Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Sign up for free
Menu
Search
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Pricing
Search
Sign in
Sign up for free
Introduction to GPU Programming in Python
Search
Sponsored
·
SiteGround - Reliable hosting with speed, security, and support you can count on.
→
Yuki Ishikawa
April 21, 2018
Technology
190
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
Introduction to GPU Programming in Python
PyData.Okinawa Meetup #34
https://pydataokinawa.connpass.com/event/82009/
Yuki Ishikawa
April 21, 2018
More Decks by Yuki Ishikawa
See All by Yuki Ishikawa
分割40%キーボードにスムーズに入門するには
hoto17296
1
320
FastAPI の並行処理モデルを完全に理解する
hoto17296
10
4.5k
o11y 何もわからない助けてくれ
hoto17296
0
130
Snowflake Openflow さわってみた
hoto17296
0
740
第3回 Snowflake 中部ユーザ会- dbt × Snowflake ハンズオン
hoto17296
4
1.5k
ORM と向き合う
hoto17296
15
12k
明日業務で役立たない Web 開発 TIPS
hoto17296
0
280
クソ bot 実装ライブコーディング
hoto17296
0
280
DeepGBM 論文の紹介
hoto17296
0
750
Other Decks in Technology
See All in Technology
ドメインエキスパートは いかにして AI を使って プロダクト開発をするか
tatsuyashiraishi
1
250
re:Inventで、人生は変わったのか? / growth-builders-hub-1-reinvent-2026
mhrtech
2
190
素人でもできた!AIを使った短編小説創作入門
delhi09
PRO
0
280
視野はAIに、視座は人に / ai-for-breadth-humans-for-perspective
nkzn
6
2.7k
自律的なチームを作るためにTechPMがやらないこと
ny7760
0
440
Systems Manager AgentがインストールされたPCを紛失した時の対策を考えてみた
amarelo_n24
1
110
GitHub、使う?使わない?
happysamurai294
0
140
なぜ東京にいる私が、新潟の技術コミュニティを運営するのか by 八雲慎之助
yakumo
0
210
これだけは抑えておきたい!後悔しない re:Invent の過ごし方 / AWS re:Invent 2026 prestudy
kinunori
2
640
Oracle Database Security 詳細解説
oracle4engineer
PRO
1
190
「作れる」と「リリースできる」の間にあったもの── PdMを外して見えた、PdMがやるべき仕事/Buildable ≠ Shippable: What Removing the PM Taught Me About the PM’s Job
yappli_developers
0
410
E2Eってつらくないですか?E2Eの管理コストを下げる手段とその実践
akaboshinit
6
2.9k
Featured
See All Featured
RailsConf & Balkan Ruby 2019: The Past, Present, and Future of Rails at GitHub
eileencodes
141
35k
Facilitating Awesome Meetings
lara
57
7.2k
A Guide to Academic Writing Using Generative AI - A Workshop
ks91
PRO
1
550
Keith and Marios Guide to Fast Websites
keithpitt
413
23k
How STYLIGHT went responsive
nonsquared
100
6.3k
Docker and Python
trallard
47
4.2k
The Spectacular Lies of Maps
axbom
PRO
1
1.1k
Leveraging Curiosity to Care for An Aging Population
cassininazir
1
550
Bioeconomy Workshop: Dr. Julius Ecuru, Opportunities for a Bioeconomy in West Africa
akademiya2063
PRO
1
440
Visual Storytelling: How to be a Superhuman Communicator
reverentgeek
2
730
Designing for Performance
lara
612
70k
Conquering PDFs: document understanding beyond plain text
inesmontani
PRO
4
3.3k
Transcript
Introduction to GPU Programming in Python 2018.04.21 PyData.Okinawa #34 @hoto17296
None
None
@hoto17296 • ͪΎΒσʔλגࣜձࣾ • σʔλੳϚϯ • JavaScript / Python /
AWS • IPv6 ͕Θ͔Βͳ͍ࠓ͜ͷ͝Ζ
Ͳͷ͝Ոఉʹ͋Δ GPU Ϛγϯ
͍͜ͳͯ͠·͔͢ʁʁʁ
ࣗͷ GPU ͷΠϝʔδ Λ͘ಈ͔ͤΔͭʂ
͍ͬͨͳ͍
GPU Λ͍ͨ͢Ίʹ CUDA Λ৮ͬͯΈΑ͏
GPU ͱ • Graphics Processing Unit • άϥϑΟοΫॲཧͷͨΊͷϓϩηοα • ୯७ͳॲཧΛฒྻԋࢉͰ͖Δ
• άϥϑΟοΫҎ֎ʹ׆༻͞ΕΔ (GPGPU) • σΟʔϓϥʔχϯάͱ͔
(NVIDIA) GPU ͷத ετϦʔϛϯά Ϛϧνϓϩηοα ଞʹϝϞϦͱ͔ Ωϟογϡͱ͔ ৭ʑ͋Δ͚Ͳলུ CUDA ίΞ
CUDA ͱ • Compute Unified Device Architecture • NVIDIA GPU
ΛͬͯฒྻܭࢉΛ͢ΔͨΊͷ ϓϩάϥϛϯάϞσϧ
CUDA ༻ޠ • ϗετͱσόΠε • CPU ଆΛϗετ, GPU ଆΛσόΠε ͱݺͿ
• Χʔωϧؔ • GPU ଆͰ࣮ߦ͢ΔॲཧΛهड़ͨؔ͠
CUDA ϓϩάϥϛϯάϞσϧ • ฒྻ͕େʹͳΔ • εϨου, ϒϩοΫ, άϦου ͱ͍͏ ·ͱ·ΓͰฒྻॲཧΛߦ͏
ग़యɿ http://www.nvidia.co.jp/object/cuda_education_jp_old.html
CUDA ϓϩάϥϛϯάϞσϧ • ฒྻ = εϨου x ϒϩοΫ x άϦου
• 1ϒϩοΫ͋ͨΓ࠷େ 512 εϨου • 1άϦου͋ͨΓ࠷େ 65536^2 ϒϩοΫ 1GPU ͋ͨΓ࠷େ 2 ஹ ฒྻʂʂʂ ✌('ω'✌ )ࡾ✌('ω')✌ࡾ( ✌’ω')✌
CUDA ϓϩάϥϛϯά Γͨ͘ͳ͖ͬͯ·ͨ͠Ͷ ʁʁʁ
CUDA ϓϩάϥϛϯάͷํ๏ • C Έ͍ͨͳݴޠͰΧʔωϧؔΛ࣮ͯ͠ nvcc ͱ͍͏ίϯύΠϥͰίϯύΠϧ͢Δ • μϧ͍ •
GPU Λར༻ͨ͠ฒྻॲཧΛॻ͍ͯΈ͍͕ͨ C ͕ॻ͖͍ͨΘ͚Ͱͳ͍ • Python Ͱॻ͔ͤͯ͘Ε
Numba • JIT ίϯύΠϧͯ͠ Python ΛߴԽͰ͖Δͭ • GPU ར༻Ͱ͖Δ (Numba
CUDA)
Χʔωϧؔͷ ఆٛ σίϨʔλΛࢦఆ͢Δ͜ͱͰ Χʔωϧؔͱͯ͠ఆٛ ͜ͷΧʔωϧ͕ؔ ฒྻ࣮ߦ͞ΕΔ ݱࡏͲͷҐஔ (ʁ) ͷεϨουͰ ࣮ߦ͍ͯ͠Δ͔औಘͰ͖Δ
εϨουͷҐஔใ͔Β ॲཧ͢Δରཁૉͷ࠲ඪΛܭࢉ͢Δ ߦྻͷରཁૉʹରͯ͠ॲཧΛߦ͏
Χʔωϧؔͷ࣮ߦ ฒྻ (griddim, blockdim) Λࢦఆ͔ͯ͠Β࣮ߦ͢Δ
͏গ͠ෳࡶͳྫɿ ΈࠐΈԋࢉ ग़యɿ http://tecmemo.wpblog.jp/category/machine-learning/deep-learning/page/2/
ϥϓϥγΞϯϑΟϧλ • ΈࠐΈԋࢉͰը૾ͷΤοδݕग़Λߦ͏ख๏ • ը૾ͷ৭ͷඍʹ૬͢Δ • ͜ͷߦྻΛϑΟϧλͱͯ͠ ΈࠐΈԋࢉΛߦ͏ 1 1
1 1 -8 1 1 1 1
ΈࠐΈԋࢉΛߦ͏ ΧʔωϧؔΛ ࣮
None
ೖྗը૾ ϑΟϧλ݁Ռ
·ͱΊ • Python Ͱ GPU ϓϩάϥϛϯάͰ͖Δ • GPU Ͱ༡Ϳͷͨͷ͍͠ ✌('ω'✌
)ࡾ✌('ω')✌ࡾ( ✌’ω')✌