04. Performance Benchmarking
Chapter focus: reproducible benchmarks to baseline hardware, network and storage — theory first, then measure, then tooling.
Outcomes
- CPU theory → estimation → measurement (three-step methodology)
- GPU / AMD / memory-bandwidth platform benchmarks
- NCCL collective-communication and parallel-FS benchmarks
- A portable HPC benchmark toolkit
🧭 Reading Map
- Prerequisites: 03. Cluster Architecture — benchmarks target the cluster you planned
- Role: Part-1 L1 benchmarking chapter — turning "is it good enough?" into a quantifiable baseline
- Order: CPU (theory→estimation→measurement) → GPU/platform → network (NCCL) → storage (IOR/mdtest) → toolkit
- Next: 05. Parallel Storage — the data plane: how training data feeds the cluster
Articles
CPU Benchmarking (Theory → Estimation → Measurement)
CPU Theoretical Peak (Rpeak) Calculation in Practice
compute Rpeak in three steps with real machine specs: AVX-512 32 FLOP/cycle, 104-core node, 80-node cluster; includes a lookup table and verification tools.
阅读文章 →
Estimating HPL Performance: from Theoretical Peak to Deliverable Efficiency
a 91-node per-node dataset: 93.4% single-node average efficiency, 78.3% at 80 nodes, 74.2% memory bandwidth, with a scaling-band estimation formula.
阅读文章 →
CPU HPL in Practice: from Single Node to 80 Nodes
full post-mortem of single-node tuning → 36 nodes → 80 nodes: HPL.dat configs, commands, real results, and pitfalls.
阅读文章 →
CPU Linpack Performance Benchmarking Guide (HPL)
a comprehensive HPL guide on Intel MKL: environment setup, HPL.dat tuning, multi-node testing, and performance analysis.
阅读文章 →
GPU & Platform Benchmarking
NVIDIA GPU HPL Benchmarking Guide (Docker)
running HPL on NVIDIA GPUs via Docker: startup parameters, MPI commands, and result analysis.
阅读文章 →
AMD CPU Linpack (HPL) Performance Guide
HPL testing and tuning for AMD EPYC (Genoa/Zen 4): OpenMPI binding, BIOS settings, and multi-node scripts.
阅读文章 →
Memory Bandwidth Testing & STREAM Guide
server memory bandwidth evaluation with STREAM: DDR5 theoretical calculation, compiler optimizations, and case studies.
阅读文章 →
Building an All-in-One HPC Benchmark Toolkit
a portable, containerized toolkit integrating HPL, Intel oneAPI, STREAM, FIO, and OSU benchmarks.
阅读文章 →