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

benchmarking: further tests done. Seems like transpiler takes ages, need to investigate further
Some checks failed
CI / Julia ${{ matrix.version }} - ${{ matrix.os }} - ${{ matrix.arch }} - ${{ github.event_name }} (x64, ubuntu-latest, 1.10) (push) Has been cancelled
Details
CI / Julia ${{ matrix.version }} - ${{ matrix.os }} - ${{ matrix.arch }} - ${{ github.event_name }} (x64, ubuntu-latest, 1.6) (push) Has been cancelled
Details
CI / Julia ${{ matrix.version }} - ${{ matrix.os }} - ${{ matrix.arch }} - ${{ github.event_name }} (x64, ubuntu-latest, pre) (push) Has been cancelled
Details

Browse Source
This commit is contained in:
Daniel
2025-05-11 16:54:19 +02:00
parent 5b31fbb270
commit 3d80ae95e4
6 changed files with 39 additions and 38 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
package/src/Interpreter.jl
View File

@ -18,7 +18,7 @@ function interpret(expressions::Vector{Expr}, variables::Matrix{Float32}, parame
@inbounds for i in eachindex(expressions)
exprs[i] = ExpressionProcessing.expr_to_postfix(expressions[i])
end
variableCols = size(variables, 2) # number of variable sets to use for each expression
cudaVars = CuArray(variables)
cudaParams = Utils.create_cuda_array(parameters, NaN32) # column corresponds to data for one expression
@ -30,7 +30,7 @@ function interpret(expressions::Vector{Expr}, variables::Matrix{Float32}, parame
cudaResults = CuArray{Float32}(undef, variableCols, length(exprs))
# Start kernel for each expression to ensure that no warp is working on different expressions
@inbounds for i in eachindex(exprs)
@inbounds Threads.@threads for i in eachindex(exprs)
numThreads = min(variableCols, 256)
numBlocks = cld(variableCols, numThreads)