The Portland Group (PGI) produces compilers (Fortran, C & C++) for high-performance computers. They also provide Fortran compilers with GPU support (CUDA Fortran as well as an implementation of OpenACC).
See also PGI Documentation.
Questions tagged [pgi]
160 questions
2
votes
1 answer
Why does this code seg fault (during allocation) with pgi but not intel?
This code works when run on intel compiler. However when ran with pgi, it seg faults between the * and ** in the subroutine listed. I'm using pgi compiler with -mcmodel-medium. I need to use PGI to start using openacc for this code. Any ideas what…
user1993893
- 99
- 1
- 6
1
vote
0 answers
OpenMP pragma parallel for only using a single thread
I am refactoring some old code which uses OpenMP to parallelise some heavy calculations. The program is written in C.
System specs:
2x 48-Core Xeons
750GB RAM
Ubuntu 20
It is worth noting the the system has multiple compilers and libraries…
Oliver Wissett
- 11
- 1
1
vote
0 answers
Avoid warning: '"cc" clobber ignored' with PGI on RUNNING_ON_VALGRIND?
We get warnings of the type
"/var/lib/buildbot/slaves/athor-linux-pgi-c-nompi/petsc/src/sys/objects/pinit.c
", line 1493: warning: "cc" clobber ignored
if (!(RUNNING_ON_VALGRIND)) {
When compiling with the latest community version of…
Barry Smith
- 21
- 2
1
vote
1 answer
PyGTK, PyGObject and Pgi in python3
In https://github.com/cztomczak/cefpython/blob/master/src/linux/binaries_64bit/kivy_.py, pygtk and gtk are used. (Note that the source code is tested in Linux only, and I am using Windows)
When I tried to pip install pygtk, there was an…
user13080049
1
vote
1 answer
Calling OpenACC code from Rust does not run on GPU
Update 09/07/2020
I'm adding a small example for this at https://gitlab.com/lisanhu2016/rust-openacc-example.git
It's a public repository with a README, you should be able to try the example there.
The libraries I have been linking to are: nvc,…
Sanhu Li
- 402
- 5
- 11
1
vote
1 answer
How to use OpenACC on 2D subvector in C++ or OpenCV SubMatrix?
I have the following code
int main(int argc, char** argv )
{
std::cout<<"running Lenna..\n";
cv::Mat mat = imread("lena.bmp", cv::IMREAD_GRAYSCALE );
//convert to vec
std::vector BWvec;
BWvec.assign((double*)mat.data,…
user5739619
- 1,748
- 5
- 26
- 40
1
vote
0 answers
serial construct in openacc, fortran
I have the following serial part of a FORTRAN code which should be executed
sequentially.
c$acc serial
nppn1=0
c
do 1200 ippas=1,50
c
nppn0=nppn1+1
nppn1=lppas(ippas)
c
c -----did we complete the passes ?
c
…
Alejandro
- 11
- 2
1
vote
2 answers
difference between kernels and parallel directives in OpenAcc standard
I have already been using the PGI compiler supporting OpenAcc for launching the code on GPU for about 3 years, but i can not understand the difference between the terms "kernels" and "parallel" so far.
I read in OpenAcc Getting Started…
And
- 310
- 1
- 12
1
vote
1 answer
how to connect pgfortran(has OpenAcc direvative ) with python by f2py
use f2py to connect python and Fortran language.
f2py website
https://docs.scipy.org/doc/numpy/f2py/
Fortran before used gfortran and pgfortran(PGI) integrate OpenMP both work.
makefile file is below
gfortran version
gfortran -c -fopenmp…
TianliBen
- 11
- 3
1
vote
1 answer
compiler dependent null pointer problem in fortran
I'm trying to compile one particular numerical code named NEMO. I'm using PGI compiler and get the following error while I'm trying to run a case.
-> report : Performance report : Time spent for XIOS : 4.53964e-05
-> report : Performance report :…
Coconut
- 184
- 1
- 15
1
vote
2 answers
OpenACC loop private clause and race condition
I'm trying to use a worker-private array with OpenACC, but i keep getting wrong results. I guess there is some kind race condition issue going on, but I can't find where.
I'm using the PGI compiler (18.10, OpenPower) and compile with :
pgf90 -gopt…
arnodu
- 51
- 3
1
vote
1 answer
How to enter CUDA fortran kernels using PGI Debugger?
I have tried adding -g option in the command line, however, I still can't enter the kernels in PGI Debugger.
S.C. Zheng
- 51
- 6
1
vote
0 answers
Constant memory in PGI Fortran complier on CUDA
When I am trying to specify a constant variable with another constant variable, the PGI compiler gives this error:
PGF90-S-0519-More than one device-resident object in assignment.
The code is as follows:
module var
use cudafor
implicit…
S.C. Zheng
- 51
- 6
1
vote
3 answers
How to use notdir, wildcard and patsubst in a Makefile?
I have the following makefile:
#.SUFFIXES:
#.SUFFIXES: .F90 .cuf .o
ROOT = /home/ccevallos/finalMIT
SRCDIR := $(ROOT)/external/lib_eigesolve
#F90SRC = $(notdir $(wildcard $(SRCDIR)/*.F90))
#F90OBJS = $(patsubst %.F90,%.o,$(F90SRC))
F90OBJS =…
Caterina
- 775
- 9
- 26
1
vote
0 answers
pgf90 cause segmentation fault when use optional logical argument
Just look at the following simple codes:
program hello
call foo()
contains
subroutine foo(bar)
logical, intent(in), optional :: bar
if (present(bar) .and. bar) then
print *, 'hello'
end if
end subroutine foo
end…
Li Dong
- 1,088
- 2
- 16
- 27