MLPERF Inference results for the GOYA processor,
November 2019 publication
MLPerf defines different product status and test methodologies of reported results to help clarify conclusions that might be made from its reporting. Here are some of the distinctions it reports.
Product status
- Available – available nor for purchase/deployment
- Preview – on a path to availability. not yet there
- Research – to test, learn and iterate
Test specifications adherence
- Closed – tested to match the specifications, enabling comparison with other closed results
- Open – tested to a set of parameters defined by the vendor to present product results in most favorable light
- Number of accelerators contained in the tested solution
- Type of host processor employed
Other important factors , such as power, were not included in the measurements.
Goya performance shown here was reported in the available and closed categories
MLPerf Inference 0.5 results
Benchmark | Dataset | Division | Status | Single stream (msec) | Multi stream (SPQ) | Server (QPS) | Offline (Throughput) |
---|---|---|---|---|---|---|---|
Resnet - 50 V1.5 | ImageNet | Closed | Available | 0.24 | 700 | 70013090* | 14451 |
SSD - Large | COCO - 1200X1200 | Closed | Available | 3.85 | 18 | 296.7 | 326.3 |
QPS = Queries per second @99% tail latency
(*) ResNet-50 v1.5 Server scenario result not verified by MLPERF
For more details, see the MLPERF industry – wide results and whitepaper