similar to: Status of CUDA 11 support

Hello, When generating the PTX output from CUDA file(.cu file), the minimum target that is accepted by LLVM is sm_20. But I have a specific requirement to generate PTX output for compute capability 1.0 (sm_10). Is there any previous version of LLVM supporting this? Thank you, Ginu -------------- next part -------------- An HTML attachment was scrubbed... URL:

Clang currently doesn't support CUDA separate compilation and thus extern __device__ functions and variables cannot be used. Could someone give me any pointers where to look or what has to be done to support this? If at all possible, I'd like to see what's missing and possibly try to tackle it. -------------- next part -------------- An HTML attachment was scrubbed... URL:

+Artem Belevich <tra at google.com> On Fri, Mar 23, 2018 at 7:53 PM Bharath Bhoopalam via llvm-dev < llvm-dev at lists.llvm.org> wrote: > I was wondering if anyone has encountered this issue when cross compiling > cuda on Nvidia TX2 running android. > > The error is > In file included from <built-in>:1: > In file included from >

I was wondering if anyone has encountered this issue when cross compiling cuda on Nvidia TX2 running android. The error is In file included from <built-in>:1: In file included from prebuilts/clang/host/linux-x86/clang-4667116/lib64/clang/7.0.1/include/__clang_cuda_runtime_wrapper.h:219: ../cuda/targets/aarch64-linux-androideabi/include/math_functions.hpp:3477:19: error: no matching function

Dear colleagues! In early 2009 there was a discussion about fast BLAS library initiated by Sachin. He reported a faster BLAS library made by Nvidia CUBLAS library. Uwe Ligges showed an interest for placing the optimized rblas.dll into windows/contrib section managed by him. Unfortunately there is no any CUBLAS version of rblas.dll in this section at present. So, is anybody interested in CUBLAS

Hello, I have a question regarding subsetting of vectors. Here's an example of what I'm trying to do: vect.1 <- c(76,195, 290, 380) vect.2 <- c(63, 95, 133, 170, 215, 253, 285, 299, 325, 375) I would like to subset vect.2 so that it has the same length as vect.1, and its numbers are the first corresponging higher value compared to vect.1. The output should be: final.output =

im learning rails and i got a error while writing a sample code. Script : ------- class GuestBookController < ActionController::Base def index @entry = GuestBook.find_all end def list_parameters params = request.parameters render :text=>"Parameters #{params}" end def list params = request.parameters @entry = GuestBook.new(params[:name])

Hello, the following is a part of a question asked on R-help. I realized that it is better suited for asking here. Apologies for the cross-posting! I'm on Ubuntu artful, and upgraded with 'apt'. Then ---------------------------------------------------------------- goran at M6800:~/src/R-3.4.3$ /usr/bin/R /usr/lib/R/bin/exec/R: symbol lookup error:

Hi, I propose to make function inliner parameters adjustable for specific target. Currently function inlining pass appears to be target-agnostic with various constants for calculating call cost hardcoded. While it works reasonably well for general purpose CPUs, some quirkier targets like NVPTX would benefit from target-specific tuning. Currently it appears that there are two things that need to

David's change makes nvvm_reflect_anchor unnecessary. The issue with dots in names generated by llvm still needs to be fixed. On Apr 9, 2016 8:32 AM, "Jingyue Wu" <jingyue at google.com> wrote: > Artem, > > With David's http://reviews.llvm.org/rL265060, do you think > __nvvm_reflect_anchor is still necessary? > > On Fri, Apr 8, 2016 at 9:37 AM, Yuanfeng

IMO, the appropriate thing for TTI to inform the inliner about is how costly the actual act of a "call" is likely to be. I would hope that this would only be used on targets where there is some really dramatic overhead of actually doing a function call such that the code size cost incurred by inlining is completely dwarfed by the improvements. GPUs are one of the few platforms that

Hi , I am currently using xapian with plaintext parsr (i think) to get output on konsole itself. How it cud be possible get that output on the/as the html page or xml page Thank You. -------------- next part -------------- An HTML attachment was scrubbed... URL: http://lists.tartarus.org/pipermail/xapian-discuss/attachments/20060327/dbe044f3/attachment.htm

IMO, a good inliner with a precise cost/benefit model will eventually need what Art is proposing here. Giving the function call overhead as an example. It depends on a couple of factors: 1) call/return instruction latency; 2) function epilogue/prologue; 3) calling convention (argument parsing, using registers or not, what register classes etc). All these factors depend on target information. If

Hi everyone, I have made a faster BLAS library thanks to Nvidia CUBLAS library. I was wondering how I could upload this new Rblas.dll. I've included a powerpoint presentation I made on the project. Highlights include upto 2000% improvement in matrix multiplication timings. Unfortunately the link included in the presentation is only accessible by CSIRO employees only. I will gladly include

Hi All, A few years back when I was a CSIRO (an Australian research centre) intern I developed a BLAS package for R that uses the GPU. I believe that there is something similar right now, except it uses a few CuBLAS (Nvidia BLAS) routines, but doesnt replace them. My question is, is it technically illegal to hold back on source code? Thanks, Sachin [[alternative HTML version deleted]]

hi all, When Trying to upload 2GB of stream i got invalid content length error am running Apache as frontend server to mongrel and chrome as my browser. One more thing one i do it with mongrel alone am able to upload this 2 GB of stream ,cud anybody tell me whats the problem and how do i configure content length in apache?? -- Posted via http://www.ruby-forum.com/. -- You received this

Dear R-devel, We are planning a package that provides R interface to cuBLAS (CUDA accelerated BLAS). Due to CUDA's requirement, we are wondering if anyone can provide some guidance and suggestions on best way forward. CUDA lists Visual Studio as a requirement on Windows, and it looks like no one had succeed in building a DLL that can be called from R using the mingw tools in Rtools. Google

> On Mar 10, 2016, at 10:34 AM, Xinliang David Li via llvm-dev <llvm-dev at lists.llvm.org> wrote: > > > > On Thu, Mar 10, 2016 at 6:49 AM, Chandler Carruth <chandlerc at google.com <mailto:chandlerc at google.com>> wrote: > IMO, the appropriate thing for TTI to inform the inliner about is how costly the actual act of a "call" is likely to be. I

This buildbot appears to have been failing for several weeks now ( http://lab.llvm.org:8011/builders/clang-ppc64-elf-linux2/builds/19490 ). Does anyone know/own/care about it? ---------- Forwarded message ---------- From: <llvm.buildmaster at lab.llvm.org> Date: Mon, Sep 28, 2015 at 11:17 PM Subject: buildbot failure in LLVM on clang-ppc64-elf-linux2 To: Aaron Ballman <aaron at

Hi, Is there anything known about ZFS under 10.0-BETA4 when FreeBSD was upgraded from 9.2-RELEASE? I have two servers, with very different hardware (on is with soft raid and the other have not) and after a zpool upgrade, no way to get the server booting. Do I miss something when upgrading? I cannot get the error message for the moment. I reinstalled the raid server under Linux and the other