Using Bayesian Techniques to Speed up HPC Solutions
Using
Bayesian
Techniques
to
Speed
up
HPC
Solutions
Thursday,
August
26,
2021
REGISTER
12:00
pm
-
1:00
pm
About
the
Event
Recent
advances
at
IBM
Research
in
the
area
of
Bayesian
statistical
techniques
have
resulted
in
an
IBM
software
product
that
is
agnostic
to
any
HPC
vendor
system
to
dramatically
speed
up
the
total
time
it
takes
to
complete
hundreds
and
thousands
of
iterative
HPC
jobs.
The
areas
of
focus
are
currently
Reservoir
Simulation,
Computational
Fluid
Dynamics,
Computational
Biology/Chemistry
and
Drug
Discovery.
Others
may
come
forth
as
the
science
is
tested.
It
doesn’t
matter
what
HPC
system
you
use
since
the
software
AI
engine
is
out
of
band.
Results
for
tuning
and
optimizing
the
“next
run”
are
created
in
seconds
with
API
feedback
to
the
associated
simulation
solver
for
the
“next
run.”
IBM
Research
has
worked
with
scientists
all
over
the
world
ranging
from
UT
Austin
Petroleum
Engineering
to
Merck
Pharmaceuticals
in
the
UK
to
perfect
the
methodology.
The
software
is
free
for
the
academic
community
to
do
research,
while
it
is
a
paid
subscription
for
commercial/industrial
entities.
Speaker
Bios:
Terry
Leatherland
is
a
resident
of
Sugar
Land,
Texas,
who
has
spent
35-plus
years
at
Hewlett
Packard
and
IBM
doing
technical
sales
across
the
Gulf
Coast
and
entire
country.
As
a
graduate
of
the
University
of
Alabama,
BS
Chemistry/Computer
Science,
his
work
for
the
first
15
years
spanned
the
Chemistry
Quality
Assurance
environment
for
HP
across
the
Gulf
Coast.
He
has
sold
and
engineered
Laboratory
Automation
systems
to
every
major
Oil/Chemical
company
on
the
coast
interfacing
with
all
major
laboratory
instrumentation
and
process
control
systems.
