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

implementation: started writing interpreter section; finished CPU-side part; also found error with interpreter
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
2025-04-27 13:17:35 +02:00
parent e571fa5bd6
commit 101b13e7e7
8 changed files with 278 additions and 57 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
package/src/Interpreter.jl
View File

@ -23,7 +23,7 @@ function interpret(expressions::Vector{Expr}, variables::Matrix{Float32}, parame
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
cudaExprs = Utils.create_cuda_array(exprs, ExpressionElement(EMPTY, 0)) # column corresponds to data for one expression
cudaExprs = Utils.create_cuda_array(exprs, ExpressionElement(EMPTY, 0)) # column corresponds to data for one expression; TODO: replace this 0 with 'undef' if possible
# put into seperate cuArray, as this is static and would be inefficient to send seperatly to every kernel
cudaStepsize = CuArray([Utils.get_max_inner_length(parameters), size(variables, 1)]) # max num of values per expression; max nam of parameters per expression; number of variables per expression
@ -32,6 +32,7 @@ function interpret(expressions::Vector{Expr}, variables::Matrix{Float32}, parame
# Start kernel for each expression to ensure that no warp is working on different expressions
@inbounds for i in eachindex(exprs)
# TODO: Currently only the first expression gets evaluated. Either use a view on "cudaExprs" to determine the correct expression or extend cudaStepsize to include this information (this information was removed in a previous commit)
kernel = @cuda launch=false fastmath=true interpret_expression(cudaExprs, cudaVars, cudaParams, cudaResults, cudaStepsize, i)
# config = launch_configuration(kernel.fun)
threads = min(variableCols, 128)