evaluation: found thath benchmark 2 can't be executed by any implementation due to RAM constraints

package/src/ExpressionExecutorCuda.jl

@@ -16,7 +16,7 @@ export interpret_gpu,interpret_cpu
 export evaluate_gpu
 
 # Some assertions:
-# Variables and parameters start their naming with "1" meaning the first variable/parameter has to be "x1/p1" and not "x0/p0"
+# Variables and parameters start their indexing with "1" meaning the first variable/parameter has to be "x1/p1" and not "x0/p0"
 # Matrix X is column major
 # each index i in exprs has to have the matching values in the column i in Matrix X so that X[:,i] contains the values for expr[i]. The same goes for p
 #     This assertion is made, because in julia, the first index doesn't have to be 1
@@ -109,14 +109,4 @@ function interpret_cpu(exprs::Vector{Expr}, X::Matrix{Float32}, p::Vector{Vector
 	res
 end
 
-# Flow
-# input: Vector expr    == expressions contains eg. 4 expressions
-#        Matrix X       == |expr| columns, n rows. n == number of variabls x1..xn; n is the same for all expressions --- WRONG
-#        Matrix X       == k columns, n rows. k == number of variables in the expressions (every expression must have the same number of variables); n == number of different values for xk where k is the column
-#        VectorVector p == vector size |expr| containing vector size m. m == number of parameters per expression. p can be different for each expression
-# 
-# The following can be done on the CPU
-#     convert expression to postfix notation (mandatory)
-#     optional: replace every parameter with the correct value (should only improve performance if data transfer is the bottleneck)
-
 end

package/src/Interpreter.jl

@@ -24,7 +24,7 @@ function interpret(cudaExprs, numExprs::Integer, exprsInnerLength::Integer,
 	cudaResults = CuArray{Float32}(undef, variableColumns, numExprs)
 
 	# Start kernel for each expression to ensure that no warp is working on different expressions
-	numThreads = min(variableColumns, 121)
+	numThreads = min(variableColumns, 128)
 	numBlocks = cld(variableColumns, numThreads)
 
 	Threads.@threads for i in 1:numExprs # multithreaded to speedup dispatching (seems to have improved performance)

package/src/Transpiler.jl

@@ -19,7 +19,7 @@ function evaluate(expressions::Vector{ExpressionProcessing.PostfixType}, cudaVar
 	# each expression has nr. of variable sets (nr. of columns of the variables) results and there are n expressions
 	cudaResults = CuArray{Float32}(undef, variableColumns, length(expressions))
 
-	threads = min(variableColumns, 256)
+	threads = min(variableColumns, 128)
 	blocks = cld(variableColumns, threads)
 	
 	kernelName = "evaluate_gpu"