Neuron Nki Profile Querying

# Ingest and start API server (no web UI)
neuron-explorer view \
  -n ./kernel.neff \
  -s ./profile.ntff \
  --data-path ~/.local/share/neuron-profile \
  --display-name my-kernel \
  --disable-ui &

# Wait for server
sleep 10

# Query
curl -s -X POST http://localhost:3002/api/v1/db/my-kernel/_search \
  -H 'Content-Type: application/json' \
  -d '{"type":"databaseExplorerQuery","tableName":"Summary","query":"SELECT total_time, mfu_estimated_percent, tensor_engine_active_time_percent, dma_active_time_percent FROM Summary"}'

which neuron-explorer && neuron-explorer --version

# After ingesting (Step 2), check for DMA packet data
curl -s -X POST http://localhost:3002/api/v1/db/${PROFILE_NAME}/_search \
  -H 'Content-Type: application/json' \
  -d '{"type":"databaseExplorerQuery","tableName":"DmaPacket","query":"SELECT COUNT(*) as cnt FROM DmaPacket"}'

import os
os.environ["XLA_IR_DEBUG"] = "1"
os.environ["XLA_HLO_DEBUG"] = "1"
os.environ["NEURON_FRAMEWORK_DEBUG"] = "1"
os.environ["NEURON_RT_VISIBLE_CORES"] = ... # Restrict available cores when running experiments in parallel.
os.environ["NEURON_RT_INSPECT_ENABLE"] = "1"
os.environ["NEURON_RT_INSPECT_DEVICE_PROFILE"] = "1"
os.environ["NEURON_RT_INSPECT_SYSTEM_PROFILE"] = "0"
os.environ["NEURON_RT_INSPECT_OUTPUT_DIR"] = ... # This is for the NEFF generation if needed. NTFF will go to the -s capture path in the next command. 

NEFF_PATH=$(find ./output -name "*.neff" | head -1)
NEURON_RT_ENABLE_DGE_NOTIFICATIONS=1 neuron-explorer capture \
  -n "$NEFF_PATH" \
  -s profile.ntff \
  --profile-nth-exec=2

NEFF_PATH=<resolved neff path>
NTFF_PATH=<resolved ntff path>
PROFILE_NAME=<descriptive name, e.g. "my-matmul">
NE_DATA_PATH=~/.local/share/neuron-profile

curl -s http://localhost:3002/api/v1/health

neuron-explorer view \
  -n "$NEFF_PATH" \
  -s "$NTFF_PATH" \
  --data-path "$NE_DATA_PATH" \
  --display-name "$PROFILE_NAME" \
  --disable-ui \
  > /tmp/neuron-explorer-${PROFILE_NAME}.log 2>&1 &
NE_PID=$!
echo "neuron-explorer started (PID: $NE_PID), waiting for API..."

for i in $(seq 1 60); do
  if curl -s http://localhost:3002/api/v1/health 2>/dev/null | grep -q healthy; then
    echo "API server ready"
    break
  fi
  sleep 1
done

curl -s -X POST http://localhost:3002/api/v1/db/${PROFILE_NAME}/_search \
  -H 'Content-Type: application/json' \
  -d '{"type":"tableSchema","tableName":"Instruction"}' | python3 -m json.tool

curl -s -X POST http://localhost:3002/api/v1/db/${PROFILE_NAME}/_search \
  -H 'Content-Type: application/json' \
  -d '{"type": "listDbFiles"}' | python3 -m json.tool

curl -s -X POST http://localhost:3002/api/v1/db/${PROFILE_NAME}/_search \
  -H 'Content-Type: application/json' \
  -d '{"type":"databaseExplorerQuery","tableName":"Summary","query":"SELECT total_time, mfu_estimated_percent, tensor_engine_active_time_percent, vector_engine_active_time_percent, dma_active_time_percent, hbm_read_bytes, hbm_write_bytes FROM Summary"}' | python3 -m json.tool

curl -s -X POST http://localhost:3002/api/v1/db/${PROFILE_NAME}/_search \
  -H 'Content-Type: application/json' \
  -d '{"type":"databaseExplorerQuery","tableName":"Instruction","query":"SELECT engine, opcode, COUNT(*) as cnt, SUM(duration_ns) as total_dur_ns, SUM(evt_wait_time_ns) as total_evt_wait_ns FROM Instruction GROUP BY engine, opcode ORDER BY total_dur_ns DESC"}' | python3 -m json.tool

curl -s -X POST http://localhost:3002/api/v1/db/${PROFILE_NAME}/_search \
  -H 'Content-Type: application/json' \
  -d '{"type":"databaseExplorerQuery","tableName":"Instruction","query":"SELECT bir_debug_info_source_location, engine, opcode, COUNT(*) as cnt, SUM(duration_ns) as total_dur_ns FROM Instruction WHERE bir_debug_info_source_location IS NOT NULL GROUP BY bir_debug_info_source_location, engine, opcode ORDER BY total_dur_ns DESC LIMIT 10"}' | python3 -m json.tool

<data-path>/profiles/global/<display-name>@latest/<Table>.parquet

import duckdb

NE_DATA_PATH = "~/.local/share/neuron-profile"
PROFILE = "my-kernel"
PARQUET_DIR = f"{NE_DATA_PATH}/profiles/global/{PROFILE}@latest"

con = duckdb.connect()

# Load tables directly from parquet
con.execute(f"CREATE VIEW Instruction AS SELECT * FROM '{PARQUET_DIR}/Instruction.parquet'")
con.execute(f"CREATE VIEW DmaPacket AS SELECT * FROM '{PARQUET_DIR}/DmaPacket.parquet'")

# Example: measure LDWEIGHTS/MATMUL temporal overlap
result = con.execute("""
    SELECT
        CASE WHEN lw.end_ts <= mm.start_ts THEN 'lw_before'
             WHEN lw.start_ts >= mm.end_ts THEN 'lw_after'
             ELSE 'overlap' END as rel,
        COUNT(*) as cnt
    FROM Instruction mm
    JOIN Instruction lw ON mm.bir_id = lw.bir_id
    WHERE mm.opcode = 'MATMUL' AND lw.opcode = 'LDWEIGHTS'
      AND mm.tensor_instruction_type = 'REGULAR'
      AND lw.tensor_instruction_type = 'REGULAR'
    GROUP BY rel
""").fetchdf()
print(result)

import pandas as pd, numpy as np, os

NE = os.path.expanduser("~/.local/share/neuron-profile/profiles/global")
profile = "my-kernel"
d = f"{NE}/{profile}@latest"

# Load tables
summary  = pd.read_parquet(f"{d}/Summary.parquet").iloc[0]
inst     = pd.read_parquet(f"{d}/Instruction.parquet")
active   = pd.read_parquet(f"{d}/ActiveTime.parquet")
metadata = pd.read_parquet(f"{d}/Metadata.parquet").iloc[0]
dma_pkts = pd.read_parquet(f"{d}/DmaPacket.parquet")
dma_agg  = pd.read_parquet(f"{d}/DmaPacketAggregated.parquet")
tensors  = pd.read_parquet(f"{d}/TensorInfo.parquet")
flow     = pd.read_parquet(f"{d}/Flow.parquet")

kill $NE_PID 2>/dev/null