this area. ## How TVM can work with MLIR First of all, MLIR won't make TVM obsolete. In the contrary, it can help TVM stack by providing insights in IR design and possibly some lowering infrastructure.The community will keep improving our current IR infrastructure toward a better unified TVM-IR infra. We will try to define TVM dialects in MLIR to see if it makes sense to allow bi-directional translation between MLIR and TVM-IR, this way we can take benefit of some of the infra provided by MLIR and make TVM work together with MLIR's ecosystem. --- [Visit Topic](https://discuss.tvm.ai/t/google-lasted-work-mlir-primer/1721/15) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.tvm.ai/email/unsubscribe/ce284d9a37cb5de47ee3fcab532dd17b2fff248996213b64a072d0bd95980f33). Tianqi Chen, UW, Seattle, WA, 98105, United States http://tracking.discuss.tvm.ai/tracking/unsubscribe?msgid=oFfzY6AgreTn0Y-vgk1jfw2 --=-eZCfC0TT5ByaBsCMb/0hORCMxANphPQj23WKzA==--