Browsed by
Category: Compilers

Topics on use of the most common compilers in HPC

Python 3.13.0 built with LLVM 19 and full LTO

Python 3.13.0 built with LLVM 19 and full LTO

Finally! We managed to compile the code of Python 3.13.0 using LLVM 19, with full link-time optimization (LTO): The installation passes all 44 standard optimization tests: Using random seed: 4347316840:00:00 load avg: 1.72 Run 44 tests sequentially in a single process0:00:00 load avg: 1.72 [ 1/44] test_array0:00:00 load avg: 1.72 [ 2/44] test_base640:00:00 load avg: 1.72 [ 3/44] test_binascii0:00:00 load avg: 1.72 [ 4/44] test_binop0:00:00 load avg: 1.72 [ 5/44] test_bisect0:00:00 load avg: 1.72 [ 6/44] test_bytes0:00:03 load avg: 1.67…

Read More Read More

Towards full adoption of LLVM: building a productive SQLite3 library installation required by TensorFlow

Towards full adoption of LLVM: building a productive SQLite3 library installation required by TensorFlow

Nowadays, the management of TensorFlow models using the SQLite3 library is becoming more and more demanded. It has become a standard practice for applicants for HPC resources to insist on accessing an optimized installation of the SQLite3 library, and avoid the one provided by the Linux distribution or delivered by Conda. Until one becomes involved in dealing with the constant changing of large sets of models, that might seem like an exaggeration or overstatement. It should be noted that the…

Read More Read More

Discoverer is advancing its commitment towards the full adoption of the LLVM compiler infrastructure

Discoverer is advancing its commitment towards the full adoption of the LLVM compiler infrastructure

The new version of the LLVM Compiler Infrastructure, 19, is available in the software repository. That version includes numerous improvements and fixes. We uphold our commitment to maintain openness and transparency in our way of doing system and software engineering, which entails consistently publishing our build recipes. In the case of LLVM 19, those recipes are publicly available here: https://gitlab.discoverer.bg/vkolev/recipes/-/tree/main/llvm/19 Adopting the LLVM 19 puts a new milestone in our computation model. We can start confidently moving the entire executables…

Read More Read More

Major update to the hosted LLVM compiler collections

Major update to the hosted LLVM compiler collections

The Discoverer’s software repository received a major update to the hosted LLVM compiler collections. Versions 16.0.0-16.0.6 and 17.0.0-17.0.6 are available and the LLVMgold plugin is included in all bundles. We thoroughly examined the hosted LLVM compiler collections by employing the clang and clang++ compilers to compile C and C++ code projects like GROMACS and NAMD. Despite the absence of significant issues with the compilation of C and C++ code, it is expected that the compilation of Fortran code using flang…

Read More Read More

The Discoverer bids farewell to the era-old Intel compilers

The Discoverer bids farewell to the era-old Intel compilers

The latest version of Intel oneAPI – 2024.0.0 – is now available in Discoverers open-source software repository. One big change in the new version is that the classic Intel compilers are no longer available. As of version 2024.0, they have been excluded from the bundle. The users have to load one of the available pre-2024.0 versions if they need access to any of the classic compilers. The old versions of Intel oneAPI (≤2023.2) that include the classic compilers will remain…

Read More Read More

GCC compiler collection on Discoverer receives yet another update

GCC compiler collection on Discoverer receives yet another update

It seems that July has been a busy month for many GCC code developers. The project released a minor new version of GCC, 13.2, which addresses problems discovered in the previously released 13.1 version. More information on the included fixes and changes can be found here: https://gcc.gnu.org/gcc-13/changes.html The code of 13.2 was compiled and installed in the public software repository to provide our users with the most up-to-date version of GCC 13. The build recipe the compilation process is based…

Read More Read More

Discoverer is LLVM-ready

Discoverer is LLVM-ready

We’ve been examining the deployment of LLVM compiler infrastructure in high-performance computing for more than a year. LLVM compilers provide novel and significantly more optimal and reliable schemas for the generation of binary code. More and more source code distributions come with LLVM-compatible CMake configurations. GROMACS is one of them. The Python universe of applications also actively adopts LLVM for HPC. Numba is one of those applications. It serves as a foundation for the development of bindings for the creation of…

Read More Read More

Discoverer receives a massive GCC compiler collection update

Discoverer receives a massive GCC compiler collection update

In an effort to support more effective code compilation and code optimisation, we have updated the GCC compiler collection installation available in the public software repository. This update brings to the repository GCC versions 13.1.0, 12.3.0, and 11.4.0. Each new version includes GMP, MPC, MPFR, and iSL libraries. Zstandard 1.5.5 is linked as an external compressor. For optimal workload, we optimised those libraries by adding support for AVX2 SIMD extensions. Currently, AVX2 is the highest SIMD extension supported by the…

Read More Read More

Intel retire their C/C++ classic compiler in mid 2023

Intel retire their C/C++ classic compiler in mid 2023

Intel® C++ Compiler Classic (icc) is deprecated and will be removed in a oneAPI release in the second half of 2023. Intel recommends that customers transition now to using the LLVM-based Intel® oneAPI DPC++/C++ Compiler (icx) for continued Windows* and Linux* support, new language support, new language features, and optimizations. https://community.intel.com/t5/Intel-oneAPI-IoT-Toolkit/DEPRECATION-NOTICE-Intel-C-Compiler-Classic/m-p/1412267 What that means for the users of Discoverer HPC who need to compile their C and C++ code by using Intel® C/C++/Fortran compiler? The classic compilers icc, icpc, ifort…

Read More Read More

Create high productive CP2K 2022.1 build that works on AMD Zen2 microarchitecture

Create high productive CP2K 2022.1 build that works on AMD Zen2 microarchitecture

CP2K is a quantum chemistry and solid state physics software package that can perform atomistic simulations of solid state, liquid, molecular, periodic, material, crystal, and biological systems. While it can be successfully compiled by using Intel oneAPI, Intel oneAPI MKL, and Intel MPI, the produced executables cannot run simulations of large systems on AMD Zen2 CPU. For instance, the SCF minimization fails by sending “Segmentation fault” message to the standard error. The debugging results point to a problem with handling…

Read More Read More

WordPress Appliance - Powered by TurnKey Linux