Interconnect Your Future Supercomputing Nov 2015 Paving the Road to Exascale
Interconnect Your Future Supercomputing Nov 2015
Paving the Road to Exascale
© 2015 Mellanox Technologies 2
The Ever Growing Demand for Higher Performance
2000 2020 2010 2005
“Roadrunner”
1st
2015
Terascale Petascale Exascale
Single-Core to Many-Core SMP to Clusters
Performance Development
Co-Design
HW SW
APP
Hardware Software
Application
The Interconnect is the Enabling Technology
© 2015 Mellanox Technologies 3
Co-Design Architecture to Enable Exascale Performance
CPU-Centric Co-Design
Limited to Main CPU Usage Results in Performance Limitation
Creating Synergies Enables Higher Performance and Scale
Software Software
In-CPU Computing
In-Network Computing
In-Storage Computing
© 2015 Mellanox Technologies 4
The Intelligence is Moving to the Interconnect
CPU
Interconnect
Past Future
© 2015 Mellanox Technologies 5
Co-Design Architecture Depends on Offloading Technologies
Programmability
RDMA GPUDirect Virtualization
Backward and Future Compatibility
Direct Communications
Applications (Innovations, Scalability, Performance)
Software-Defined Network (SDN)
Co-Design Requires Intelligent Interconnect
Offloading Technologies: Intelligent Interconnect
© 2015 Mellanox Technologies 6
Breaking the Application Latency Wall
§ Today: Network device latencies are on the order of 100 nanoseconds
§ Challenge: Enabling the next order of magnitude improvement in application performance
§ Solution: Creating synergies between software and hardware – intelligent interconnect
Intelligent Interconnect Paves the Road to Exascale Performance
10 years ago
~10 microsecond
~100 microsecond
Network Communication Framework
Today
~10 microsecond
Communication Framework
~0.1 microsecond
Network
~1 microsecond
Communication Framework
Future
~0.05 microsecond
Co-Design Network
© 2015 Mellanox Technologies 7
Introducing Switch-IB 2 World’s First Smart Switch
© 2015 Mellanox Technologies 8
Introducing Switch-IB 2 World’s First Smart Switch
§ The world fastest switch with <90 nanosecond latency
§ 36-ports, 100Gb/s per port, 7.2Tb/s throughput, 7.02 Billion messages/sec
§ Adaptive Routing, Congestion control, support for multiple topologies
World’s First Smart Switch
Build for Scalable Compute and Storage Infrastructures
10X Higher Performance with The New Switch SHArP Technology
© 2015 Mellanox Technologies 9
SHArP (Scalable Hierarchical Aggregation Protocol) Technology
Delivering 10X Performance Improvement
for MPI and SHMEM/PAGS Applications
Switch-IB 2 Enables the Switch Network to
Operate as a Co-Processor
SHArP Enables Switch-IB 2 to Manage and
Execute MPI Operations in the Network
© 2015 Mellanox Technologies 10
The Intelligence is Moving to the Interconnect
Communication Frameworks (MPI, SHMEM/PGAS)
The Only Approach to Deliver 10X Performance Improvements
Applications Transport RDMA SR-IOV
Collectives Peer-Direct GPUDirect
More…
MPI / SHMEM Offloads
© 2015 Mellanox Technologies 11
High-Performance Designed 100Gb/s Interconnect Solutions
Transceivers
Active Optical and Copper Cables
(10 / 25 / 40 / 50 / 56 / 100Gb/s) VCSELs, Silicon Photonics and Copper
36 EDR (100Gb/s) Ports, <90ns Latency
Throughput of 7.2Tb/s
7.02 Billion msg/sec (195M msg/sec/port)
100Gb/s Adapter, 0.7us latency
150 million messages per second
(10 / 25 / 40 / 50 / 56 / 100Gb/s)
32 100GbE Ports, 64 25/50GbE Ports
(10 / 25 / 40 / 50 / 100GbE)
Throughput of 6.4Tb/s
© 2015 Mellanox Technologies 12
Intelligent Interconnect Delivers Higher Datacenter ROI
Users
NETWORK
COMPUTING
NETWORK
Users
Intelligence
Network Offloads Computing for applications
Smart Network Increase Datacenter Value
Network functions On CPU
COMPUTING
© 2015 Mellanox Technologies 13
Mellanox InfiniBand Proven and Most Scalable HPC Interconnect
“Summit” System “Sierra” System
Paving the Road to Exascale
© 2015 Mellanox Technologies 14
Technology Roadmap – One-Generation Lead over the Competition
2000 2020 2010 2005
“Roadrunner” Mellanox Connected
1st 3rd TOP500 2003
Virginia Tech (Apple)
2015
Terascale Petascale Exascale
10G 20G 40G 56G 100G 200G 400G
TrueScale
No-Offload Network
40G (InfiniBand)
Same PathScale Technology
Under Intel Logo
InfiniPath
No-Offload Network
20G (InfiniBand)
OmniPath
No-Offload Network
100G (Proprietary)
Same PathScale Technology
Under QLogic Logo
© 2015 Mellanox Technologies 15
Mellanox InfiniBand Solutions Deliver Highest ROI for Any Scale
100 Gb/s Link Speed Higher Performance
Unlimited Scalability Higher Resiliency
Proven!
Smart Network For Smart Systems RDMA, Acceleration Engines, Programmability 200
Gb/s Link Speed
2014
Gain Competitive Advantage Today, Protect Your Future
1 Mellanox Estimations
25% Lower
20% Lower
Scalability CPU efficiency1
Power Consumption Per Switch Port
Switch Latency
2X Higher
Message Rate
44% Higher
2017
© 2015 Mellanox Technologies 16
Mellanox Delivers Best Interconnect
§ 100Gb/s throughput at 0% CPU utilization
§ Adapter: 150 Million messages/sec on today’s systems, 44% higher
§ Switch: 7.02 Billion messages/sec (195 Million per port)
§ 20% lower switch latency, with deterministic latency!
Higher Performance
Lower TCO
Higher Reliability
§ 25% lower power consumption per switch port
§ Standard-based solutions, large eco-system support
§ Backward and future compatibility – protect investments
§ Offloading Architecture (RDMA, GPUDirect etc.) delivers highest system efficiency
§ 1,000X higher reliability - Mellanox delivers Bit Error Rate of 10-15 versus 10-12
§ Superior signal integrity
§ Support for Multiple data integrity mechanisms (FEC1, LLR2, COD3 and more)
1- Forward Error Correction; 2 – Link Level Retransmission; 3- Correction on Demand
© 2015 Mellanox Technologies 17
End-to-End Interconnect Solutions for All Platforms
Highest Performance and Scalability for
X86, Power, GPU, ARM and FPGA-based Compute and Storage Platforms
10, 20, 25, 40, 50, 56 and 100Gb/s Speeds
X86 Open POWER GPU ARM FPGA
Smart Interconnect to Unleash The Power of All Compute Architectures
© 2015 Mellanox Technologies 18
Mellanox Solutions Interconnect Your Future
The Interconnect is The Competitive Advantage
Mellanox Interconnect
Performance, Scalability, Reliability, Proven
Speed-Up Your Present, Protect Your Future Paving The Road to Exascale Computing Together
Thank You