Matei
Zaharia
DC
2585
3:00pm
Matei
Zaharia,
who
will
be
receiving
the
Faculty
of
Mathematics
Alumni
Achievement
Medal,
will
be
giving
a
talk
about
his
recent
work,
along
with
a
hands-on
demonstration.
Talk:
Cluster-Scale
Programming
with
Spark
Ever
wonder
what
all
that
functional
programming
you
learned
in
CS
was
useful
for?
In
large-scale
data
processing,
functional
programming
and
a
number
of
other
advanced
programming
concepts
have
become
commonplace,
as
they
offer
an
effective
way
to
express
computation
that
can
be
split
across
machines.
I'll
present
the
Spark
cluster
computing
framework,
which
offers
rich
APIs
for
parallel
data
processing
in
Scala,
Java
and
Python,
and
demo
how
to
use
it
in
various
tasks.
I'll
also
demo
graphical
exploration
tools
we
are
building
on
top
of
Spark
in
Databricks
Cloud.
Together,
these
tools
aim
to
make
it
possible
for
a
developer
to
work
with
data
sets
spread
across
a
cluster
as
they
do
with
collections
on
a
single
machine.
Biography
Matei
Zaharia
is
an
Assistant
Professor
at
MIT
and
CTO
at
Databricks,
the
startup
company
commercializing
Spark.
He
started
Spark
as
a
research
project
while
he
was
a
PhD
student
at
UC
Berkeley.
Before
that,
he
got
his
undergraduate
degree
at
the
University
of
Waterloo.