Image

Run PiperSR benchmark suite

Runs the PiperSR 2x benchmark suite (A-G). Tiled pipeline (A-E): single-tile latency, batch throughput, full-frame 720p, sustained 300 frames, resolution sweep. Full-frame pipeline (F): auto-discovers all PiperSR_2x_video_* models, compares cpuAndNeuralEngine vs all compute units, reports p50/p95/p99 percentiles. End-to-end (G): synthetic H.264 through full decode/upscale/encode path. Takes 60-120 seconds. Only one benchmark can run at a time (429 if concurrent).

post/v1/benchmark/upscale

Request

  • Base URL: http://localhost:9998
  • URL: http://localhost:9998/v1/benchmark/upscale
  • Auth: HTTP bearer

Response

Benchmark results with timing data and recommendation

single_tileobject

Benchmark A: Single tile latency (1000 iterations)

batch_throughputobject

Benchmark B: Batch throughput at sizes 1/2/4/8

full_frame720pobject

Benchmark C: Full frame pipeline at 720p

sustainedobject

Benchmark D: 300-frame sustained throughput

resolution_sweepobject[]

Benchmark E: 480p, 720p, 1080p pipeline timing

full_frame_pipelineobject[] nullable

Benchmark F: Per-model full-frame results with compute unit comparison and p50/p95/p99

end_to_endobject nullable

Benchmark G: End-to-end H.264 pipeline throughput with I/O overhead

recommendationstring
formatted_tablestring

ASCII-formatted results table

Changes

No recorded changes to this operation across all 1 revision of this API.