Learn how the compiler optimizes iteration for different vector lengths — Vectors in Rust contain a pointer to a heap vector buffer ( buf) and a length ( len). The vector buffer is a pointer to a buffer of the type T. The length is the number of elements in the vector. Here is an excerpt from the std::vec::Vec implementation: Sample vector handling code

Map the Rust array, tuple, Box, and Option to assembly. See how the Rust compiler inlines functions. — We have already seen how Rust handles enums under the hood. We also looked at the code generation for the Box smart pointer. …

Understand the generated assembly code for enum discriminated unions — Matching an enum and associated fields Enums in Rust are discriminated unions that can save one of the multiple variants. The enum discriminator identifies the current interpretation of the discriminated union. The following code shows a simple enum in Rust that represents a generalized Number that can be an Integer, a Float or Complex. Here Number…

Understand the assembly code generated for passing a parameter by value, reference, Box, Rc, and Arc — Here we will be exploring the performance implications of the passing the self parameter by value, reference, and smart pointers (Box, Rc and Arc). The generated assembly code will help us understand what happens under the hood. We will be working with the Complex struct defined below. The code shows…

Auto-vectorization of for loops results in significant performance improvement — Developers can take advantage of built-in auto-vectorization support in GCC. Let’s explore vectorization with the GCC 11.2 compiler with the following compiler options to enable auto-vectorization. -O3 -march=skylake-avx512 -mno-vzeroupper Vector operations with 8 iterations Let’s start with the following code. We are performing vector operations where the compiler knows that the code will loop 8…

Deep dive into the 5G Radio Link Control in Acknowledged Mode — The RLC layer in the 5G NR stack is responsible for: Transfer of upper layer PDUs in Acknowledged Mode (AM), Unacknowledged Mode (UM) and Transparent Mode (TM) Error correction via retransmission of lost RLC PDUs (AM) Segmentation and reassembly of RLC SDUs (UM and AM) Re-segmentation of RLC data PDUs…

Assisting the compiler in optimizing if conditions — A look at the Linux kernel code will show many if conditions enclosed in likely and unlikely macros. These macros invoke compiler directives that give the compiler a hint on the code leg that should be optimized for performance. For example, the following translation lookaside buffer (TLB) insert function from…

Understand the closure generated from a lambda expression — Lambda expressions in C++ let developers define anonymous functions that can be used to inject code. Lambda expressions are more than just functions, they can capture the context from the code enclosing the lambda function. …

Develop an intuitive understanding of polar codes — 3GPP has selected polar codes as the error correcting code on the 5G NR control channels. Polar codes are unique in the way they split the channel into good and bad bit-channels. We will learn about the channel splitting by running experiments using Linux tools awk and gnuplot. …