Add NCCL PDF matrix topology report

configs/multinode_nccl_nccl227_pdf_matrix.yaml

@@ -0,0 +1,88 @@
+tools:
+  install_dir: /opt/gpu-test-tools
+
+report:
+  output_dir: ./reports
+  format: md
+
+multinode_nccl:
+  enabled: true
+  mode: cross-leaf-pdf-matrix-nccl-2.27.7
+  hosts:
+    - name: nccl-gpu-1
+      addr: 172.72.8.12
+      slots: 8
+    - name: nccl-gpu-2
+      addr: 172.72.8.16
+      slots: 8
+  ssh_user: root
+  ssh_preflight: true
+  mpirun_path: /usr/mpi/gcc/openmpi-4.1.9a1/bin/mpirun
+  mpi_ld_preload: null
+  extra_ld_library_path:
+    - /usr/mpi/gcc/openmpi-4.1.9a1/lib
+    - /tmp/nccl-2.27.7-cuda12.4/usr/lib/x86_64-linux-gnu
+    - /usr/local/cuda-12.4/targets/x86_64-linux/lib
+  nccl_tests_dir: null
+  tests:
+    - all_reduce_perf
+    - alltoall_perf
+  topologies:
+    - nodes: 2
+      gpus_per_node: 1
+      label: 2 nodes x 1 GPU (PDF 2 machines 2 GPUs)
+      min_peak_busbw_gbps:
+        allreduce: 48.90
+        alltoall: 27.25
+    - nodes: 2
+      gpus_per_node: 2
+      label: 2 nodes x 2 GPUs (PDF 2 machines 4 GPUs)
+      min_peak_busbw_gbps:
+        allreduce: 136.93
+        alltoall: 54.41
+    - nodes: 2
+      gpus_per_node: 4
+      label: 2 nodes x 4 GPUs (PDF 2 machines 8 GPUs)
+      cuda_visible_devices: 0,1,4,5
+      op_env:
+        alltoall:
+          NCCL_IB_QPS_PER_CONNECTION: 4
+          NCCL_MIN_NCHANNELS: 4
+          NCCL_IB_SPLIT_DATA_ON_QPS: 1
+      min_peak_busbw_gbps:
+        allreduce: 335.48
+        alltoall: 73.73
+    - nodes: 2
+      gpus_per_node: 8
+      label: 2 nodes x 8 GPUs (PDF 2 machines 16 GPUs)
+      min_peak_busbw_gbps:
+        allreduce: 491.84
+        alltoall: 76.54
+  begin_size: 16G
+  end_size: 16G
+  step_factor: 2
+  warmup_iters: 10
+  gpus_per_rank: 1
+  timeout_sec: 1800
+  debug: INFO
+  socket_ifname: bond0
+  oob_tcp_ifname: bond0
+  plm_rsh_args: "-o StrictHostKeyChecking=accept-new -o ConnectTimeout=10 -o ServerAliveInterval=30"
+  ib_gid_index: 3
+  ib_sl: 5
+  ib_tc: 136
+  ib_hca: mlx5_0,mlx5_1,mlx5_6,mlx5_7
+  ib_timeout: 22
+  qps_per_connection: null
+  min_nchannels: null
+  net_plugin: none
+  nvls_enable: 1
+  split_data_on_qps: null
+  extra_env:
+    NCCL_DEBUG_SUBSYS: INIT,NET
+    NCCL_NET_GDR_LEVEL: 5
+    NCCL_NET_GDR_READ: 1
+    NCCL_DMABUF_ENABLE: 0
+  min_peak_busbw_gbps:
+    allreduce: 0
+    alltoall: 0

modules/multinode_nccl_test.py

@@ -95,10 +95,14 @@ class MultiNodeNCCLTest:
                 "nodes": nodes,
                 "gpus_per_node": gpus_per_node,
                 "label": topo.get("label") or f"{nodes} nodes x {gpus_per_node} GPUs",
+                "cuda_visible_devices": topo.get("cuda_visible_devices"),
+                "env": topo.get("env") or {},
+                "op_env": topo.get("op_env") or topo.get("test_env") or {},
+                "min_peak_busbw_gbps": topo.get("min_peak_busbw_gbps"),
             })
         return normalized
 
-    def _env_exports(self) -> list[tuple[str, str]]:
+    def _env_exports(self, topo: dict = None, label: str = None, binary: str = None) -> list[tuple[str, str]]:
         env_cfg = {
             "NCCL_DEBUG": self.cfg.get("debug", "WARN"),
             "NCCL_SOCKET_IFNAME": self.cfg.get("socket_ifname"),
@@ -124,11 +128,29 @@ class MultiNodeNCCLTest:
             )
         extra_env = self.cfg.get("extra_env") or {}
         if isinstance(extra_env, dict):
-            for key, value in extra_env.items():
+            self._merge_env(env_cfg, extra_env)
-                if value is not None:
+        if topo:
-                    env_cfg[str(key)] = str(value)
+            if topo.get("cuda_visible_devices"):
+                env_cfg["CUDA_VISIBLE_DEVICES"] = str(topo["cuda_visible_devices"])
+            if isinstance(topo.get("env"), dict):
+                self._merge_env(env_cfg, topo["env"])
+            op_env = topo.get("op_env")
+            if isinstance(op_env, dict):
+                for key in (label, binary):
+                    overrides = op_env.get(key)
+                    if isinstance(overrides, dict):
+                        self._merge_env(env_cfg, overrides)
         return [(k, str(v)) for k, v in env_cfg.items() if v is not None]
 
+    @staticmethod
+    def _merge_env(env_cfg: dict, overrides: dict):
+        for key, value in overrides.items():
+            key = str(key)
+            if value is None:
+                env_cfg.pop(key, None)
+            else:
+                env_cfg[key] = str(value)
+
     def _mpi_ld_preload(self) -> str:
         preload = self.cfg.get("mpi_ld_preload")
         if isinstance(preload, list):
@@ -253,7 +275,7 @@ class MultiNodeNCCLTest:
         plm_rsh_args = self.cfg.get("plm_rsh_args")
         if plm_rsh_args:
             cmd.extend(["--mca", "plm_rsh_args", str(plm_rsh_args)])
-        for key, value in self._env_exports():
+        for key, value in self._env_exports(topo=topo, label=label, binary=os.path.basename(binary)):
             cmd.extend(["-x", f"{key}={value}"])
 
         cmd.extend([
@@ -286,7 +308,7 @@ class MultiNodeNCCLTest:
 
         parsed = self._parse_nccl_output(r.stdout)
         net_diag = self._parse_network_diagnostics(r.stdout + "\n" + r.stderr)
-        threshold = self._threshold_for(label)
+        threshold = self._threshold_for(label, topo)
         wrong = sum(row.get("wrong", 0) for row in parsed["by_size"])
         has_bw = parsed["peak_busbw_gbps"] > 0
         status = "PASS" if r.returncode == 0 and has_bw and wrong == 0 and parsed["peak_busbw_gbps"] >= threshold else "FAIL"
@@ -296,6 +318,7 @@ class MultiNodeNCCLTest:
             "gpus_per_node": gpus_per_node,
             "ranks": ranks,
             "hosts": selected_hosts,
+            "cuda_visible_devices": topo.get("cuda_visible_devices"),
             "command": " ".join(cmd),
             "returncode": r.returncode,
             "status": status,
@@ -313,10 +336,31 @@ class MultiNodeNCCLTest:
             "finished_at": datetime.now().isoformat(),
         }
 
-    def _threshold_for(self, label: str) -> float:
+    def _threshold_for(self, label: str, topo: dict = None) -> float:
+        if topo and topo.get("min_peak_busbw_gbps") is not None:
+            topo_thresholds = topo.get("min_peak_busbw_gbps")
+            if isinstance(topo_thresholds, dict):
+                return float(topo_thresholds.get(label, 0) or 0)
+            return float(topo_thresholds or 0)
+
         thresholds = self.cfg.get("min_peak_busbw_gbps") or {}
         if isinstance(thresholds, dict):
-            return float(thresholds.get(label, 0) or 0)
+            op_threshold = thresholds.get(label, 0)
+            if isinstance(op_threshold, dict):
+                keys = []
+                if topo:
+                    keys.extend([
+                        topo.get("label"),
+                        f"{topo.get('nodes')}x{topo.get('gpus_per_node')}",
+                        f"{topo.get('nodes')} nodes x {topo.get('gpus_per_node')} GPUs",
+                        str(topo.get("gpus_per_node")),
+                    ])
+                keys.append("default")
+                for key in keys:
+                    if key in op_threshold:
+                        return float(op_threshold.get(key) or 0)
+                return 0.0
+            return float(op_threshold or 0)
         return float(thresholds or 0)
 
     @staticmethod

modules/report.py

@@ -481,13 +481,14 @@ class ReportGenerator:
             lines.append("")
             for op, data in (multinode.get("tests") or {}).items():
                 lines.append(f"### Multi-node NCCL {op}\n")
-                lines.append("| Topology | Peak Bus BW | Peak Size | Avg Bus BW | Threshold | Status |")
+                lines.append("| Topology | CUDA Visible Devices | Peak Bus BW | Peak Size | Avg Bus BW | Threshold | Status |")
-                lines.append("|----------|-------------|-----------|------------|-----------|--------|")
+                lines.append("|----------|----------------------|-------------|-----------|------------|-----------|--------|")
                 for topo in data.get("topologies", []):
                     threshold = topo.get("min_required_gbps", 0) or 0
                     threshold_text = f">= {threshold:.0f} GB/s" if threshold else "-"
+                    cuda_visible = topo.get("cuda_visible_devices") or "-"
                     lines.append(
-                        f"| {topo.get('label', '')} | {topo.get('peak_busbw_gbps', 0):.2f} GB/s | "
+                        f"| {topo.get('label', '')} | {cuda_visible} | {topo.get('peak_busbw_gbps', 0):.2f} GB/s | "
                         f"{topo.get('peak_size', '')} | {topo.get('avg_busbw_gbps', 0):.2f} GB/s | "
                         f"{threshold_text} | {topo.get('status', '?')} |"
                     )

reports_multinode_nccl_diagnosis_20260523.md

@@ -14,6 +14,8 @@
 
 继续 tuning 后发现，配置里固定的 `NCCL_MIN_NCHANNELS=4`、`NCCL_IB_QPS_PER_CONNECTION=4`、`NCCL_IB_SPLIT_DATA_ON_QPS=1` 会明显压低 16G allreduce。去掉这些固定参数、让 NCCL 2.27.7 自动选择后，正式脚本报告中 2 节点 x 8 GPU allreduce 提升到 `354.60 GB/s`，alltoall 小幅提升到 `30.01 GB/s`。当前剩余问题不再是 GDR disabled，而是 GDR enabled 且 NCCL 自动调参后，仍低于当前配置里的验收阈值。
 
+按 `sx算力节点跨Leaf NCCL测试报告.pdf` 的矩阵继续对齐后，发现 2 机 4 卡档位的核心问题是默认 GPU 选择不符合 GPU-NIC 亲和性。显式选择 `CUDA_VISIBLE_DEVICES=0,1,4,5` 后，2 机 4 卡 allreduce 可以恢复到 `333-335 GB/s` 区间，接近 PDF 的 `335.48 GB/s`；alltoall 配合 PDF 固定 NCCL 参数可到 `72.93 GB/s`，接近 PDF 的 `73.73 GB/s`。但 2 机 8 卡档位仍只有 allreduce `354.02 GB/s`、alltoall `30.04 GB/s`，与 PDF 的 `491.84/76.54 GB/s` 差距明显。
+
 同时，`nccl-gpu-2` 的 SSH 入口曾因未认证连接过多触发 `MaxStartups` 随机拒绝，导致 `mpirun` 拉起远端 rank 失败。已经做了临时 SSHD 缓解并拿到有效的 2 节点 x 8 GPU allreduce/alltoall 报告。
 
 ## 已完成的修正
@@ -29,6 +31,8 @@
 9. 从 NVIDIA apt 源下载但不安装 `libnccl2=2.27.7-1+cuda12.4`，解压到两台机器 `/tmp/nccl-2.27.7-cuda12.4`，用 `LD_LIBRARY_PATH` 临时覆盖 NCCL 运行库验证。
 10. 增强报告解析，能够区分 `GPU Direct RDMA ENABLED` 和 `DISABLED`，并列出 enabled/disabled HCA。
 11. 将 multi-node NCCL 配置中的 `qps_per_connection`、`min_nchannels`、`split_data_on_qps` 改为 `null`，避免默认导出会压低大包 allreduce 的固定 NCCL 参数。
+12. 增加 topology 级 `cuda_visible_devices`、`env`、`op_env` 配置能力，支持按 GPU/NIC 亲和性和不同 NCCL op 分别设置环境变量。
+13. 生成 PDF 矩阵式原始报告 `reports_multinode_nccl_pdf_matrix_nccl227.md`，覆盖 2 机 1/2/4/8 GPU per node。
 
 ## 关键证据
 
@@ -224,6 +228,50 @@ NET/IB : GPU Direct RDMA Disabled for HCA 0 'mlx5_0'
 
 带宽仍约 `13.4 GB/s`。测试后已经恢复默认 `peerdirect_support=0,persistent_api_support=1`。
 
+### 7. PDF 矩阵对齐与 GPU-NIC 亲和性
+
+参考 PDF 的跨 Leaf 命令覆盖 2 机 2/4/8/16 卡矩阵，并使用：
+
+- `NCCL_IB_GID_INDEX=3`
+- `NCCL_IB_SL=5`
+- `NCCL_IB_TC=136`
+- `NCCL_SOCKET_IFNAME=bond0`
+- `NCCL_IB_TIMEOUT=22`
+- `NCCL_NET_PLUGIN=none`
+- `NCCL_NVLS_ENABLE=1`
+
+本环境与 PDF 参考机器有一个关键硬件差异：当前两台机器只有 `mlx5_0,mlx5_1,mlx5_6,mlx5_7` 是 400Gb/s NDR；`mlx5_4,mlx5_5` 是 100Gb/s HDR；`mlx5_2,mlx5_8` 是 25Gb/s；`mlx5_3,mlx5_9` 为 DOWN。参考 PDF 的命令列出了更多 HCA，但当前节点不能等价使用为 8 条 400G rail。
+
+`nvidia-smi topo -m` 显示：
+
+| GPU | 最近的 400G HCA |
+|-----|-----------------|
+| GPU0 | `mlx5_0` |
+| GPU1 | `mlx5_1` |
+| GPU4 | `mlx5_6` |
+| GPU5 | `mlx5_7` |
+
+默认 2 机 4 卡会选择 GPU0/1/2/3，其中 GPU2 最近的是 25G/down 端口，GPU3 没有直接对应 400G rail。因此 2 机 4 卡默认 allreduce 只有约 `168 GB/s`。显式设置 `CUDA_VISIBLE_DEVICES=0,1,4,5` 后：
+
+| 场景 | allreduce | alltoall | 说明 |
+|------|-----------|----------|------|
+| 默认 GPU0/1/2/3 | `167.89 GB/s` | `39.68 GB/s` | GPU/NIC 亲和性错误 |
+| `CUDA_VISIBLE_DEVICES=0,1,4,5` + auto NCCL | `335.34 GB/s` | `63.90 GB/s` | allreduce 接近 PDF |
+| `CUDA_VISIBLE_DEVICES=0,1,4,5` + PDF 固定参数 | `225.29 GB/s` | `73.10 GB/s` | alltoall 接近 PDF，但 allreduce 被压低 |
+
+因此当前脚本支持按 op 配环境变量：4 卡 allreduce 用 auto，4 卡 alltoall 用 PDF 固定参数。
+
+矩阵式正式报告：`reports_multinode_nccl_pdf_matrix_nccl227.md`
+
+| Topology | allreduce | PDF Reference | Status | alltoall | PDF Reference | Status |
+|----------|-----------|---------------|--------|----------|---------------|--------|
+| 2 nodes x 1 GPU | `47.23 GB/s` | `48.90 GB/s` | FAIL | `24.84 GB/s` | `27.25 GB/s` | FAIL |
+| 2 nodes x 2 GPUs | `136.97 GB/s` | `136.93 GB/s` | PASS | `47.67 GB/s` | `54.41 GB/s` | FAIL |
+| 2 nodes x 4 GPUs | `333.22 GB/s` | `335.48 GB/s` | FAIL | `72.93 GB/s` | `73.73 GB/s` | FAIL |
+| 2 nodes x 8 GPUs | `354.02 GB/s` | `491.84 GB/s` | FAIL | `30.04 GB/s` | `76.54 GB/s` | FAIL |
+
+解释：2 机 4 卡档位已经基本定位并修复到接近 PDF；2 机 8 卡档位不是简单 GPU 顺序问题。尝试调整 8 卡 `CUDA_VISIBLE_DEVICES` 顺序、加入 100G/25G active HCA、以及套 PDF 固定参数都没有改善；固定参数反而会把 8 卡 allreduce 从约 `354 GB/s` 压到约 `239 GB/s`。
+
 ## 当前阻塞
 
 ### 阻塞 1：当前生产 NCCL 版本过旧，GDR 被禁用
@@ -236,15 +284,18 @@ NET/IB : GPU Direct RDMA Disabled for HCA 0 'mlx5_0'
 
 判断：底层 RDMA 能力存在，GDR 禁用主要由旧 NCCL 版本触发。建议正式安装并固定 NCCL 2.27.7+cuda12.4 或更新的已验证版本。
 
-### 阻塞 2：GDR enabled 且 NCCL 自动调参后带宽仍低于当前阈值
+### 阻塞 2：2 机 8 GPU 档位仍低于 PDF 参考值
 
 现象：
 
-- 2x8 16G allreduce：`354.60 GB/s`，阈值 `>= 480 GB/s`
+- 2x8 16G allreduce：`354.02 GB/s`，PDF 参考 `491.84 GB/s`
-- 2x8 16G alltoall：`30.01 GB/s`，阈值 `>= 75 GB/s`
+- 2x8 16G alltoall：`30.04 GB/s`，PDF 参考 `76.54 GB/s`
 - 已使用 4 个 400Gb/s HCA：`mlx5_0, mlx5_1, mlx5_6, mlx5_7`
+- 加入 `mlx5_4,mlx5_5` 100G HCA 或 `mlx5_2,mlx5_8` 25G HCA 基本无收益
+- 调整 8 卡 `CUDA_VISIBLE_DEVICES` 顺序基本无收益
+- 套 PDF 固定参数会让 8 卡 allreduce 明显变差
 
-判断：需要确认当前 PDF/config 阈值是否适用于跨 Leaf 两节点场景；如果阈值确实要求跨 Leaf 也达到这些数值，则还需要继续查链路聚合、多 rail 使用、交换网络、NCCL net plugin/SHARP 或 rail mapping。
+判断：2 机 8 GPU 档位的剩余差距更像硬件 rail 数量/交换网络/路由/拥塞/NCCL net plugin 能力问题，不再是旧 NCCL GDR disabled 或 4 卡 GPU 选择问题。
 
 ### 阻塞 3：`nccl-gpu-2` SSH 存在外部连接压力
 
@@ -261,10 +312,12 @@ NET/IB : GPU Direct RDMA Disabled for HCA 0 'mlx5_0'
 
 1. 从网络/安全侧处理 `172.239.10.85` 等来源的 SSH 未认证连接压力，或者保留更高的 `MaxStartups` 配置作为测试窗口临时策略。
 2. 正式安装并固定已验证的 NCCL 2.27.7+cuda12.4 或更新版本，不要依赖 pip NCCL 2.21.5；当前 `/tmp/nccl-2.27.7-cuda12.4` 只是临时解压验证。
-3. multi-node NCCL 默认不要固定 `NCCL_MIN_NCHANNELS=4`、`NCCL_IB_QPS_PER_CONNECTION=4`、`NCCL_IB_SPLIT_DATA_ON_QPS=1`；当前脚本配置已改成 `null`，让 NCCL 自动选择。
+3. 4 卡 per node 测试应显式使用 `CUDA_VISIBLE_DEVICES=0,1,4,5`，避免默认 GPU0/1/2/3 落到错误 GPU/NIC 亲和性。
-4. 尝试安装或启用匹配当前 OFED/driver 的 NCCL net plugin/SHARP；当前日志显示 `Could not find: libnccl-net.so`，NCCL 使用的是 internal IB plugin。
+4. 4 卡 allreduce 建议继续让 NCCL 自动选择 channel/QP；4 卡 alltoall 如果要贴近 PDF，可单独套 `NCCL_IB_QPS_PER_CONNECTION=4`、`NCCL_MIN_NCHANNELS=4`、`NCCL_IB_SPLIT_DATA_ON_QPS=1`。
-5. 核对跨 Leaf 链路的 rail mapping、交换机端口速率、路由和拥塞计数，确认 4 个 400Gb/s HCA 是否都在跨节点通信中充分利用。
+5. 8 卡 per node 不建议套上述固定参数，会降低 allreduce；继续用 auto。
-6. 确认当前 `allreduce >= 480 GB/s`、`alltoall >= 75 GB/s` 阈值是否应直接用于跨 Leaf 两节点场景；如果是，继续按链路和 NCCL rail 聚合方向排查。
+6. 尝试安装或启用匹配当前 OFED/driver 的 NCCL net plugin/SHARP；当前日志显示 `Could not find: libnccl-net.so`，NCCL 使用的是 internal IB plugin。
+7. 核对跨 Leaf 链路的 rail mapping、交换机端口速率、路由和拥塞计数，确认 4 个 400Gb/s HCA 是否都在跨节点通信中充分利用。
+8. 确认当前 PDF 的 `491.84/76.54 GB/s` 是否要求当前这两台节点在只有 4 条 400G rail 的形态下也达到；如果要求一致，需要网络/硬件侧继续介入。
 
 ## 当前可交付物
 
@@ -273,9 +326,11 @@ NET/IB : GPU Direct RDMA Disabled for HCA 0 'mlx5_0'
 - `configs/multinode_nccl_nccl227_sweep.yaml`：NCCL 2.27.7 1M 到 4G sweep 配置
 - `configs/multinode_nccl_nccl227_16g.yaml`：NCCL 2.27.7 16G 大包配置
 - `configs/multinode_nccl_nccl227_auto_16g.yaml`：NCCL 2.27.7 16G 自动 channel/QP 配置
+- `configs/multinode_nccl_nccl227_pdf_matrix.yaml`：按 PDF 矩阵和 GPU 亲和性优化后的跨 Leaf 配置
 - `reports_multinode_nccl_diagnostic_2x8_sshfix.md`：脚本生成的原始 2x8 诊断报告
 - `reports_multinode_nccl_diagnostic_2x8_nccl227_v2.md`：NCCL 2.27.7 256M 诊断报告
 - `reports_multinode_nccl_sweep_2x8_nccl227.md`：NCCL 2.27.7 1M 到 4G sweep 报告
 - `reports_multinode_nccl_16g_2x8_nccl227.md`：NCCL 2.27.7 16G 大包报告
 - `reports_multinode_nccl_16g_2x8_nccl227_auto.md`：NCCL 2.27.7 16G 自动 channel/QP 原始报告
+- `reports_multinode_nccl_pdf_matrix_nccl227.md`：NCCL 2.27.7 PDF 矩阵式原始报告
 - `reports_multinode_nccl_diagnosis_20260523.md`：本中文诊断总结

reports_multinode_nccl_pdf_matrix_nccl227.md

@@ -0,0 +1,83 @@
+# GPU Test Report
+
+- **Date:** 2026-05-23T08:32:58.113416
+- **Host:** aikubeworker0012
+
+## Overall Acceptance Verdict
+
+**Result: FAIL**
+
+Missing required evidence:
+- GPU Info
+- Health Check
+- Memory Bandwidth
+- Compute Throughput
+- NVLink/NVSwitch
+- NCCL
+- Stress Test
+- RDMA
+- DCGM
+- Training
+
+## Summary
+
+| Test | Result |
+|------|--------|
+| Multi-node NCCL | FAIL |
+
+## Multi-node NCCL / Cross Leaf
+
+Source: nccl-tests-mpirun | Mode: cross-leaf-pdf-matrix-nccl-2.27.7
+
+- **Hosts:** nccl-gpu-1(172.72.8.12), nccl-gpu-2(172.72.8.16)
+- **Preflight:** PASS
+
+### Multi-node NCCL allreduce
+
+| Topology | CUDA Visible Devices | Peak Bus BW | Peak Size | Avg Bus BW | Threshold | Status |
+|----------|----------------------|-------------|-----------|------------|-----------|--------|
+| 2 nodes x 1 GPU (PDF 2 machines 2 GPUs) | - | 47.23 GB/s | 16G | 47.24 GB/s | >= 49 GB/s | FAIL |
+| 2 nodes x 2 GPUs (PDF 2 machines 4 GPUs) | - | 136.97 GB/s | 16G | 137.17 GB/s | >= 137 GB/s | PASS |
+| 2 nodes x 4 GPUs (PDF 2 machines 8 GPUs) | 0,1,4,5 | 333.22 GB/s | 16G | 333.24 GB/s | >= 335 GB/s | FAIL |
+| 2 nodes x 8 GPUs (PDF 2 machines 16 GPUs) | - | 354.02 GB/s | 16G | 353.92 GB/s | >= 492 GB/s | FAIL |
+
+| Topology | NCCL Network | GPU Direct RDMA | GDR Enabled HCAs | GDR Disabled HCAs |
+|----------|--------------|-----------------|------------------|-------------------|
+| 2 nodes x 1 GPU (PDF 2 machines 2 GPUs) | IB | ENABLED | mlx5_0, mlx5_1, mlx5_6, mlx5_7 | - |
+| 2 nodes x 2 GPUs (PDF 2 machines 4 GPUs) | IB | ENABLED | mlx5_0, mlx5_1, mlx5_6, mlx5_7 | - |
+| 2 nodes x 4 GPUs (PDF 2 machines 8 GPUs) | IB | ENABLED | mlx5_0, mlx5_1, mlx5_6, mlx5_7 | - |
+| 2 nodes x 8 GPUs (PDF 2 machines 16 GPUs) | IB | ENABLED | mlx5_0, mlx5_1, mlx5_6, mlx5_7 | - |
+
+| Topology | Return Code | Error / Output Tail |
+|----------|-------------|---------------------|
+| 2 nodes x 1 GPU (PDF 2 machines 2 GPUs) | 0 | E aikubeworker0012:2157248:2157325 [0] NCCL INFO comm 0x5595f28bf420 rank 0 nranks 2 cudaDev 0 busId 18000 - Destroy COMPLETE # Out of bounds values : 0 OK # Avg bus bandwidth    : 47.2399  # # Collective test concluded: all_reduce_perf #   |
+| 2 nodes x 4 GPUs (PDF 2 machines 8 GPUs) | 0 | ker0012:2157429:2157526 [3] NCCL INFO comm 0x55a8a0147090 rank 3 nranks 8 cudaDev 3 busId ab000 - Destroy COMPLETE aikubeworker0012:2157427:2157524 [1] NCCL INFO comm 0x55b1b0f86630 rank 1 nranks 8 cudaDev 1 busId 2a000 - Destroy COMPLETE   |
+| 2 nodes x 8 GPUs (PDF 2 machines 16 GPUs) | 0 |  aikubeworker0016:1138578:1139592 [0] NCCL INFO comm 0x556eff26c190 rank 8 nranks 16 cudaDev 0 busId 18000 - Destroy COMPLETE # Out of bounds values : 0 OK # Avg bus bandwidth    : 353.915  # # Collective test concluded: all_reduce_perf #   |
+
+### Multi-node NCCL alltoall
+
+| Topology | CUDA Visible Devices | Peak Bus BW | Peak Size | Avg Bus BW | Threshold | Status |
+|----------|----------------------|-------------|-----------|------------|-----------|--------|
+| 2 nodes x 1 GPU (PDF 2 machines 2 GPUs) | - | 24.84 GB/s | 16G | 24.89 GB/s | >= 27 GB/s | FAIL |
+| 2 nodes x 2 GPUs (PDF 2 machines 4 GPUs) | - | 47.67 GB/s | 16G | 47.91 GB/s | >= 54 GB/s | FAIL |
+| 2 nodes x 4 GPUs (PDF 2 machines 8 GPUs) | 0,1,4,5 | 72.93 GB/s | 16G | 72.97 GB/s | >= 74 GB/s | FAIL |
+| 2 nodes x 8 GPUs (PDF 2 machines 16 GPUs) | - | 30.04 GB/s | 16G | 30.04 GB/s | >= 77 GB/s | FAIL |
+
+| Topology | NCCL Network | GPU Direct RDMA | GDR Enabled HCAs | GDR Disabled HCAs |
+|----------|--------------|-----------------|------------------|-------------------|
+| 2 nodes x 1 GPU (PDF 2 machines 2 GPUs) | IB | ENABLED | mlx5_0, mlx5_1, mlx5_6, mlx5_7 | - |
+| 2 nodes x 2 GPUs (PDF 2 machines 4 GPUs) | IB | ENABLED | mlx5_0, mlx5_1, mlx5_6, mlx5_7 | - |
+| 2 nodes x 4 GPUs (PDF 2 machines 8 GPUs) | IB | ENABLED | mlx5_0, mlx5_1, mlx5_6, mlx5_7 | - |
+| 2 nodes x 8 GPUs (PDF 2 machines 16 GPUs) | IB | ENABLED | mlx5_0, mlx5_1, mlx5_6, mlx5_7 | - |
+
+| Topology | Return Code | Error / Output Tail |
+|----------|-------------|---------------------|
+| 2 nodes x 1 GPU (PDF 2 machines 2 GPUs) | 0 | ETE aikubeworker0012:2157727:2157802 [0] NCCL INFO comm 0x55a0349b02b0 rank 0 nranks 2 cudaDev 0 busId 18000 - Destroy COMPLETE # Out of bounds values : 0 OK # Avg bus bandwidth    : 24.8897  # # Collective test concluded: alltoall_perf #   |
+| 2 nodes x 2 GPUs (PDF 2 machines 4 GPUs) | 0 | ETE aikubeworker0016:1141290:1142410 [0] NCCL INFO comm 0x55fabbea6410 rank 2 nranks 4 cudaDev 0 busId 18000 - Destroy COMPLETE # Out of bounds values : 0 OK # Avg bus bandwidth    : 47.9094  # # Collective test concluded: alltoall_perf #   |
+| 2 nodes x 4 GPUs (PDF 2 machines 8 GPUs) | 0 | ETE aikubeworker0012:2158071:2158172 [0] NCCL INFO comm 0x563312baa7f0 rank 0 nranks 8 cudaDev 0 busId 18000 - Destroy COMPLETE # Out of bounds values : 0 OK # Avg bus bandwidth    : 72.9657  # # Collective test concluded: alltoall_perf #   |
+| 2 nodes x 8 GPUs (PDF 2 machines 16 GPUs) | 0 | 016:1143717:1145948 [7] NCCL INFO comm 0x5558cc9de640 rank 15 nranks 16 cudaDev 7 busId db000 - Destroy COMPLETE aikubeworker0016:1143713:1145946 [3] NCCL INFO comm 0x55c1af080e60 rank 11 nranks 16 cudaDev 3 busId 5d000 - Destroy COMPLETE   |
+
+**Overall: FAIL**
+
+---
+*Generated by GPU Test Suite v0.2.0*