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

implementation: finished interpreter 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
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
2025-05-01 14:36:14 +02:00
parent 101b13e7e7
commit c4187a131e
5 changed files with 79 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
package/src/Interpreter.jl
View File

@ -33,6 +33,7 @@ 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
kernel = @cuda launch=false fastmath=true interpret_expression(cudaExprs, cudaVars, cudaParams, cudaResults, cudaStepsize, i)
# config = launch_configuration(kernel.fun)
threads = min(variableCols, 128)
@ -48,7 +49,7 @@ end
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)
@inbounds variableCols = length(variables) / stepsize[2]
@inbounds variableCols = length(variables) / stepsize[2] # number of variable sets
if varSetIndex > variableCols
return
@ -79,29 +80,29 @@ function interpret_expression(expressions::CuDeviceArray{ExpressionElement}, var
operationStackTop += 1
operationStack[operationStackTop] = reinterpret(Float32, expr.Value)
elseif expr.Type == OPERATOR
type = reinterpret(Operator, expr.Value)
if type == ADD
opcode = reinterpret(Operator, expr.Value)
if opcode == ADD
operationStackTop -= 1
operationStack[operationStackTop] = operationStack[operationStackTop] + operationStack[operationStackTop + 1]
elseif type == SUBTRACT
elseif opcode == SUBTRACT
operationStackTop -= 1
operationStack[operationStackTop] = operationStack[operationStackTop] - operationStack[operationStackTop + 1]
elseif type == MULTIPLY
elseif opcode == MULTIPLY
operationStackTop -= 1
operationStack[operationStackTop] = operationStack[operationStackTop] * operationStack[operationStackTop + 1]
elseif type == DIVIDE
elseif opcode == DIVIDE
operationStackTop -= 1
operationStack[operationStackTop] = operationStack[operationStackTop] / operationStack[operationStackTop + 1]
elseif type == POWER
elseif opcode == POWER
operationStackTop -= 1
operationStack[operationStackTop] = operationStack[operationStackTop] ^ operationStack[operationStackTop + 1]
elseif type == ABS
elseif opcode == ABS
operationStack[operationStackTop] = abs(operationStack[operationStackTop])
elseif type == LOG
elseif opcode == LOG
operationStack[operationStackTop] = log(operationStack[operationStackTop])
elseif type == EXP
elseif opcode == EXP
operationStack[operationStackTop] = exp(operationStack[operationStackTop])
elseif type == SQRT
elseif opcode == SQRT
operationStack[operationStackTop] = sqrt(operationStack[operationStackTop])
end
else