Posts by Tags

CPU-FPGA

[2021-01-26] GraphACT: Accelerating GCN Training on CPU-FPGA Heterogeneous Platforms

1 minute read

Published:

This paper is a CPU-FPGA heterogenrous platform for GCN training. CPU will do the communication intensive operations, and leave the computation intensive parts to CPU.

Background and Motivation

It is challenging to accelerate Graph Convolutional Networks because: (1) substantial and irregular data communication to propagate information within the graph (2) intensive computation to propagate information along the neural network layers (3) Degree-imbalance ofgraph nodes can significantly degrade the performance of feature propagation.

DL coprocessor

DNN training

GNN

[2021-01-26] GraphACT: Accelerating GCN Training on CPU-FPGA Heterogeneous Platforms

1 minute read

Published:

This paper is a CPU-FPGA heterogenrous platform for GCN training. CPU will do the communication intensive operations, and leave the computation intensive parts to CPU.

Background and Motivation

It is challenging to accelerate Graph Convolutional Networks because: (1) substantial and irregular data communication to propagate information within the graph (2) intensive computation to propagate information along the neural network layers (3) Degree-imbalance ofgraph nodes can significantly degrade the performance of feature propagation.

GPU

LSTM

LUT

ML accelerator

[2021-10-12] ISCA 2021 Section 3A: Machine Learning 1

1 minute read

Published:

This reading blog is about three papers in Section 3A: Machine Learning 1 of ISCA 2021.

RaPiD: AI Accelerator for Ultra-Low Precision Training and Inference

This accelerator supports mixed precisions for both training and inference: 16 and 8-bit floating-point and 4 and 2-bit fixed point. It imporves both performance(TOPS) and energy efficiency(TOPS/W) at ultra-low preceision. In my opinion, this work contributes more on the engineering part (architecture).

NN acceleration

PIM

TPU

[2021-10-12] ISCA 2021 Section 3A: Machine Learning 1

1 minute read

Published:

This reading blog is about three papers in Section 3A: Machine Learning 1 of ISCA 2021.

RaPiD: AI Accelerator for Ultra-Low Precision Training and Inference

This accelerator supports mixed precisions for both training and inference: 16 and 8-bit floating-point and 4 and 2-bit fixed point. It imporves both performance(TOPS) and energy efficiency(TOPS/W) at ultra-low preceision. In my opinion, this work contributes more on the engineering part (architecture).

VR

accelerator

[2021-01-26] GraphACT: Accelerating GCN Training on CPU-FPGA Heterogeneous Platforms

1 minute read

Published:

This paper is a CPU-FPGA heterogenrous platform for GCN training. CPU will do the communication intensive operations, and leave the computation intensive parts to CPU.

Background and Motivation

It is challenging to accelerate Graph Convolutional Networks because: (1) substantial and irregular data communication to propagate information within the graph (2) intensive computation to propagate information along the neural network layers (3) Degree-imbalance ofgraph nodes can significantly degrade the performance of feature propagation.

compiler

computer architecture

[2020-07-16]Wild and Crazy Ideas (ASPLOS 2020)

1 minute read

Published:

Today I am not going to read a specific paper. Rather, I watch a talk about some innovative ideas and oppotunities for computer architecture. The vedio of the talk can be found here

data transformation

dataflow architecture

edge computing

general-purpose

graph

[2021-01-17] [CS224W] Graph Repesentation Learning

2 minute read

Published:

Network embedding

Task: We map each node in a network into a low-dimensional space Goal: encode nodes so that similarity in the embedding space (e.g., dot product) approximates similarity in the original network.

[2021-01-12] [CS224W] Motifs and Structural Roles in Networks

1 minute read

Published:

Subgraphs, Motifs

Network motifs: recurring, significant patterns of interconnections

  • induced subgraphs - consider all edges connecting pairs of vertices in subset
  • recurrence - allow overlapping of motifs
  • signficance of a motif: Motifs are overrepresented in a network when compared to randomized networks

[2021-01-11] [CS224W] Properties of Networks and Random Graph Models

2 minute read

Published:

I would like to learn GNN to see if there is any opportunity to optimize/accelerate it. But the surveying paper for GNN has too many expressions, notations which are hard to understand. So I will watch the CS224W Machine Learning with Graphs lecture to learn it in a smooth way. I will write down some key points I learned.

idea

[2020-07-16]Wild and Crazy Ideas (ASPLOS 2020)

1 minute read

Published:

Today I am not going to read a specific paper. Rather, I watch a talk about some innovative ideas and oppotunities for computer architecture. The vedio of the talk can be found here

machine learning

[2021-01-17] [CS224W] Graph Repesentation Learning

2 minute read

Published:

Network embedding

Task: We map each node in a network into a low-dimensional space Goal: encode nodes so that similarity in the embedding space (e.g., dot product) approximates similarity in the original network.

[2021-01-12] [CS224W] Motifs and Structural Roles in Networks

1 minute read

Published:

Subgraphs, Motifs

Network motifs: recurring, significant patterns of interconnections

  • induced subgraphs - consider all edges connecting pairs of vertices in subset
  • recurrence - allow overlapping of motifs
  • signficance of a motif: Motifs are overrepresented in a network when compared to randomized networks

[2021-01-11] [CS224W] Properties of Networks and Random Graph Models

2 minute read

Published:

I would like to learn GNN to see if there is any opportunity to optimize/accelerate it. But the surveying paper for GNN has too many expressions, notations which are hard to understand. So I will watch the CS224W Machine Learning with Graphs lecture to learn it in a smooth way. I will write down some key points I learned.

memory footprint

reading paper

[2021-10-12] ISCA 2021 Section 3A: Machine Learning 1

1 minute read

Published:

This reading blog is about three papers in Section 3A: Machine Learning 1 of ISCA 2021.

RaPiD: AI Accelerator for Ultra-Low Precision Training and Inference

This accelerator supports mixed precisions for both training and inference: 16 and 8-bit floating-point and 4 and 2-bit fixed point. It imporves both performance(TOPS) and energy efficiency(TOPS/W) at ultra-low preceision. In my opinion, this work contributes more on the engineering part (architecture).

[2021-01-26] GraphACT: Accelerating GCN Training on CPU-FPGA Heterogeneous Platforms

1 minute read

Published:

This paper is a CPU-FPGA heterogenrous platform for GCN training. CPU will do the communication intensive operations, and leave the computation intensive parts to CPU.

Background and Motivation

It is challenging to accelerate Graph Convolutional Networks because: (1) substantial and irregular data communication to propagate information within the graph (2) intensive computation to propagate information along the neural network layers (3) Degree-imbalance ofgraph nodes can significantly degrade the performance of feature propagation.

server

studying

[2021-01-17] [CS224W] Graph Repesentation Learning

2 minute read

Published:

Network embedding

Task: We map each node in a network into a low-dimensional space Goal: encode nodes so that similarity in the embedding space (e.g., dot product) approximates similarity in the original network.

[2021-01-12] [CS224W] Motifs and Structural Roles in Networks

1 minute read

Published:

Subgraphs, Motifs

Network motifs: recurring, significant patterns of interconnections

  • induced subgraphs - consider all edges connecting pairs of vertices in subset
  • recurrence - allow overlapping of motifs
  • signficance of a motif: Motifs are overrepresented in a network when compared to randomized networks

[2021-01-11] [CS224W] Properties of Networks and Random Graph Models

2 minute read

Published:

I would like to learn GNN to see if there is any opportunity to optimize/accelerate it. But the surveying paper for GNN has too many expressions, notations which are hard to understand. So I will watch the CS224W Machine Learning with Graphs lecture to learn it in a smooth way. I will write down some key points I learned.