HC34-T2: Heterogeneous Compilation in MLIR

  Рет қаралды 5,144

hotchipsvideos

hotchipsvideos

Күн бұрын

Tutorial 2, Hot Chips 34 (2022), Sunday, August 21, 2022.
Chair: Stephen Neuendorffer, AMD
This tutorial covers a number of issues related to improved compilation of machine learning models to a wide variety of software and hardware accelerators.
Basic Concepts
Jacques Pienaar, Google
Code Generation
Harsh Menon, Nod.AI
ML Frontends and frameworks
Suraj Sudhir, ARM
CIRCT
Andrew Lenharth, SiFive, and John Demme, Microsoft

Пікірлер
2022 LLVM Dev Mtg: Paths towards unifying LLVM and MLIR
45:44
When mom gets home, but you're in rollerblades.
00:40
Daniel LaBelle
Рет қаралды 122 МЛН
Flipping Robot vs Heavier And Heavier Objects
00:34
Mark Rober
Рет қаралды 60 МЛН
Writing a compiler with LLVM - Cailin Smith - NDC Oslo 2022
47:58
NDC Conferences
Рет қаралды 46 М.
HC2023-S2: CPU 1
1:37:15
hotchipsvideos
Рет қаралды 1,7 М.
"TVM: An End to End Deep Learning Compiler Stack" by Thiery Moreau (OctoML)
1:01:04
Harvard CS249R: Intro to TinyML
Рет қаралды 11 М.
HC2023-K2: Hardware for Deep Learning
1:05:28
hotchipsvideos
Рет қаралды 12 М.