Chapter 2 - Compression Techniques “I have made this longer than usual because I have not had time to make it shorter.” Blaise Pascal In the last chapter, we discussed a few ideas to improve the deep deep learning efficiency. Now, we will elaborate on one of those ideas, the compression techniques. Compression techniques aim to reduce the model footprint (size, latency, memory etc.). We can reduce the chapter, we introduce Quantization, a model compression technique that addresses both these issues. We’ll start with a gentle introduction to the idea of compression. Details of quantization and its applications

== 3 9 . 4/ String Compression Lets make a compressed string table https://github.com/AshleyRoll/squeeze map from enum Key to Compressed String Hu�man Coding for compression Output struct: Mapping choose an arbitrary amount of work they will allow in constexpr context Complex processing like compression will hit the limits Had to make more complex implementation to cache bit streams rather than walk

Advanced Compression Techniques “The problem is that we attempt to solve the simplest questions cleverly, thereby rendering them unusually complex. One should seek the simple solution.” — Anton Pavlovich Pavlovich Chekhov In this chapter, we will discuss two advanced compression techniques. By ‘advanced’ we mean that these techniques are slightly more involved than quantization (as discussed in the second of our models. Did we get you excited yet? Let’s learn about these techniques together! Model Compression Using Sparsity Sparsity or Pruning refers to the technique of removing (pruning) weights during

Core Features 237 INTERVAL Data Type Handling 237 Additional PostgreSQL Features 238 Zstandard Compression Algorithm 238 Relaxed Rules for Specifying Table Distribution Columns 239 Resource Groups Features Greenplum 6 Documentation VMware, Inc 23 Using Compression (Append-Optimized Tables Only) 563 To create a compressed table 565 Checking the Compression and Distribution of an Append-Optimized Table 565 Run-length Encoding 566 Adding Column-level Compression 566 Default Compression Values 568 Precedence of Compression Settings 568 Optimal Location for Column Compression Settings 568 Storage Directives Examples

Core Features 230 INTERVAL Data Type Handling 230 Additional PostgreSQL Features 231 Zstandard Compression Algorithm 231 Relaxed Rules for Specifying Table Distribution Columns 231 Resource Groups Features 541 To create a column-oriented table 542 Using Compression (Append-Optimized Tables Only) 543 To create a compressed table 544 Checking the Compression and Distribution of an Append-Optimized Table 544 Run-length Encoding 545 Adding Column-level Compression 545 Default Compression Values 547 Precedence of Compression Settings 547 Optimal Location for Column Compression Settings 547 Storage Directives Examples

Core Features 227 INTERVAL Data Type Handling 227 Additional PostgreSQL Features 227 Zstandard Compression Algorithm 228 Relaxed Rules for Specifying Table Distribution Columns 228 Resource Groups Features 539 To create a column-oriented table 540 Using Compression (Append-Optimized Tables Only) 540 To create a compressed table 541 Checking the Compression and Distribution of an Append-Optimized Table 541 Column-level Compression 542 VMware Tanzu Greenplum 6 Documentation VMware, Inc. 23 Default Compression Values 544 Precedence of Compression Settings 544 Optimal Location for Column Compression Settings

Core Features 209 INTERVAL Data Type Handling 209 Additional PostgreSQL Features 210 Zstandard Compression Algorithm 210 Relaxed Rules for Specifying Table Distribution Columns 210 Resource Groups Features 0 Data Model 315 Heap vs. Append-Optimized Storage 315 Row vs. Column Oriented Storage 315 Compression 316 Distributions 316 Resource Queue Memory Management 316 Partitioning 318 Indexes 318 Resource Storage Model 328 Heap Storage or Append-Optimized Storage 329 Row or Column Orientation 329 Compression 330 Distributions 330 Local (Co-located) Joins 331 Data Skew 331 Processing Skew 332 Partitioning

Core Features 217 INTERVAL Data Type Handling 217 Additional PostgreSQL Features 218 Zstandard Compression Algorithm 218 Relaxed Rules for Specifying Table Distribution Columns 218 VMware Greenplum v6 0 Data Model 324 Heap vs. Append-Optimized Storage 324 Row vs. Column Oriented Storage 324 Compression 325 Distributions 325 Resource Queue Memory Management 325 Partitioning 327 Indexes 327 Resource Storage Model 337 Heap Storage or Append-Optimized Storage 338 Row or Column Orientation 338 Compression 339 Distributions 339 Local (Co-located) Joins 340 Data Skew 340 Processing Skew 341 Partitioning

Core Features 269 INTERVAL Data Type Handling 269 Additional PostgreSQL Features 270 Zstandard Compression Algorithm 271 Relaxed Rules for Specifying Table Distribution Columns 271 Resource Groups Features 567 To create a column-oriented table 568 Using Compression (Append-Optimized Tables Only) 569 To create a compressed table 570 Checking the Compression and Distribution of an Append-Optimized Table 570 by Broadcom 27 Adding Column-level Compression 572 Default Compression Values 573 Precedence of Compression Settings 573 Optimal Location for Column Compression Settings 574 Storage Directives Examples

Core Features 206 INTERVAL Data Type Handling 206 Additional PostgreSQL Features 206 Zstandard Compression Algorithm 207 Relaxed Rules for Specifying Table Distribution Columns 207 Resource Groups Features 459 To create a column-oriented table 460 Using Compression (Append-Optimized Tables Only) 460 To create a compressed table 461 Checking the Compression and Distribution of an Append-Optimized Table 461 Run-length Encoding 462 Adding Column-level Compression 462 Default Compression Values 464 Precedence of Compression Settings 464 Optimal Location for Column Compression Settings 464 Storage Directives Examples