In this interview, GigaIO CEO Alan Benjamin talks about systems performance problems and wasted compute resources when implementing ML, HPDA and other high demand workloads that involve high data volumes. At issue, Benjamin explains, is today’s rack architecture, which is decades old and unsuited for combinations of CPUs, GPUs and other accelerators needed for advanced computing strategies. The answer: the “composable disaggregated infrastructure.”
Home » HPC Hardware » GPUs » Video: GigaIO on Optimizing Compute Resources for ML, HPDA and other Advanced Workloads
Video: GigaIO on Optimizing Compute Resources for ML, HPDA and other Advanced Workloads
Related Content:
- GigaIO and Microchip Power Native PCI Express Network Fabric for Composable Disaggregated Infrastructure
- HPC Predictions 2021: Quantum Beyond Qubits; the Rising Composable and Memory-Centric Tide; Neural Network Explosion; 5G’s Slow March
- At SC20: GigaIO Launches PCIe 4.0 Accelerator Pooling Appliance for the Composable Data Center
- Composable Computing at SDSC
- vScaler Integrates SLURM with GigaIO FabreX for Elastic HPC Cloud Device Scaling
Filed Under: Compute, Coprocessors, Datacenter, Enterprise HPC, Government, GPUs, High Performance Analytics, Machine Learning, Manufacturing, News, Research / Education, Video Tagged With: composable infrastructure, disaggregated infrastructure, GigaIO, Heterogeneous Computing, hpc, Weekly Newsletter Articles