SPEC Blog

Now integrated directly into the SPECapc for Siemens NX 2024 benchmark download, the SPECapc for Siemens NX 2024 WDK offers a parallel customization framework that gives you the power, flexibility, and security to measure the performance of your own GPU-specific workloads, design models, and assemblies.

When you invest in a new computing system – whether it’s a high-performance cluster, a mission-critical server, or a high-end workstation – how do you know it will deliver the performance your workloads actually demand? For nearly four decades, the SPEC CPU benchmark suites have cut through marketing claims and delivered a trusted measure of real-world performance for procurement teams, engineers, and hardware vendors worldwide. Today, this venerable benchmark gets even better with the release of the SPEC CPU 2026 benchmark suites, a major update that brings broader workload coverage, expanded memory benchmarking, and tighter alignment with the open source software that now powers modern computing.

The SPEC Graphics and Workstation Performance Group (GWPG) is committed to supporting the Siemens NX user and development communities with reliable, vendor-neutral benchmarks, and 2025 saw the release of two crucial new tools to ensure every component of the processor-intensive design software can be accurately assessed.

In 2025, the SPEC Graphics Performance Characterization (SPECgpc) Committee set out to modernize our worldwide standard SPECviewperf benchmark to meet the demands of the latest graphics workflows and to make it easier to update the benchmark in the future. I’m extremely pleased to report that our team delivered not one, but two major steps toward those goals, releasing the SPECviewperf 15 benchmark in May, followed by the SPECviewperf 15.0.1 benchmark in December.

The SPEC Cloud Committee is currently developing a novel system-level benchmark for datacenters that mimics emerging cloud use-cases and exercises all the relevant components of the modern infrastructure. The primary objective of the benchmark is to establish a comprehensive suite of real-world, cloud-enabled workloads and key performance indicators that adequately capture the performance of modern datacenter systems at scale. The benchmark will also provide valuable insights that will help in the design of future generations of computing platforms. Beyond performance characterization, the benchmark is expected to model portability, reproducibility, transparency and observability, with the help of integrated telemetry and detailed reporting, thereby fostering broad industry-wide adoption.

In 2020, regulatory changes from the U.S. government inadvertently affected SPEC’s efforts to establish and promote global standardized benchmarks related to energy efficiency. The changes also had the unintended consequence of impacting U.S.-based computing system manufacturers. However, a dedicated group of internationally based SPEC International Standards Group (ISG) members worked tirelessly – and successfully – to clarify the U.S. government’s position, consequently, ensuring SPEC could continue enabling governments and businesses to more effectively achieve sustainable development and carbon emission reduction goals.

We are delighted to share highlights from the recently concluded 16th annual ACM/SPEC International Conference on Performance Engineering (ICPE) 2025, held May 5-9 in Toronto, Canada. ICPE has been the flagship conference in the area of performance engineering over the years and has a tradition of bringing together both academic scholars and industrial practitioners to discuss recent advances in the area.

One of the difficulties in processor simulation is finding workloads that are based on real applications. The gem5 simulator, combined with SPEC CPU 2017, has recently helped to highlight complex areas of processor design related to moving data more efficiently.

In the rapidly evolving field of artificial intelligence (AI) and machine learning (ML), enhancing the accuracy and computational efficiency of large models remains a critical challenge. As of 2024, there are over 100 commercial large language models worldwide, with OpenAI’s ChatGPT boasting more than 500 million users. The swift development of these models is driving significant advances in AI capabilities.