similar to: instrumenting device code with gpucc

It's hard to tell what is wrong without a concrete example. E.g., what is the program you are instrumenting? What is the definition of the hook function? How did you link that definition with the binary? One thing suspicious to me is that you may have linked the definition of _Cool_MemRead_Hook as a host function instead of a device function. AFAIK, PTX assembly cannot be linked. So, if you

Hi Jingyue, Sorry to ask again, but how exactly could I glue the fatbin with the instrumented host code? Or does it mean we actually cannot instrument both the host & device code at the same time? Thanks! yuanfeng On Tue, Mar 15, 2016 at 10:09 AM, Jingyue Wu <jingyue at google.com> wrote: > Including fatbin into host code should be done in frontend. > > On Mon, Mar 14, 2016

Hey Jingyue, Thanks for being so responsive! I finally figured out a way to resolve the issue: all I have to do is to use `-only-needed` when merging the device bitcodes with llvm-link. However, since we actually need to instrument the host code as well, I encountered another issue when I tried to glue the instrumented host code and fatbin together. When I only instrumented the device code, I

Hey Jingyue, Though I tried `opt -nvvm-reflect` on both bc files, the nvvm reflect anchor didn't go away; ptxas is still complaining about the duplicate definition of of function '_ZL21__nvvm_reflect_anchorv' . Did I misused the nvvm-reflect pass? Thanks! yuanfeng On Fri, Mar 11, 2016 at 10:10 AM, Jingyue Wu <jingyue at google.com> wrote: > According to the examples you

OK, I see the problem. You were right that we weren't picking up libdevice. CUDA 7.0 only ships with the following libdevice binaries (found /path/to/cuda/nvvm/libdevice): libdevice.compute_20.10.bc libdevice.compute_30.10.bc libdevice.compute_35.10.bc If you ask for sm_50 with cuda 7.0, clang can't find a matching libdevice binary, and it will apparently silently give up and try to

Hi Justin, Thanks for your response! The clang & llvm I'm using was built from source. Below is the output of compiling with -v. Any suggestions would be appreciated! *clang version 3.9.0 (trunk 270145) (llvm/trunk 270133)* *Target: x86_64-unknown-linux-gnu* *Thread model: posix* *InstalledDir: /usr/local/bin* *Found candidate GCC installation: /usr/lib/gcc/x86_64-linux-gnu/4.8*

Hi, Yuanfeng. What version of clang are you using? CUDA is only known to work at tip of head, so you must build clang yourself from source. I suspect that's your problem, but if building from source doesn't fix it, please attach the output of compiling with -v. Regards, -Justin On Sun, Jul 31, 2016 at 9:24 PM, Chandler Carruth <chandlerc at google.com> wrote: > Directly

Hi Alexey, Just want to make sure I understand what you said because I'm not familiar with the llvm pipeline, it's this line: /net/gs/vol3/software/modules-sw/cuda/10.0/Linux/RHEL6/x86_64/bin/ptxas" -m64 -g --dont-merge-basicblocks --return-at-end -v --gpu-name sm_75 --output-file /tmp/60663577.1.login.q/testparticles-4fd988.o /tmp/60663577.1.login.q/testparticles-1d20c4.s that

Hi Alexey, I submitted the bug report to nvidia. While they are working on it, can you share some insight in what could potentially cause this? I just want to get a sense if such a bug require significant amount of work to fix, which can help me make some decision moving forward with my project. Thanks, Char At 2019-02-27 03:19:02, "Alexey Bataev" <a.bataev at outlook.com>

Hi Alexey, Is there any option for clang to turn on debug for the host code only but not the device code? I've been using something like -ggdb3 -O0 but this generate debug info for both host and device. I'm trying to work around the aforementioned ptxas bug. Thanks, Char At 2019-02-28 02:09:54, "Alexey Bataev" <a.bataev at outlook.com> wrote: Hi Char, it looks like

Hi Alexey, Almost a year has passed and Nvidia finally fixes the ptxas issue in CUDA 10.2 according to: https://docs.nvidia.com/cuda/cuda-toolkit-release-notes/index.html#cuda-compiler-resolved-issues However, I can not yet use it with llvm 9.0.0 release because CUDA 10.2 is not supported yet. Is there other branches of the llvm repo that supports CUDA 10.2 now? Or do I need to wait for llvm 10

Hi Alexey, Thanks for the great work! The version I checked out works most of the time. But I do encounter crashes sometimes. I can't file a bug report on https://bugs.llvm.org/ because I don't have an account. I sent an email to bugs-admin at lists.llvm.org for an account already but I haven't heard back. Meanwhile, can you take a look at the issue? I'm attaching the bug report

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

Hi all, I compiled the *llvm3.9* source code on the *Nvidia TX1* board. And now I am following the document in the docs/CompileCudaWithLLVM.rst to compile cuda program with clang++. However, when I compile `axpy.cu` using `nvcc`, *nvcc* can generate the correct the binary; while compiling `axpy.cu` using clang++, the detailed command is `clang++ axpy.cu -o axpy --cuda-gpu-arch=sm_53

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

Yeah, '.' is the direct reason for the ptxas failure here. I'm curious, however, about what the purpose of nvvm_reflect_anchorv() is here, and why does the front-end always generate this function? Since the current PTX emission doesn't mangle dots, it would be a reasonable workaround for me to prevent the front-end from generating this function in the first place. Is there any

+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 >

Yes, I followed the guide. The same error showed up: >clang++ axpy.cu -o axpy --cuda-gpu-arch=sm_35 -L/usr/local/cuda/lib64 -I/usr/local/cuda/include -lcudart_static -ldl -lrt -pthread error: unable to create target: 'No available targets are compatible with this triple.' ________________________________ From: Kevin Choi <code.kchoi at gmail.com> Sent: Wednesday, August 2,

Hi, I have trouble compiling CUDA code with Clang. The following is a command I tried: > clang++ axpy.cu -o axpy --cuda-gpu-arch=sm_35 --cuda-path=/usr/local/cuda The error message is error: unable to create target: 'No available targets are compatible with this triple.' The info of the LLVM I'm using is as follows: > lang++ --version clang version 6.0.0

Dear LLVM NVPTX maintainers, Just to have the issue recorded, I don't know how important it is: clang generates linkonce_odr out of __inline__, and NVPTX generates .weak out of linkonce_odr (how it happens - a big question, btw, because I can't find anything related in NVPTX asm printer - does it chain to some other printer?), and finally ptxas (both 4.2 and 5) fails to compile it to