Update steps

int8/benchmarks/x5h_mwmx_npu_apm80_12core.yaml

@@ -1,87 +1,86 @@
-hardware:
-  vendor: renesas
-  chip: rcar-x5h
-  cpu: arm-cortex-a720
-  npu: npx6-48k
-  npu_count: 2
-  npu_cores: 12
-  npu_default_freq_mhz: 1066
-  accelerator:
-    - npu
-
-runtime:
-  engine: mwmx
-  toolchain_version: "MWMX SDK v4.35.0"
-  format: onnx
-  execution_provider: npu
-  execution_precision: int8
-
-configuration:
-  npu_instances: 1
-  npu_cores_per_instance: 12
-  npu_freq_mhz: 850
-
-benchmark:
-  type: hil
-  parameters:
-    batch_size: 1
-    input_resolution: [1, 3, 512, 1024]   # explicit in the source checkpoint name (512x1024, Cityscapes)
-
-performance:
-  fps: null
-  latency: 38.103941        # APM80 pipeline run (metawaremx_runtime CI); this artifact is ONE segment
-  # of a 4-way split model ("custom_seg_split_4_split_2") — not full end-to-end latency.
-  # 1-core run for this artifact failed to compile — no figure available for that slice.
-
-metrics:
-  accuracy: null
-  top5_accuracy: null
-
-memory:
-  peak_mb: null
-
-power:
-  avg_w: null
-
-# Exact commands verified against the NNAC "Getting Started" chapter. Rendered
-# by the AI-Dashboard in place of the generic placeholder flow — see
-# downloadRunHTML() / parse_reproduce() in AI-Dashboard/app.js.
-# CAVEAT: this artifact is segment "split_2" of a 4-way split network (see
-# README) — these steps reproduce only this segment's latency, not an
-# end-to-end DeepLabV3+ result. The 1-AI-core config also fails to compile
-# for this artifact, so no 1-core reproduce block exists.
-reproduce:
-  steps:
-    - title: Download the ONNX model and compile config
-      command: hf download Renesas/DeepLabV3Plus-R50-ONNX --repo-type=model --include "fp32/*" --include "compile_config/*"
-    - title: Configure the network for the 12-core build (required — this model has no working 1-core config)
-      command: |
-        cat >> ${WORKDIR}/nnac_config/config.yaml << 'EOF'
-        network_configuration:
-          deeplabv3plus_r50_oss_sim_inf:
-            optimization_options:
-              - -segmentation_json ./compile_config/l2_seg_48k_add_split_4_split_2.json
-              - -enable_dma_fusion
-              - -enable_stu_multi_channel
-              - -stu_multi_channel_config 0x15212420
-              - -stu_weight
-              - -distributed_coef_stu
-        EOF
-        # If config.yaml already has a network_configuration: key (e.g. from a
-        # previous model), merge this block into it instead of appending a duplicate key.
-    - title: Compile with the NNAC toolchain (INT8 auto-cast from the FP32 graph)
-      command: |
-        python3 nnac_frontend/legalize.py -d binary/nnx ./fp32/deeplabv3plus_r50_oss_sim_inf.onnx
-    - title: Set up the R-Car X5H board
-      command: Configure the board per the AI Compiler (NNAC) "Getting Started" guide, section 3.4 (host TFTP/NFS setup, bootloader flashing, U-Boot, Linux boot, login) -- exact steps depend on your board/network setup.
-    - title: Copy the compiled artifact to the board
-      command: Copy ${WORKDIR}/binary/nnx to the board -- method may vary (NFS mount, scp, USB, etc.).
-    - title: Run on R-Car X5H (single NPU cluster, 12 AI cores)
-      command: |
-        cd binary
-        ./host_app ./arc_prog_npus ./nnx/deeplabv3plus_r50_oss_sim_inf
-  notes: >-
-    hash[n] = 0x...(OK) means the run's output matches the reference hash in
-    hash.txt; latency is the NPX execution time reported in cycles and ms.
-    This is one segment (split_2 of 4) of the full segmentation pipeline —
-    not whole-model latency.
+hardware:
+  vendor: renesas
+  chip: rcar-x5h
+  cpu: arm-cortex-a720
+  npu: npx6-48k
+  npu_count: 2
+  npu_cores: 12
+  npu_default_freq_mhz: 1066
+  accelerator:
+    - npu
+
+runtime:
+  engine: mwmx
+  toolchain_version: "MWMX SDK v4.35.0"
+  format: onnx
+  execution_provider: npu
+  execution_precision: int8
+
+configuration:
+  npu_instances: 1
+  npu_cores_per_instance: 12
+  npu_freq_mhz: 850
+
+benchmark:
+  type: hil
+  parameters:
+    batch_size: 1
+    input_resolution: [1, 3, 512, 1024]   # explicit in the source checkpoint name (512x1024, Cityscapes)
+
+performance:
+  fps: null
+  latency: 38.103941        # APM80 pipeline run (metawaremx_runtime CI); this artifact is ONE segment
+  # of a 4-way split model ("custom_seg_split_4_split_2") — not full end-to-end latency.
+  # 1-core run for this artifact failed to compile — no figure available for that slice.
+
+metrics:
+  accuracy: null
+  top5_accuracy: null
+
+memory:
+  peak_mb: null
+
+power:
+  avg_w: null
+
+# Exact commands verified against the NNAC "Getting Started" chapter. Rendered
+# by the AI-Dashboard in place of the generic placeholder flow — see
+# downloadRunHTML() / parse_reproduce() in AI-Dashboard/app.js.
+# CAVEAT: this artifact is segment "split_2" of a 4-way split network (see
+# README) — these steps reproduce only this segment's latency, not an
+# end-to-end DeepLabV3+ result. The 1-AI-core config also fails to compile
+# for this artifact, so no 1-core reproduce block exists.
+reproduce:
+  steps:
+    - title: Download the ONNX model and compile config
+      command: hf download Renesas/DeepLabV3Plus-R50-ONNX --repo-type=model --include "fp32/*" --include "compile_config/*"
+    - title: Configure the network for the 12-core build (required — this model has no working 1-core config)
+      command: |
+        cat >> ${WORKDIR}/nnac_config/config.yaml << 'EOF'
+        network_configuration:
+          deeplabv3plus_r50_oss_sim_inf:
+            optimization_options:
+              - -segmentation_json ./compile_config/l2_seg_48k_add_split_4_split_2.json
+              - -enable_dma_fusion
+              - -enable_stu_multi_channel
+              - -stu_multi_channel_config 0x15212420
+              - -stu_weight
+              - -distributed_coef_stu
+        EOF
+        # If config.yaml already has a network_configuration: key (e.g. from a
+        # previous model), merge this block into it instead of appending a duplicate key.
+    - title: Compile with the NNAC toolchain (INT8 auto-cast from the FP32 graph)
+      command: |
+        python3 nnac_frontend/legalize.py -d binary/nnx ./fp32/deeplabv3plus_r50_oss_sim_inf.onnx
+    - title: Set up the R-Car X5H board
+      command: Configure the board per the AI Compiler (NNAC) "Getting Started" guide, section 3.4 (host TFTP/NFS setup, bootloader flashing, U-Boot, Linux boot, login) -- exact steps depend on your board/network setup.
+      kind: note
+    - title: Copy the compiled artifact to the board
+      command: Copy ${WORKDIR}/binary/nnx to the board -- method may vary (NFS mount, scp, USB, etc.).
+      kind: note
+    - title: Run on R-Car X5H (single NPU cluster, 12 AI cores)
+      command: |
+        cd binary
+        ./host_app ./arc_prog_npus ./nnx/deeplabv3plus_r50_oss_sim_inf
+      expected: hash[n] = 0x...(OK) means the run's output matches the reference hash in hash.txt; latency is the NPX execution time reported in cycles and ms.
+  notes: This is one segment (split_2 of 4) of the full segmentation pipeline — not whole-model latency.