similar to: llvm/cuda: Indentify kernel functions and optimizations

https://github.com/llvm-mirror/llvm/blob/652375a8cc49615de31fd9d424753795059185b6/lib/Target/NVPTX/NVPTXUtilities.h#L58 Does this solve your problem? On Wed, Dec 21, 2016 at 2:29 PM, Gurunath Kadam via llvm-dev < llvm-dev at lists.llvm.org> wrote: > Hi, > > I am trying to instrument CUDA kernel functions only (llvm-3.9.0). > > Is there a way to identify cuda kernel

On 2016年12月22日 15:37, via llvm-dev wrote: > Send llvm-dev mailing list submissions to > llvm-dev at lists.llvm.org > > To subscribe or unsubscribe via the World Wide Web, visit > http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-dev > or, via email, send a message with subject or body 'help' to > llvm-dev-request at lists.llvm.org > > You can reach the

Hi, I am sorry for sending this query again here, but maybe I sent it to wrong list yesterday. I am trying to compile LonestarGPU-rev2.0 <http://iss.ices.utexas.edu/?p=projects/galois/lonestargpu/download> benchmark suite with LLVM/CLANG. This suite has a following piece of code (more info here

> On Nov 27, 2016, at 6:40 PM, Gurunath Kadam via llvm-dev <llvm-dev at lists.llvm.org> wrote: > > Hi Sandeep, > > Thanks. > > One question about: > > Value* AddrPointer = Inst->getIperand(0); > > So this works for LVALUE(S) i.e. in my case pointer on LHS of '='. I cannot find anything online about getloperand online. > > For reference

Hi, Sent via the Samsung Galaxy Note® 3, an AT&T 4G LTE smartphone -------- Original message -------- From: Gurunath Kadam via llvm-dev <llvm-dev at lists.llvm.org> Date: 11/27/2016 7:49 PM (GMT-06:00) To: llvm-dev at lists.llvm.org Subject: [llvm-dev] LLVM Pass for Instructions in Function (error Hi, Please find the embedded code. Also you may follow

Dear R users, I would like to know how to indentify the polygons that are located on the border of a map (i.e.shapefile). Do you have any suggestion on how to do it? Thank you very much, Leo Monasterio. [[alternative HTML version deleted]]

Hi, I just found this solution for identifying a job in the job table: http://stackoverflow.com/questions/3638250/how-to-cancel-scheduled-job-with-delayed-job-in-rails They are using this code: class MyJob < Struct.new(:user_id); def perform # ... end def display_name return "MyJob-User-#{user_id}" end end # store reference to a User my_job =

Hi, I am trying to write a CUDA memory instrumentation code. So far I have made little progress, please see attached file. In lines 82 and 88 I get error as: ‘LoadOperand’ is not captured and ‘StoreOperand’ is not captured Unfortunately, I am not able to tell if the error is generic C++ or LLVM related. Earlier I had verified the "syntax" of such code in a dummy C++ implementation,

On Wed, Mar 20, 2013 at 11:29 AM, upit <uday_pitambare at yahoo.com> wrote: > OK. That helps. > It does flash a warning though > > [DEVICE-C++] nbody.kernel.cpp > nbody.kernel.cpp:29:9: warning: '__constant__' macro redefined > #define __constant__ __attribute__((address_space(2))) > ^ > /opt/cuda/include/host_defines.h:183:9: note: previous

OK. That helps. It does flash a warning though [DEVICE-C++] nbody.kernel.cpp nbody.kernel.cpp:29:9: warning: '__constant__' macro redefined #define __constant__ __attribute__((address_space(2))) ^ /opt/cuda/include/host_defines.h:183:9: note: previous definition is here #define __constant__ \ ^ 1 warning generated. Another question is What about extern __shared__ ? I

Hi, all. Samba 3.022 on Ubuntu Edgy: I have a situation where win XP clients logon to our one and only PDC. They access home dirs and save stuff there. They can also, for e.g add a shortcut to their desktop. Wierd thing is any edits to screen effects are dropped, for instance. They also can't set the proxy server address & port in IE. A check after they click OK shows the entry has been

Hey eveyone! I hope someone can help wiht this question. I have a matirux of all zeros and ones and I would like to indentify all unique patterns in the rows andthe number of times the pattern occurs. I changed all zeros to NA tried to use prelim.norm to identify all patterns of missing data in the rows. I got the message Warning message: NAs introduced by coercion Any ideas of how

I'm building a simple R extension around a CUDA-enabled dynamic library, and I want to run the whole package with cuda-memcheck for debugging purposes. I can run it just fine with Valgrind: $ R --no-save -d valgrind < test.R However, if I try the same thing with cuda-memcheck, $ R --no-save -d cuda-memcheck < test.R I get: *** Further command line arguments ('--no-save ')

On Wed, Apr 8, 2015 at 10:12 AM, Dmitry Mikushin <dmitry at kernelgen.org> wrote: > A tool of this kind here: https://github.com/apc-llc/nvcc-llvm-ir > > 2015-04-08 19:01 GMT+02:00 Ahmed ElTantawy <ahmede at ece.ubc.ca>: > >> Hi, >> >> I wanted to ask whether there is ongoing effort (or an already >> established tool) that enables to convert CUDA

I was reading this page: http://api.rubyonrails.org/classes/Fixtures.html#M000326 and was trying to get hashed labels working. However, calling it from within a unit test results in this error: def test_defaults_to_disabled identify(''one'') end 2) Error: test_defaults_to_disabled(AdminTest): NoMethodError: undefined method `identify'' for

Hi, I wanted to ask whether there is ongoing effort (or an already established tool) that enables to convert CUDA kernels (that uses CUDA specific intrinsics, e.g., threadId.x, __syncthreads(), ...) to LLVM IR. I am aware that I can do this for OpenCL with the help of libclc but I can not find something similar for CUDA. Thanks -------------- next part -------------- An HTML attachment was

I can't get identify to work, using R 2.0.1 under windows xp pro, service pack 2. Here's what I enter, and the result: > plot((our.frame2$c1),(our.frame2$c9)) # Produces desired plot > identify(our.frame2$c1) # Plot comes to forefront, so I select a point warning: no point with 0.25 inches numeric(0) Is my call to identify correct? The help page for indentify (from

Hi, I am trying to convert a simple CUDA program to LLVM IR using clang 3.0. The program is as follows, #include<stdio.h> #nclude<clang/test/SemaCUDA/cuda.h> __global__ void kernfunc(int *a) { *a=threadIdx.x+blockIdx.x*blockDim.x; } int main() { int *h_a,*d_a,n; n=sizeof(int); h_a=(int*)malloc(n); *h_a=5; cudaMalloc((void*)&d_a,n); cudaMemcpy(d_a,h_a,n,cudaMemcpyHostToDevice);

Hi, I received an email from Nvidia, saying that llvm now supports ptx code generation. I am confused how to use llvm as my backend, as it seems clang's support for cuda is not complete yet. My question is: given a cuda program, how can I use llvm to generate ptx code? Thanks, Bo -------------- next part -------------- An HTML attachment was scrubbed... URL:

Hi: Does Clang support CUDA? I am looking for a front end for my compiler that can take CUDA programming framework. Thanks, -- *Abid ****************************************************** "I have learned silence from the talkative, toleration from the intolerant, and kindness from the unkind"---Gibran "Success is not for the chosen few, but for the few who choose" --- John