Daniel/master-thesis
1
0
Fork 0
Code Issues 3 Pull Requests Actions 1 Packages Projects 1 Releases Wiki Activity

benchmarking: moved compilation of kernel to evaluate function, as it required too much memory
Some checks are pending
CI / Julia ${{ matrix.version }} - ${{ matrix.os }} - ${{ matrix.arch }} - ${{ github.event_name }} (x64, ubuntu-latest, 1.10) (push) Waiting to run
Details
CI / Julia ${{ matrix.version }} - ${{ matrix.os }} - ${{ matrix.arch }} - ${{ github.event_name }} (x64, ubuntu-latest, 1.6) (push) Waiting to run
Details
CI / Julia ${{ matrix.version }} - ${{ matrix.os }} - ${{ matrix.arch }} - ${{ github.event_name }} (x64, ubuntu-latest, pre) (push) Waiting to run
Details

Browse Source
This commit is contained in:
Daniel
2025-05-19 11:58:24 +02:00
parent f33551e25f
commit e29199d865
2 changed files with 7 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
package/src/Transpiler.jl
View File

@ -35,7 +35,7 @@ end
"
A simplified version of the evaluate function. It takes a list of already compiled kernels to be executed. This should yield better performance, where the same expressions should be evaluated multiple times i.e. for parameter optimisation.
"
function evaluate(kernels::Vector{CuFunction}, cudaVars::CuArray{Float32}, nrOfVariableSets::Integer, parameters::Vector{Vector{Float32}})::Matrix{Float32}
function evaluate(kernels::Vector{String}, cudaVars::CuArray{Float32}, nrOfVariableSets::Integer, parameters::Vector{Vector{Float32}}, kernelName::String)::Matrix{Float32}
cudaParams = Utils.create_cuda_array(parameters, NaN32) # maybe make constant (see PerformanceTests.jl for more info)
@ -46,7 +46,8 @@ function evaluate(kernels::Vector{CuFunction}, cudaVars::CuArray{Float32}, nrOfV
blocks = cld(nrOfVariableSets, threads)
@inbounds Threads.@threads for i in eachindex(kernels)
cudacall(kernels[i], (CuPtr{Float32},CuPtr{Float32},CuPtr{Float32}), cudaVars, cudaParams, cudaResults; threads=threads, blocks=blocks)
compiledKernel = CompileKernel(kernel[i], kernelName)
cudacall(compiledKernel, (CuPtr{Float32},CuPtr{Float32},CuPtr{Float32}), cudaVars, cudaParams, cudaResults; threads=threads, blocks=blocks)
end
return cudaResults