- Gaudi Delivers Record-Breaking Performance and Native Integration of Ethernet 
for Scaling

Habana Labs, Ltd. (www.habana.ai), a leading developer of AI processors, today 
announced the Habana Gaudi(TM) AI Training Processor. Training systems based on 
Gaudi processors will deliver an increase in throughput of up to four times 
over systems built with equivalent number GPUs.

Photo - https://mma.prnewswire.com/media/903245/HLS_1_with_heatsink_small.jpg 
Photo - https://mma.prnewswire.com/media/903246/HL_205_small.jpg 
Photo - 
https://mma.prnewswire.com/media/903247/HLS_1_Open_Overhead_View_smaller.jpg 
Logo - https://mma.prnewswire.com/media/744578/Habana_Labs_Ltd___Logo.jpg 

Gaudi's innovative architecture enables near-linear scaling of training systems 
performance, as high throughput is maintained even at smaller batch sizes, thus 
allowing performance scaling of Gaudi-based systems from a single device to 
large systems built with hundreds of Gaudi processors. 

In addition to record-breaking performance, Gaudi brings another industry first 
to AI training: on-chip integration of RDMA over Converged Ethernet (RoCE v2) 
functionality within the AI processor, to enable the scaling of AI systems to 
any size, using standard Ethernet. With Gaudi, Habana Labs' customers can now 
utilize standard Ethernet switching for both scaling-up and scaling-out AI 
training systems. Ethernet switches are multi-sourced, offering virtually 
unlimited scalability in speeds and port-count, and are already used in 
datacenters to scale compute and storage systems. In contrast to Habana's 
standards-based approach, GPU-based systems rely on proprietary system 
interfaces, that inherently limit scalability and choice for system designers.

"With its new products, Habana has quickly extended from inference into 
training, covering the full range of neural-network functions," commented 
Linley Gwennap, principal analyst of The Linley Group. "Gaudi offers strong 
performance and industry-leading power efficiency among AI training 
accelerators. As the first AI processor to integrate 100G Ethernet links with 
RoCE support, it enables large clusters of accelerators built using 
industry-standard components."

The Gaudi processor includes 32GB of HBM-2 memory and is currently offered in 
two forms: 

    -- HL-200 – a PCIe card supporting eight ports of 100Gb Ethernet; 
    -- HL-205 – a mezzanine card compliant with the OCP-OAM specification, 
       supporting 10 ports of 100Gb Ethernet or 20 ports of 50Gb Ethernet. 

Habana is also introducing an 8-Gaudi system called HLS-1, which includes eight 
HL-205 Mezzanine cards, with PCIe connectors for external Host connectivity and 
24 100Gbps Ethernet ports for connecting to off-the-shelf Ethernet switches, 
thus allowing scaling-up in a standard 19'' rack by populating multiple HLS-1 
systems.

Gaudi is the second purpose-built AI processor to be launched by Habana Labs in 
the past year, following the Habana Goya(TM) AI Inference Processor. Goya has 
been shipping since Q4, 2018, and has demonstrated industry-leading inference 
performance, with the industry's highest throughput, highest power efficiency 
(images-per-second per Watt), and real-time latency.

"Training AI models require exponentially higher compute every year, so it's 
essential to address the urgent needs of the datacenter and cloud for radically 
improved productivity and scalability. With Gaudi's innovative architecture, 
Habana delivers the industry's highest performance, while integrating 
standards-based Ethernet connectivity, enabling unlimited scale," said David 
Dahan, CEO of Habana Labs. "Gaudi will disrupt the status quo of the AI 
Training processor landscape." 

"Facebook is seeking to provide open platforms for innovation around which our 
industry can converge," said Vijay Rao, Director of Technology, Strategy at 
Facebook. "We are pleased that the Habana Goya AI inference processor has 
implemented and open-sourced the backend for the Glow machine learning compiler 
and that the Habana Gaudi AI training processor is supporting the OCP 
Accelerator Module (OAM) specification."

The Gaudi Processor is fully programmable and customizable, featuring a second- 
generation Tensor Processing Core (TPC(TM)) cluster, along with development 
tools, libraries, and a compiler, that collectively deliver a comprehensive and 
flexible solution. Habana Labs SynapseAI(TM) software stack consists of a rich 
kernel library and open toolchain for customers to add proprietary kernels. 

Habana will sample Gaudi platforms to select customers in the second half of 
2019. For more information on Gaudi AI Training and Goya AI Inference 
Processors, please visit www.habana.ai 

ABOUT HABANA LABS

Habana Labs is an AI Processor company founded in 2016 to develop from the 
ground-up processor platforms that are optimized for training deep neural 
networks and for inference deployment in production environments. We are 
unlocking the true potential of AI with platforms offering orders of magnitude 
improvements in processing performance, scalability, cost, and power 
consumption. Habana is located in Tel-Aviv, Israel, San Jose, California, 
Beijing, China and Gdansk, Poland, employing 150 people worldwide. 

For more information, please visit www.habana.ai or contact pr@habana.ai.

SOURCE  Habana Labs, Ltd.