Add CPU Interpreter and a test case.

package/src/ExpressionExecutorCuda.jl

@@ -2,7 +2,12 @@ module ExpressionExecutorCuda
 include("ExpressionProcessing.jl")
 include("Interpreter.jl")
 
-export interpret_gpu
+module CpuInterpreter
+include("Code.jl")
+include("CpuInterpreter.jl")
+end
+
+export interpret_gpu,interpret_cpu
 export evaluate_gpu
 export test
 
@@ -22,8 +27,21 @@ function evaluate_gpu(exprs::Vector{Expr}, X::Matrix{Float32}, p::Vector{Vector{
 	# Look into this to maybe speed up PTX generation: https://cuda.juliagpu.org/stable/tutorials/introduction/#Parallelization-on-the-CPU
 end
 
-end
 
+# Evaluate Expressions on the CPU
+function interpret_cpu(exprs::Vector{Expr}, X::Matrix{Float32}, p::Vector{Vector{Float32}})::Matrix{Float32}
+	@assert axes(exprs) == axes(p)
+	nrows = size(X, 1)
+	
+	# each column of the matrix has the result for an expr
+	res = Matrix{Float32}(undef, nrows, length(exprs))
+
+	for i in eachindex(exprs) 
+		CpuInterpreter.interpret!((@view res[:,i]), exprs[i], X, p[i])
+	end
+
+	res
+end
 
 
 # Flow
@@ -35,3 +53,5 @@ end
 # 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