FLEX LOGIX DISCLOSES REAL-WORLD EDGE AI INFERENCE BENCHMARKS SHOWING SUPERIOR PRICE/PERFORMANCE FOR ALL MODELS
InferX X1 sampling expected Q3 2020
Flex LogixÒ Technologies, Inc., the leading supplier of embedded FPGA (eFPGA) IP, architecture and software, today announced real-world benchmarks for its InferXÔ X1 edge inference co-processor, showing significant price/performance advantages when compared to Nvidia’s Tesla T4 and Xavier NX when run on actual customer models. These details were presented at today’s Linley Spring Processor Conference by Vinay Mehta, Flex Logix’s inference technical marketing manager, which can be viewed at this link.
The InferX X1 has a very small die size: 1/7th the area of Nvidia’s Xavier NX and 1/11th the area of Nvidia’s Tesla T4. Despite being so much smaller, the InferX X1 has latency for YOLOv3, an open source model that many customers plan to use, similar to Xavier NX. On two real customer models, InferX X1 was much faster, as much as 10x faster in one case.
In terms of price/performance as measured by streaming throughput divided by die size, InferX X1 is 2-10x better than Tesla T4 and 10-30x better than Xavier NX.
“Customers expect that they can use performance on ResNet-50 to compare alternatives. These benchmarks demonstrate that the relative performance of an inference accelerator on one model does not apply to all models,” said Geoff Tate, CEO and co-founder of Flex Logix. “Customers should really be asking each vendor they evaluate to benchmark the model that they will use to find out the performance they will experience. We are doing this for customers now and welcome more – we can benchmark any neural network model in TensorFlow Lite or ONNX.”
The InferX X1 is completing final design checks and will tape-out soon with sampling expected in Q3 2020 as a chip and as a PCIe board.
Flex Logix’s InferX X1 edge inference co-processor provides excellent inference efficiency, delivering more throughput on tough models for less $, less watts. It has been optimized for what the edge needs: large models and large models at batch=1. InferX X1 offers throughput close to data center boards that sell for thousands of dollars, but does so at single digit watts and at a fraction of the price. InferX X1 is programmed using TensorFlow Lite and ONNX: a performance modeler is available now.