BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//swoogo.com//NONSGML kigkonsult.se iCalcreator 2.41.90//
CALSCALE:GREGORIAN
UID:63396265-3439-4535-b066-633639626338
BEGIN:VEVENT
UID:397c78048a5ada106c27c34b9e0e92ad172a56a7@swoogo.com
DTSTAMP:20261006T174433Z
DESCRIPTION:In this technical talk\, we discuss how compiler support for sp
 arse tensor computations was added to MLIR (LLVM’s extensible infrastructu
 re for building domain specific compilers). We discuss the concept of spar
 se tensor types as first class citizens and show how this simplifies the i
 ntroduction of new front-ends and back-ends for systems that want to add s
 parse tensor support. We also show how MLIR can be used for rapid sparse l
 ibrary development\, driven by either exhaustively searching for suitable 
 sparse storage formats or using ML to find such formats quicker\, or even 
 for end-to-end solutions mapping sparse agnostic specification of kernels 
 to efficient sparse code at runtime. Finally\, we discuss how you can cont
 ribute to this new sparse tensor support in MLIR.
DTSTART:20211117T184500Z
DTEND:20211117T191500Z
LAST-MODIFIED:20261006T174433Z
LOCATION:https://llvm.swoogo.com/2021DevMtg/v/s-705660
SEQUENCE:0
STATUS:CONFIRMED
SUMMARY:Compiler Support for Sparse Tensor Computations in MLIR
TRANSP:OPAQUE
X-ALT-DESC;FMTTYPE=text/html:<p>In this technical talk\, we discuss how com
 piler support for sparse tensor computations was added to MLIR (LLVM’s ext
 ensible infrastructure for building domain specific compilers). We discuss
  the concept of sparse tensor types as first class citizens and show how t
 his simplifies the introduction of new front-ends and back-ends for system
 s that want to add sparse tensor support. We also show how MLIR can be use
 d for rapid sparse library development\, driven by either exhaustively sea
 rching for suitable sparse storage formats or using ML to find such format
 s quicker\, or even for end-to-end solutions mapping sparse agnostic speci
 fication of kernels to efficient sparse code at runtime. Finally\, we disc
 uss how you can contribute to this new sparse tensor support in MLIR.</p>
BEGIN:VALARM
UID:62623661-3537-4765-a130-653431616533
ACTION:DISPLAY
DESCRIPTION:In this technical talk\, we discuss how compiler support for sp
 arse tensor computations was added to MLIR (LLVM’s extensible infrastructu
 re for building domain specific compilers). We discuss the concept of spar
 se tensor types as first class citizens and show how this simplifies the i
 ntroduction of new front-ends and back-ends for systems that want to add s
 parse tensor support. We also show how MLIR can be used for rapid sparse l
 ibrary development\, driven by either exhaustively searching for suitable 
 sparse storage formats or using ML to find such formats quicker\, or even 
 for end-to-end solutions mapping sparse agnostic specification of kernels 
 to efficient sparse code at runtime. Finally\, we discuss how you can cont
 ribute to this new sparse tensor support in MLIR.
TRIGGER:-PT15M
END:VALARM
END:VEVENT
END:VCALENDAR