BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//DATE2026//date-conference.com//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
DTSTART;TZID=Europe/Rome:20260420T131500
DTEND;TZID=Europe/Rome:20260420T140000
LOCATION:Room Auditorium
CREATED:20260421T174602
DTSTAMP:20260421T174602
SUMMARY:LK01 IEEE CEDA Distinguished Lecturer Lunchtime Keynote "Unifying Accelerator Design and Programming for Evolvable Computing"
URL;VALUE=URI:https://date26date-conference.com/programme#LK01
BEGIN:VALARM
TRIGGER:-PT15M
ACTION:DISPLAY
DESCRIPTION:Reminder
END:VALARM
DESCRIPTION:Get the latest session information at
https://date26date-conference.com/programme#LK01\n\n\nWe are living
through a fundamental shift in computing, where performance and efficiency
gains increasingly come from specialised accelerators tailored to "hot"
domains like AI. Yet as accelerator-centric computing proliferates, it
continues to build atop a longstanding disconnect between the way we
design these systems and the way we program them. This divide slows
hardware innovation, complicates the software stack, and makes
accelerators far harder to evolve than the rapidly changing applications
they are meant to serve.\nIn this talk, I will present our recent research
on closing this gap through a unified hardware-software co-design stack.
At the core is a new abstraction that generalises single program multiple
data beyond largely independent threads to encompass spatial structure and
communication. It offers a single, composable model for expressing both
how accelerators are constructed and how they are programmed. I will show
how this abstraction is realised in Allo, an open-source, Python-based,
MLIR-powered framework to enable concise specifications that map
efficiently across FPGA, ASIC, NPU, and GPU platforms. I will conclude
with a forward-looking perspective on automated compiler construction,
differentiable hardware synthesis, and agentic design automation, and
discuss how these directions may help move us toward truly evolvable
heterogeneous computing.\nIn this talk, I will present our recent research
on closing this gap through a unified hardware-software co-design stack.
At the core is a new abstraction that generalizes single program multiple
data beyond largely independent threads to encompass spatial structure and
communication. It offers a single, composable model for expressing both
how accelerators are constructed and how they are programmed. I will show
how this abstraction is realized in Allo, an open-source, Python-based,
MLIR-powered framework to enable concise specifications that map
efficiently across FPGA, ASIC, NPU, and GPU platforms. I will conclude
with a forward-looking perspective on automated compiler construction,
differentiable hardware synthesis, and agentic design automation, and
discuss how these directions may help move us toward truly evolvable
heterogeneous computing.
X-ALT-DESC;FMTTYPE=text/html:Get the latest session
information at https://date26date-conference.com/programme#LK01
We
are living through a fundamental shift in computing, where performance and
efficiency gains increasingly come from specialised accelerators tailored
to "hot" domains like AI. Yet as accelerator-centric computing
proliferates, it continues to build atop a longstanding disconnect between
the way we design these systems and the way we program them. This divide
slows hardware innovation, complicates the software stack, and makes
accelerators far harder to evolve than the rapidly changing applications
they are meant to serve.In this talk, I will present our recent research
on closing this gap through a unified hardware-software co-design stack.
At the core is a new abstraction that generalises single program multiple
data beyond largely independent threads to encompass spatial structure and
communication. It offers a single, composable model for expressing both
how accelerators are constructed and how they are programmed. I will show
how this abstraction is realised in Allo, an open-source, Python-based,
MLIR-powered framework to enable concise specifications that map
efficiently across FPGA, ASIC, NPU, and GPU platforms. I will conclude
with a forward-looking perspective on automated compiler construction,
differentiable hardware synthesis, and agentic design automation, and
discuss how these directions may help move us toward truly evolvable
heterogeneous computing.In this talk, I will present our recent research
on closing this gap through a unified hardware-software co-design stack.
At the core is a new abstraction that generalizes single program multiple
data beyond largely independent threads to encompass spatial structure and
communication. It offers a single, composable model for expressing both
how accelerators are constructed and how they are programmed. I will show
how this abstraction is realized in Allo, an open-source, Python-based,
MLIR-powered framework to enable concise specifications that map
efficiently across FPGA, ASIC, NPU, and GPU platforms. I will conclude
with a forward-looking perspective on automated compiler construction,
differentiable hardware synthesis, and agentic design automation, and
discuss how these directions may help move us toward truly evolvable
heterogeneous computing.
UID:DATE-LK01-20260420T131500-20260420T140000
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Rome
TZURL:http://tzurl.org/zoneinfo/Europe/Rome
X-LIC-LOCATION:Europe/Rome
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19810329T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CEST
DTSTART:19961027T030000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
BEGIN:STANDARD
TZOFFSETFROM:-001444
TZOFFSETTO:+0000
TZNAME:WET
DTSTART:19010101T000000
RDATE:19010101T000000
END:STANDARD
END:VTIMEZONE
END:VCALENDAR