#35 – Darkroom: Compiling High-Level Image Processing Code into Hardware Pipelines

20/10/2018 31 min

再生 "#35 – Darkroom: Compiling High-Level Image Processing Code into Hardware Pipelines"

Descargar episodio Ver en sitio original

エピソードの概要

画像処理用の DSL を FPGA にコンパイルする研究や、その延長で作られた画像処理用 Domain Specific Architecture である Pixel Visual Core について森田が話します。感想 … "#35 – Darkroom: Compiling High-Level Image Processing Code into Hardware Pipelines"の続きを読む

この番組のほかのエピソード Misreading Chat

#143 – SWE-bench: Can Language Models Resolve Real-World GitHub Issues? 11/12/2024

#142: An Empirical Study of Rust-for-Linux: The Success, Dissatisfaction, and Compromise 04/12/2024

#141: SQL Has Problems. We Can Fix Them: Pipe Syntax In SQL 13/11/2024

#140: GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models 24/10/2024

#139: NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis 02/10/2024

#138: Distilling the Knowledge in a Neural Network 11/09/2024

#137: Optimal Quantile Approximation in Streams 13/08/2024

#136: Distinct Elements in Streams: An Algorithm for the (Text) Book 07/08/2024

#135: In-Datacenter Performance Analysis of a Tensor Processing Unit 02/07/2024

#134: LoRA: Low-Rank Adaptation of Large Language Models 09/06/2024

Ver todos los episodios