Maciej Waruszewski
Maciej Waruszewski
See the title. Works in a `CUDA` kernel and in `KA` on Julia 1.4.1. MWE ``` using CUDA using KernelAbstractions function cuda_kernel(A) @inbounds A[1] = eps(A[1]) nothing end @kernel function...
The following code ``` using KernelAbstractions using CuArrays struct S{FT} dummy1::FT dummy2::Int x::FT end @kernel function kernel!(s::S, a, b, dummy3, dummy4) sin(s.x) @inbounds a[1] = b[1] end let FT =...
``` using KernelAbstractions using KernelAbstractions.Extras: @unroll using CuArrays @kernel function kernel!(::Val{nreduce}, ::Val{Nq}) where {nreduce, Nq} s_MJQ = @localmem Float64 (Nq * Nq) i, j = @index(Local, NTuple) @inbounds begin @unroll...
``` using KernelAbstractions @kernel function kernel_index!(a) i = KernelAbstractions.@index(Global) @inbounds a[i] = i end let a = zeros(1) kernel! = kernel_index!(CPU(), 1, 1) event = kernel!(a) wait(event) end ``` fails...
This PR aims to bring some of the functionality added in https://github.com/CliMA/ClimateMachine.jl/pull/2188 to the Atmos model. It adds Kennedy Gruber split form of the Atmos model equations using the tendency...
Recently I ran into a surprising (for me) behavior demonstrated by the MWE below ``` using CuArrays, CUDAnative, GPUifyLoops function kernel(rho, T) P = rho[1] * T[1] if (abs(P -...
The motivation is that there could be different backends for the same device, e.g. a single threaded and multithreaded backend for CPUs. The current usage of `Device` looks to me...
The following code can fail on Sunspot with `(max_a, max_b) = (2, 2)`. It doesn't happen with `GATOR_DISABLE=1`. It also doesn't fail when `SYCL_PI_LEVEL_ZERO_USE_IMMEDIATE_COMMANDLISTS=1`. I am using the experimental runtime...
I am not familiar with this code at all, but this line looks suspect to me and it caused overflows in some of my DP-SCREAM runs: https://github.com/E3SM-Project/E3SM/blob/f50d2639c68c1607a521407b420af040080c1380/share/streams/shr_dmodel_mod.F90#L386 Shouldn't it be...