Stack Overflow
Stack Overflow

Questions tagged [nvidia-hpc-compilers]

For questions specific to the NVIDIA HPC Fortran, C++ and C compilers. Additionally use tags for the particular language(s) and programming features used, if relevant.

NVIDIA HPC compiler suite for Fortran, C++ and C supporting OpenACC, OpenMP and CUDA.

9 questions
2
votes
0 answers

Trying to understand/resolve NVIDIA HPC SDK Fortran module memory management problem

Update: NVIDIA responded to my bug report (link is at bottom of this description) stating that they are able to reproduce the problem locally, and will have people look into it. This is a complex problem which I've tried to abbreviate to bare…
DonMorton
  • 393
  • 2
  • 11
1
vote
1 answer

How to enable out of bounds memory checking on nvfortran compiler?

Description and source example Below are two simple, crude test programs that try to access out of bounds memory in cpu and gpu code. I put the gpu example separately, so one can test the cpu example with different compilers and examine their…
SadBoySquad
  • 21
  • 2
1
vote
0 answers

Getting different results when using pgfortran vs. gfortran for same exact problem

In a computational fluid dynamics solver I have written, I am getting a different result based on the compiler I use. When I compile this code using gfortran with the following flags: -ffree-line-length-512 -Ofast -march=native, I get the "correct"…
Natan Hoffmann
  • 19
  • 2
0
votes
1 answer

Maximum number of dimensions in Nvidia HPC compiler

Does anyone know what the maximum number of dimensions is for the Nvidia HPC compiler for Fortran? It used to be 7, but a thread in 2019 said they were working on adding it.…
Laurence_jj
  • 646
  • 1
  • 10
  • 23
0
votes
0 answers

Random numbers inside OpenACC loop (nvfortran compiler)

Is there a straightforward way to generate random numbers inside an OpenACC parallel loop? I want the seed within each loop/thread to be different. The reference code that demonstrates the required task to be done is as follows: PROGRAM…
Dumbledore Albus
  • 15
  • 4
0
votes
1 answer

Long cuMemToHostAlloc call after exiting a kernel with copyout

I am accelerating a Fortran code with OpenACC. When I profile the program with NVIDIA Nsight, I noticed the first call of a kernel with a copyout clause exhibited a long call to cuMemToHostAlloc. Here is a trivial example illustrating this. The…
Paul Zehner
  • 33
  • 4
0
votes
0 answers

Parallelizing DO loop with nvfortran on gpu

I am tring to parallelize a do loop in Fortran. Using OMP parallel do (and converted to standard do loop) it works nicely (using both gfortran and nvfortran), but when compiling it with nvfortran -stdpar=gpu it compiles, but running it, it crashes…
fpl
  • 1
  • 2
0
votes
1 answer

Inter GPU communication in MPI+OpenACC programming

I am trying to learn how to perform inter-gpu data communication using the following toy code. The task of the program is to send array 'a' data in gpu-0 in to gpu-1's memory. I took the following root to do so, which involved four steps: After…
Dumbledore Albus
  • 15
  • 4
0
votes
1 answer

Getting started with OpenACC + MPI Fortran program

I have a working serial code and a working parallel single GPU code parallelized via OpenACC. Now I am trying to increase the parallelism by running on multiple GPUs, employing mpi+openacc paradigm. I wrote my code in Fortran-90 and compile it using…
Dumbledore Albus
  • 15
  • 4