concept & design: improved existing sections
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:
@ -24,7 +24,7 @@ function interpret(expressions::Vector{Expr}, variables::Matrix{Float32}, parame
|
||||
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
|
||||
# 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(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
|
||||
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
|
||||
|
||||
# each expression has nr. of variable sets (nr. of columns of the variables) results and there are n expressions
|
||||
cudaResults = CuArray{Float32}(undef, variableCols, length(exprs))
|
||||
@ -46,20 +46,20 @@ 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)
|
||||
variableCols = length(variables) / stepsize[3]
|
||||
@inbounds variableCols = length(variables) / stepsize[2]
|
||||
|
||||
if varSetIndex > variableCols
|
||||
return
|
||||
end
|
||||
|
||||
firstExprIndex = ((exprIndex - 1) * stepsize[1]) + 1 # Inclusive
|
||||
lastExprIndex = firstExprIndex + stepsize[1] - 1 # Inclusive
|
||||
firstParamIndex = ((exprIndex - 1) * stepsize[2]) # Exclusive
|
||||
# firstExprIndex = ((exprIndex - 1) * stepsize[1]) + 1 # Inclusive
|
||||
# lastExprIndex = firstExprIndex + stepsize[1] - 1 # Inclusive
|
||||
@inbounds firstParamIndex = ((exprIndex - 1) * stepsize[1]) # Exclusive
|
||||
|
||||
operationStack = MVector{MAX_STACK_SIZE, Float32}(undef) # Try to get this to function with variable size too, to allow better memory usage
|
||||
operationStackTop = 0 # stores index of the last defined/valid value
|
||||
|
||||
firstVariableIndex = ((varSetIndex-1) * stepsize[3]) # Exclusive
|
||||
@inbounds firstVariableIndex = ((varSetIndex-1) * stepsize[2]) # Exclusive
|
||||
|
||||
@inbounds for expr in expressions
|
||||
if expr.Type == EMPTY
|
||||
|
Reference in New Issue
Block a user