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
2
750
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
Go言語での実装を通して学ぶLLMファインチューニングの仕組み / fukuokago22-llm-peft
monochromegane
0
170
不確実性下における目的と手段の統合的探索に向けた連続腕バンディットの応用 / iot70_gp_rff_mab
monochromegane
2
270
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
6.7k
ベクトル検索システムの気持ち
monochromegane
38
12k
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
260
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
320
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
1.1k
Online Nonstationary and Nonlinear Bandits with Recursive Weighted Gaussian Process
monochromegane
0
780
AIを前提とした体験の実現に向けて/toward_ai_based_experiences
monochromegane
2
1.1k
Other Decks in Programming
See All in Programming
Combinatorial Interview Problems with Backtracking Solutions - From Imperative Procedural Programming to Declarative Functional Programming - Part 2
philipschwarz
PRO
0
140
ゆくKotlin くるRust
exoego
1
200
The Art of Re-Architecture - Droidcon India 2025
siddroid
0
160
例外処理とどう使い分ける?Result型を使ったエラー設計 #burikaigi
kajitack
16
5.5k
今こそ知るべき耐量子計算機暗号(PQC)入門 / PQC: What You Need to Know Now
mackey0225
3
320
Denoのセキュリティに関する仕組みの紹介 (toranoana.deno #23)
uki00a
0
230
なぜSQLはAIぽく見えるのか/why does SQL look AI like
florets1
0
270
Grafana:建立系統全知視角的捷徑
blueswen
0
290
2年のAppleウォレットパス開発の振り返り
muno92
PRO
0
180
JETLS.jl ─ A New Language Server for Julia
abap34
2
480
GISエンジニアから見たLINKSデータ
nokonoko1203
0
190
Unicodeどうしてる? PHPから見たUnicode対応と他言語での対応についてのお伺い
youkidearitai
PRO
0
580
Featured
See All Featured
Visualization
eitanlees
150
16k
Amusing Abliteration
ianozsvald
0
87
The untapped power of vector embeddings
frankvandijk
1
1.5k
The Psychology of Web Performance [Beyond Tellerrand 2023]
tammyeverts
49
3.3k
Jamie Indigo - Trashchat’s Guide to Black Boxes: Technical SEO Tactics for LLMs
techseoconnect
PRO
0
42
Building Better People: How to give real-time feedback that sticks.
wjessup
370
20k
What Being in a Rock Band Can Teach Us About Real World SEO
427marketing
0
160
Save Time (by Creating Custom Rails Generators)
garrettdimon
PRO
32
1.9k
Large-scale JavaScript Application Architecture
addyosmani
515
110k
Mind Mapping
helmedeiros
PRO
0
49
Fashionably flexible responsive web design (full day workshop)
malarkey
408
66k
Ruling the World: When Life Gets Gamed
codingconduct
0
130
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