The Standard Performance Evaluation Corporation (SPEC), the trusted global leader in computing benchmarks, this month announced a major update to its workstation computer benchmark, a trusted standard in the industry.
SPECworkstation 4.0 adds significant changes from version 3.1 and includes all key aspects of modern workstation performance workflows, including new AI and ML (machine learning) workflows.
SPECworkstation 4.0
The SPECworkstation 4.0 benchmark allows testers to gain a solid understanding of real-world CPU, graphics, accelerator, and disk performance for workstation computers, including any system that can run the benchmark, such as notebook computers.
SPECworkstation 4.0 is the latest benchmark for comprehensive workstation system performance testing.
The benchmark is directed to the needs of workstation users such as architects, engineers, scientists, and software developers who rely on workstation-class hardware for daily needs. It includes real-world leading applications used by professionals including Blender, Handbrake, LLVM and more. The benchmark provides comprehensive testing measures across several different industry verticals, each focused on specific use cases. These include:
- AI & Machine Learning
- Energy
- Financial Services
- Life Sciences
- Media & Entertainment (DCC)
- Product Design (MCAD)
- Productivity & Development
“A key value of this release lies in its ability to provide AI professionals with insights into how different hardware configurations handle diverse AI workloads,” said SPECwpc Chair Chandra Sakthivel. “This is essential for optimizing workstation setups for AI/ML tasks, driving the development of more efficient models, and ultimately advancing the capabilities of AI technology. As AI models evolve, a standardized benchmark that can assess performance across various dimensions – such as precision, throughput, and latency – will be invaluable for industry professionals and researchers.”
Key New Features of SPECworkstation 4.0
Designed to more accurately reflect today’s workloads, the new benchmark includes all of the following types of tests and measures:
- Support for AI/ML – The benchmark includes a dedicated set of tests focusing on AI and ML workloads, including data science tasks and ONNX runtime-based inference tests, reflecting the growing importance of AI/ML in workstation environments.
- New workloads
And…
- Autodesk Inventor: Measures key performance metrics in Inventor, a popular software package in the architecture, engineering, and construction (AEC) segment.
- LLVM-Clang: Measure code compilation performance using the LLVM compiler and toolchain.
- Data Science: Represents a data scientist’s workflow, including data scrubbing, ETL (extract, transform, load), and classical ML operations using tools such as Numpy, Pandas, Scikit-learn, and XGBoost.
- Hidden Line Removal: Measures time taken to remove occluded edges from wireframe models.
- MFEM: Uses finite element methods to perform dynamic adaptive mesh refinement (AMR).
- ONNX Inference: Benchmarks AI/ML inference latency and throughput using the ONNX runtime, a popular framework for evaluating machine learning models.
- Updated CPU Workloads: Updates for popular workloads like Blender, Handbrake, NAMD, and Octave improve relevance, accuracy, and compatibility for performance measurements.
- Updated Graphics Workloads: Tests adapted from the SPECviewperf2020 v3.1: measure the performance of professional graphics cards using application-based traces.
There is also…
- New Accelerator subsystem – This release introduces the Accelerator subsystem, recognizing the rapid innovation in the computing space. With accelerators playing a critical role in speeding up tasks such as AI/ML processing, video transcoding, and other compute-intensive operations, measuring and understanding their performance in the workstation environment is essential.
SPECworkstation 4.0 boasts a completely redesigned UI that simplifies the benchmarking process, making it easier to understand and use. And a command line interface (CLI) enables easier automation.
To learn more and obtain the new benchmark, go here. It is free for the user community and USD 5,000 for sellers of computer-related products and services (both hardware systems and software systems, and services). SPEC/GWPG members receive benchmark licenses as a membership benefit.
About SPEC
SPEC is a non-profit organization that establishes, maintains and endorses standardized benchmarks and tools to evaluate performance for the newest generation of computing systems. Its membership comprises more than 120 leading computer hardware and software vendors, educational institutions, research organizations, and government agencies worldwide.