XELERA SILVA

XGBoost and LightGBM Acceleration

Xelera Silva provides best-in-class throughput and latency for XGBoost, LightGBM and CatBoost inference.

decision treee acceleration software picture

Best-in-class Throughput

22M inferences/s XGBoost inference throughput.

Best-in-class Latency

Microseconds query latency without jitter.

Seamsless adoption Icon

High
Integration

Bring your own model.

High
Efficiency

Concurrent execution of multiple XGBoost / LightGBM models.

XGBoost Acceleration

Machine learning based on gradient boosting frameworks such as XGBoost and LightGBM is increasingly used in many application domains, such as algorithmic trading systems, recommender systems, bioscience, or ransomware and DDoS detection systems.

Xelera Silva overcomes the latency drawback or throughput limitations of machine learning algorithms: It enables users to take advantage of in-loop machine learning inference with ultra-low latency or to eliminate throughput bottlenecks. Xelera Silva is available in a latency- and throughput-optimized accelerator mode.

network security icon
Network security
(DDOS prevention)
ransomware detection icon
Ransomware detection
anomaly detection
Anomaly detection
small network icon
Algorithmic trading
Round-Trip Latency (API Call on Host)

3 µs Inference Latency

Benchmark:

  • XGBoost regression model
  • Number of decision trees per model: 1000
  • Number of levels: 6

Test setup:

  • Xelera Silva on hardware accelerator (AMD Alves U50)
  • XGBoost on CPU (Intel Xeon Gold 5118)

Application Areas

High-Frequency Trading
Latency-Optimized Mode

High Frequency Traders use decision algorithms to automate trading instructions. The automated decisions are increasingly made by XGBoost and LightGBM models. A low latency is key for these systems. Silva overcomes the latency disadvantage of machine learning algorithms: Inference of XGBoost and LightGBM models is performed with a latency of a few microseconds. This enables customer to make better decisions and win speed races.

The turn-key accelerator connects to the software-based trading system and offloads the XGBoost/ LightGBM inference to a PCIe-attached AMD Alveo accelerator card (PCIe transfer included in round-trip latency).

high-frequency trading use-case

Real-Time Database
Throughput-Optimized Mode

The network is the first instance that must be protected to secure the enterprise IT system. Firewalls using Gradient Boosting Decision Trees perform inspection of the network flow data to detect suspicious patterns (e.g., a DDOS attack). Silva provides the necessary inference speed to ensure that the computationally intensive classification of network flows can be performed at the required bandwidth to avoid slowing down the network system.

Xelera Silva connects to the data analytics pipeline of a real-time database or instrument. The accelerator performs XGBoost inference on a 3.9 TB data set in a 10-minutes window.

Network intrusion detection

Do you want to know more about Xelera Silva?

Sign-Up for our quarterly newsletter to get insights on Xelera Silva!

Do you have any Questions?

If you have any questions, our Team will be happy to help you out. Take advantage of our expertise and get in touch with us now!

contact picture
Dr. Andrea Suardi
Head of Acceleration Technology