Tag
Go 1.27 introduces size-specialized memory allocation for allocations of 80 bytes or fewer, improving allocation speeds by 20-30% and overall program performance by up to 1% for allocation-heavy code.
C++26 standardizes trivial infinite loops as well-defined behavior, eliminating undefined behavior that previously allowed compilers to optimize them away, which was problematic in embedded and kernel applications.
The posters for PyTorch Con North America are now available, showcasing research in areas like compiler optimization, CUDA Graphs, AI architectures, and reinforcement learning. The conference will be held in San Jose, CA on October 20-21, with early registration discounts.
This research describes compiler-invented loads, where compiler optimizations create additional memory reads not present in source code, turning seemingly secure code into vulnerable binaries with TOCTOU races. It includes audits across kernels, hypervisors, enclaves, and firmware.
This article explains how HotSpot's C2 JIT compiler uses a 'known bits' abstraction to track which bits of an integer are definitely zero or one, enabling optimizations like eliminating redundant bitwise AND operations.
Article comparing old C++ performance tricks with modern compiler capabilities, showing that compilers can now optimize naive code better than hand-tuned hacks. Includes benchmarks on AMD Zen 5 with Clang 21.
A developer shares months of work building a compiler that outperforms cuBLAS for matrix multiplication on an A100 GPU, with visualizations.
The article explores the optimal ApplicativeDo scheduling problem in GHC, which is disabled by default due to slowness, and draws an analogy to the dynamic programming algorithm used for RNA folding to improve compiler performance.
A technical blog post demonstrating how Profile-Guided Optimization (PGO) with LLVM can significantly improve binary performance beyond standard -O3 and LTO, using SQLite as a benchmark.
A talk tracing the evolution from goto spaghetti to structured loops and finally to recursion schemes, showing how control-flow abstractions mirror data structures and why most languages still hide the best combinators.
Matt Godbolt explores compiler optimizations that convert an O(n) summation loop into an O(1) closed-form solution, highlighting how Clang and GCC employ sophisticated techniques like loop unrolling and mathematical simplification to dramatically improve code performance.
Droid ASC is a fast decompilation engine for Android APKs that uses R8 compiler optimizations to query compiled artifacts directly, enabling millisecond code searches and decompilation with minimal memory usage.