benchmarking: added tests for performance tuning with Nsight compute and systems

package/test/PerformanceTuning.jl

@@ -0,0 +1,30 @@
+using CUDA
+
+using .Transpiler
+using .Interpreter
+
+varsets_medium = 1000
+X = randn(Float32, 5, varsets_medium)
+
+exprsGPU = [
+	# CPU interpreter requires an anonymous function and array ref s
+	:(p1 * x1 + p2), # 5 op
+	:((((x1 + x2) + x3) + x4) + x5), # 9 op
+	:(log(abs(x1))), # 3 op
+	:(powabs(p2 - powabs(p1 + x1, 1/x1),p3)) # 13 op
+] # 30 op
+
+# p is the same for CPU and GPU
+p = [randn(Float32, 10) for _ in 1:length(exprsGPU)] # generate 10 random parameter values for each expr
+expr_reps = 1
+
+
+
+@testset "Interpreter Tuning" begin
+    CUDA.@profile interpret_gpu(exprsGPU, X, p; repetitions=expr_reps)
+end
+
+
+@testset "Transpiler Tuning" begin
+    CUDA.@profile evaluate_gpu(exprsGPU, X, p; repetitions=expr_reps)
+end