From 83d6d5888f176608565768a7dd965cc920289444 Mon Sep 17 00:00:00 2001 From: Hamidreza Norouzi Date: Sat, 27 Aug 2022 05:04:33 -0700 Subject: [PATCH 1/2] fix readme --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 6dad4e72..203eee44 100644 --- a/README.md +++ b/README.md @@ -8,7 +8,7 @@ phasicFlow uses [Kokkos]( https://github.com/kokkos/kokkos) as the backend for p # Requirements phasicFlow should work with every gnu compiler that implements C++17 standards. For now, it is tested on Ubuntu distribution of linux operating systems. If the minimum requirements are met, there should not be any problem with compiling the code. However, there are always compiler bugs from one version to another that may need you extra attempts for upgrading to newer versions or downgrading to prior versions of the compiler. * CPU builds: It requires gcc-6.x or higher. -* GPU (CUDA): NVCC-10.x or higher. +* GPU (CUDA-enabled): NVCC-10.x or higher. You also need to have CMake installed on your computer. At the moment CMake-3.22 or higher is needed. From f07be43a916cebca45a89c7da09a8c376f78718a Mon Sep 17 00:00:00 2001 From: Hamidreza Norouzi Date: Sun, 28 Aug 2022 00:31:23 -0700 Subject: [PATCH 2/2] fix readme --- README.md | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/README.md b/README.md index 203eee44..49e14d10 100644 --- a/README.md +++ b/README.md @@ -1,15 +1,18 @@ # phasicFlow -phasicFlow is a parallel C++ code for performing DEM simulations. It can run on shared-memory multi-core computational units such as multi-core CPUs or GPUs (for now it works on CUDA-enabled GPUs). The parallelization method now mainly relies on loop-level parallelization on a shared-memory computational unit. You can build and run phasic flow in serial mode on regualr PCs, build it for multi-core CPUs to be executed in parallel, or build it for a GPU device to off-load computations to GPU. +phasicFlow is a parallel C++ code for performing DEM simulations. It can run on shared-memory multi-core computational units such as multi-core CPUs or GPUs (for now it works on CUDA-enabled GPUs). The parallelization method mainly relies on loop-level parallelization on a shared-memory computational unit. You can build and run phasicFlow in serial mode on regualr PCs, in parallel mode for multi-core CPUs, or build it for a GPU device to off-load computations to a GPU. -# Required packages -phasicFlow uses [Kokkos]( https://github.com/kokkos/kokkos) as the backend for parallelization. So, you need to also have the code in the local machine alongside phasicFlow. The make system is adjusted in a way so you do not need to compile Kokkos separately and the required code is compiled alongside the phasicFlow. # Requirements +## Compilers phasicFlow should work with every gnu compiler that implements C++17 standards. For now, it is tested on Ubuntu distribution of linux operating systems. If the minimum requirements are met, there should not be any problem with compiling the code. However, there are always compiler bugs from one version to another that may need you extra attempts for upgrading to newer versions or downgrading to prior versions of the compiler. -* CPU builds: It requires gcc-6.x or higher. -* GPU (CUDA-enabled): NVCC-10.x or higher. +* for CPU builds: It requires gcc-6.x or higher. +* for GPU (CUDA-enabled): NVCC-10.x or higher. +## Required packages +phasicFlow uses [Kokkos]( https://github.com/kokkos/kokkos) as the backend for parallelization. So, you need to have the code in the local machine alongside phasicFlow. The make system is adjusted in a way so you do not need to compile Kokkos separately and the required source code files from Kokkos are compiled alongside the phasicFlow. + +## CMake You also need to have CMake installed on your computer. At the moment CMake-3.22 or higher is needed. # How to build?