Azure Provides Excellent HPC Cloud Performance With HBv4 Series Powered By AMD EPYC Genoa-X

Written by Michael Larabel in Processors on 4 August 2023 at 03:00 PM EDT. Page 4 of 5. 7 Comments.
OSPRay benchmark with settings of Performance Per Core, Benchmark: particle_volume/ao/real_time. HBv4 was the fastest.
OSPRay benchmark with settings of Performance Per Core, Benchmark: particle_volume/scivis/real_time. HBv4 was the fastest.
OSPRay benchmark with settings of Performance Per Core, Benchmark: gravity_spheres_volume/dim_512/ao/real_time. HC was the fastest.

With Intel's OSPRay software for example it's well optimized for AVX-512 and can scale up to the 176 vCPUs available with the HBv4 series, making its raw performance and value a no-brainer for those carrying out rendering workloads in the cloud.

7-Zip Compression benchmark with settings of Performance Per Core, Test: Compression Rating. HBv4 was the fastest.
Timed Node.js Compilation benchmark with settings of Performance Per Core, Time To Compile. HC was the fastest.

While the HB-series are tailored for HPC workloads, the HBv4 performance impressed outside of those key areas.

oneDNN benchmark with settings of Performance Per Core, Harness: Recurrent Neural Network Training, Data Type: bf16bf16bf16, Engine: CPU. HC was the fastest.
oneDNN benchmark with settings of Performance Per Core, Harness: Recurrent Neural Network Inference, Data Type: bf16bf16bf16, Engine: CPU. HC was the fastest.

The AVX-512 with Genoa-X helped the new VMs really shine in some areas.


Related Articles
Ampere Computing 2024 Roadmap Update: 256 Core 3nm CPU In 2025
Benchmarking The First RISC-V Cloud Server: Scaleway EM-RV1 Performance
AMD Announces Ryzen PRO 8840 & PRO 8000G Series CPUs
Intel Announces Gaudi 3 AI Accelerator, Intel Xeon 6 Brand
AMD Zen 4 vs. Zen 4C Performance, Zen 4C Core Scaling With Ryzen 5 8500G
Intel Core i3 14100 / i5 14500 vs. AMD Ryzen 5 8500G / 8600G In 500+ Benchmarks