#17 - Add RTX PRO 6000 benchmark YAMLs and baseline

.gitignore

@@ -2,6 +2,14 @@ build*/
 site/
 bench-results/
 
+# Benchmark plot generation (scripts/plot_rtx_pro_bench.py, plot_mq_payload_sweep.py)
+bench-results/**/plots/
+bench-results/**/*.svg
+bench-results/**/*.png
+bench-results/*.log
+docs/images/rtx-pro-*.svg
+docs/images/rtx-pro-*.png
+
 # tune_system.py default output
 pcie_schematic.png
 

AGENTS.md

@@ -35,7 +35,7 @@ There is no unit test suite. Verification is done via the benchmark executables
 
 | Executable | Source | Typical config |
 |---|---|---|
-| `daqiri_bench_raw_gpudirect` | `raw_gpudirect_bench.cpp` | `daqiri_bench_raw_tx_rx.yaml`, `daqiri_bench_raw_tx_rx_4q.yaml`, `daqiri_bench_raw_tx_rx_spark.yaml`, `daqiri_bench_raw_{tx,rx}_spark_xhost.yaml`, `daqiri_bench_raw_sw_loopback.yaml`, `daqiri_bench_raw_rx_multi_q.yaml`, `daqiri_bench_raw_tx_rx_vxlan.yaml`, `daqiri_bench_raw_tx_rx_vlan.yaml`, `daqiri_bench_raw_tx_rx_gre.yaml`, `daqiri_bench_raw_tx_rx_nvgre.yaml`, `daqiri_bench_raw_tx_rx_spark_mq.yaml` (mq base; `run_spark_mq_bench.sh` derives the 4 cells via `scripts/gen_spark_mq_config.py`), `daqiri_bench_raw_tx_rx_pacing.yaml` (per-queue `pacing_mbps`; DPDK engine only) |
+| `daqiri_bench_raw_gpudirect` | `raw_gpudirect_bench.cpp` | `daqiri_bench_raw_tx_rx.yaml`, `daqiri_bench_raw_tx_rx_4q.yaml`, `daqiri_bench_raw_tx_rx_spark.yaml`, `daqiri_bench_raw_tx_rx_rtx_pro_6000.yaml`, `daqiri_bench_raw_tx_rx_rtx_pro_6000_nic.yaml`, `daqiri_bench_raw_tx_rx_rtx_pro_6000_nic_same_port.yaml`, `daqiri_bench_raw_{tx,rx}_spark_xhost.yaml`, `daqiri_bench_raw_sw_loopback.yaml`, `daqiri_bench_raw_sw_loopback_rtx_pro_6000.yaml`, `daqiri_bench_raw_rx_multi_q.yaml`, `daqiri_bench_raw_tx_rx_vxlan.yaml`, `daqiri_bench_raw_tx_rx_vlan.yaml`, `daqiri_bench_raw_tx_rx_gre.yaml`, `daqiri_bench_raw_tx_rx_nvgre.yaml`, `daqiri_bench_raw_tx_rx_spark_mq.yaml` (mq base; `run_spark_mq_bench.sh` derives the 4 cells via `scripts/gen_spark_mq_config.py`), `daqiri_bench_raw_tx_rx_pacing.yaml` (per-queue `pacing_mbps`; DPDK engine only) |
 | `daqiri_example_dynamic_rx_flow` | `dynamic_rx_flow_example.cpp` | `daqiri_example_dynamic_rx_flow.yaml` — `flow_isolation: true` startup followed by runtime RX queue-steering and raw-engine decap/pop flow add/delete |
 | `daqiri_bench_raw_hds` | `raw_hds_bench.cpp` | `daqiri_bench_raw_tx_rx_hds.yaml` |
 | `daqiri_bench_raw_reorder_seq` | `raw_reorder_seq_bench.cpp` | `daqiri_bench_raw_tx_rx_reorder_seq_1024*.yaml`, `daqiri_bench_raw_rx_reorder_seq_*.yaml` |

docs/benchmarks/raw_benchmarking.md

@@ -59,6 +59,26 @@ docker run --rm -it --privileged \
 
     The Spark configs also pin the benchmark application's `bench_tx.cpu_core` / `bench_rx.cpu_core` fields to the high-frequency Cortex-X925 cores. Keep both the DAQIRI queue cores and the application worker cores on cores 16-19 unless you intentionally want a lower-power core in the measurement.
 
+!!! tip "RTX PRO 6000 Blackwell (x86_64 workstation / server)"
+
+    For discrete Blackwell RTX PRO 6000 systems, build with [`CMAKE_CUDA_ARCHITECTURES=120`](../tutorials/bare-metal-cmake-build.md) and use these configs:
+
+    - [`daqiri_bench_raw_sw_loopback_rtx_pro_6000.yaml`](https://github.com/nvidia/daqiri/blob/main/examples/daqiri_bench_raw_sw_loopback_rtx_pro_6000.yaml) — software loopback, no NIC required. Validates the GPUDirect build path; throughput is not wire-rate. See measured numbers in [`examples/rtx_pro_6000_baseline.md`](https://github.com/nvidia/daqiri/blob/main/examples/rtx_pro_6000_baseline.md).
+    - [`daqiri_bench_raw_tx_rx_rtx_pro_6000_nic.yaml`](https://github.com/nvidia/daqiri/blob/main/examples/daqiri_bench_raw_tx_rx_rtx_pro_6000_nic.yaml) — prefilled dual-port NIC run (dev-box PCIe BDFs; fill `eth_dst_addr` from the rx_port MAC). Port 0 TX on GPU CUDA 0, port 1 RX on GPU CUDA 1. Requires an L2 link between the two ports (QSFP cable, passive loopback optic, or switch). `carrier=1` on both ports does not guarantee they are looped to each other.
+    - [`daqiri_bench_raw_tx_rx_rtx_pro_6000.yaml`](https://github.com/nvidia/daqiri/blob/main/examples/daqiri_bench_raw_tx_rx_rtx_pro_6000.yaml) — generic `<placeholder>` template for cross-card or custom topology (800 Gbps target once cabled).
+    - [`daqiri_bench_raw_tx_rx_rtx_pro_6000_nic_same_port.yaml`](https://github.com/nvidia/daqiri/blob/main/examples/daqiri_bench_raw_tx_rx_rtx_pro_6000_nic_same_port.yaml) — experimental same-port TX+RX; failed `daqiri_init` on the reference box.
+
+    Unlike DGX Spark, typical RTX Pro servers expose one PF per physical port — there is no on-chip eswitch shortcut between two PFs on the same port without a link. After a NIC run, confirm whether traffic crossed the wire using `tx_phy_packets` / `rx_phy_packets` in the DPDK extended stats (near zero = on-chip or no wire loop; rising with vport counts = over-the-wire). Full constraints and baseline results: [`rtx_pro_6000_baseline.md`](https://github.com/nvidia/daqiri/blob/main/examples/rtx_pro_6000_baseline.md).
+
+    ```bash
+    sudo ./daqiri_bench_raw_gpudirect \
+      ./examples/daqiri_bench_raw_sw_loopback_rtx_pro_6000.yaml --seconds 30
+
+    # Once p0 and p1 are cabled:
+    sudo ./daqiri_bench_raw_gpudirect \
+      ./examples/daqiri_bench_raw_tx_rx_rtx_pro_6000_nic.yaml --seconds 30
+    ```
+
 #### Cross-host two-DGX-Spark loopback
 
 If you have two DGX Sparks cross-cabled p0↔p0 instead of a chassis QSFP loop on one machine, use the `_xhost` configs. Each host runs only its own role, so the YAML on each side configures one port instead of two. Both hosts must already be set up per the [DGX Spark profile](../tutorials/system_configuration.md#dgx-spark-profile), with one adjustment: the `daqiri-tx` (`1.1.1.1/24`) and `daqiri-rx` (`2.2.2.2/24`) nmcli profiles are *split across* the two hosts — bring up `daqiri-tx` on the TX host's p0 and `daqiri-rx` on the RX host's p0, instead of both on one box.

docs/tutorials/configuration-walkthrough.md

@@ -32,6 +32,13 @@ For a shorter selection guide, start with the [Benchmarking overview](../benchma
     - **DGX Spark multi-queue core-scaling matrix** (prefilled) — one base config [`daqiri_bench_raw_tx_rx_spark_mq.yaml`](https://github.com/nvidia/daqiri/blob/main/examples/daqiri_bench_raw_tx_rx_spark_mq.yaml) (the balanced TX=2/RX=2 superset; cores TX → 16,17, RX → 18,19) from which `examples/run_spark_mq_bench.sh` (via `scripts/gen_spark_mq_config.py`) derives the four `(TX, RX)` cells — (1,1), (1,2) (RX scaling), (2,1) (TX scaling), (2,2) (balanced) — by pruning queues/flows. All run on `daqiri_bench_raw_gpudirect` at the native 8 KB shape.
     - **DGX Spark cross-host** (prefilled, runs on two Sparks) — [`daqiri_bench_raw_tx_spark_xhost.yaml`](https://github.com/nvidia/daqiri/blob/main/examples/daqiri_bench_raw_tx_spark_xhost.yaml) on the TX host and [`daqiri_bench_raw_rx_spark_xhost.yaml`](https://github.com/nvidia/daqiri/blob/main/examples/daqiri_bench_raw_rx_spark_xhost.yaml) on the RX host. Each host runs `daqiri_bench_raw_gpudirect` against its own half; cables connect p0↔p0 between the two boxes. Apply the [cross-host network setup](../tutorials/system_configuration.md#cross-host-variant-two-sparks) before running. See the [Cross-host two-DGX-Spark loopback](../benchmarks/raw_benchmarking.md#cross-host-two-dgx-spark-loopback) section for run details.
     - **No physical NIC available** — [`daqiri_bench_raw_sw_loopback.yaml`](https://github.com/nvidia/daqiri/blob/main/examples/daqiri_bench_raw_sw_loopback.yaml). `loopback: "sw"`, no NIC required. Useful for first-time build verification, not representative of production performance.
+    - **RTX PRO 6000 Blackwell — no cable** — [`daqiri_bench_raw_sw_loopback_rtx_pro_6000.yaml`](https://github.com/nvidia/daqiri/blob/main/examples/daqiri_bench_raw_sw_loopback_rtx_pro_6000.yaml). `kind: device`, `affinity: 0`; build with [`CMAKE_CUDA_ARCHITECTURES=120`](../tutorials/bare-metal-cmake-build.md). SW loopback smoke test only.
+    - **RTX PRO 6000 Blackwell — real NIC, dual-port on one card** (prefilled dev box) — [`daqiri_bench_raw_tx_rx_rtx_pro_6000_nic.yaml`](https://github.com/nvidia/daqiri/blob/main/examples/daqiri_bench_raw_tx_rx_rtx_pro_6000_nic.yaml). `61:00.0` p0 → `61:00.1` p1, GPU 0 TX / GPU 1 RX; needs L2 link between ports (not SW loopback). See [`rtx_pro_6000_baseline.md`](https://github.com/nvidia/daqiri/blob/main/examples/rtx_pro_6000_baseline.md) for hardware limits and measured baseline.
+    - **RTX PRO 6000 — same-PF NIC attempt** (experimental) — [`daqiri_bench_raw_tx_rx_rtx_pro_6000_nic_same_port.yaml`](https://github.com/nvidia/daqiri/blob/main/examples/daqiri_bench_raw_tx_rx_rtx_pro_6000_nic_same_port.yaml). Single port `61:00.0` TX+RX; failed `daqiri_init` on reference box — kept for follow-up.
+    - **RTX PRO 6000 Blackwell — dual-NIC loopback** (generic template) — [`daqiri_bench_raw_tx_rx_rtx_pro_6000.yaml`](https://github.com/nvidia/daqiri/blob/main/examples/daqiri_bench_raw_tx_rx_rtx_pro_6000.yaml). Placeholders for Cliff's 800 Gbps cross-card target; fill PCIe BDFs and MACs.
+    - **RTX PRO 6000 Blackwell — header-data split wire loopback** — [`daqiri_bench_raw_tx_rx_hds_rtx_pro_6000.yaml`](https://github.com/nvidia/daqiri/blob/main/examples/daqiri_bench_raw_tx_rx_hds_rtx_pro_6000.yaml). Runs on `daqiri_bench_raw_hds`; CPU header segment + GPU (`kind: device`) payload segment over the dual-port L2 link.
+    - **RTX PRO 6000 Blackwell — multi-queue core-scaling matrix** — one base config [`daqiri_bench_raw_tx_rx_rtx_pro_6000_mq.yaml`](https://github.com/nvidia/daqiri/blob/main/examples/daqiri_bench_raw_tx_rx_rtx_pro_6000_mq.yaml) (the TX=2/RX=2 superset; GPU 0 TX / GPU 1 RX) from which `examples/run_rtx_pro_mq_bench.sh` (via `scripts/gen_rtx_pro_mq_config.py`) derives the four `(TX, RX)` cells — (1,1), (1,2), (2,1), (2,2) — by pruning queues/flows and sweeping payload sizes. All run on `daqiri_bench_raw_gpudirect`.
+    - **RTX PRO 6000 Blackwell — ibverbs (MPRQ) RX, paired DPDK TX** — the RX side uses [`daqiri_bench_raw_rx_ibverbs_rtx_pro_6000.yaml`](https://github.com/nvidia/daqiri/blob/main/examples/daqiri_bench_raw_rx_ibverbs_rtx_pro_6000.yaml) (`engine: ibverbs`, runs on `daqiri_bench_raw_gpudirect` built with `ibverbs`), fed by a DPDK TX sender from [`daqiri_bench_raw_tx_only_rtx_pro_6000_nic.yaml`](https://github.com/nvidia/daqiri/blob/main/examples/daqiri_bench_raw_tx_only_rtx_pro_6000_nic.yaml) on the other port over the L2 link.
 
     **Raw Ethernet hardware tunnel transforms** — run on `daqiri_bench_raw_gpudirect`; replace placeholders and use a raw DPDK or raw ibverbs build.
 
@@ -47,6 +54,7 @@ For a shorter selection guide, start with the [Benchmarking overview](../benchma
     **Socket — RoCE (RDMA)** (`stream_type: "socket"`, `roce://` endpoints) — runs on `daqiri_bench_rdma` (use `--mode {tx,rx,both}`). Configs use `kind: host_pinned` regardless of platform.
 
     - **Generic** (template — replace IPs) — [`daqiri_bench_rdma_tx_rx.yaml`](https://github.com/nvidia/daqiri/blob/main/examples/daqiri_bench_rdma_tx_rx.yaml).
+    - **RTX PRO 6000 Blackwell** (prefilled dual-port RoCE) — [`daqiri_bench_rdma_tx_rx_rtx_pro_6000.yaml`](https://github.com/nvidia/daqiri/blob/main/examples/daqiri_bench_rdma_tx_rx_rtx_pro_6000.yaml). Client/server on `10.100.0.1`/`10.100.0.2` across the two cabled ports; `examples/run_rtx_pro_bench.sh` auto-assigns the RoCE IPs and sysctls for a self-contained single-host loop.
     - **DGX Spark** (prefilled) — [`daqiri_bench_rdma_tx_rx_spark.yaml`](https://github.com/nvidia/daqiri/blob/main/examples/daqiri_bench_rdma_tx_rx_spark.yaml). See [Socket and RDMA Benchmarking](../benchmarks/socket_benchmarking.md#run-the-rdma-roce-benchmark) for namespace and wire-counter run details.
     - **DGX Spark netns wire loopback** (prefilled, combined base) — [`daqiri_bench_rdma_tx_rx_spark_netns.yaml`](https://github.com/nvidia/daqiri/blob/main/examples/daqiri_bench_rdma_tx_rx_spark_netns.yaml). Carries both roles; `examples/run_spark_bench.sh` (via `scripts/gen_spark_netns_config.py`) splits it per role and runs each in its own network namespace (`--mode server` / `--mode client`) so RDMA-CM resolves over the wire; see [Socket and RDMA Benchmarking](../benchmarks/socket_benchmarking.md#run-the-rdma-roce-benchmark).
     - **DGX Spark cross-host** (prefilled, runs on two Sparks) — [`daqiri_bench_rdma_tx_rx_spark_xhost.yaml`](https://github.com/nvidia/daqiri/blob/main/examples/daqiri_bench_rdma_tx_rx_spark_xhost.yaml). Run with `--mode server` on the RX host and `--mode client` on the TX host. Apply the [cross-host network setup](../tutorials/system_configuration.md#cross-host-variant-two-sparks) before running. See the [Cross-host two-DGX-Spark loopback](../benchmarks/raw_benchmarking.md#cross-host-two-dgx-spark-loopback) section for run details.

examples/CMakeLists.txt

@@ -41,6 +41,8 @@ set(DAQIRI_BENCH_CONFIGS
   daqiri_bench_raw_tx_rx_4q.yaml
   daqiri_bench_raw_tx_rx_pacing.yaml
   daqiri_bench_raw_tx_rx_hds.yaml
+  daqiri_bench_raw_tx_rx_hds_rtx_pro_6000.yaml
+  daqiri_bench_raw_rx_ibverbs_rtx_pro_6000.yaml
   daqiri_bench_raw_tx_rx_reorder_seq_1024.yaml
   daqiri_bench_raw_tx_rx_reorder_seq_1024_cpu.yaml
   daqiri_bench_raw_sw_loopback_reorder_seq_1024.yaml
@@ -49,12 +51,18 @@ set(DAQIRI_BENCH_CONFIGS
   daqiri_bench_raw_rx_reorder_seq_batch.yaml
   daqiri_bench_raw_rx_multi_q.yaml
   daqiri_bench_raw_sw_loopback.yaml
+  daqiri_bench_raw_sw_loopback_rtx_pro_6000.yaml
+  daqiri_bench_raw_tx_rx_rtx_pro_6000.yaml
+  daqiri_bench_raw_tx_rx_rtx_pro_6000_nic.yaml
+  daqiri_bench_raw_tx_rx_rtx_pro_6000_nic_same_port.yaml
+  daqiri_bench_raw_tx_only_rtx_pro_6000_nic.yaml
   daqiri_example_dynamic_rx_flow.yaml
   daqiri_example_gds_write_sw_loopback.yaml
   daqiri_example_gds_write_tx_rx.yaml
   daqiri_example_pcap_writer_sw_loopback.yaml
   daqiri_example_pcap_writer_tx_rx.yaml
   daqiri_bench_rdma_tx_rx.yaml
+  daqiri_bench_rdma_tx_rx_rtx_pro_6000.yaml
   daqiri_bench_socket_udp_tx_rx.yaml
   daqiri_bench_socket_tcp_tx_rx.yaml
 )
@@ -67,7 +75,7 @@ function(link_daqiri_bench target)
   target_compile_features(${target} PRIVATE cxx_std_17)
   if(NOT BUILD_SHARED_LIBS AND UNIX AND NOT APPLE)
     set(DAQIRI_EXAMPLE_STATIC_LIBS daqiri::daqiri)
-    foreach(engine IN ITEMS dpdk socket rdma)
+    foreach(engine IN ITEMS dpdk socket rdma ibverbs)
       if(TARGET daqiri_${engine})
         list(APPEND DAQIRI_EXAMPLE_STATIC_LIBS daqiri_${engine})
       endif()

examples/daqiri_bench_raw_rx_ibverbs_rtx_pro_6000.yaml

@@ -0,0 +1,54 @@
+# RTX PRO 6000 Blackwell -- ibverbs MPRQ RX-only (host-staged).
+#
+# Selected via `engine: "ibverbs"` under `stream_type: "raw"`. Uses HOST hugepage
+# memory (GPUDirect device registration is not yet available on this backend).
+# FFT/GEMM workloads therefore include host->device staging cost -- label results
+# as `host-staged` when comparing against DPDK HDS.
+#
+# RX-only: pair with a DPDK TX sender (run_rtx_pro_bench.sh ibverbs mode starts
+# daqiri_bench_raw_gpudirect on tx_port in the background).
+#
+# Run (manual):
+#   sudo ./build/examples/daqiri_bench_raw_gpudirect \
+#     ./build/examples/daqiri_bench_raw_tx_rx_rtx_pro_6000_nic.yaml --seconds 30 &
+#   sudo ./build/examples/daqiri_bench_raw_gpudirect \
+#     ./build/examples/daqiri_bench_raw_rx_ibverbs_rtx_pro_6000.yaml \
+#     --seconds 30 --workload fft
+#
+%YAML 1.2
+---
+daqiri:
+  cfg:
+    version: 1
+    stream_type: "raw"
+    engine: "ibverbs"
+    master_core: 3
+    debug: false
+    log_level: "info"
+    loopback: ""
+
+    # affinity is the NUMA node for the huge-page RX region. Keep it on the RX
+    # port's node (discover with: cat /sys/class/net/<rx-iface>/device/numa_node).
+    memory_regions:
+      - name: "Data_RX_HOST"
+        kind: "huge"
+        affinity: 0
+        num_bufs: 4096
+        buf_size: 8064
+
+    interfaces:
+      - name: "rx_port"
+        address: 0000:61:00.1
+        rx:
+          queues:
+            - name: "rx_q_0"
+              id: 0
+              cpu_core: 9
+              batch_size: 1024
+              timeout_us: 2000
+              memory_regions:
+                - "Data_RX_HOST"
+
+bench_rx:
+  interface_name: "rx_port"
+  cpu_core: 8

examples/daqiri_bench_raw_sw_loopback_rtx_pro_6000.yaml

@@ -0,0 +1,77 @@
+# RTX PRO 6000 Blackwell (discrete dGPU) software-loopback smoke test.
+# No NIC or cable required — validates build + GPUDirect on one GPU.
+# Not representative of wire-speed performance; use the hardware template
+# (daqiri_bench_raw_tx_rx_rtx_pro_6000.yaml) once a QSFP loopback cable is installed.
+#
+# Build (native sm_120):
+#   cmake -S . -B build -DBUILD_SHARED_LIBS=ON -DDAQIRI_BUILD_PYTHON=OFF \
+#     -DDAQIRI_ENGINE="dpdk ibverbs" -DCMAKE_CUDA_ARCHITECTURES=120
+#   cmake --build build -j
+#
+# Run:
+#   ./build/examples/daqiri_bench_raw_gpudirect \
+#     ./build/examples/daqiri_bench_raw_sw_loopback_rtx_pro_6000.yaml --seconds 30
+#
+# memory_regions[].affinity is the CUDA device index (not nvidia-smi GPU id).
+# Change affinity to target a different GPU, e.g. affinity: 1 for CUDA device 1.
+#
+%YAML 1.2
+---
+daqiri:
+  cfg:
+    version: 1
+    stream_type: "raw"
+    master_core: 3
+    debug: false
+    log_level: "info"
+    loopback: "sw"
+
+    memory_regions:
+    - name: "Data_TX_GPU"
+      kind: "device"
+      affinity: 0
+      num_bufs: 51200
+      buf_size: 8064
+    - name: "Data_RX_GPU"
+      kind: "device"
+      affinity: 0
+      num_bufs: 51200
+      buf_size: 8064
+
+    interfaces:
+    - name: "loopback_ports"
+      address: "loopback"
+      tx:
+        queues:
+        - name: "tx_q_0"
+          id: 0
+          batch_size: 10240
+          cpu_core: 11
+          timeout_us: 1000
+          memory_regions:
+            - "Data_TX_GPU"
+          offloads:
+            - "tx_eth_src"
+      rx:
+        queues:
+        - name: "rq_q_0"
+          id: 0
+          cpu_core: 9
+          timeout_us: 1000
+          batch_size: 10240
+          memory_regions:
+            - "Data_RX_GPU"
+
+bench_rx:
+  interface_name: "loopback_ports"
+
+bench_tx:
+  interface_name: "loopback_ports"
+  batch_size: 10240
+  payload_size: 8000
+  header_size: 64
+  eth_dst_addr: 00:00:00:00:00:00
+  ip_src_addr: 0.0.0.0
+  ip_dst_addr: 0.0.0.0
+  udp_src_port: 4096
+  udp_dst_port: 4096

examples/daqiri_bench_raw_tx_only_rtx_pro_6000_nic.yaml

@@ -0,0 +1,46 @@
+# RTX PRO 6000 -- DPDK GPUDirect TX-only sender for ibverbs RX pairing.
+# Binds a single TX port; the RX port stays kernel-bound for ibverbs MPRQ.
+#
+%YAML 1.2
+---
+daqiri:
+  cfg:
+    version: 1
+    stream_type: "raw"
+    master_core: 3
+    debug: false
+    log_level: "info"
+    loopback: ""
+
+    memory_regions:
+    - name: "Data_TX_GPU"
+      kind: "device"
+      affinity: 0
+      num_bufs: 51200
+      buf_size: 8064
+
+    interfaces:
+    - name: "tx_port"
+      address: 0000:61:00.0
+      tx:
+        queues:
+        - name: "tx_q_0"
+          id: 0
+          batch_size: 10240
+          cpu_core: 11
+          memory_regions:
+            - "Data_TX_GPU"
+          offloads:
+            - "tx_eth_src"
+
+bench_tx:
+  interface_name: "tx_port"
+  cpu_core: 10
+  batch_size: 10240
+  payload_size: 8000
+  header_size: 64
+  eth_dst_addr: <00:00:00:00:00:00>
+  ip_src_addr: 1.2.3.4
+  ip_dst_addr: 5.6.7.8
+  udp_src_port: 4096
+  udp_dst_port: 4096