similar to: [LLVMdev] [PATCH] OpenCL half support

Displaying 20 results from an estimated 60000 matches similar to: "[LLVMdev] [PATCH] OpenCL half support"

2011 Mar 18
0
[LLVMdev] [PATCH] OpenCL half support
> Maybe worth pointing out that there are architectures that natively support > 16bit floating point in llvm. PTX, the new backend of which has just been > added to 2.9 can handle fp16 -> fp32 conversion in hardware. FWIW: there are already intrinsics for such conversions (currently only used in ARM backend). There is no need for new type if you want just to convert stuff. -- With
2012 May 18
0
[LLVMdev] [PATCH] OpenCL half support
> Sure! > Any further comments? LGTM -- With best regards, Anton Korobeynikov Faculty of Mathematics and Mechanics, Saint Petersburg State University
2012 Nov 16
0
[LLVMdev] [cfe-dev] 3.2 Release has branched :T+2 hours
Should be there On Fri, Nov 16, 2012 at 3:00 PM, NAKAMURA Takumi <geek4civic at gmail.com> wrote: > Anton, please add release_32 also in; > > clang-tools-extra > compiler-rt > dragonegg > libcxxabi > lldb > > They have release_32 in svn. I don't know they might be released, though. > > And, could you suppress generating refs/heads/svn-tags and prune them
2010 Apr 28
0
[LLVMdev] Half float docs in 2.7 missing
Hello, Paul > In the 2.7 relnotes the 16-bit half float type is described, with a link > to the corresponding LangRef section. However, this section seems to be > missing in the 2.7 LangRef, I do see it in trunk, though... That's correct, half fp was added after 2.7 branched. -- With best regards, Anton Korobeynikov Faculty of Mathematics and Mechanics, Saint Petersburg State
2012 Nov 14
0
[LLVMdev] 3.2 Release has branched :T+2 hours
Should be there. Please let me know if there are any problems with them On Wed, Nov 14, 2012 at 9:19 PM, Anton Korobeynikov <anton at korobeynikov.info> wrote: >> I can't find any release_32 branch at http://llvm.org/git/llvm.git or http://llvm.org/git/clang.git. > Unfortunately, this requires manual grafting, since git-svn does > really bad job here. > > I'm going
2012 Nov 16
2
[LLVMdev] [cfe-dev] 3.2 Release has branched :T+2 hours
Anton, please add release_32 also in; clang-tools-extra compiler-rt dragonegg libcxxabi lldb They have release_32 in svn. I don't know they might be released, though. And, could you suppress generating refs/heads/svn-tags and prune them for now? I am sure that orphan branches will stress the llvm.org server to begin git-pack-ing whole tree. ...Takumi 2012/11/15 Anton Korobeynikov
2011 May 13
1
[LLVMdev] [PATCH] OpenCL half support
Hi Anton, Sorry for dropping this. Can you resend your current patch? Lets just start and iterate on the llvm patch first. -Chris On Mar 22, 2011, at 10:40 AM, Anton Lokhmotov wrote: > Chris Lattner wrote: >> I'm sorry I don't have the patch anymore. Please resend. > Attached. (Copying to cfe-dev, as the patch is dual Clang/LLVM.) > > Anton Korobeynikov wrote:
2013 Nov 20
0
[LLVMdev] [Announcement] LLVM 3.4 Has Branched!
In particular, by now they are alive. On Wed, Nov 20, 2013 at 8:34 AM, Anton Korobeynikov <anton at korobeynikov.info> wrote: >> Seems release_34 is orphan in llvm.git and clang.git. Could you tweak them? > They will be created as soon as there will be commits to them. > > -- > With best regards, Anton Korobeynikov > Faculty of Mathematics and Mechanics, Saint
2012 Mar 06
2
[LLVMdev] Assembly Mips from bitecode llvm
llvm-gcc (GCC) 4.2.1 (Based on Apple Inc. build 5658) (LLVM build 2.9) Copyright (C) 2007 Free Software Foundation, Inc. This is free software; see the source for copying conditions. There is NO warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. llc --version: Low Level Virtual Machine (http://llvm.org/): llvm version 2.9 Optimized build. Built Mar 5 2012
2013 Jan 23
0
[LLVMdev] Half Float fp16 Native Support
> i understand that is not right but this was the only way not to use the fadd > for f32 "add.s" and use the "add.h" what ever i tried llvm moved everything > to the float registers and did add.s and not the half add.h It seems you do not understand the issue. Half floating poing operations can be done in two ways: 1. Storage-only (fp16 is used to store value, all
2013 Jan 22
0
[LLVMdev] Half Float fp16 Native Support
> def FADD_H : NemaCorePseudo< (outs HGR16:$fd), (ins HGR16:$fs, HGR16:$ft), > "add.h\t$fd, $fs, $ft", [(set (i16 HGR16:$fd),(i16 (f32_to_f16 (f32 (fadd > (f32 (f16_to_f32 (i16 HGR16:$fs))), > (f32 (f16_to_f32 (i16 HGR16:$ft))))))))]>; > > so i can have a half floating point add two half point variables and seems > to work fine. This does not look right. Note
2011 Feb 20
0
[LLVMdev] Fwd: Windows/Visual Studio 2010 warnings (WARNINGS!)
Forwarding to llvmdev ---------- Forwarded message ---------- From: Mikael Lyngvig <mikael at lyngvig.org> Date: Sun, Feb 20, 2011 at 16:02 Subject: Re: [LLVMdev] Windows/Visual Studio 2010 warnings (WARNINGS!) To: Anton Korobeynikov <anton at korobeynikov.info> I was joking about the fact that I am only a Windows user (LLVM initially does look rather *nix biased). But I guess you
2012 Jan 21
2
[LLVMdev] Fwd: How to force the creation of arrays with zeroes?
Sorry, forgot to reply-all ---------- Forwarded message ---------- From: Anton Korobeynikov <anton at korobeynikov.info> Date: Sat, Jan 21, 2012 at 20:59 Subject: Re: [LLVMdev] How to force the creation of arrays with zeroes? To: Stepan Dyatkovskiy <STPWORLD at narod.ru> > Though, there is also cases when we really need to transform it to 10,000 zeroes (just look at CBackend.cpp,
2011 Mar 18
3
[LLVMdev] [PATCH] OpenCL half support
<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"> <html> <head> <meta content="text/html;charset=ISO-8859-1" http-equiv="Content-Type"> </head> <body bgcolor="#ffffff" text="#000000"> <br> <br> Villmow, Micah wrote: <blockquote
2011 Apr 14
0
[LLVMdev] Fwd: LLVM Scheduler and Itinieraries: Negative latency?
Forwarding to llvm-dev... ---------- Forwarded message ---------- From: Magnus Pettersson <mangepe at gmail.com> Date: Thu, Apr 14, 2011 at 21:33 Subject: Re: [LLVMdev] LLVM Scheduler and Itinieraries: Negative latency? To: Anton Korobeynikov <anton at korobeynikov.info> Hello Anton, I am trying to model a fairly simple five stage pipelined processor. The problem is that some
2013 May 07
1
[LLVMdev] [cfe-dev] [Announcement] 3.3 Tentative Release Schedule
I will add release branches soon. I just decided to wait a bit in case of some emergency re-creation of branches, etc. On Tue, May 7, 2013 at 4:51 PM, Rafael EspĂ­ndola <rafael.espindola at gmail.com> wrote: >> We will be branching for the 3.3 release one Monday, May 6th at 5PM PDT (Tuesday, May 7th 12:00 midnight GMT). > > I noticed there is a 3.3 branch in svn, but not in git.
2010 May 13
2
[LLVMdev] Handling of thread_local globals by llc -march=cpp
Thanks for the quick reply and fix. Now it just means I have to hunt further in exploring why, in my simple test program, replacing the following line of code: GlobalVariable* global = new GlobalVariable(*MyModule, IntegerType::get(getGlobalContext(), 32), false, GlobalValue::ExternalLinkage, 0, "global"); with the following line of code: GlobalVariable* global = new
2012 Mar 04
3
[LLVMdev] Passing arguments to opt via clang
Thanks, but I'm not sure I understand. I see no such flag in clang 2.9 nor couldn't I find any mention of it. What does it do? Harel Cain On Sun, Mar 4, 2012 at 15:03, Anton Korobeynikov <anton at korobeynikov.info>wrote: > > In the good old llvmc, the -Wo flag could be used to pass arguments to > the > > optimizer. Is there a similar mechanism anywhere for clang?
2011 Mar 10
2
[LLVMdev] [cfe-dev] GIT mirrors
> The extra branches that Anton added to clang.git didn't rewrite anything. > Here's hoping it won't be necessary for llvm.git either. I was hoping that the rebuilt won't change the sha's and noone will notice anything (well, except those who already branched out of branches / tags). But it seems that after rebuild stuff was changed (I really dunno, why). So, we'll go
2011 Mar 10
0
[LLVMdev] [cfe-dev] GIT mirrors
On Mar 10, 2011, at 10:39 AM, Anton Korobeynikov wrote: >> The extra branches that Anton added to clang.git didn't rewrite anything. >> Here's hoping it won't be necessary for llvm.git either. > I was hoping that the rebuilt won't change the sha's and noone will > notice anything (well, except those who already branched out of > branches / tags). > But