Runs llama-bench pp512 at 24 CU, 40 CU, then 24 CU again with cooldown
between each state. Uses UMR to toggle SPI_PG_ENABLE_STATIC_WGP_MASK.
Auto-detects model, bench binary, and UMR paths.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>