114 questions
1
vote
0
answers
34
views
OpenMP target error `alias definitions not supported in this configuration`
I want to use OpenMP target construct to run a loop on a GPU device. After many trial, I discovered that my gcc compiler fails to compile a recursive function.
After many trials, I isolated my problem ...
- 2,328
0
votes
0
answers
37
views
where is the TLS session key stored when configuring nginx ssl engine as pkcs11?
I configure ssl_engine in nginx as pkcs11. It means that nginx server used the key stored in hsm as its identity in TLS connection. However, the TLS master key (or shared key, or session key) is ...
- 29
0
votes
0
answers
84
views
GCC 11.2.0 Installation with nvptx-tools Fails on CentOS 7: 'ACCEL_COMPILER_acc_device' Not Declared
I am trying to run OpenACC code on a GPU and need to use GCC for compiling the C++ code. Specifically, I am attempting to install GCC 11.2.0 with nvptx-tools on a cluster running CentOS 7. The compute ...
- 6,584
1
vote
0
answers
43
views
Domain decomposition chunks: Verification passes on 1 GPU but fails on 2 GPUs
I am using OpenMP, C++, icpx, on Intel Developer Cloud's 4x GPU Max 1100 + Xeon
CPU code:
double rsd[ISIZ3][ISIZ2/2*2+1][ISIZ1/2*2+1][5];
double frct[ISIZ3][ISIZ2/2*2+1][ISIZ1/2*2+1][5];
double rho_i[...
- 11
1
vote
0
answers
99
views
How to use CMake with offloading-enabled gcc built from source
I want to use an offloading-enabled gcc in a CMake project.
To this end, I built gcc from source to use it for OpenMP offloading to an NVIDIA GPU. I could not use distro packages, because of recent ...
- 927
1
vote
1
answer
183
views
Bluefield-2 NVMe-oF Target Offloading received IB Backend ctrl event: XRQ NVMF backend ctrl timeout error (22)
I'm trying to build the NVMe-oF Target offloading environment based on the Bluefield-2.
I installed the MLNX OFED driver MLNX_OFED_LINUX-23.10-2.1.3.1-rhel7.9-x86_64. The OS version is Centos 7.2009 ...
0
votes
0
answers
105
views
OpenMP GPU offloading vector iterator
I have this working test code, which maps std::vector for offloading and checks if the calculation is correct:
#include <iostream>
#include <chrono>
#include <vector>
int main()
{
...
1
vote
0
answers
124
views
HAProxy's TLS offload feature not working as I expect
I am in the process of setting up HAProxy 2.8 via Docker to leverage it's ability to provide TLS offload in my network to avoid having certificates attached to every VM instance I deploy.
My problem ...
- 11
1
vote
0
answers
33
views
GPU offloading of triangular loop
I have triangular loop to calculate forces, which I ported to GPU via OpenMP offloading:
!$omp target teams distribute parallel do simd &
!$omp private(i,j,ii,jj,rinvdenom,tp,index,fix0) &...
- 11
0
votes
1
answer
112
views
OpenMP task reduction with target offloading segfaults when running single threaded
I was using OpenMP with target offload and found that my application segfaults when limiting OpenMP to a single thread.
I could boil it down to the following snippet:
#include <omp.h>
int main()...
- 927
1
vote
1
answer
743
views
OpenMP Offload Error during linking with gcc with nvptx-none: unresolved symbol _fputwc_r
I am trying to compile a simple test problem using OpenMP offloading for an Nvidia GPU. I am using gcc with the nvptx-none target. I have installed the gcc+nvptx package with spack (or compiled gcc-13 ...
- 13
0
votes
1
answer
520
views
Receive side scaling (RSS) based on just one field inside UDP payload
I have an issue with HW-offloaded balancing of network packets between CPU cores on DPDK.
In my case I have only several endpoints whose number is less than the number of CPU cores I have.
All the ...
- 475
1
vote
1
answer
797
views
OpenMP offloading target map alloc - how does it work
I have always been confused and never understood how the alloc map-type of the map clause of the target (or target data) construct works.
What is my application - I would like to have a temporary ...
- 107
0
votes
1
answer
247
views
OpenMP Vs. OpenMP Offloading
I am trying to code vector addition code using OpenMP in host and OpenMP Offloading. But time taken for OpenMP offloading is more than OpenMP in host. Why is that?
openmp-host.c
#include <assert.h&...
3
votes
1
answer
579
views
OpenMP offloading on GPU, 'simd' specificities
I was wondering how to interpret the following OpenMP constructs:
#pragma omp target teams distribute parallel for
for(int i = 0; i < N; ++i) {
// compute
}
#pragma omp target teams distribute ...
- 656
0
votes
1
answer
243
views
Intel VTune - Estimate data offload to GPU
I'm interested in estimate the data transfer, in terms of bytes, of an algorithm or function to be executed on a GPU using Intel VTune. For example, if my algorithm computes a multiplication between ...
2
votes
0
answers
436
views
OpenMP offload doesn't recognize my Nvidia GPU
I'm trying to test OpenMP's GPU offloading on my machine with a GTX 1660ti card. Running this code gives me a 0.
#include <omp.h>
#include <stdio.h>
int main() {
printf("%d\n&...
1
vote
2
answers
2k
views
OpenMP offloading with Intel oneAPI DPC++ compiler to NVIDIA GPU
I'm on a mission to write a program with OpenMP offloading to a GPU. At the moment I compile my code with Intel oneAPI DPC++ compiler icpx v2022.1.0 and aim to utilise an NVIDIA Tesla V100 at the ...
- 1,033
0
votes
0
answers
82
views
Does OpenMP 5.x support classes/type bound procedures in Fortran?
It looks like OpenACC supports Fortran Type Bound Procedures. So I took that code and translated the directives to OpenMP Offloading directives and that code bombs out (memory error, using nvhpc 22.x)....
- 19
0
votes
0
answers
589
views
OpenMP: Marking functions to be included in the offloaded code
I'm trying to compile a simple vector addition example daxpy with OpenMP offloading to GPU. When I compile the code with g++ v10.2.0 I see the following error:
daxpy_loop_target.cpp:37:6: error: ...
- 1,033
2
votes
1
answer
323
views
How to correctly use the update() clause in OpenMP
I have a program that was originally being executed sequentially and now I'm trying to parallelize it via OpenMP Offloading. The thing is that when I use the update clause, depending on the case, if I ...
- 95
0
votes
0
answers
237
views
OpenMP target offloading matrix multiplication compilation error
I am currently trying to implement a simple matrix multiplication of 2 nxn matrices using OpenMP target offloading. The code is taken from here:
template<typename T>
void multiplyJIK(T *A, T *B, ...
- 31
0
votes
1
answer
599
views
Dpdk - Segmentation/fragmentation offload for application-level packet reassembly
I'm looking into the capabilities of fragment/packet reassembly hardware and wondering whether one could use them to perform application-level packet reassembly.
I have to receive and reassemble a ...
0
votes
1
answer
326
views
Why OpenMP Doesn't Offload Arrays to GPU?
I am currently writing some codes in C and want to utilize GPUs to do the calculation. My code has a test function like this:
void test_func(int *x, int N){
// x is allocated using x = malloc(N*(...
1
vote
1
answer
797
views
OpenMP Target Task reduction
I'm using OpenMP target offloading do offload some nested loops to the gpu. I'm using the nowait to tun it asynchronous. This makes it a task. With the same input values the result differs from the ...
- 92
1
vote
2
answers
863
views
DPDK19.11.10: HW offload for IPV4 with VLAN tag is not working properly
I am using DPDK19.11.10 on centos.
The application is working fine with HW offloading if I send only the IPV4 packet without the VLAN header.
If I add the VLAN header with IPV4, HW offloading is not ...
2
votes
0
answers
156
views
Python C extension compiled with nvc++ OpenMP offloading cannot run on GPU
I have a Python extension in C/C++ that I want to use OpenMP offloading with. Using NVIDIA's nvc++, compiling works out as well as using/running the extension in python.
The problem ist that it's not ...
- 92
0
votes
1
answer
221
views
Perform a triple pointer (C) offloading to NVIDIA GPU with OpenMP
I've been working with a heat transfer code. This code, basically, stablishes the initial conditions for a cube and all of its faces. The six faces start at different temperatures, and then the code ...
- 3
1
vote
0
answers
359
views
GPU number threads not showing in OpenMP runtime
I am trying out offloading an array calculation with GPU (GTX 1080Ti) using OpenMP and C++ on this dummy code that I have written:
#include <omp.h>
#include <iostream>
using namespace std;...
- 53
3
votes
1
answer
375
views
GPU array addition using OpenMP
I am trying out OpenMP offloading with an nvidia GPU and I am trying to do some array calculations with it in C++.
Right now my output is not desirable, as I am new with offloading calculations with ...
- 53
1
vote
1
answer
320
views
Errors when trying to offload to GTX-1050 with GCC9.3 and OpenMP
The build log:
-------------- Clean: Release in OffloadTest (compiler: GNU GCC Compiler)---------------
Cleaned "OffloadTest - Release"
-------------- Build: Release in OffloadTest (...
3
votes
0
answers
121
views
OpenMP offloading data race
I'm currently working on a project to invert matrices on the GPU using OpenMP. However, when normalizing a row of a matrix I have a data race.
The code looks like this:
#pragma omp target data map(...
0
votes
0
answers
481
views
Trying to load xdp on nic (offloaded)
I am trying to load my XDP program directly on the NIC (offloaded XDP).
According to this answer, I need to specify the device to the following functions:
BPF()
load_func()
I did it like so:
b = BPF(...
- 27
6
votes
1
answer
2k
views
OpenMP runtime does not sees my GPU devices
I am trying to do some OpenMP offloading to the GPU on my local machine which is employed with a GTX 1060 graphic card. All of my CUDA and Cublas examples run just fine. However, when I tried to run ...
- 341
5
votes
0
answers
2k
views
GCC fails to compile OpenMP offloading to GPU
I'm using GCC 9.3 on Ubuntu 20.04. I want to offload the famous SAXPY example to GPU using OpenMP. I installed GCC's offloading capabilities by sudo apt install gcc-9-offload-nvptx . Then compiled the ...
1
vote
1
answer
238
views
OpenMP offloading in a dynamic library fails to compile
I want to compile C code with OpenMP offloading and create a dynamic library libtest.so.
When I use the following command:
gcc -fPIC -shared -fopenmp -foffload=nvptx-none="-fPIC" test.c -o ...
- 153
1
vote
2
answers
1k
views
DPDK - RSS Offloads (Hash Calculations): ETH_RSS_IPV6_EX - Explanation
So I am currently working on understanding how to Receive Side Scaling (RSS) Offloads work inside DPDK (Data Plane Development Kit). So basically from my understanding depending on which offload you ...
- 95
0
votes
2
answers
2k
views
Do I have to build clang-11 from source on Ubuntu 18.04 to have OpenMP GPU target offload?
I installed clang-11 from https://apt.llvm.org/ on Ubuntu 18.04 and I have OpenMP host device functionality working in my C++ test project, but omp_get_num_devices() returns 0, even though I have ...
- 8,041
4
votes
0
answers
2k
views
Gcc offload compilation options
I'm trying to build the simplest OpenMP or OpenACC C++ program with GPU offload using gcc-10, CUDA 11 on Ubuntu 18.04 and this CMakeLists.txt file (or OpenMP version):
cmake_minimum_required(VERSION 3....
- 8,041
0
votes
1
answer
109
views
Intel Advisor beta offloading analysis: No execution count
I am trying to use Intel oneAPI advisor beta to do a GPU offloading analysis (via analyze.py and collect.py). I have the problem that all non offloaded regions show Cannot be modelled: No Execution ...
- 35
0
votes
1
answer
471
views
OpenMP Offloading with Private Arrays of Unknown Size at Compile Time
I am trying to offload several nested for loops in fortran using OpenMP, XL compiler suite. 90% of the routines are straight forward, but a handful of the loops involve private 1D arrays that are of ...
- 156
1
vote
0
answers
524
views
linux network acceleration ,hardware offload
I am learning network hardware acceleration in Linux kernel for quiet a long time, but there still are several problems that make me very very confused.
After deeply inspecting source code in kernel ,...
- 11
1
vote
1
answer
477
views
Declare all Fortran module variables target OpenMP 4.5+
I have a fortran90 code that use chemical species properties (i.e. molecular weight, viscosity, etc.) for calculations.
To easily swap in and out groups of chemical species, we keep module files that ...
- 156
0
votes
2
answers
419
views
Difference between offloading decision and task scheduling in context of fog computing
In context of fog computing, the computation offloading decision decides where to offload- on cloud or on fog or execute it locally. While task scheduling also decides where to execute task on fog or ...
0
votes
0
answers
343
views
Tomcat MAX Thread VS sessions
We are using protocol="org.apache.coyote.http11.Http11NioProtocol" and I have a question as to what the max concurrent sessions Tomcat can handle?
As per my understanding http11.Http11NioProtocol ...
- 11
0
votes
1
answer
40
views
Azure App Gateway SSL Offloading to a Datacentre server?
So I am looking at using Azure App Gateway to overcome a set of legacy servers (Win2003) that will not support TLS 1.2 and therefore come March+ 2020 the client browsers will not be able to access the ...
- 113
0
votes
1
answer
236
views
Debug OpenMP Python C extension offloading
I am using the modeling toolbox Anuga and have set it up to run with parallel support. To my current knowledge the mechanism behind is that Numpy is being extended by modules in C which are exposed to ...
0
votes
1
answer
312
views
Private Variables in Offloaded Fortran Parallel Loop
I am offloading code to a GPU using OpenMP 4.5. So far everything is working on the GPU, except when I try to make parallel sections with private variables that are allocated before I offload.
I am ...
- 77
0
votes
1
answer
512
views
libcoi_device.so.0 Not found Compiling Error with Intel 19.0.4 OpenMP 5.0 Offloading
I just installed Intel® Parallel Studio XE Cluster Edition for Linux*
2019 and am trying to use OpenMP to offload to a Xeon Phi accelerator. I am using cmake, with flags
CC=~/intel/bin/icc CXX=~/...
- 77
0
votes
1
answer
1k
views
Using OpenMP target offloading in llvm-8.0.0
When trying to use openmp target offloading with llvm I get the following error
$ cat offload.cpp
#include <omp.h>
int main() {
#pragma omp target teams distribute parallel for
for(int i=0; ...
- 33