master-thesis/package/src/Interpreter.jl

module Interpreter
using CUDA

export CudaTest

@enum Operators Add=1 Subtract=2 Multiply=3 Division=4 Power=5 Abs=6 Log=7 Exp=8 Sqrt=9

function CudaTest()
	N = 2^20
	x = CUDA.fill(1.0f0, N)
	y = CUDA.fill(2.0f0, N)

	kernelAdd = @cuda launch=false InterpretExplicit!(Add, x, y)
	config = launch_configuration(kernelAdd.fun)
	threads = min(length(y), config.threads)
	blocks = cld(length(y), threads)
	
	kernelAdd(Add, x, y; threads, blocks)
	println(y[1])
	# @test all(Array(y) .== 3.0f0)
	
	kernelSubtract = @cuda launch=false InterpretExplicit!(Subtract, x, y)
	configSub = launch_configuration(kernelSubtract.fun)
	threadsSub = min(length(y), configSub.threads)
	blocksSub = cld(length(y), threadsSub)
	CUDA.fill!(y, 2.0f0)
	
	kernelSubtract(Subtract, x, y; threadsSub, blocksSub)
	# @test all(Array(y) .== -1.0f0)
	println(y[1])
end


# Kernel
function InterpretExplicit!(op::Operators, x, y)
	index = (blockIdx().x - 1) * blockDim().x + threadIdx().x
	stride = gridDim().x * blockDim().x

	if op == Add
		@cuprintln("Performing Addition") # Will only be displayed when the GPU is synchronized
		for i = index:stride:length(y)
			@inbounds y[i] += x[i]
		end
		return
	elseif op == Subtract
		@cuprintln("Performing Subtraction") # Will only be displayed when the GPU is synchronized
		for i = index:stride:length(y)
			@inbounds y[i] -= x[i]
		end
		return
	end
end

end