Cross-Architecture Assembly
$6.99
Buy on Amazon View on Apple BooksPrefer it in print? See every format on Amazon →
Price on Apple Books. Amazon’s price may differ.
- Published
Description
Cross-Architecture Assembly is a practical guide to writing, measuring, and reasoning about assembly language across the three instruction sets that dominate modern computing: x86-64, AArch64, and RISC-V.
It begins with instruction sets, ABIs, and the assembler and linker toolchains, then builds a working model of microarchitecture: pipelines, out-of-order execution, caches, and branch prediction. From there it turns to measurement, using hardware performance counters and profilers to connect source and binary to real costs.
The optimization chapters cover instruction selection, register allocation, loop transformations, and cache-aware layout, followed by in-depth SIMD and bit-level work with AVX2, AVX-512, NEON, and SVE. A full treatment of concurrency explains memory ordering on strong and weak architectures, fences, atomics, and lock-free structures.
Later chapters move from object files, relocations, dynamic linking, and program startup into reverse engineering: disassembly, control- and data-flow recovery, decompilation, dynamic instrumentation, and patching. The book closes with systems-level integration, stable ABI boundaries, high-performance system calls, and hardening for production.
Code listings and command examples run throughout. The book assumes you can already program and have seen basic assembly, and it is written for performance engineers, systems programmers, and security researchers who work close to the hardware.
It begins with instruction sets, ABIs, and the assembler and linker toolchains, then builds a working model of microarchitecture: pipelines, out-of-order execution, caches, and branch prediction. From there it turns to measurement, using hardware performance counters and profilers to connect source and binary to real costs.
The optimization chapters cover instruction selection, register allocation, loop transformations, and cache-aware layout, followed by in-depth SIMD and bit-level work with AVX2, AVX-512, NEON, and SVE. A full treatment of concurrency explains memory ordering on strong and weak architectures, fences, atomics, and lock-free structures.
Later chapters move from object files, relocations, dynamic linking, and program startup into reverse engineering: disassembly, control- and data-flow recovery, decompilation, dynamic instrumentation, and patching. The book closes with systems-level integration, stable ABI boundaries, high-performance system calls, and hardening for production.
Code listings and command examples run throughout. The book assumes you can already program and have seen basic assembly, and it is written for performance engineers, systems programmers, and security researchers who work close to the hardware.