{
  "action": "Replace the threadgroup-memory softmax reduction
             with a register-only reduction: each SIMD group
             owns 8 query rows and reduces across lanes with
             simd_shuffle_xor, removing a threadgroup_barrier.",
  "difficulty_1_to_5": 4,
  "impacts": {
    "memory_bandwidth":  8,
    "register_pressure": 4,   // risk: spill if Br > 8
    "compute_hw_fit":    9    // SIMD width 32; keep tile 8x8
  },
  "overall_rating_0_to_10": 8,
  "confidence_0_to_1": 0.7
}