Mixed Feelings About Mixed Precisions: Birds of a Feather at SC24!

kaust-hicma-sc24-bof-mixed-precisions.webp
Hardware Evolution for Mixed-Precision Support

Context

Motivated by the quickly changing hardware landscape, which nowadays is prominently equipped in low-precision arithmetic support, mixing floating-point precision formats has become a mainstream algorithmic optimization for simulations and AI workloads. The trade-offs are also important to consider and are not immediately obvious. These optimizations require support from the usual software stack (libraries, middleware, and application codes), strong numerical validation procedures, and ultimately scientific evidence that the applications’ key results survived the intermediate precision loss.

The emphasis on alternatives to the IEEE 754 floating-point standard, emerged in recent years due to machine learning’s insatiable need for computational power to train deep models composed of convolutional neural networks or ever growing transformer models based on attention mechanism for natural language processing or human-level models that play open-ended games such as Go, DOTA 2, and Poker or predict structural properties of folded proteins (recall AlphaGo, AlphaZero, or AlphaFold). A successful training session for these models requires in excess of Peta-FLOPS per day and costs millions of dollars due their hardware and energy requirements. To reduce the power draw, drastic reduction in floating-point storage bits is required to reap energy-saving benefits in addition to other tricks-of-the-trade such as sparsification and related approaches based on lottery ticket hypothesis. These were the driving factors towards lower-precision representations and specialized tensor FP units that enable Peta-FLOPS level performance from a single compute node.

Unlike machine learning models, scientific applications are much more demanding in terms of accuracy but there are early success stories about exploiting a mix of precisions in HPC, including real-time adaptive optics simulations on ground-based telescopes, genome-wide association study for human genomes and agricultural genomics, computational statistics for climate-weather forecasting, and solving inverse problems for seismic processing.

kaust-hicma-earth-system-models-ESMs.webp
Src: ACM Gordon Bell Climate Modeling Finalist @ SC24 by a multidisciplinary team from KAUST, MIT, NCAR, and NVIDIA. ERA5 surface temperature dataset at 25 km spatial resolution (1,038,240 locations).

History

This is the fourth event of a series on the topic of mixed precisions, which started at SC22, and continued during ISC23 and SC23. Our previous exchanges with the audience were enriching and permitted to foster the necessary interdisciplinary research collaborations required to address the various computational challenges related to mixed precisions.

Format

We plan to begin with introductions and a quick round of introductory remarks from the experts and practitioners in the mixed-precision field. These will be focused by driving them with questions and prompts distributed prior to the BoF. Their goal is to lead into the relevant mixed-precision topics but leave enough to explore with clarifying questions from the audience that could steer the discussion towards the specifics of interest. We will follow up with more rounds of prompts towards the invited experts and interaction with the audience to drive the discussion and formulate viewpoints and perspectives that will become the main takeaways of the BoF. The prompt-based interaction will mimic a chat bot session between audience and experts.

We will conclude with the summary of the BoF’s outcomes and explore potential follow-on events while connecting the interest parties for more focused groups engaged in more narrow topics of mixed-precision landscape.

Organizers

  • Hartwig Anzt, Chair of Computational Mathematics, School of Computation, Information and Technology, Technical University of Munich
  • Harun Bayraktar, Senior Director of Software Engineering, NVIDIA Corporation
  • Hatem Ltaief, Principal Research Scientist, King Abdullah University of Science and Technology
  • Piotr Luszczek, Technical Staff Scientist at MIT Lincoln Lab and Research Assistant Professor, ICL, University of Tennessee Knoxville

SC24 BoF Date, Time and Location

Wednesday, November 20th 12:15pm-1:15pm

Room B211

Related URLs