feat(hw/sim): distinguish query-only and end-to-end performance cycles in retrieval benchmark

Add explicit separation between query-only cycles (accept→last) and end-to-end cycles
(load + write + noise + queries) in hardware retrieval benchmarks.

- Add query_only_cycles_per_query, load_write_noise_cycles, end_to_end_cycles metrics
- Refactor summarize_query_timings() to use accept_to_last_result_cycles as query-only base
- Add build_hardware_performance() to compute end-to-end performance separately
- Add current_sim_cycle() helper using cocotb get_sim_time
- Update CSV/Markdown outputs and RETRIEVAL_PERF_RESULT log format
- Update documentation to clarify cycle-counting methodology
- Update tests to cover new performance measurement logic

hw/sim/tests/top/utils.py

@@ -216,7 +216,7 @@ async def query_topk_once_with_latency(dut, query, timeout_cycles=None):
     ``timing`` 字段：
       - accept_to_first_result_cycles: query 接受到首个 result_valid beat
       - accept_to_last_result_cycles: query 接受到 result_last beat（Top-K 完成）
-      - total_query_cycles: 从拉高 query_valid 到 Top-K 完成的总上升沿数
+      - total_query_cycles: 纯查询事务周期，等于 accept_to_last_result_cycles
 
     ``query_ready`` 是组合信号，握手周期在上升沿前采样；结果信号在
     ReadOnly settled phase 采样，避免重新引入 query_ready 采样时序问题。
@@ -236,8 +236,10 @@ async def query_topk_once_with_latency(dut, query, timeout_cycles=None):
 
     await RisingEdge(dut.clk)
     edge_count += 1
+    q_valid = int(dut.query_valid.value)
     q_ready = int(dut.query_ready.value)
     assert q_ready, "Query accept handshake was missed despite query_ready pre-wait"
+    assert q_valid, "Query valid deasserted before accept handshake"
     accept_edge = edge_count
     dut.query_valid.value = 0
 
@@ -252,7 +254,9 @@ async def query_topk_once_with_latency(dut, query, timeout_cycles=None):
         await RisingEdge(dut.clk)
         edge_count += 1
         await ReadOnly()
-        if int(dut.result_valid.value):
+        result_valid = int(dut.result_valid.value)
+        result_ready = int(dut.result_ready.value)
+        if result_valid and result_ready:
             if first_result_edge is None:
                 first_result_edge = edge_count
             rank = int(dut.result_rank.value)
@@ -282,7 +286,7 @@ async def query_topk_once_with_latency(dut, query, timeout_cycles=None):
     timing = {
         "accept_to_first_result_cycles": int(first_result_edge - accept_edge),
         "accept_to_last_result_cycles": int(last_result_edge - accept_edge),
-        "total_query_cycles": int(edge_count),
+        "total_query_cycles": int(last_result_edge - accept_edge),
     }
     return beats, beats[0][1], beats[0][2], score_debug, timing