Develop and optimize custom operators using AscendC programming language. Analyze operator performance bottlenecks and conduct optimization validation. Based...
by huaweicloud-skills-team1 installs
Coding
huawei-cloud-ascend-op-mfu-calculator
Try itCalculate MFU (Machine FLOP Utilization) for operators like matmul/GEMM/FlashAttention on Ascend NPU, providing clear formulas and derivation process Use thi...
What it does
Calculate MFU (Machine FLOP Utilization) for operators like matmul/GEMM/FlashAttention on Ascend NPU, providing clear formulas and derivation process Use this skill when the user wants to: (1) calculate MFU for matrix operations, (2) analyze operator performance efficiency, (3) understand hardware utilization, (4) optimize operator implementation Trigger: user mentions "MFU", "machine flop utilization", "operator FLOPs", "matmul performance", "GEMM efficiency", "Ascend MFU", "算子MFU", "算力利用率", "矩阵乘效率", "GEMM性能", "FlashAttention性能"
The skill document
Huawei Cloud Ascend Operator MFU Calculator
Overview
This skill calculates MFU (Machine FLOP Utilization) for operators like matmul/GEMM/FlashAttention on Ascend NPU, providing clear formulas and derivation process.
Architecture: Input Validation → FLOPs Calculation → Achieved TFLOPs/s → MFU Calculation → Result Analysis
Related Skills:
huawei-cloud-ascend-profiler-db-explorer- Profiling data analysis for operator performance data
Prerequisites
- Python 3.8+ installed
- Basic understanding of FLOPs calculation concepts
Usage Scenarios
Typical Problem Scenarios:
- Evaluating how well an operator utilizes Ascend NPU compute power
- Comparing performance of different operator implementations
- Identifying optimization opportunities for matrix operations
Typical User Utterances:
- "Calculate MFU for my GEMM operator"
- "What's the machine FLOP utilization for FlashAttention?"
- "Analyze my matmul operator performance efficiency"
Workflow
- Input Collection: Gather operator parameters (matrix dimensions, data types, execution time)
- FLOPs Calculation: Compute theoretical FLOPs for the operation
- Achieved Performance: Calculate achieved TFLOPs/s from execution time
- MFU Calculation: Apply formula MFU = Achieved FLOPs / Peak FLOPs
- Result Analysis: Provide interpretation and optimization suggestions
MFU Calculation Formula
MFU = (Achieved FLOPs / Peak FLOPs) × 100%
Where:
- Achieved FLOPs = Operation FLOPs / Execution Time
- Peak FLOPs = Hardware-specific peak performance (e.g., Ascend 910B: 256 TFLOPs for FP16)
Reference Documents
| Document | Description |
|---|---|
| Ascend 910B Series Technical Specifications | Official Ascend 910B series product specifications |
| MFU Calculation Methodology | Detailed MFU calculation formulas and examples |
| FlashAttention Technical Paper | Original FlashAttention research paper |
Enhanced Features
Intelligent Bottleneck Diagnoser
- AI-powered bottleneck diagnosis that analyzes profiling data to identify root causes automatically
- Classifies bottlenecks into categories: memory-bound, compute-bound, communication-bound, or operator-fallback
- Provides actionable optimization recommendations with priority ranking
- Includes pattern matching for known performance anti-patterns
Parameter Confirmation
| Parameter | Description | Required |
|---|---|---|
| operator | Operator type (matmul/flash_attention/gemm, etc.) | Yes |
| flops | Theoretical FLOPs of the operator | Yes |
| time_ms | Operator execution time (milliseconds) | Yes |
| peak_tflops | Hardware peak computing power (TFLOPS) | Yes |
| device | NPU device type (910B/910, etc.) | No |
Related skills
Collect operator-level performance data on Ascend NPU using msopprof tool. Supports both device mode and simulator mode, generates performance analysis repor...
by huaweicloud-skills-team1 installs
Manage Huawei Ascend NPUs with natural language commands that translate to npu-smi, locally or over SSH.
by huaweicloud-skills-team7 installs
Convert plain-language questions into safe SQL queries for Ascend PyTorch Profiler and msprof databases.
by huaweicloud-skills-team6 installs
Migrate vision/detection/segmentation small models to Ascend NPU, covering the full workflow: model structure analysis, migration verification, performance p...
by huaweicloud-skills-team1 installs
Deploy and test LLM, VL, Embedding, and Rerank models on Huawei Cloud Ascend 910B DevServer with single- or dual-node topologies.
by huaweicloud-skills-team7 installs
More from huaweicloud-skills-team
Browse all skillsManage Huawei Ascend NPUs with natural language commands that translate to npu-smi, locally or over SSH.
by huaweicloud-skills-team7 installs
Deploy and test LLM, VL, Embedding, and Rerank models on Huawei Cloud Ascend 910B DevServer with single- or dual-node topologies.
by huaweicloud-skills-team7 installs
Read-only queries against Huawei Cloud resources for inventory, verification, and parameter discovery.
by huaweicloud-skills-team6 installs
Query Huawei Cloud IAM resources (users, groups, policies, agencies, AK/SK, MFA, security settings) read-only via local Python SDK.
by huaweicloud-skills-team6 installs
Deploy the OpenClaw AI Agent platform on Huawei Cloud Flexus L Instance and configure models and channels via COC.
by huaweicloud-skills-team7 installs
One-click deploy Hermes AI Agent platform on Huawei Cloud Flexus L instances with model and channel configuration.
by huaweicloud-skills-team6 installs