[GPU] evaluateDerivatives (SPH and SolidSPH)#456

Open

ldowen wants to merge 81 commits intodevelopfrom

feature/gpu/eval-deriv

Commits on Aug 20, 2025

Created the FlexPointer class and a basic capture test
ldowen
committed

Commits on Aug 21, 2025

Remove unnecessary delete kernel launches
ldowen
committed
Update chai submodule, changed getPointer to data, removed FlexPointer and replaced tests with managed pointer tests
ldowen
committed

Commits on Aug 25, 2025

Commits on Sep 16, 2025

Commits on Sep 25, 2025

Merge branch 'feature/gpu/kernel' into feature/gpu/art_visc
ldowen
committed

Commits on Sep 26, 2025

Create a wrapper for chai::managed_ptr and update the managed pointer tests
ldowen
committed

Commits on Oct 6, 2025

Merge branch 'feature/gpu/kernel' into feature/gpu/art_visc
ldowen
committed

Commits on Oct 13, 2025

Commits on Oct 15, 2025

Commits on Oct 16, 2025

Commits on Oct 17, 2025

Art Visc mostly working but still issue with RZ and handling inheritance of value member data/functions
ldowen
committed

Commits on Oct 22, 2025

Commits on Oct 24, 2025

Commits on Oct 29, 2025

Commits on Oct 30, 2025

Merge branch 'feature/gpu/kernel' into feature/gpu/art_visc
ldowen
committed

Commits on Nov 5, 2025

Added gpu-rdc compile and link flag, made eigen geometry routines, some utility routines, and QPiij functions host device, added a eigenvector cpp test, removed use of the Tensor one and zero stati…
ldowen
committed

Commits on Nov 6, 2025

Commits on Nov 10, 2025

Change compiler warning cmake options back no having spheral prefix
ldowen
committed

Commits on Nov 12, 2025

Commits on Nov 18, 2025

Commits on Nov 21, 2025

Commits on Nov 24, 2025

Merge branch 'feature/gpu/kernel' into feature/gpu/art_visc
ldowen
committed

Commits on Dec 1, 2025

Commits on Dec 2, 2025

Changed art visc View.cc to ViewInline.hh, added rdc CMake flag that cannot be used ATM, going back to building a CXX shared library if python is enabled
ldowen
committed

Commits on Dec 4, 2025

Merge branch 'feature/gpu/kernel' into feature/gpu/art_visc
ldowen
committed

Commits on Dec 10, 2025

Commits on Dec 15, 2025

Commits on Dec 16, 2025

Merge branch 'develop' into feature/gpu/art_visc
ldowen
committed

Commits on Dec 17, 2025

Commits on Dec 18, 2025

Commits on Dec 20, 2025

Commits on Jan 5, 2026

Added the SPHERAL_ENABLE_OPENMP CMake variable and compiler definition, added openmp as one of the cpp test execution options, fixed the cpp tests so gpu counters are only filled if the test is a p…
ldowen
committed

Commits on Jan 12, 2026

Added RAJA atomic wrappers for tensor and vector geometry classes, fixed type discrepancy in artificial viscosity classes, added basic exec policy to config that is subject to improvement, started …
ldowen
committed

Commits on Jan 15, 2026

Added ~fortran variant to silo, WIP eval deriv GPU loop
ldowen
committed

Commits on Jan 28, 2026

Many nasty dev changes for hackathon purposes, switched rocm version to 6.4.3
ldowen
committed

Commits on Jan 30, 2026