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

benchmarking: prepared tests for using actual data
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
2025-05-09 13:58:10 +02:00
parent 2c8a9cd2d8
commit 327e4ebf1b
3 changed files with 46 additions and 90 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
package/src/Interpreter.jl
View File

@ -23,8 +23,8 @@ 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; 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
cudaExprs = Utils.create_cuda_array(exprs, ExpressionElement(EMPTY, 0)) # column corresponds to data for one expression;
# put into seperate cuArray, as this is static and would be inefficient to send seperatly to each kernel
cudaStepsize = CuArray([Utils.get_max_inner_length(exprs), 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
# each expression has nr. of variable sets (nr. of columns of the variables) results and there are n expressions
@ -32,9 +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)
# If a "view" is used, then the ExpressionProcessing must be updated to always include the stop opcode at the end
numThreads = min(variableCols, 128)
numThreads = min(variableCols, 256)
numBlocks = cld(variableCols, numThreads)
@cuda threads=numThreads blocks=numBlocks fastmath=true interpret_expression(cudaExprs, cudaVars, cudaParams, cudaResults, cudaStepsize, i)
@ -43,7 +41,6 @@ function interpret(expressions::Vector{Expr}, variables::Matrix{Float32}, parame
return cudaResults
end
#TODO: Add @inbounds to all indexing after it is verified that all works https://cuda.juliagpu.org/stable/development/kernel/#Bounds-checking
const MAX_STACK_SIZE = 25 # The depth of the stack to store the values and intermediate results
function interpret_expression(expressions::CuDeviceArray{ExpressionElement}, variables::CuDeviceArray{Float32}, parameters::CuDeviceArray{Float32}, results::CuDeviceArray{Float32}, stepsize::CuDeviceArray{Int}, exprIndex::Int)
varSetIndex = (blockIdx().x - 1) * blockDim().x + threadIdx().x # ctaid.x * ntid.x + tid.x (1-based)