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
Go言語でMac GPUプログラミング
Search
monochromegane
December 18, 2023
Programming
1
630
Go言語でMac GPUプログラミング
2023.12.18 Fukuoka.go#19 Reboot
https://fukuokago.connpass.com/event/302717/
monochromegane
December 18, 2023
Tweet
Share
More Decks by monochromegane
See All by monochromegane
なめらかなシステムと運用維持の終わらぬ未来 / dicomo2025_coherently_fittable_system
monochromegane
0
890
ベクトル検索システムの気持ち
monochromegane
34
11k
Go言語での実装を通して学ぶ、高速なベクトル検索を支えるクラスタリング技術/fukuokago-kmeans
monochromegane
1
190
Go言語でターミナルフレンドリーなAIコマンド、afaを作った/fukuokago20_afa
monochromegane
2
260
多様かつ継続的に変化する環境に適応する情報システム/thesis-defense-presentation
monochromegane
1
930
Online Nonstationary and Nonlinear Bandits with Recursive Weighted Gaussian Process
monochromegane
0
570
AIを前提とした体験の実現に向けて/toward_ai_based_experiences
monochromegane
2
970
Contextual and Nonstationary Multi-armed Bandits Using the Linear Gaussian State Space Model for the Meta-Recommender System
monochromegane
1
1.1k
迅速な学習機構を用いて逐次適応性を損なうことなく非線形性を扱う文脈付き多腕バンディット手法/extreme_neural_linear_bandits
monochromegane
0
2.3k
Other Decks in Programming
See All in Programming
LT 2025-06-30: プロダクトエンジニアの役割
yamamotok
0
870
レトロゲームから学ぶ通信技術の歴史
kimkim0106
0
110
ソフトウェア品質を数字で捉える技術。事業成長を支えるシステム品質の マネジメント
takuya542
2
15k
状態遷移図を書こう / Sequence Chart vs State Diagram
orgachem
PRO
2
210
Android 16KBページサイズ対応をはじめからていねいに
mine2424
0
440
Hack Claude Code with Claude Code
choplin
7
2.6k
なぜ「共通化」を考え、失敗を繰り返すのか
rinchoku
1
680
リバースエンジニアリング新時代へ! GhidraとClaude DesktopをMCPで繋ぐ/findy202507
tkmru
3
970
The Niche of CDK Grant オブジェクトって何者?/the-niche-of-cdk-what-isgrant-object
hassaku63
1
620
NEWT Backend Evolution
xpromx
1
140
Claude Code派?Gemini CLI派? みんなで比較LT会!_20250716
junholee
1
530
AI コーディングエージェントの時代へ:JetBrains が描く開発の未来
masaruhr
1
200
Featured
See All Featured
How to Think Like a Performance Engineer
csswizardry
25
1.7k
Designing Experiences People Love
moore
142
24k
JavaScript: Past, Present, and Future - NDC Porto 2020
reverentgeek
50
5.5k
Code Review Best Practice
trishagee
69
19k
実際に使うSQLの書き方 徹底解説 / pgcon21j-tutorial
soudai
PRO
181
54k
Fashionably flexible responsive web design (full day workshop)
malarkey
407
66k
Fireside Chat
paigeccino
37
3.5k
"I'm Feeling Lucky" - Building Great Search Experiences for Today's Users (#IAC19)
danielanewman
229
22k
[RailsConf 2023] Rails as a piece of cake
palkan
55
5.7k
[RailsConf 2023 Opening Keynote] The Magic of Rails
eileencodes
29
9.6k
The Web Performance Landscape in 2024 [PerfNow 2024]
tammyeverts
8
700
A designer walks into a library…
pauljervisheath
207
24k
Transcript
Lightning Talks ࡾ༔հ / Pepabo R&D Institute, GMO Pepabo, Inc.
2023.12.18 Fukuoka.go#19 Reboot GoݴޠͰMac GPUϓϩάϥϛϯά
ϓϦϯγύϧΤϯδχΞ ࡾ ༔հ / @monochromegane 2 https://blog.monochromegane.com Yusuke Miyake ϖύϘݚڀॴ
ݚڀһ
• ଟมྔਖ਼ن ʹै͏ཚੜʹ͕͔͔࣌ؒΔ • ͜ͷཚੜͷखॱʢͷҰͭʣҎԼͷ௨Γ 1. ֤ཁૉ͕ඪ४ਖ਼نʹै͏ཚ ΛಘΔ 2. ڞࢄߦྻ
ΛίϨεΩʔղʢ ʣͯ͠ࡾ֯ߦྻ ΛಘΔ 3. ΛٻΊΔ • ಛʹɺ֬ͷύϥϝʔλʢ ͱ ʣ͕ҟͳͬͨΓɺ࣍ݩ ͕େ͖͍ ߹ʹɺཚੜʹ͕͔͔࣌ؒͬͯ͠·͏ y ∼ 𝒩 (μ, Σ), μ ∈ ℝD, Σ ∈ ℝD×D z = {zi }1≤i≤D , zi ∼ 𝒩 (0,1) Σ Σ = LL⊤ L y = μ + Lz μ Σ D 3 ͡Ίʹ
• ߦྻܭࢉಠཱ͔ͭฒߦͨ͠λεΫΛଟؚ͘ΉͨΊɺߴԽʹฒྻԽ͕༗ޮ • ͢ͳΘͪɺSIMDɺCPUͷϚϧνίΞɺGPUͳͲʹΑΔฒྻԽ • CPUόϯυͰλεΫཻখ͍͞ͷͰgoroutine͔ͳ͍ʢͱࢥ͏ʣ • GoݴޠͰͷߦྻܭࢉϥΠϒϥϦGonumCPUͷϚϧνίΞΛαϙʔτ͢Δ BLASͷόΠϯσΟϯάΛఏڙ͍ͯ͠Δ •
Apple silicon (M1) ʹGPU͕ࡌ͞Ε͍ͯΔͷͰɺͦͪΒ׆༻͍ͨ͠ 4 ͡Ίʹ
• GPUͷΞΫηεΛఏڙ͢ΔOSඪ४ࡌͷϑϨʔϜϫʔΫ • άϥϑΟοΫεॲཧҎ֎ʹɺGPU্Ͱͷฒྻܭࢉॲཧѻ͑Δ • Objective-C·ͨSwift͔ΒɺGPU্ͷॲཧΛهड़ͨ͠γΣʔμʔؔΛݺͿ • γΣʔμʔؔC++ϕʔεͷMetal Shader Language
(MSL) Ͱهड़ • Metal Performance Shaders (MPS) ͱ͍͏γΣʔμʔؔ܈ఏڙ͞ΕΔ 5 Metal: MacͰGPUϓϩάϥϛϯά
6 Metal: MacͰGPUϓϩάϥϛϯά • جຊతͳྲྀΕɺσόΠεʢGPUʣͷίϚϯυΩϡʔʹର͠ɺίϚϯυόο ϑΝͱ͍͏୯ҐͰγΣʔμʔؔΛొ͠ɺ݁ՌΛड͚औΔͱ͍͏ͷ • ͳ͓ɺCPUͱGPUͷͷΓऔΓʹઐ༻ͷόοϑΝ͕༻ҙ͞Ε͍ͯΔ ίϚϯυΩϡʔ ͷ४උ
ΓऔΓ༻ͷ όοϑΝͷ४උ όοϑΝͷσʔλ͔Β ߦྻΠϯελϯεੜ .14ͷγΣʔμʔؔ ΛॳظԽɺίϚϯυ όοϑΝͱͯ͠Τϯ ίʔυɺΩϡʔʹొ όοϑΝ͔Β݁Ռͷड ͚औΓ 0CKFDUJW$Ͱͷ ࣮ྫ
• Goݴޠ͔ΒcgoΛ͑͜ΕΒͷObjective-CͷίʔυΛݺΔ༷ࢠ • https://github.com/a-h/gpu ϥΠϒϥϦͱͯ͠ར༻Ͱ͖Δ͕MPSʹରԠ͍ͯ͠ͳ͍ • https://github.com/mikecvet/go-mm MPSͷݺͼग़͠Λ࣮͍ͯ͠Δ͕ϕϯνϚʔΫͷίʔυͷΈ • ্هΛࢀߟʹͭͭ͠ɺGoݴޠ্ͰͷGPUΛ༻͍ͨଟมྔਖ਼نʹै͏ཚ
ੜ͕Ͱ͖ͦ͏ 7 Cgo: GoݴޠͰMac GPUϓϩάϥϛϯά
1. Objective-CͷϔομϑΝΠϧΛinclude͠ɺLDFLAGSʹMetalϑϨʔϜϫʔΫΛࢦఆ͢Δ 2. ʢඞཁʹԠͯ͡ʣࣗલͷγΣʔμʔؔΛgo:embedͰΈࠐΜͰ͓͘ 3. C.xxͱͯ͠Objective-CͰهड़ͨ͠ॳظԽγΣʔμʔؔΛ࣮ߦ͢ΔؔΛݺͿɻ࣮ߦ࣌ ͷύϥϝʔλ݁ՌunsafeύοέʔδΛͬͯΞΫηεɻ 8 Cgo: GoݴޠͰMac
GPUϓϩάϥϛϯά (PͰͷ࣮ྫ
• Goݴޠ্ͰͷGPUΛ༻͍ͨଟมྔਖ਼نʹै͏ཚੜ • Goͷίʔυ͔Β ΛcgoΛܦ༝ͯ͠Objective-Cͷؔʹ͢ • MPSͷMPSMatrixDecompositionCholeskyΛ༻͍ͯίϨεΩʔղ • ࣗલγΣʔμʔؔΛ༻͍ͯԼࡾ֯ߦྻҎ֎Λ0ʹຒΊΔ •
MPSͷMPSMatrixVectorMultiplicationΛ༻͍ͯ Λܭࢉ • MPSͷMPSMatrixSumΛ༻͍ͯ Λܭࢉ • GoͷίʔυͰ݁ՌΛड͚औΔ z, μ, Σ Lz μ + Lz 9 Cgo: GoݴޠͰMac GPUϓϩάϥϛϯά
• GonumͱMetal࣮ͷ࣮ߦΛൺֱʢ1000࣍ݩʣ 10 ඪ४ਖ਼نཚͷมͷൺֱ BenchmarkTransformNormMetal-8 9 117668310 ns/op BenchmarkTransformNormGonumBLAS-8 55
21494668 ns/op BenchmarkTransformNormGonum-8 21 54288034 ns/op BenchmarkTransformNormCholMetal-8 1140 1070094 ns/op BenchmarkTransformNormCholGonumBLAS-8 15124 78960 ns/op BenchmarkTransformNormCholGonum-8 6712 177368 ns/op • ίϨεΩʔղͷ݁ՌΛผ్͢Α͏ʹͨ͠߹ͷൺֱ • MPSͷίϨεΩʔղগ͍͔͠͠Εͳ͍͕ɺͦͷଞͷࠩԿ͔
• ߦྻʢ1000x1000ʣͱߦྻʢ1000x1000ʣͷࢉΛൺֱ 11 ߦྻࢉͷൺֱ BenchmarkMatrixMultipicationMetal-8 494 2222134 ns/op BenchmarkMatrixMultipicationGonumBLAS-8 60
22063894 ns/op BenchmarkMatrixMultipicationGonum-8 19 59507228 ns/op BenchmarkMatrixVectorMultipicationMetal-8 1497 792244 ns/op BenchmarkMatrixVectorMultipicationGonumBLAS-8 10000 114843 ns/op BenchmarkMatrixVectorMultipicationGonum-8 972 1239177 ns/op • ߦྻʢ1000x1000ʣͱϕΫτϧʢ1000x1ʣͷࢉΛൺֱ • ߦྻಉ࢜ͷΑ͏ͳܭࢉྔͰGPUͷํ͕ߴɻ ͷΑ͏ͳߦྻͱϕΫτϧͷࢉͰ͜ ͷ࣍ݩʹ͓͍ͯGPUҠৡͷΦʔόʔϔουͷํ͕େ͖͔ͬͨͱߟ͑ΒΕΔ Lz
• GoݴޠͰMac GPUϓϩάϥϛϯά͢Δํ๏Λհͨ͠ • ؆қతͳͷൺֱධՁΛ௨ͯ͠ɺ͍ॴͷഽײΛಘΔ͜ͱ͕Ͱ͖ͨ • MPSͷϚχϡΞϧΛಡΉͱχϡʔϥϧωοτϫʔΫͷαϙʔτ͋ΓɺΞΠ σΟΞ࣍ୈͰ໘ന͍͜ͱ͕Ͱ͖ͦ͏ • MPSͷݺͼग़͠ՄೳͳϥΠϒϥϦΛ࡞ͬͯΈ͍ͨ
• Ͳ͏ϝϞϦϦʔΫͯͦ͠͏ͳͷͰͦͷลΓվળ͍ͨ͠ • ࡾGo 12 ·ͱΊ
None