[PATCH] D78606: [DAGCombine] Adding a new Newton-Raphson implementation to leverage the FMA

Wed Apr 22 06:00:08 PDT 2020

Sorry, I need to withdraw that revision now. Sorry for the confusion and inconvenience. I meant to save it and submit later but unfortunately got it out.

Best regards

steven.zhang(张青山)
XL/LLVM on Power Compiler Developer

IBM China Development Lab, Shanghai 
Tel: (8621)609-28454 Mobile: +8615900986116
E-mail: qshanz at cn.ibm.com

-----Roman Lebedev <lebedev.ri at gmail.com> wrote: -----
To: reviews+D78606+public+456f57fe4e796193 at reviews.llvm.org, Scott Manley via Phabricator <reviews at reviews.llvm.org>
From: Roman Lebedev <lebedev.ri at gmail.com>
Date: 04/22/2020 04:11PM
Cc: qshanz at cn.ibm.com, Sanjay Patel <spatel at rotateright.com>, Simon Pilgrim <llvm-dev at redking.me.uk>, Hal Finkel <hfinkel at anl.gov>, enenkel at ca.ibm.com, evandro.menezes at sifive.com, jji at us.ibm.com, Nemanja Ivanovic <nemanja.i.ibm at gmail.com>, victorhuangibm at gmail.com, harish at dotlall.com, amyk.ibm at gmail.com, baptiste.saleil at ibm.com, kamau.a.bridgeman at gmail.com, wanyu9511 at gmail.com, xiangxdh at gmail.com, hualilia at ca.ibm.com, pjeeva01 at ca.ibm.com, alfredo at freebsd.org, jrh29 at alumni.cwru.edu, jedilyn at 163.com, sfertile at ca.ibm.com, lyh.kernel at gmail.com, stefanp at ca.ibm.com, lkail at cn.ibm.com, ecnelises at icloud.com, Kang Zhang <shkzhang at cn.ibm.com>, Zheng CZ Chen <czhengsz at cn.ibm.com>, kit.barton at gmail.com, lei at ca.ibm.com, john.reagan at vmssoftware.com, jun.l at samsung.com, llvm-commits at lists.llvm.org, Austin.Kerbow at amd.com, Nicolai Haehnle <nhaehnle at gmail.com>, jholewinski at nvidia.com, p8u8i7l5t1q9r8w3 at ibm-systems-z.slack.com, powerllvm at ca.ibm.com, wuzish at cn.ibm.com
Subject: [EXTERNAL] Re: [PATCH] D78606: [DAGCombine] Adding a new Newton-Raphson implementation to leverage the FMA

You Shall Not Pass: Restricted Differential Revision
^ please fix that

On Wed, Apr 22, 2020 at 6:01 AM Scott Manley via Phabricator via
llvm-commits <llvm-commits at lists.llvm.org> wrote:
>
> rscottmanley added a comment.
>
> Are your accuracy and speedup numbers applicable for both f32 and f64 sqrt?
>
>
> Repository:
>   rG LLVM Github Monorepo
>
> CHANGES SINCE LAST ACTION
>   https://urldefense.proofpoint.com/v2/url?u=https-3A__reviews.llvm.org_D78606_new_&d=DwIBaQ&c=jf_iaSHvJObTbx-siA1ZOg&r=4FedcNQfP4QcaBGfhp8oq2wPQHIv51RNpo7UEhopmZc&m=e1nTqh4vxQFZVc5ljTTVTR40oGwWrJke3CokrDckQjM&s=0f83yhFWJHJ20IWJcey0515uNWfdmlsdSDWfjxGQLh0&e= 
>
> https://urldefense.proofpoint.com/v2/url?u=https-3A__reviews.llvm.org_D78606&d=DwIBaQ&c=jf_iaSHvJObTbx-siA1ZOg&r=4FedcNQfP4QcaBGfhp8oq2wPQHIv51RNpo7UEhopmZc&m=e1nTqh4vxQFZVc5ljTTVTR40oGwWrJke3CokrDckQjM&s=iyz1N7-2WsmBodoVJHkaqowA0IebC2fDfc0el8DCEDA&e= 
>
>
>
> _______________________________________________
> llvm-commits mailing list
> llvm-commits at lists.llvm.org
> https://urldefense.proofpoint.com/v2/url?u=https-3A__lists.llvm.org_cgi-2Dbin_mailman_listinfo_llvm-2Dcommits&d=DwIBaQ&c=jf_iaSHvJObTbx-siA1ZOg&r=4FedcNQfP4QcaBGfhp8oq2wPQHIv51RNpo7UEhopmZc&m=e1nTqh4vxQFZVc5ljTTVTR40oGwWrJke3CokrDckQjM&s=1aqH8PoEUiM33TzlyYZCVDV9OFktiuwJRP1SA7zaB-E&e= 

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20200422/ed92b64a/attachment.html>