Enter your email above, then click "Sign Up" to join the STAC mail list and (optionally) register to access materials on the site. Click for terms.
NVIDIA publish unaudited STAC-AI inferencing benchmark results for GH200
2.89x the speed of previous generation x86 solution in warm runs of baseline Greeks
Highest throughput and efficiency for any publicly reported system to date
Skylake-based servers set multiple records in STAC-M3 Shasta benchmarks
32.7x the throughput of a larger Hadoop streaming cluster.
Spark throughput was highest when managed by IBM Spectrum Conductor with Spark.
Highest throughput to date for a system with a single CPU, GPU, or other co-processor
Solution breaks more than half the records in both baseline and scale benchmarks
Read the latest about research, events, and other important news from STAC.