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
Yuki Ishikawa
April 21, 2018
Technology
180
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
32
Snowflake Openflow さわってみた
hoto17296
0
640
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
250
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
730
試行錯誤のための Docker 活用術
hoto17296
4
3.4k
Hive 集計テクニック
hoto17296
0
550
Other Decks in Technology
See All in Technology
コンテナ・K8s研修【MIXI 26新卒技術研修】#2
mixi_engineers
PRO
1
190
テックカンファレンス三大ステークホルダーの文化人類学 ─ 違いを認め合う関係性作り
bash0c7
2
710
エンタープライズデータへ安全につなぐ Production-ready なエージェント設計 ― AI × MCP リファレンスアーキテクチャ ― #AIDevDay
cdataj
1
110
reFACToring
moznion
0
590
PHPで作って学ぶリアルタイム音声対話AIとWebSocket入門 by ムナカタ
munakata
0
160
Oracle Base Database Service 技術詳細
oracle4engineer
PRO
15
110k
AI驚き屋発見器
yama3133
1
330
AIで楽になるはずが、なぜ疲れる?
kinopeee
0
100
kaonavi Tech Night#1
kaonavi
0
180
Claude Mythos、Fable...フロンティアAIの最新動向と企業のセキュリティ対策
flatt_security
0
150
GoでCコンパイラを作った話
repunit
0
160
AI研修(Day1)【MIXI 26新卒技術研修】
mixi_engineers
PRO
1
1.3k
Featured
See All Featured
The Director’s Chair: Orchestrating AI for Truly Effective Learning
tmiket
1
220
Game over? The fight for quality and originality in the time of robots
wayneb77
1
230
No one is an island. Learnings from fostering a developers community.
thoeni
21
3.8k
Helping Users Find Their Own Way: Creating Modern Search Experiences
danielanewman
31
3.3k
Creating an realtime collaboration tool: Agile Flush - .NET Oxford
marcduiker
35
2.5k
How to train your dragon (web standard)
notwaldorf
97
6.7k
Bioeconomy Workshop: Dr. Julius Ecuru, Opportunities for a Bioeconomy in West Africa
akademiya2063
PRO
1
180
Save Time (by Creating Custom Rails Generators)
garrettdimon
PRO
32
3.9k
Mozcon NYC 2025: Stop Losing SEO Traffic
samtorres
1
420
For a Future-Friendly Web
brad_frost
183
10k
The AI Search Optimization Roadmap by Aleyda Solis
aleyda
1
6k
The Power of CSS Pseudo Elements
geoffreycrofte
82
6.5k
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')✌