ParallelStencil.jl 0.7.1

Release notes

• Make shared memory allocation robust for compilation throughout all CUDA/AMDGPU versions (#98)

ParallelStencil.jl 0.7.0

Release notes

• Add keyword memopt to @parallel and @parallel_indices, exposing generalized optimization of fast memory usage (of registers and shared memory) (#81, #94 )
• Add support for AMDGPU (#69, #81 , #93, #95 )
• Add support for arrays of small arrays/structs leveraging CellArrays via keywords in the hardware-agnostic allocators (#54, #95)
• Add @fill, @falses and trues allocators (#54)
• Enable allocation with enums using @fill and @rand (#62)
• Support numbertype omission in ParallelStencil initialization (#47)
• Add macro to compute harmonic averages (#57)
• Add documentation for memopt optimization, CellArrays and AMDGPU (#97)
• Add support for CUDA v4 (#81)
• Add support for Julia 1.9 (#81)

ParallelStencil.jl 0.6.1

Release notes

• Fix incremental compilation issue when using @hide_communication (#83)

ParallelStencil.jl 0.6.0

Release notes

• Add support for explicit use of architecture-agnostic low level kernel language constructs in @parallel_indices kernels (#43)
• Fix, improve and unify all unit tests (#44)

ParallelStencil.jl 0.5.7

Release notes

• Make kernel launch parameter computation also for small problems performance-negligable (#39)

ParallelStencil.jl 0.5.6

Release notes

• Fix TagBot release draft workflow (initiated in #37, fixed here)

ParallelStencil.jl 0.5.5

Release notes

• Add environment variable PS_THREAD_BOUND_CHECK to enable deactivation of thread bounds check (#34)
• Ignore startup file in unit tests (#35)

ParallelStencil.jl 0.5.4

Release notes

• Adjust the examples scalar_porowaves2D.jl and HydroMech2D.jl to be compatible with CUDA.jl >= v3 (#25)

ParallelStencil.jl 0.5.3

Release notes

• Add support for CUDA 3 (#24)
• Skip CUDA unit tests if CUDA not functional (#24)

ParallelStencil.jl 0.5.2

Release notes

• Add support for Julia 1.6 (#21)