Dear Yuri, have you tried compiling yourself? You could test less aggressive compiler options, like -O0, -O1, -O2, and leave out -ffast-math. Best regards, Markus
Now I tried compiling elk with the latest Intel OneAPI compiler and linking against the latest MKL. Our test above runs at 2m23s (with a single MKL thread), so very close to the result with gcc/AOCL. But still a bit worse than gcc + OpenBLAS. Warning: Do not use -xHost! This produces a super-slow executable. Instead, use the following line for ifort: F90_OPTS = -O3 -march=skylake-avx512 -ipo -qopenmp -qmkl=sequential The problems with a slow codepath for MKL on AMD that were reported in the past...
You can find one now in the Elk Users forum.
Hi all, just a quick guide for newcomers for compiling elk 8.7.10 on a Workstation (or a PC) running Ubuntu 22.04 LTS. Download elk from the Sourceforge website. Create a new directory in your user folder (e.g. "elk" and move the .tgz file here). Open a Terminal and type "cd elk". Unpack the file with "tar -xvzf elk-8.7.10.tgz". Go to the new directory with "cd elk-8.7.10". Edit the file make.inc, you can use your graphical text editor (or nano): We build a single-node version, i.e. without MPI....
Hello and welcome! There's a ton of examples in the examples folder, just have a look at these. Start with the basic examples. Elk uses just one single input file, elk.in. You can generate your structure with the spacegroup utility, have a look at the elk manual. Happy computing!
By the way.... I'm testing the machine with Ubuntu 22.04.2 LTS' openblas / lapack / fftw3 packages. Indeed, this is pretty performant and runs the test described above in 2m17s when setting OPENBLAS_NUM_THREADS=1. But please note that other tasks might work better on AOCL, depends certainly on the usage of certain routines where AOCL or OpenBLAS+FFTW3 outperform, respectively. But embarrassingly for AMD, HPL spits out an optimized 944 GFLOP/s with Ubuntu's openblas. So it seems that running elk with...
Sure, here's a minimal make.inc for gfortran. I've stripped off all the comments etc. This is a make.inc for the single-threaded version of blis, which is fine for a workstation. Except maybe for diagonalizing the BSE hamiltonian or running molecules in a large vacuum cell, where you don't have k-point parallelism; here you would want to link the multi-threaded library and create a separate executable for only these tasks. MAKE = make AR = ar SRC_MKL = mkl_stub.f90 SRC_OBLAS = oblas_stub.f90 SRC_BLIS...
Dear elkies, here I just want to quickly share some (unscientific) benchmarks of the Ryzen 9 7950X CPU with HPL and elk. TLDR: This CPU is a beast! I link against the latest AOCL 4.0, using F90_LIB = -lblis -lflame -lfftw3 -lfftw3f HPL gives me an optimized 910 GFLOP/s, however limited by the small 32 GB RAM in my system. Note that SMT should be disabled and we run 16 MPI processes or 16 threads. Now let's throw in elk 8.7.10. We do the basic/HfSiO4 example, but to give the CPU some work, we increase...