by Arkaprava Basu, Natalia Gavrilenko, Keijo Heljanko, Reese Levine, Ajay Ashok Nayak, Hernan Luis Ponce de Leon, Tyler Sorensen and Haining Tong on Jun 6, 2025 | Tags: gpu, memory models
Context A recent MICRO 2024 article titled “Over-synchronization in GPU Programs” describes how eliminating redundant or coarser-grained (slower) synchronization in GPU programs can lead to significant gains in performance and introduces a tool called ScopeAdvice to...
Read more...
by Babak Falsafi on Jun 2, 2025 | Tags: Cloud computing, Data Centers, Energy-Efficiency, Methods, Sustainability
There has been a lively debate on Computer Architecture Today about whether we should focus our attention on computing’s embodied carbon or operational carbon. In recent years, there has also been a lot of concern about the growth of AI and its impact on both energy...
Read more...
by Vijay Janapa Reddi on May 6, 2025 | Tags: Industry
The Research Pipeline is Stalling The U.S. National Science Foundation (NSF) froze all outgoing funding, including new awards and scheduled payments on active grants. Over 1,000 NSF research projects were abruptly canceled in a few days, resulting in roughly $739...
Read more...
by Emery Berger and Michael D. Moffitt on May 2, 2025 | Tags: Conferences, Industry track
In late March 2025, computer systems researchers from around the globe descended upon Rotterdam, Netherlands to participate in another edition of ASPLOS. The event was distinguished from previous installments for a number of reasons; the conference is now celebrating...
Read more...
by Seunghee Shin on Apr 28, 2025 | Tags: Conferences
Prologue ASPLOS 2025 just wrapped up, and I’m still carrying the energy from an unforgettable week in Rotterdam, Netherlands. With its striking skyline, bold architecture, and dynamic urban design, the city feels like a living symbol of innovation and...
Read more...
by Toru Koizumi, Ryota Shioya, Hidetsugu Irie on Apr 2, 2025 | Tags: Architecture, CPU, gpu, ISA Design
CPU cores have become significantly wider over the past decade. Ten years ago, the highest-performance CPUs could decode only up to four instructions simultaneously and execute up to eight instructions. However, top-tier CPUs released in recent years have grown to...
Read more...
by Shuwen Deng on Mar 26, 2025 | Tags: Conferences
The 31st IEEE International Symposium on High-Performance Computer Architecture (HPCA’25) was held from March 1 to 5, 2025 in Las Vegas, USA. Co-located with PPoPP, CGO, and CC as part of the “Parallel Programming, Architecture and Compilation (PARC)” event, HPCA’25...
Read more...
by David Patterson on Mar 5, 2025 | Tags: AI accelerator, AI hardware, Carbon emissions, Carbon footprint, Data center
“It’s not that easy bein’ green.” – Kermit the Frog, 1976 We likely just published the first paper to report the carbon footprint of manufacturing AI accelerators. This life-cycle assessment in a real-world setting found that hardware operation emits more...
Read more...
by Yao Fu, Luo Mai and Dmitrii Ustiugov on Feb 28, 2025 | Tags: Cloud computing, generative ai, machine learning systems, serverless ai, serverless computing
Artificial Intelligence (AI) is revolutionizing the world, powering productivity tools, healthcare, and education innovations through large-scale models like ChatGPT, DeepSeek, Gemini, and Claude. Most of these models, managed by tech giants such as OpenAI, Google,...
Read more...
by Amir Yazdanbakhsh on Feb 4, 2025 | Tags: abstraction, AGI, compound AI systems, Computer Architecture, Computer Systems, intelligent systems, Machine Learning, Uncertainty
“The growing complexity of intelligent systems can outpace the ability of conventional computing abstractions to support them effectively.” IET REACH 2024, Amir Yazdanbakhsh. I came across this observation by Edsger Dijkstra recently while scrolling X, and...
Read more...