;; Test Fused Pipeline - Should be much faster than interpreted
;;
;; This uses the fused-pipeline primitive which compiles all effects
;; into a single CUDA kernel instead of interpreting them one by one.

(stream "fused_pipeline_test"
  :fps 30
  :width 1920
  :height 1080
  :seed 42

  ;; Load primitives
  (require-primitives "streaming_gpu")
  (require-primitives "image")
  (require-primitives "math")

  ;; Define the effects pipeline (compiled to single CUDA kernel)
  (def effects-pipeline
    [{"op" "rotate" "angle" 0}
     {"op" "zoom" "amount" 1.0}
     {"op" "hue_shift" "degrees" 30}
     {"op" "ripple" "amplitude" 15 "frequency" 10 "decay" 2 "phase" 0 "center_x" 960 "center_y" 540}
     {"op" "brightness" "factor" 1.0}])

  ;; Frame pipeline
  (frame
    (let [;; Create a gradient image
          r (+ 0.5 (* 0.5 (math:sin (* t 1))))
          g (+ 0.5 (* 0.5 (math:sin (* t 1.3))))
          b (+ 0.5 (* 0.5 (math:sin (* t 1.7))))
          color [(* r 255) (* g 255) (* b 255)]
          base (image:make-image 1920 1080 color)

          ;; Dynamic parameters (change per frame)
          angle (* t 30)
          zoom (+ 1.0 (* 0.2 (math:sin (* t 0.5))))
          phase (* t 2)]

      ;; Apply fused pipeline - all effects in ONE CUDA kernel!
      (streaming_gpu:fused-pipeline base effects-pipeline
        :rotate_angle angle
        :zoom_amount zoom
        :ripple_phase phase))))