Daisuke Miyamoto DaisukeMiyamoto

GPU インスタンス

Workshop Studio で起動している既存の Amazon Braket (Amazon SageMaker AI) Notebook ml.t3.2xlarge を停止 (Stop) する。
Amazon SageMaker AI サービスの画面で、インスタンスタイプを ml.p3.2xlarge に変更する。https://us-east-1.console.aws.amazon.com/sagemaker/home?region=us-east-1#/notebook-instances
その Notebook インスタンスを起動 (Start) する。
Jupyter の kernel config vi ~/.local/share/jupyter/kernels/docker_cudaq/kernel.json に3行追記。 https://gist.github.com/hariby/47c2a32755969f4fb3c6235d718390a7#file-kernel-json-L8-L10

Notebook

cudaq_target.ipynb
- n = 26 まで for n in range(10, 27):

👾 Slurm CUDA MPS Prolog

The following Slurm Prolog starts the CUDA MPS server on each compute node before the job is started.

cat << EOF > /opt/slurm/etc/prolog.sh
#!/bin/sh

# start mps
nvidia-cuda-mps-control -d

RELION interoperabiity with Warp and M

This document examines how to use RELION 4.0 (beta2 as of writing) with Warp 1.09 and M 1.09 for single particle analysis.

Special thanks to Alister Burt, Pranav Shah and Dimitry Tegunov for discussion on this Twitter thread.

Download the movies

We use the RELION tutorial dataset (beta-galactosidase collected on JEOL CRYO ARM 200, a subset of EMPIAR-10204).

AWS ParallelCluster + AWS Batch

Today I'm going to demonstrate running High Performance Conjucate Grandients (HPCG) in a containerized workload. This takes advantage of AWS ParallelCluster, AWS Batch, and OpenMPI.

First install aws-parallelcluster:

$ pip install aws-parallelcluster

	---
	AWSTemplateFormatVersion: '2010-09-09'

	Description: Mobile App CICD Demo

	Parameters:

	DeviceFarmProjectName:
	Type: String
	Default: demo-app-devicefarm

	Latency Comparison Numbers
	--------------------------
	L1 cache reference/hit 1.5 ns 4 cycles
	Floating-point add/mult/FMA operation 1.5 ns 4 cycles
	L2 cache reference/hit 5 ns 12 ~ 17 cycles
	Branch mispredict 6 ns 15 ~ 20 cycles
	L3 cache hit (unshared cache line) 16 ns 42 cycles
	L3 cache hit (shared line in another core) 25 ns 65 cycles
	Mutex lock/unlock 25 ns
	L3 cache hit (modified in another core) 29 ns 75 cycles

	source :gemcutter
	gem 'pit'
	gem 'sauberia-aws-s3'