大模型深度定制以及在芯片设计应用中的探索（英文版）.docx

ChipNeMo-DomainAdapted

LLMsforChipDesign

刘鸣杰MingjieLiu

SlidescontentsfromHaoxingRenandMiguelMartinez

Outline

LLMIntroduction

HowcanLLMhelpchipdesignprocess

Domain-adaptionLLMtechniquesforchipdesign

LLMApplicationsToday

NaturalLanguageTasks

Generation:writeemails

Open/ClosedQA:answerquestionswith/withoutcontext

Brainstorming:generateideasChat

Rewrite:languagetranslationSummarization

Classification:sentimentanalysisReasoning:math/logic

Applications

ChatBot,APIs

CodingTasks

Understand/explaincode,errormessagesDocument,commentcode

Generatecodesnippetsfromspecs

TranslatecodetoadifferentlanguageEdit,debugcode

ToolUse/Agents

Applications

CoPilot

PromptEngineering

Zeroshot

Prompt:

Classifythetextintoneutral,negativeorpositive.

Text:Ithinkthevacationisokay.

Sentiment:

Response:

Neutral

Fewshot

Prompt:

Thisisawesome!//NegativeThisisbad!//Positive

Wowthatmoviewasrad!//PositiveWhatahorribleshow!//

Response:

Negative

mptingguide.ai/

ChainofThoughts(CoT)

Prompt:

Iwenttothemarketandbought10apples.Igave2applestotheneighborand2applestotherepairman.Ithenwentandbought5

moreapplesandate1.HowmanyapplesdidIremainwith?

Letsthinkstepbystepandcalculateeachstep.

Response:

Youhave10apples.

Yougive2applestotheneighborand2to

therepairman.

Youhave6applesremaining.Youbuy5moreapples.

Youhave11apples.Youeat1apple.

Youhave10applesremaining.

RetrievalAugmentedGeneration

AddContexttoGroundLLMonUnseenFacts

54

5

LLMResponse“TellmeaboutSM”

LLM

Response

1

1

4

4

VectorDBsupporting

VectorDBsupportingsimilaritysearch

RetrievalModel

EmbeddingChunk

Embedding

Chunk

xxxx

AGPUcontainstwoormore

StreamingMultiprocessors(SM)dependingupon…

2

EmbeddingVector

3

HowcanLLMHelpChipDesignProcess?

Know-howAssistance+CodingAssistance

Know-howAssistanceGeneratinginsights,knowledge,ideas

Desi