Bug#996958: ITP: mumax -- GPU accelerated micromagnetic simulator
> This sentence was copy/pasted from http://mumax.github.io/. I haven't really > started working on the package yet, nor am I a regular user. I see. > I guess you should ask upstream rather than me, I'm just a poor packager in > this case :-) Thanks. signature.asc Description: PGP signature
Bug#996958: ITP: mumax -- GPU accelerated micromagnetic simulator
Le 21/10/2021 à 15:13, Thaddeus H. Black a écrit : That's a neat project. The README.md says: if you don't have git: * seriously, no git? The question is not whether one does not have git, but whether one does not have CUDA, unfortunately. Yes, this will have to go to contrib. The Design and Verification of mumax3: http://scitation.aip.org/content/aip/journal/adva/4/10/10.1063/1.4899186 The hyperlink seems to be paywalled or broken. Same for me. You write: A speed-up of the order of 100x compared to CPU-based simulations can easily be reached Since I am unable to view the paper, would you briefly, approximately tell me how you achieved the speed-up? Alternately, would you link me to relevant presentation slides, a presentation video, or the like? Again alternately, would you advise me in which source file one should look for the core of the main loop, where the 100x speed-up is implemented? This sentence was copy/pasted from http://mumax.github.io/. I haven't really started working on the package yet, nor am I a regular user. […] Anyway, if you believe that your code is a good example, then I'd be interested to see how you have achieved the 100x. I guess you should ask upstream rather than me, I'm just a poor packager in this case :-) Roland.
Bug#996958: ITP: mumax -- GPU accelerated micromagnetic simulator
That's a neat project. The README.md says: > if you don't have git: > > * seriously, no git? The question is not whether one does not have git, but whether one does not have CUDA, unfortunately. > The Design and Verification of mumax3: > > http://scitation.aip.org/content/aip/journal/adva/4/10/10.1063/1.4899186 The hyperlink seems to be paywalled or broken. You write: > A speed-up of the order of 100x compared to CPU-based simulations can > easily be reached Since I am unable to view the paper, would you briefly, approximately tell me how you achieved the speed-up? Alternately, would you link me to relevant presentation slides, a presentation video, or the like? Again alternately, would you advise me in which source file one should look for the core of the main loop, where the 100x speed-up is implemented? I ask because I have a simulation that improperly relies on g++'s optimizer to vectorize the simulation's main loop, the elements being 64+64 = 128-bit complex doubles. Even if my loop technique were not clumsy and 15 years outdated, the optimizer goes only to SSE hardware, and not (as far as I can tell by reviewing the disassembly) to the GPU at all. One could try OpenCL, of course; but without a good example to follow, I'd probably flounder around six months trying to figure out how to apply OpenCL intelligently Anyway, if you believe that your code is a good example, then I'd be interested to see how you have achieved the 100x. signature.asc Description: PGP signature
Bug#996958: ITP: mumax -- GPU accelerated micromagnetic simulator
Package: wnpp Severity: wishlist Owner: Roland Mas X-Debbugs-Cc: debian-de...@lists.debian.org * Package name: mumax Version : 3.10 Upstream Author : Arne Vansteenkiste * URL : https://github.com/mumax/3 * License : GPL-3 Programming Lang: Go Description : GPU accelerated micromagnetic simulator mumax3 is a GPU-accelerated micromagnetic simulation program developed at the DyNaMat group of Prof. Van Waeyenberge at Ghent University. A speed-up of the order of 100x compared to CPU-based simulations can easily be reached, even with relatively inexpensive gaming GPUs. Additionally, the software is optimized for low memory use and can handle about 16 million FD cells with 2GB of GPU RAM. Features: - Landau-Lifshitz micromagnetic formalism - Magnetostatic field - Heisenberg exchange - Arbitrary inter-region exchange like RKKY coupling - Dzyaloshinskii-Moriya interaction - Spin-transfer torque (Zhang-Li and Slonczewski) - Uniaxial and cubic magnetocrystalline anisotropy - Thermal fluctuations (Brown) - Voronoi tessellation - Time- and space dependent material parameters - Arbitrary complex excitation (field, current) - Simulation window can automatically follow a moving domain wall - Edge charges can be removed to simulate an infinitely long geometry - Optional 1D, 2D or 3D periodic boundary conditions