Scalable compute node with optical I/O for creation of directly-coupled, dense FPGA clusters
The 520 is a PCIe accelerator card featuring Intel's Stratix 10 FPGA and designed to address a range of compute-intensive and latency- critical applications including Machine Learning, Gene Sequencing, Oil & Gas and real-time Network Analytics. Introducing ground-breaking single precision floating point performance of up to 10 TFLOPS per device, the OpenCL-programmable 520 features an Intel Stratix 10 FPGA and four banks of DDR4 external memory.
Four optical network ports enable dramatic FPGA-to-FPGA scaling independent of the PCIe bus, plus support for an array of serial I/O protocols operating at 10/25/40/100G.
- Up to 10 TFLOPS of peak single precision performance
- 25MBytes of L1 cache @ up to 94 TBytes/s peak bandwidth
- 2X Core performance gains over Arria 10
- 70% lower power consumption
- Four 10/25/40/100G Network Ports
Nallatech’s new 520 is a PCIe accelerator card designed to address a range of computeintensive and latency-critical applications
- Machine Learning
- Gene Sequencing
- Oil & Gas
- Real-time Network Analytics