Looking into x86_64 ASM In the x86_64 assembly I was looking for any particularly large instructions that might be sensitive to alignment. To start I found the section of the binary that the decompress all tags function is in. Also the disassembly contains the byte pattern from the inline assembler. asm(“.byte 0x0f, 0x1f, 0x84, 0x00, …
Project Investigation: Why this optimization failed Read More »
This is the code I am looking at optimizing. The assembler code is aligning instructions in the binary. These instructions are aligned by 32+16 bytes. As this is aligning with bytes and not bits, this is not aligning to a word boundary. If this code was aligning to a word boundary then it would not …
I was going to test this project on a raspberry pi running Fedora. However I have had trouble getting the pi setup on my network. I will hopefully get it working in the next few days, however I will shift my benchmarking over to the aarch64 servers for now. Because the provided test and benchmarks …
This build will work on all platforms that I will be testing on. There will be to main builds we will use: First make a build directory under the main directory, and cd into it. The release build will be our main build for benchmarking. It is compiled with “-O2 -DNDEBUG -rdynamic”. cmake ../ -DCMAKE_BUILD_TYPE=Release …
At this point I am wondering if there is even any optimization that I can do. What I want to do is get the compiler to tell me what it is doing. So that I can focus on areas that the compiler is not optimizing. In order to do this I need to learn the …
Project Investigation Part 2: Can I even optimize this? Read More »
The function I want to look at is this: void DecompressAllTags(Writer* writer) { // In x86, pad the function body to start 16 bytes later. This function has // a couple of hotspots that are highly sensitive to alignment: we have // observed regressions by more than 20% in some metrics just by moving the …
In this lab we are looking at the assembly code in an open source package. I chose the mjpegtools package, which is a package for working with mjpeg video. Lets begin by looking at how much assembler there is and where it is. Running this command will find any asm files. find . -name ‘*.[sS]’ …
This post is a follow up to this post. Why this package? This package interested me because it is designed to be a fast compressor. It is used in massive data storage senarios, it is also used by common open source databases like mongoDB. This compressor is used on a wide variaty of data, some …
The project requirements are to find an open source package related to compression or hashing. Then to benchmark and optimize a part of the package for aarch64 systems. I have chosen to investigate the snappy package. This compression library is created by google to be fast and robust,and is used to compress large amounts of …
In this lab we will be looking at this code. What is this code? This code uses specific inline aarch64 assembly language to scale volume samples. This code focuses on using SIMD (single instruction multiple data) specifically the SQDMULH ( Signed Saturating Doubling Multiply returning High Half ) instruction. This instruction ensure that the value …