Chin up

Skip to content

Main Navigation主页笔记最近更新

切换主题

Sidebar Navigation

Cuda-Challenges

day-1-Introduction-to-GPU-Computing-&-CUDA

day-10-Shared-Memory-Fundamentals

day-100-Capstone-Project-#5

day-101-GPU-Accelerated-ML-Frameworks-(Intro)

day-102-CUDA-+-Other-Parallel-Frameworks

day-103-Tuning-GPU-Accelerated-ML-Ops

day-104-Multi-GPU-Scaling-in-ML

day-105-HPC-Memory-Throughput-&-Computation

day-106-HPC-Precision-&-Mixed-Precision

day-107-Advanced-Debugging-Tools-(cuda-memcheck,-etc.)

day-109-Large-Scale-Code,-Maintainability

day-11-Thread-Synchronization-(__syncthreads())

day-110-HPC-Tools-&-Libraries-(MAGMA,-etc.)

day-111-Testing-&-Validation-Strategies

day-112-Progress-Checkpoint

day-113-Revisiting-Key-Optimizations

day-114-GPU-Scheduling-&-CUcontext-Exploration

day-115-Final-Performance-Tweaks-&-Fine-Tuning

day-116-Memory-Hierarchy-Mastery

day-117-Detailed-Profiling-Recap

day-118-Review-of-Common-Pitfalls

day-119-Prep-for-Final-Capstone

day-12-Bank-Conflicts-in-Shared-Memory

day-120-Capstone-Project-#6

day-13-Basic-Atomic-Operations

day-14-Progress-Checkpoint

day-15-Advanced-Atomic-Operations

day-16-Kernel-Configuration-Tuning

day-17-Host-Device-Synchronization-Patterns

day-18-Error-Handling-&-cudaGetErrorString()

day-19-Unified-Memory-(UM)-Intro

day-2-Setting-Up-the-Development-Environment

day-20-Capstone-Project-#1

day-21-Streams-&-Concurrency-(Basics)

day-22-Events-&-Timing

day-23-Asynchronous-Memory-Copy

day-24-Pinned-(Page-Locked)-Memory

day-25-Double-Buffering-Technique

day-26-Constant-Memory

day-27-Texture-&-Surface-Memory-(Intro)

day-28-Progress-Checkpoint

day-29-Texture-Memory-(Practical)

day-3-GPU-vs.-CPU-Architecture-Foundations

day-30-Surface-Memory

day-31-Unified-Memory-Deep-Dive

day-32-Stream-Sync-&-Dependencies

day-33-Intro-to-CUDA-Graphs

day-35-Occupancy-&-Launch-Config-Tuning

day-36-Profiling-&-Bottleneck-Analysis

day-37-Intro-to-Warp-Level-Primitives

day-38-Warp-Divergence

day-39-Dynamic-Parallelism

day-4-Thread-Hierarchy-Grids-&-Blocks

day-40-Capstone-Project-#2

day-41-Advanced-Streams-&-Multi-Stream-Concurrency

day-42-Progress-Checkpoint

day-43-Efficient-Data-Transfers-&-Zero-Copy

day-44-Advanced-Warp-Intrinsics-(Scan,-etc.)

day-45-Cooperative-Groups-(Intro)

day-46-Peer-to-Peer-Communication-(Multi-GPU)

day-47-Intermediate-Debugging-&-Profiling-Tools

day-48-Memory-Footprint-Optimization

day-49-Thrust-for-High-Level-Operations

day-5-Thread-Hierarchy-Warps-(Intro)

day-50-Intro-to-cuBLAS

day-51-Intro-to-cuFFT

day-52-Code-Optimization-(Part-1)

day-53-Code-Optimization-(Part-2)

day-54-Nsight-Compute-Kernel-Analysis

day-55-Intro-to-Device-Libraries-(cuRAND,-etc.)

day-56-Progress-Checkpoint

day-57-Robust-Error-Handling-&-Debugging

day-58-Handling-Large-Data-Sets

day-59-MPS-(Multi-Process-Service)

day-6-Basic-Kernel-Launch-&-Execution

day-60-Capstone-Project-#3

day-61-GPU-Accelerated-Sorting

day-62-Stream-Compaction-&-Parallel-Patterns

day-63-Concurrency-Patterns-(Producer-Consumer)

day-64-Pinned-+-Unified-Memory-Hybrid

day-65-Collaborative-Grouping-Techniques

day-66-Peer-to-Peer-(P2P)-&-Multi-GPU-Scaling

day-67-GPU-Accelerated-Graph-Analytics-(Intro)

day-68-Memory-Pool-&-Custom-Allocators

day-69-Occupancy-Based-Tuning-for-Large-Problems

day-7-Memory-Model-(Global-Memory-Basics)

day-70-Progress-Checkpoint

day-71-Advanced-Streams-&-Overlapping

day-72-CUDA-Graphs-Complex-Workflows

day-73-Dynamic-Graph-Launches

day-74-Multi-GPU-Programming-(Deeper-Exploration)

day-75-Performance-Metrics-&-Roofline-Analysis

day-76-Mixed-Precision-&-Tensor-Cores-(If-Supported)

day-77-UM-Advanced-Topics-(Prefetch,-Advise)

day-78-Large-Scale-Projects-Modular-Kernel-Design

day-79-Portability-&-Scalability-Best-Practices

day-8-Memory-Allocation-&-Pointers

day-80-Capstone-Project-#4

day-81-Cooperative-Groups-Advanced-Patterns

day-82-Large-Scale-Batch-Processing

day-83-External-Libraries-(cuDNN,-etc.)

day-84-Progress-Checkpoint

day-85-Instruction-Throughput-Profiling

day-86-Occupancy-vs.-ILP

day-87-Custom-Memory-Allocators

day-88-Kernel-Fusion-&-Loop-Fusion

day-89-Algorithmic-Optimizations-(Tiling,-Blocking)

day-9-Memory-Alignment-&-Coalescing

day-90-Minimizing-Data-Transfers

day-91-Enterprise-Level-Code-Structure

day-92-Advanced-Debugging-(Races-&-Deadlocks)

day-93-Real-Time-GPU-Computing-Techniques

day-94-Host-Multithreading-+-GPU-Coordination

day-95-CUDA-Graph-Updates-&-Reusability

day-96-Precision-&-Numerical-Stability

day-97-Advanced-P2P-&-Clustering-(If-Possible)

day-98-Progress-Checkpoint

day-99-Graph-API-for-Complex-DAG-Workloads

使用教程

1.Git 拉取代码库

2.使用Obsidian编辑md

金融经济学

第5讲：均值方差分析

第6讲：资本资产定价模型（CAPM）（Ⅰ）

第6讲：资本资产定价模型（CAPM）（Ⅱ）

第7讲：对CAPM的讨论

阿啸的2025年2月

2.16

2.17

2.18

2.19

2.20

2.21

2.22

2.23

阿啸的2025年3月

3.2

3.6

3.7

阿啸的2025年4月

4.10

4.11

4.12

4.13

4.14

4.15

4.16

4.18

4.19

4.20

4.21

4.23

4.29

4.3

4.30

4.7

4.8

阿啸的2025年5月

5.12

5.13

5.16

5.17

5.18

5.19

5.20

5.21

5.31

5.6

5.7

5.8

5.9

阿啸的2025年6月

6.2

页面大纲

字数

74 字

阅读时间

1 分钟

cuda challenge day5

下图可以用三元符减少warp divergence

问了下deepSeek原因

cuda challenge day9

对比结果

这个时间是不是不太对劲？

贡献者

文件历史

最后编辑于 27 天前查看完整历史

d2467-vault backup: 2025-05-06 22:40:30

使用 CC BY-SA 4.0 许可协议进行共享

编辑本页面

Pager

Previous page4.29

用 ♥ 撰写

CC BY-SA 4.0 © 2022-PRESENT Chin up 的创作者们