23:05

Acacia Training | Introduction to Object Storage

09:38

Acacia Training | Comparing filesystems and Object Storage

14:32

Acacia Training | Introducing Acacia Object Storage

25:20

Acacia Training | Getting an access key from the Pawsey Portal

08:48

Acacia Training | Accessing Setonix via SSH

12:36

Acacia Training | Downloading course content onto scratch

33:13

Acacia Training | Setting up the Rclone client for use with Acacia

08:10

Acacia Training | Getting started with Rclone on Acacia

14:49

Acacia Training | Creating and manipulating buckets

14:51

Acacia Training | Working with files as objects

11:44

Acacia Training | Pseudofolders, copying and moving files

52:48

Acacia Training | Working with user defined metadata

23:33

Acacia Training | Constructing shareable URLs, mirroring files and parallel transfers

29:51

Acacia Training | Acacia in HPC workflows, using tar, archiving and compression

13:22

Acacia Training | Integrating object storage in Pawsey job submission scripts

15:59

Acacia Training | Q&A on using Acacia with the Pawsey Team

05:29

Advanced HIP Workshop | Porting CUDA programs to HIP | Porting CUDA to HIP Exercise

10:57

Advanced HIP Workshop | Porting CUDA programs to HIP | Learnings from the porting process

10:15

Advanced HIP Workshop | Porting CUDA programs to HIP | Case studies in porting codes

15:28

Advanced HIP Workshop | Porting CUDA programs to HIP | Porting techniques with hipify tools

08:19

Advanced HIP Workshop | Porting CUDA programs to HIP | General porting process

07:13

Advanced HIP Workshop | Porting CUDA programs to HIP | Introduction

07:48

Advanced HIP Workshop | Optimising compute with concurrent IO | HipMemcpy3D and asynchronous copies

15:22

Advanced HIP Workshop | Optimising compute with concurrent IO | Converting output to pinned memory

16:48

Advanced HIP Workshop | Optimising compute with concurrent IO | Sequential (synchronous) IO solution

11:59

Advanced HIP Workshop | Optimising compute with concurrent IO | Explore IO with the 2D wave equation

11:55

Advanced HIP Workshop | Memory Management in HIP | Introduction

19:38

Advanced HIP Workshop | Memory Management in HIP | Pitched Memory Allocations

08:16

Advanced HIP Workshop | Memory Management in HIP | Filling buffers with a known value

15:21

Advanced HIP Workshop | Memory Management in HIP | Zero Copy Allocation

15:53

Advanced HIP Workshop | Memory Management in HIP | Using pinned memory in a kernel

09:30

Advanced HIP Workshop | Memory Management in HIP | Managed Memory

26:54

Advanced HIP Workshop | Memory Management in HIP | Explicit memory transfers in HIP

14:36

Advanced HIP Workshop | Memory Management in HIP | Memory spaces visible to the kernel

27:12

Advanced HIP Workshop | Memory Management in HIP | Shared memory

08:32

Advanced HIP Workshop | Memory Management in HIP | Limits on the size of shared memory requests

07:39

Advanced HIP Workshop | Memory Management in HIP | Vectors in HIP

16:59

Advanced HIP Workshop | Memory Management in HIP | Example using vectors for matrix multiplication

10:55

Advanced HIP Workshop | Memory Management in HIP | Atomics in HIP

07:38

Advanced HIP Workshop | Memory Management in HIP | Memory management exercise

07:54

Advanced HIP Workshop | Optimising HIP kernels | Introduction

10:18

Advanced HIP Workshop | Optimising HIP kernels | Latency

11:48

Advanced HIP Workshop | Optimising HIP kernels | Fundamentals of CPU and GPU architectures

15:52

Advanced HIP Workshop | Optimising HIP kernels | Throughput

07:33

Advanced HIP Workshop | Optimising HIP kernels | CPU architecture specifics

14:54

Advanced HIP Workshop | Optimising HIP kernels | GPU architecture specifics

17:24

Advanced HIP Workshop | Optimising HIP kernels | Registers and occupancy

08:22

Advanced HIP Workshop | Optimising HIP kernels | Launch bounds as a compiler hint

09:29

Advanced HIP Workshop | Optimising HIP kernels | Instruction branching in GPU kernels

08:32

Advanced HIP Workshop | Optimising HIP kernels | Strategies to optimise compute device use

17:33

Advanced HIP Workshop | Optimising HIP kernels | Arithmetic intensity

11:27

Advanced HIP Workshop | Optimising HIP kernels | Testbench setup

13:43

Advanced HIP Workshop | Optimising HIP kernels | Block size optimisation and coalesced memory access

07:23

Advanced HIP Workshop | Optimising HIP kernels | Rearranging memory for better access

12:23

Advanced HIP Workshop | Optimising HIP kernels | Shared memory and bank conflicts

13:37

Advanced HIP Workshop | Optimising HIP kernels | Vectors

13:10

Advanced HIP Workshop | Optimising HIP kernels | Summary

09:45

Advanced HIP Workshop | Optimising compute with concurrent IO | Introduction

21:04

HIP Workshop | Measuring performance in HIP applications | Performance measurement with AMD tools

19:26

HIP Workshop | Measuring performance in HIP applications | Introduction