benchmarking: redid inbounds tests because first test run did not use inbounds everywhere

package/src/Transpiler.jl

@@ -71,12 +71,12 @@ function evaluate(expressions::Vector{Expr}, variables::Matrix{Float32}, paramet
 	cudaResults = CuArray{Float32}(undef, variableCols, length(expressions))
 
 	# execute each kernel (also try doing this with Threads.@threads. Since we can have multiple grids, this might improve performance)
-	@inbounds for i in eachindex(kernels)
+	for kernel in kernels
 		# config = launch_configuration(kernels[i])
 		threads = min(variableCols, 256)
 		blocks = cld(variableCols, threads)
 
-		cudacall(kernels[i], (CuPtr{Float32},CuPtr{Float32},CuPtr{Float32}), cudaVars, cudaParams, cudaResults; threads=threads, blocks=blocks)
+		cudacall(kernel, (CuPtr{Float32},CuPtr{Float32},CuPtr{Float32}), cudaVars, cudaParams, cudaResults; threads=threads, blocks=blocks)
 	end
 
 	return cudaResults

package/test/PerformanceTests.jl

@@ -64,6 +64,8 @@ end
 	# https://cuda.juliagpu.org/v2.6/lib/driver/#Memory-Management
 end
 
+After these tests have been redone, use Nsight Compute/Systems as described here: 
+#https://cuda.juliagpu.org/stable/development/profiling/#NVIDIA-Nsight-Systems
 compareWithCPU = true
 
 
@@ -172,15 +174,3 @@ else
 	println(oldVsGPUT_std)
 end
 
-
-
-
-
-
-
-
-REDO @inbounds performance tests because I added more @inbounds and removed not needed code from interpreter
-Also updated Expression processing and transpiler
-
-After these tests have been redone, use Nsight Compute/Systems as described here: 
-#https://cuda.juliagpu.org/stable/development/profiling/#NVIDIA-Nsight-Systems