Related papers: Improved Ahead-of-Time Compilation of Stack-Based …
Hardware heterogeneity is here to stay for high-performance computing. Large-scale systems are currently equipped with multiple GPU accelerators per compute node and are expected to incorporate more specialized hardware in the future. This…
High-performance micro-kernels must fully exploit today's diverse and specialized hardware to deliver peak performance to DNNs. While higher-level optimizations for DNNs are offered by numerous compilers (e.g., MLIR, TVM, OpenXLA),…
Tokenization is widely used in large language models because it significantly improves performance. However, tokenization imposes several disadvantages, such as performance biases, increased adversarial vulnerability, decreased…
Regression testing assures software correctness after changes but is resource-intensive. Test Case Prioritisation (TCP) mitigates this by ordering tests to maximise early fault detection. Diversity-based TCP prioritises dissimilar tests,…
The optimization of the energy demand is crucial for modern video codecs. Previous studies show that the energy demand of VVC decoders can be improved by more than 50% if specific coding tools are disabled in the encoder. However, those…
With the skyrocketing costs of GPUs and their virtual instances in the cloud, there is a significant desire to use CPUs for large language model (LLM) inference. KV cache update, often implemented as allocation, copying, and in-place…
The utilization of paging for virtual machine (VM) memory management is the root cause of memory virtualization overhead. This paper shows that paging is not necessary in the hypervisor. In fact, memory fragmentation, which explains paging…
Vision Transformers (ViTs) have achieved strong performance in visual recognition, yet their deployment in resource-constrained industrial environments remains limited. Some main challenges are their high computational cost, memory…
Scan-based operations, such as backstage compaction and value filtering, have emerged as the main bottleneck for LSM-Trees in supporting contemporary data-intensive applications. For slower external storage devices, such as HDD and SATA…
Scalable video coding (SVC) is extended from its predecessor advanced video coding (AVC) because of its flexible transmission to all type of gadgets. However, SVC is more flexible and scalable than AVC, but it is more complex in determining…
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…
MapReduce is a technique used to vastly improve distributed processing of data and can massively speed up computation. Hadoop and its MapReduce relies on JVM and Java which is expensive on memory. High Performance Computing based MapReduce…
Large Language Models (LLMs) demonstrate strong capabilities in general coding tasks but encounter two key challenges when optimizing code: (i) the complexity of writing optimized code (such as performant CUDA kernels and competition-level…
Energy consumption dictates the cost and environmental impact of deploying Large Language Models. This paper investigates the impact of on-chip SRAM size and operating frequency on the energy efficiency and performance of LLM inference,…
Discrete GPU accelerators, while providing massive computing power for supercomputers and data centers, have their separate memory domain. Explicit memory management across device and host domains in programming is tedious and error-prone.…
Key-Value (KV) cache has become a de facto component of modern Large Vision-Language Models (LVLMs) for inference. While it enhances decoding efficiency in Large Language Models (LLMs), its direct adoption in LVLMs introduces substantial…
Quantum computation holds the promise of solving certain complex problems exponentially faster than classical computers. However, the high prevalent noise in current quantum devices impedes the accurate execution of even basic algorithms.…
Unlike offline processing, streaming video vision-language models face two fundamental constraints: causality and accumulation. Causality prevents access to future frames that offline methods exploit, while accumulation causes tokens to…
Object stores are widely used software stacks that achieve excellent scale-out with a well-defined interface and robust performance. However, their traditional get/put interface is unable to exploit data locality at its fullest, and limits…
WebAssembly (Wasm) is a compact, well-specified bytecode format that offers a portable compilation target with near-native execution speed. The bytecode format was specifically designed to be fast to parse, validate, and compile,…