Technology
AMD attacks Nvidia's FP64 emulation at SC26, touts native double-precision on Instinct MI430X — says Ozaki schemes fit less than 10% of HPC workloads and triple memory use and emulated FP64 is a poor fit for many HPC workloads
CRAYON summary
Tom's Hardware reports that AMD used Supercomputing 2026 (SC26) to promote the native FP64 double-precision support in its Instinct MI430X accelerator while criticizing Nvidia's FP64 emulation approach. According to the report, AMD says Ozaki-scheme FP64 emulation fits less than 10% of HPC workloads and triples memory use. AMD presents the MI430X as a unique foundation for next-generation supercomputing installations.
Based on Tom's Hardware's report - only one outlet has covered this so far. Read the original.▲ Sign in to vote stories up
Coverage 1 source · 1 report
Chronological.
-
AMD attacks Nvidia's FP64 emulation at SC26, touts native double-precision on Instinct MI430X — says Ozaki schemes fit less than 10% of HPC workloads and triple memory use and emulated FP64 is a poor fit for many HPC workloads
AMD is touting the benefits of the native FP64 support provided by its MI430X accelerator at Supercomputing 2026. The company says that Ozaki FP64 emulation only covers the needs of a small portion of HPC workloads, making the MI430X a unique foundation for next-gen supercomputing installations.
Discussion 0 comments