Related papers: Library Liberation: Competitive Performance Matmul…
Image processing and machine learning applications benefit tremendously from hardware acceleration, but existing compilers target either FPGAs, which sacrifice power and performance for flexible hardware, or ASICs, which rapidly become…
Interest in deploying Deep Neural Network (DNN) inference on edge devices has resulted in an explosion of the number and types of hardware platforms to use. While the high-level programming interface, such as TensorFlow, can be readily…
Compiler backends should be automatically generated from hardware design language (HDL) models of the hardware they target. Generating compiler components directly from HDL can provide stronger correctness guarantees, ease development…
To meet the increasing demand of deep learning (DL) models, AI chips are employing both off-chip memory (e.g., HBM) and high-bandwidth low-latency interconnect for direct inter-core data exchange. However, it is not easy to explore the…
Medical image processing is often limited by the computational cost of the involved algorithms. Whereas dedicated computing devices (GPUs in particular) exist and do provide significant efficiency boosts, they have an extra cost of use in…
Lifting low-level or legacy code into a domain-specific language (DSL) improves our ability to understand it, enables deeper formal reasoning, and facilitates safe modification. We present the CoCompiler, a bidirectional compiler and lifter…
Current compiler optimization reports often present complex, technical information that is difficult for programmers to interpret and act upon effectively. This paper assesses the capability of large language models (LLM) to understand…
The rapidly growing importance of Machine Learning (ML) applications, coupled with their ever-increasing model size and inference energy footprint, has created a strong need for specialized ML hardware architectures. Numerous ML…
GCC and LLVM underpin much of modern software infrastructure, relying on distinct Intermediate Representations (IRs) to drive optimizations and code generation. However, the semantic and structural differences between these IRs create…
ZeroML is a new generation programming language for AutoML to drive the ML pipeline in a compiled and multi-paradigm way, with a pure functional core. Meeting the shortcomings introduced by Python, R, or Julia such as slow-running time,…
Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of tasks, but their deployment is often constrained by substantial memory footprints and computational costs. While prior work has achieved…
High-performance GPU kernels are critical to modern machine learning systems, yet developing efficient implementations remains a challenging, expert-driven process due to the tight coupling between algorithmic structure, memory hierarchy…
Selecting the right compiler optimisations has a severe impact on programs' performance. Still, the available optimisations keep increasing, and their effect depends on the specific program, making the task human intractable. Researchers…
As software becomes larger, programming languages become higher-level, and processors continue to fail to be clocked faster, we'll increasingly require compilers to reduce code bloat, eliminate abstraction penalties, and exploit interesting…
Gain Cell memory (GCRAM) offers higher density and lower power than SRAM, making it a promising candidate for on-chip memory in domain-specific accelerators. To support workloads with varying traffic and lifetime metrics, GCRAM also offers…
Multimodal information retrieval (MMIR) has gained attention for its flexibility in handling text, images, or mixed queries and candidates. Recent breakthroughs in multimodal large language models (MLLMs) boost MMIR performance by…
Code is increasingly becoming a core data modality of modern machine learning research impacting not only the way we write code with conversational agents like OpenAI's ChatGPT, Google's Bard, or Anthropic's Claude, the way we translate…
Scaling language models improves performance but comes with significant computational costs. This paper proposes UL2R, a method that substantially improves existing language models and their scaling curves with a relatively tiny amount of…
Large Language Models (LLMs) show promise for automated code optimization but struggle without performance context. This work introduces Opal, a modular framework that connects performance analytics insights with the vast body of published…
Recently, crossbar array based in-memory accelerators have been gaining interest due to their high throughput and energy efficiency. While software and compiler support for the in-memory accelerators has also been introduced, they are…