Uncompromised Ethernet – AI/ML material benchmark

At present, we’re exploring how Ethernet stacks up in opposition to InfiniBand in AI/ML environments, specializing in how Cisco Silicon One™ manages community congestion and enhances efficiency for AI/ML workloads. This put up emphasizes the significance of benchmarking and KPI metrics in evaluating community options, showcasing the Cisco Zeus Cluster outfitted with 128 NVIDIA® H100 GPUs and cutting-edge congestion administration applied sciences like dynamic load balancing and packet spray.

Networking requirements to satisfy the wants of AI/ML workloads

AI/ML coaching workloads generate repetitive micro-congestion, stressing community buffers considerably. The east-to-west GPU-to-GPU site visitors throughout mannequin coaching calls for a low-latency, lossless community material. InfiniBand has been a dominant expertise within the high-performance computing (HPC) surroundings and these days within the AI/ML surroundings.

Ethernet is a mature different, with superior options that may deal with the rigorous calls for of the AI/ML coaching workloads and Cisco Silicon One can successfully execute load balancing and handle congestion. We got down to benchmark and evaluate Cisco Silicon One versus NVIDIA Spectrum-X™ and InfiniBand.

Analysis of community material options for AI/ML

Community site visitors patterns fluctuate primarily based on mannequin measurement, structure, and parallelization methods utilized in accelerated coaching. To judge AI/ML community material options, we recognized related benchmarks and key efficiency indicator (KPI) metrics for each AI/ML workload and infrastructure groups, as a result of they view efficiency by means of completely different lenses.

We established complete assessments to measure efficiency and generate metrics particular to AI/ML workload and infrastructure groups. For these assessments, we used the Zeus Cluster, that includes devoted backend and storage with an ordinary 3-stage leaf-spine Clos material community, constructed with Cisco Silicon One–primarily based platforms and 128 NVIDIA H100 GPUs. (See Determine 1.)

We developed benchmarking suites utilizing open-source and industry-standard instruments contributed by NVIDIA and others. Our benchmarking suites included the next (see additionally Desk 1):

• Distant Direct Reminiscence Entry (RDMA) benchmarks—constructed utilizing IBPerf utilities—to judge community efficiency throughout congestion created by incast
• NVIDIA Collective Communication Library (NCCL) benchmarks, which consider utility throughput throughout coaching and inference communication part amongst GPUs
• MLCommons MLPerf set of benchmarks, which evaluates probably the most understood metrics, job completion time (JCT) and tokens per second by the workload groups

Legend:

JCT = Job Completion Time

Bus BW = Bus bandwidth

ECN/PFC = Specific Congestion Notification and Precedence Movement Management

NCCL benchmarking in opposition to congestion avoidance options

Congestion builds up in the course of the again propagation stage of the coaching course of, the place a gradient sync is required amongst all of the GPUs collaborating in coaching. Because the mannequin measurement will increase, so does the gradient measurement and the variety of GPUs. This creates huge micro-congestion within the community material. Determine 2 reveals outcomes of the JCT and site visitors distribution benchmarking. Observe how Cisco Silicon One helps a set of superior options for congestion avoidance, akin to dynamic load balancing (DLB) and packet spray methods, and Knowledge Heart Quantized Congestion Notification (DCQCN) for congestion administration.

Determine 2 illustrates how the NCCL benchmarks stack up in opposition to completely different congestion avoidance options. We examined the most typical collectives with a number of completely different message sizes to spotlight these metrics. The outcomes present that JCT improves with DLB and packet spray for All-to-All, which causes probably the most congestion because of the nature of communication. Though JCT is probably the most understood metric from an utility’s perspective, JCT doesn’t present how successfully the community is utilized—one thing the infrastructure group must know. This data might assist them to:

• Enhance the community utilization to get higher JCT
• Know what number of workloads can share the community material with out adversely impacting JCT
• Plan for capability as use instances enhance

To gauge community material utilization, we calculated Jain’s Equity Index, the place LinkTxᵢ is the quantity of transmitted site visitors on material hyperlink:

The index worth ranges from 0.0 to 1.0, with larger values being higher. A worth of 1.0 represents the right distribution. The Site visitors Distribution on Cloth Hyperlinks chart in Determine 2 reveals how DLB and packet spray algorithms create a near-perfect Jain’s Equity Index, so site visitors distribution throughout the community material is nearly good. ECMP makes use of static hashing, and relying on stream entropy, it may result in site visitors polarization, inflicting micro-congestion and negatively affecting JCT.

Silicon One versus NVIDIA Spectrum-X and InfiniBand

The NCCL Benchmark – Aggressive Evaluation (Determine 3) reveals how Cisco Silicon One performs in opposition to NVIDIA Spectrum-X and InfiniBand applied sciences. The info for NVIDIA was taken from the SemiAnalysis publication. Observe that Cisco doesn’t know the way these assessments have been carried out, however we do know that the cluster measurement and GPU to community material connectivity is just like the Cisco Zeus Cluster.

Bus Bandwidth (Bus BW) benchmarks the efficiency of collective communication by measuring the velocity of operations involving a number of GPUs. Every collective has a selected mathematical equation reported throughout benchmarking. Determine 3 reveals that Cisco Silicon One – All Scale back performs comparably to NVIDIA Spectrum-X and InfiniBand throughout numerous message sizes.

Community material efficiency evaluation

The IBPerf Benchmark compares RDMA efficiency in opposition to ECMP, DLB, and packet spray, that are essential for assessing community material efficiency. Incast eventualities, the place a number of GPUs ship knowledge to 1 GPU, usually trigger congestion. We simulated these situations utilizing IBPerf instruments.

Determine 4 reveals how Aggregated Session Throughput and JCT reply to completely different congestion avoidance algorithms: ECMP, DLB, and packet spray. DLB and packet spray attain Hyperlink Bandwidth, bettering JCT. It additionally illustrates how DCQCN handles micro-congestions, with PFC and ECN ratios bettering with DLB and considerably dropping with packet spray. Though JCT improves barely from DLB to packet spray, the ECN ratio drops dramatically as a result of packet spray’s perfect site visitors distribution.

Coaching and inference benchmark

The MLPerf Benchmark – Coaching and Inference, revealed by the MLCommons group, goals to allow honest comparability of AI/ML methods and options.

We centered on AI/ML knowledge middle options by executing coaching and inference benchmarks. To attain optimum outcomes, we extensively tuned throughout compute, storage, and networking parts utilizing congestion administration options of Cisco Silicon One. Determine 5 reveals comparable efficiency throughout numerous platform distributors. Cisco Silicon One with Ethernet performs like different vendor options for Ethernet.

Conclusion

Our deep dive into Ethernet and InfiniBand inside AI/ML environments highlights the outstanding prowess of Cisco Silicon One in tackling congestion and boosting efficiency. These revolutionary developments showcase the unwavering dedication of Cisco to supply strong, high-performance networking options that meet the rigorous calls for of as we speak’s AI/ML purposes.

Many due to Vijay Tapaskar, Will Eatherton, and Kevin Wollenweber for his or her assist on this benchmarking course of.

Discover safe AI infrastructure

Uncover safe, scalable, and high-performance AI infrastructure you could develop, deploy, and handle AI workloads securely while you select Cisco Safe AI Manufacturing unit with NVIDIA.

 

Share: