Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
Introduction to GPU Programming in Python
Search
Sponsored
·
Ship Features Fearlessly
Turn features on and off without deploys. Used by thousands of Ruby developers.
→
Yuki Ishikawa
April 21, 2018
Technology
170
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
o11y 何もわからない助けてくれ
hoto17296
0
30
Snowflake Openflow さわってみた
hoto17296
0
600
第3回 Snowflake 中部ユーザ会- dbt × Snowflake ハンズオン
hoto17296
4
1.4k
ORM と向き合う
hoto17296
14
12k
明日業務で役立たない Web 開発 TIPS
hoto17296
0
240
クソ bot 実装ライブコーディング
hoto17296
0
260
DeepGBM 論文の紹介
hoto17296
0
720
試行錯誤のための Docker 活用術
hoto17296
4
3.3k
Hive 集計テクニック
hoto17296
0
550
Other Decks in Technology
See All in Technology
Oracle AI Database@Azure:サービス概要のご紹介
oracle4engineer
PRO
6
2k
NAB Show 2026 動画技術関連レポート / NAB Show 2026 Report
cyberagentdevelopers
PRO
0
190
AIの性能が向上しても未解決な組織の重大問題は何か?/An Unsolved Organizational Problem in the Age of AI
moriyuya
4
660
「エンジニア進化論」2028年の開発完全自動化、エンジニアはどう進化するか
cyberagentdevelopers
PRO
6
5k
RAG を使わないという選択肢
tatsutaka
1
220
Claude Code の Sandbox 機能を Anthropic Sandbox Runtime(srt) で試そう!/lets-play-anthropic-sandbox-runtime
tomoki10
1
570
フロンティアAIのゲート化と地政学リスク
nagatsu
0
130
Snowflakeと仲良くなる第一歩
coco_se
4
460
SONiC Scale-Up Working Group から探る Scale-UpやUltraEthernet機能の実装方法
ebiken
PRO
2
290
SONiCのLinuxベースを活かしたZabbix監視
sonic
0
140
20260619 私の日常業務での生成 AI 活用
masaruogura
1
200
AmazonRoute 53ではじめてのドメイン取得!HTTPS化までの道のりを整理してみた
usanchuu
3
140
Featured
See All Featured
The Art of Programming - Codeland 2020
erikaheidi
57
14k
"I'm Feeling Lucky" - Building Great Search Experiences for Today's Users (#IAC19)
danielanewman
230
23k
Agile that works and the tools we love
rasmusluckow
331
21k
Agile Leadership in an Agile Organization
kimpetersen
PRO
0
160
My Coaching Mixtape
mlcsv
0
150
Money Talks: Using Revenue to Get Sh*t Done
nikkihalliwell
0
250
Amusing Abliteration
ianozsvald
1
200
Technical Leadership for Architectural Decision Making
baasie
3
410
Design and Strategy: How to Deal with People Who Don’t "Get" Design
morganepeng
133
19k
Docker and Python
trallard
47
3.9k
30 Presentation Tips
portentint
PRO
1
320
ラッコキーワード サービス紹介資料
rakko
1
3.6M
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')✌