The Supercomputing.life platform is a network
of General Purpose Compute Nodes designed
by the Distributed Computing Research Group
at Balanced City. ¹Compute Node Architecture · Overview
A Compute Node is a group of computers that
works together on large projects.
Distributed computing research and experience in
performance engineering guided the design of the
General Purpose Compute Node GPCN2021.
General Purpose Compute Node GPCN2021A General Purpose Compute Node
has 15 computers, pictured above.· 12 x RPi A+ Primary Computers perform
the scientific work that the system is designed
· 3 x RPi B Managers orchestrate workflow,
data and communication.
raspberrypi.org12 x Raspberry Pi Model A+ 64bit ARM Cortex-53 Quad-Core 1.4GHz 3 x Raspberry Pi Model B 64bit ARM Cortex-A72 Quad-Core 1.5 GHz
Each individual RPi has a Quad-Core Processor
with 4 Central Processing Unit (CPU) Cores.
Each CPU Core can perform an independent
A General Purpose Compute Node
has a total of 60 CPU Cores.
Compute Node Workflow · Primary Computation
RPi B Managers divide the workload into partitions,
preparing data and computational tasks for up to
48 CPU Cores on 12 RPi A+ Primary Computers.
Primary Computers deliver processed data back
to Managers upon completion.
Managers consolidate processed data, checking
for accuracy and consistency.
Lastly, managers send processed data from the
Compute Node to the project's final inventory.
Compute Node Software · Scientific Libraries, Methods and Tools
Scientific libraries, methods and tools used on this
architecture are created de novo and inspired by
leadership initiatives of the NIH Biowulf Cluster ²
and Department of Energy National Laboratories ³.
· Supercomputing.life Applications
Supercomputing.life applications support scientific
research and are developed with databases ⁴ from
the National Center for Biotechnology Information,
a division of the National Library of Medicine at the
National Institutes of Health in the United States.
These applications are collectively referred to as
the Learning Health Systems and are accessible
by client applications such as OpenMD.life
This machine teaching platform benefits from
natural intelligence of users around the world.
Operational Performance · Initial Deployment
Compute Nodes began operation in Q2 2019
performing CPU intensive language processing
for the Learning Health Systems.
The utilization profile of a Compute Node typically
has 20 to 35 CPU Cores in continuous parallel
operation for several hours up to several days.
Technical measures of processor speed are less
relevant than the number of independent tasks
· Developer Productivity
Engineered to maximize performance of developers
through automation and ease of use, Compute Node
Architecture eliminates productivity barriers for rapid
prototyping, programming, optimizing and deploying
Easily deploying 1,000 computational tasks with no
complexity burden is a practical measure of system
success from the perspective of a developer.
· Operations per second
Computing benchmarks measure floating-point
operations per second (FLOPS).
The Compute Nodes described here are capable of...
· 64 GigaFLOPS peak CPU
· 85 GigaFLOPS peak CPU
Sustained operation is kept below
50 GigaFLOPS of primary computation.
An indefinite number of Compute Nodes can work
together to accomplish computational goals.
This scalability is a motivating design requirement
of the Compute Node Architecture.
· Tera Scale · 1012 FLOPS
25 Compute Nodes are estimated to sustain
1 TeraFLOP using 1,000 CPU Cores.
· Peta Scale · 1015 FLOPS
25,000 Compute Nodes are estimated to sustain
1 PetaFLOP using 1,000,000 CPU Cores.
· Exa Scale · 1018 FLOPS
25,000,000 Compute Nodes are estimated to sustain
1 ExaFLOP using 1,000,000,000 CPU Cores.
Exascale computing is a significant milestone
in computer science and engineering.
Compute Node Costs · Hardware
Compute Node hardware costs less than $1,000.
25 Compute Nodes with 1,500 total CPU Cores
cost ~ $15,000 in hardware per availability.
Operating costs are primarily determined by
software and hardware engineering labor.
Overall Assessment · Summary
Overall performance has met high expectations
with no technical issues.
The architecture has proven to be scalable and
adaptive for advanced computational research.