1. 01 Feb, 2026 1 commit
    • one's avatar
      Add kernel launch overhead benchmark and associated build scripts · 0fe0b01f
      one authored
      - Introduce kernel_launch_overhead.cu to measure kernel launch latency, system throughput, CPU dispatch overhead, and GPU dispatch time.
      - Create Makefile for building the benchmark with support for nvcc and hipcc.
      - Add run-all.sh script to execute the benchmark with specified device settings.
      0fe0b01f