Related papers: Persistent HyTM via Fast Path Fine-Grained Locking
Fine-grained sparsity promises higher parametric capacity without proportional per-token compute, but often suffers from training instability, load balancing, and communication overhead. We introduce STEM (Scaling Transformers with…
Hardware performance monitoring (HPM) is a crucial ingredient of performance analysis tools. While there are interfaces like LIKWID, PAPI or the kernel interface perf\_event which provide HPM access with some additional features, many…
Privacy-preserving machine learning (PPML) is an emerging topic to handle secure machine learning inference over sensitive data in untrusted environments. Fully homomorphic encryption (FHE) enables computation directly on encrypted data on…
Non-Volatile Memory (NVM) can deliver higher density and lower cost per bit when compared with DRAM. Its main drawback is that it is slower than DRAM. On the other hand, DRAM has scalability problems due to its cost and energy consumption.…
Storage Class Memory (SCM) is a class of memory technology which has recently become viable for use. Their namearises from the fact that they exhibit non-volatility of data, similar to secondary storage while also having latencies…
Multilayered artificial neural networks (ANN) have found widespread utility in classification and recognition applications. The scale and complexity of such networks together with the inadequacies of general purpose computing platforms have…
Consistent hashing is a technique for distributing data across a network of nodes in a way that minimizes reorganization when nodes join or leave the network. It is extensively applied in modern distributed systems as a fundamental…
Existing disk-based database systems largely fall into two categories -- they either provide very high performance but few guarantees, or expose the transaction abstraction satisfying the full ACID guarantees at the cost of lower…
High performance computing (HPC) applications have a high requirement on storage speed and capacity. Non-volatile memory is a promising technology to replace traditional storage devices to improve HPC performance. Earlier in 2017, Intel and…
Both SRAM and DRAM have stopped scaling: there is no technical roadmap to reduce their cost (per byte/GB). As a result, memory now dominates system cost. This paper argues for a paradigm shift from today's simple memory hierarchy toward…
We investigate the use of path signatures in a machine learning context for hedging exotic derivatives under non-Markovian stochastic volatility models. In a deep learning setting, we use signatures as features in feedforward neural…
This paper introduces Hamster, a novel synchronous Byzantine Fault Tolerance protocol that achieves better performance and has weaker dependency on synchrony. Specifically, Hamster employs coding techniques to significantly decrease…
As more data-intensive tasks with large footprints are deployed in virtual machines (VMs), huge pages are widely used to eliminate the increasing address translation overhead. However, once the huge page mapping is established, all the base…
Traditional neural networks require enormous amounts of data to build their complex mappings during a slow training procedure that hinders their abilities for relearning and adapting to new data. Memory-augmented neural networks enhance…
After nearly a decade of anticipation, scalable nonvolatile memory DIMMs are finally commercially available with the release of Intel's 3D XPoint DIMM. This new nonvolatile DIMM supports byte-granularity accesses with access times on the…
Previous RNN architectures have largely been superseded by LSTM, or "Long Short-Term Memory". Since its introduction, there have been many variations on this simple design. However, it is still widely used and we are not aware of a…
Non-volatile Memory (NVM) could bridge the gap between memory and storage. However, NVMs are susceptible to data remanence attacks. Thus, multiple security metadata must persist along with the data to protect the confidentiality and…
Software Transactional Memory systems (STMs) have garnered significant interest as an elegant alternative for addressing synchronization and concurrency issues with multi-threaded programming in multi-core systems. Client programs use STMs…
Processing-in-Memory (PIM) architectures offer promising solutions for efficiently handling AI applications in energy-constrained edge environments. While traditional PIM designs enhance performance and energy efficiency by reducing data…
As DRAM and other transistor-based memory technologies approach their scalability limits, alternative storage solutions like Phase-Change Memory (PCM) are gaining attention for their scalability, fast access times, and zero leakage power.…