Questions tagged [intel-oneapi]

Use this tag to ask questions about the overall oneAPI programming model which provides unified developer tools that can be used across multiple hardware platforms, including a range of performance libraries spanning several workload domains. The libraries include functions custom-coded for each target architecture so the same function call delivers optimized performance across supported architectures.

220 questions
0
votes
0 answers

Can OneAPI or ROCm run natively on Windows with AMD GPU?

I am trying to identify any potential options to accelerate linear algebra calculations by using the GPU. To be more precise I need to accelerate an explicit dynamics solver. Since in each increment it solves a linear system I thought maybe I could…
Greydas
  • 1
  • 2
0
votes
0 answers

Changing LD_LIBRARY_PATH has no effect when using Intel OneAPI in Ubuntu

I was trying to compile my code with Intel Fortran compiler in Ubuntu 20. My code needs HDF5 library, which I compiled separately, and I added the HDF5 library into LD_LIBRARY_PATH.After that, my LD_LIBRARY_PATH looks like this: $ echo…
Sam Z
  • 1
  • 1
0
votes
1 answer

How to install older versions of Intel c++ compiler using apt

I want to install Intel C++ compiler version 17, 18, 19 using apt package management tool. I searched on the official Intel website, but i can't find how to install older versions. There are explanation and list about recent version of compilers.…
Antenna_
  • 147
  • 1
  • 4
  • 15
0
votes
1 answer

View report.html after DPC++ compilation for FPGA on DevCloud connected with Jupyter

I already got report.html (optimization report), but don't known how to view it. I tried complete command "firefox repotr.html" and expecting open it by web browser Firefox, but got: Command 'firefox' not found, but can be installed with: apt…
0
votes
1 answer

No kernel named was found. First SYCL app

I'm trying to code my first SYCL app. Just some falling sand. The details aren't important. just if cell has sand and cell beneath is empty move the sand, else bottom left or bottom right or if no room do nothing. I don't have anything to visualize…
Aaron
  • 81
  • 2
  • 9
0
votes
0 answers

Intel Media SDK Encoding h265 with Intra Refresh on Intel Gen 11

I can't figure out how to encode YUV file to h265 with Intra Refresh on Intel Gen 11. And I tried to run it on both linux and windows. Here is the bug I opened on GitHub with extra details: Bug. Can someone tell me what parameters I need to…
or linzer
  • 51
  • 3
0
votes
1 answer

Are dependences backwards compatible for a given compiler or does this result in some sort of undefined behavior?

I have code that was compiled with Intel version 2020.4.304 on Linux SLES 12. Over time various other versions have been added and I switched to default to OneAPI version 2021.1.1. On Windows when I update MSVS I need to update the C++…
Matt
  • 2,554
  • 2
  • 24
  • 45
0
votes
1 answer

Device-wide synchronization in SYCL on NVIDIA GPUs

Context I'm porting a complex CUDA application to SYCL which uses multiple cudaStream to launch the kernels. In addition, it also uses the default Stream in some cases, forcing a device-wide synchronization. Problem Cuda Streams can be mapped quite…
0
votes
0 answers

PageRank algorithm Runtime Errors on FPGA and GPUs using sycl

I'm having troubles doing experiments on fpga and gpu using sycl. I'm working online with intel devcloud and I get these 2 runtime errors when performing the executables: On FPGA: terminate called after throwing an instance of…
0
votes
2 answers

Use CMake to build dependency (oneTBB as git submodule) as dynamic library?

I have a project that depends on Intel's oneTBB. My project is structured as follows: external/ | - CMakeLists.txt | - oneTBB/ (this is a git submodule) | - ... include/ lib/ include/ CMakeLists.txt I currently get things to compile…
0
votes
0 answers

Can we tune the sampling precision of intel vtune to get the exactly delay of each instruction?

When I using intel vtune to profile a application with memory access mode, some instructions have huge delay in my results, which is shown below. vtune result shows huge delay of some instructions Obviously, these two register sub instructions will…
0
votes
1 answer

Race condition in tbb::concurrent_queue

I am having a data race problem on tbb::concurrent_queue. Here is the code, producer and consumer functions are running on separate threads: tbb::concurrent_queue valid_json_queue; Consumer: ... std::string valid_json; while(1) { …
avernus
  • 304
  • 1
  • 4
  • 15
0
votes
1 answer

icx(Intel® oneAPI DPC++/C++ Compiler) don't generate files with a.o extension which use the ELF format?

when I use ifx to link object which is generate by icx, it report some error.as follows ifx -O3 -ffast-math -nofor-main -DSPEC_CPU_LP64 flincs.o fsettle.fppized.o fshake.o innerf.o flincsd.o fsettled.fppized.o fshaked.o 3dview.o atomprop.o…
nino
  • 11
  • 1
0
votes
1 answer

OneAPI: Possible to statically link libraries with DPC++/OneAPI for Visual Studio?

I've just installed the Intel compiler for Visual Studio. Under the DPC++ project settings->Code Generation the only option is Multi-Threaded DLL. Searching high and low on the internet yielded no information. Does this toolset only support dynamic…
Pulpo
  • 224
  • 2
  • 12
0
votes
1 answer

linking boost on Windows asks for versioned lib

We have a large cmake based C++ project for Linux where we build boost ourselves via cmake exernal project. The project used to build also on Windows for the classical Intel compiler. But I have no access to this old running configuration. I use…
Fabian
  • 107
  • 1
  • 5