feat: report a per-operator speedup range across two runs

The speedup column in a result table compares gems against torch, not one build
against another, so an A/B needs the two runs paired by shape. batch_summary
gains an --ab mode that indexes both run.logs by operator, dtype and size
detail, computes before/after per pair, and prints the per-shape rows plus the
range. Only rows that succeeded on both sides with a positive latency count, so
an incomplete pairing cannot masquerade as a complete range. When either side
carries a BENCHMARK_DIRECT_NO_CUDAGRAPH marker the range is annotated, because
a fallback row was timed under a different regime than a captured one.

ab_rlc_test.sh drives the pairing for the FlagTree RemoveLayoutConversions
switch the way ab_fold_test.sh does for the FlagGems one: per operator, run with
the enhancement off while recording autotune configs, then replay those configs
with it on, so the two sides differ by that switch alone. Each operator
therefore leaves exactly two run.log files, and the summary of each pair is
printed as it completes.

Checked on an S5000 against gelu_backward over five shapes: both sides captured
with no fallback, five rows paired, range -0.43% to +0.09%.

ab_rlc_test.sh

@@ -0,0 +1,68 @@
+#!/bin/bash
+# A/B 对比：FlagTree RemoveLayoutConversions 增强关 vs 开，逐算子两轮。
+#
+# 口径：每个算子先跑关（record autotune config），再用 REPLAY_FROM 回放同一套
+# config 跑开，两侧只差 FLAGTREE_<VENDOR>_RLC_ENHANCE 这一个开关。产物沿用
+# run_pytest.sh 的目录结构，所以每个算子恰好留下两份 run.log：
+#
+#   runs/<op>_<时间戳>/run.log   关（before）
+#   runs/<op>_<时间戳>/run.log   开（after）
+#
+# 跑完用 batch_summary.py --ab <before> <after> 得到该算子的 speedup 区间。
+#
+# 用法：
+#   OPS="softmax gelu_backward" bash ab_rlc_test.sh
+#   OPS="sort:perf_sort topk" bash ab_rlc_test.sh     # 冒号分隔 OP:OP_FILE
+#
+# 注意：RLC 开关名带厂商前缀，用 VENDOR 指定（默认 MUSA）。套用前先确认开关有效：
+# grep 该开关名于 FlagTree 源码应有命中，否则两侧跑的是同一份代码。
+set -uo pipefail
+
+cd "$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+
+VENDOR="${VENDOR:-MUSA}"
+ENHANCE_VAR="FLAGTREE_${VENDOR}_RLC_ENHANCE"
+
+# 空格分隔的算子表。元素为 OP 或 OP:OP_FILE（省略时 OP_FILE=OP）。
+OPS="${OPS:-softmax}"
+
+if [[ -t 1 && -z "${NO_COLOR:-}" ]]; then
+  export FLAGGEMS_PERF_COLOR=always
+fi
+
+LOG="runs/ab_rlc_$(date +%Y%m%d-%H%M%S).log"
+mkdir -p runs
+
+{
+  echo ">>> vendor=$VENDOR  switch=$ENHANCE_VAR  ops=$OPS"
+  for entry in $OPS; do
+    op="${entry%%:*}"
+    op_file="${entry#*:}"
+    [[ "$op_file" == "$entry" ]] && op_file="$op"
+
+    echo "########## $op | $ENHANCE_VAR=0 before (record) ##########"
+    if ! OP="$op" OP_FILE="$op_file" env "$ENHANCE_VAR=0" bash run_pytest.sh; then
+      echo "!!! FAILED before: $op"
+      continue
+    fi
+    BEFORE=$(ls -dt "runs/${op}_"* | head -1)
+
+    echo "########## $op | $ENHANCE_VAR=1 after (replay $BEFORE) ##########"
+    if ! OP="$op" OP_FILE="$op_file" REPLAY_FROM="$BEFORE" env "$ENHANCE_VAR=1" bash run_pytest.sh; then
+      echo "!!! FAILED after: $op"
+      continue
+    fi
+    AFTER=$(ls -dt "runs/${op}_"* | head -1)
+
+    echo "########## $op | summary ##########"
+    python batch_summary.py --ab "$BEFORE/run.log" "$AFTER/run.log" --label "$op" \
+      || echo "!!! summary failed: $op"
+  done
+  echo "########## ALL DONE ##########"
+} 2>&1 | tee "$LOG"
+
+# 去掉 ANSI 转义以便 grep/diff（终端输出保留颜色）
+sed -i -E $'s/\x1b\\[[0-9;]*[A-Za-z]//g' "$LOG"
+
+echo ">>> 总 log: $(pwd)/$LOG"
+echo ">>> 每算子两份 run.log 在 runs/<op>_<时间戳>/ 下，按时间先后即 before / after"

batch_summary.py

@@ -165,12 +165,82 @@ def summarize(batch_dir: Path, out_path: Optional[Path] = None) -> Path:
     return out_path
 
 
+def ab_rows(before_text: str, after_text: str) -> List[Dict[str, str]]:
+    """把两次 run.log 的测量行按 (op, dtype, size_detail) 配对。
+
+    speedup 列是 gems 对 torch，不是前后对比，所以这里用 gems_lat 自己算
+    before/after - 1。只有两侧都 SUCCESS 且延迟为正的行才计入；对不上的行
+    单独返回，避免用不完整的配对报一个看起来完整的区间。
+    """
+    def index(text: str) -> Dict[Tuple[str, str, str], float]:
+        out: Dict[Tuple[str, str, str], float] = {}
+        for row in parse_run_log(text):
+            if row.get("row_status") != "SUCCESS":
+                continue
+            try:
+                lat = float(row.get("gems_lat", ""))
+            except ValueError:
+                continue
+            if lat > 0:
+                out[(row.get("fg_op_name", ""), row.get("dtype", ""),
+                     row.get("size_detail", ""))] = lat
+        return out
+
+    before, after = index(before_text), index(after_text)
+    paired: List[Dict[str, str]] = []
+    for key in sorted(before.keys() & after.keys()):
+        op, dtype, size = key
+        b, a = before[key], after[key]
+        paired.append({
+            "fg_op_name": op, "dtype": dtype, "size_detail": size,
+            "before_lat": f"{b:.6f}", "after_lat": f"{a:.6f}",
+            "speedup_percent": f"{(b / a - 1.0) * 100.0:.2f}",
+        })
+    return paired
+
+
+def report_ab(before: Path, after: Path, label: str = "") -> List[Dict[str, str]]:
+    """打印一个算子的前后对比：逐行 speedup 与整体区间。"""
+    before_text = before.read_text(encoding="utf-8", errors="replace")
+    after_text = after.read_text(encoding="utf-8", errors="replace")
+    rows = ab_rows(before_text, after_text)
+    name = label or (rows[0]["fg_op_name"] if rows else "?")
+    if not rows:
+        print(f"[ab] {name}: 没有可配对的测量行"
+              f"（before={before} after={after}）")
+        return rows
+    values = [float(r["speedup_percent"]) for r in rows]
+    for r in rows:
+        print(f"  {r['dtype']:<16} {float(r['speedup_percent']):+7.2f}%  "
+              f"{r['before_lat']} -> {r['after_lat']}  {r['size_detail']}")
+    fallback = ""
+    if DIRECT_NO_CUDAGRAPH_RE.search(before_text) or \
+            DIRECT_NO_CUDAGRAPH_RE.search(after_text):
+        # 回退行用的是 do_bench 口径，与 cudagraph 行不同表可比性
+        fallback = "  [含 BENCHMARK_DIRECT_NO_CUDAGRAPH 回退行]"
+    print(f"[ab] {name}: {len(rows)} 行配对，speedup "
+          f"{min(values):+.2f}% ~ {max(values):+.2f}%{fallback}")
+    return rows
+
+
 def main() -> None:
     p = argparse.ArgumentParser(description=__doc__.splitlines()[0])
-    p.add_argument("batch_dir", type=Path, help="run_batch.py 的产物目录")
+    p.add_argument("batch_dir", type=Path, nargs="?",
+                   help="run_batch.py 的产物目录")
     p.add_argument("-o", "--output", type=Path, default=None,
                    help="输出 CSV（默认 <batch_dir>/summary.csv）")
+    p.add_argument("--ab", nargs=2, type=Path, metavar=("BEFORE", "AFTER"),
+                   help="两份 run.log，按 shape 配对输出该算子的 speedup 区间")
+    p.add_argument("--label", default="", help="--ab 报告里的算子名")
     args = p.parse_args()
+    if args.ab:
+        for path in args.ab:
+            if not path.is_file():
+                raise SystemExit(f"run.log 不存在: {path}")
+        report_ab(args.ab[0], args.ab[1], args.label)
+        return
+    if args.batch_dir is None:
+        raise SystemExit("需要 batch_dir，或用 --ab BEFORE AFTER")
     if not args.batch_dir.is_dir():
         raise SystemExit(f"目录不存在: {args.batch_dir}")
     out = summarize(args.batch_dir, args.output)