implementation: started transpiler section
Some checks are pending
CI / Julia ${{ matrix.version }} - ${{ matrix.os }} - ${{ matrix.arch }} - ${{ github.event_name }} (x64, ubuntu-latest, 1.10) (push) Waiting to run
CI / Julia ${{ matrix.version }} - ${{ matrix.os }} - ${{ matrix.arch }} - ${{ github.event_name }} (x64, ubuntu-latest, 1.6) (push) Waiting to run
CI / Julia ${{ matrix.version }} - ${{ matrix.os }} - ${{ matrix.arch }} - ${{ github.event_name }} (x64, ubuntu-latest, pre) (push) Waiting to run
Some checks are pending
CI / Julia ${{ matrix.version }} - ${{ matrix.os }} - ${{ matrix.arch }} - ${{ github.event_name }} (x64, ubuntu-latest, 1.10) (push) Waiting to run
CI / Julia ${{ matrix.version }} - ${{ matrix.os }} - ${{ matrix.arch }} - ${{ github.event_name }} (x64, ubuntu-latest, 1.6) (push) Waiting to run
CI / Julia ${{ matrix.version }} - ${{ matrix.os }} - ${{ matrix.arch }} - ${{ github.event_name }} (x64, ubuntu-latest, pre) (push) Waiting to run
This commit is contained in:
@ -34,12 +34,10 @@ function interpret(expressions::Vector{Expr}, variables::Matrix{Float32}, parame
|
||||
@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)
|
||||
# If a "view" is used, then the ExpressionProcessing must be updated to always include the stop opcode at the end
|
||||
kernel = @cuda launch=false fastmath=true interpret_expression(cudaExprs, cudaVars, cudaParams, cudaResults, cudaStepsize, i)
|
||||
# config = launch_configuration(kernel.fun)
|
||||
threads = min(variableCols, 128)
|
||||
blocks = cld(variableCols, threads)
|
||||
numThreads = min(variableCols, 128)
|
||||
numBlocks = cld(variableCols, numThreads)
|
||||
|
||||
kernel(cudaExprs, cudaVars, cudaParams, cudaResults, cudaStepsize, i; threads, blocks)
|
||||
@cuda threads=numThreads blocks=numBlocks fastmath=true interpret_expression(cudaExprs, cudaVars, cudaParams, cudaResults, cudaStepsize, i)
|
||||
end
|
||||
|
||||
return cudaResults
|
||||
|
Reference in New Issue
Block a user