Minsoo Rhu

Convolutional Neural Networks (CNNs) have emerged as a fundamental technology for machine learning. High performance and extreme energy efficiency are critical for deployments of CNNs, especially in mobile platforms such as autonomous vehicles, cameras, and electronic personal assistants. This paper introduces the Sparse CNN (SCNN) accelerator architecture, which improves performance and energy efficiency by exploiting the zero-valued weights that stem from network pruning during training and ze

Convolutional Neural Networks (CNNs) have emerged as a fundamental technology for machine learning. High performance and extreme energy efficiency are critical for deployments of CNNs, especially in mobile platforms such as autonomous vehicles, cameras, and electronic personal assistants. This paper introduces the Sparse CNN (SCNN) accelerator architecture, which improves performance and energy efficiency by exploiting the zero-valued weights that stem from network pruning during training and ze

The most widely used machine learning frameworks require users to carefully tune their memory usage so that the deep neural network (DNN) fits into the DRAM capacity of a GPU. This restriction hampers a researcher's flexibility to study different machine learning algorithms, forcing them to either use a less desirable network architecture or parallelize the processing across multiple GPUs. We propose a runtime memory manager that virtualizes the memory usage of DNNs such that both GPU and CPU me

Recent studies from several hyperscalars pinpoint to embedding layers as the most memory-intensive deep learning (DL) algorithm being deployed in today's datacenters. This paper addresses the memory capacity and bandwidth challenges of embedding layers and the associated tensor operations. We present our vertically integrated hardware/software co-design, which includes a custom DIMM module enhanced with near-memory processing cores tailored for DL tensor operations. These custom DIMMs are popula

Homomorphic encryption (HE) enables the secure offloading of computations to the cloud by providing computation on encrypted data (ciphertexts). HE is based on noisy encryption schemes in which noise accumulates as more computations are applied to the data. The limited number of operations applicable to the data prevents practical applications from exploiting HE. Bootstrapping enables an unlimited number of operations or fully HE (FHE) by refreshing the ciphertext. Unfortunately, bootstrapping r

Homomorphic Encryption (HE) is one of the most promising post-quantum cryptographic schemes that enable privacy-preserving computation on servers. However, noise accumulates as we perform operations on HE-encrypted data, restricting the number of possible operations. Fully HE (FHE) removes this restriction by introducing the bootstrapping operation, which refreshes the data; however, FHE schemes are highly memory-bound. Bootstrapping, in particular, requires loading GBs of evaluation keys and pl

Convolutional Neural Networks (CNNs) have emerged as a fundamental technology for machine learning. High performance and extreme energy efficiency are critical for deployments of CNNs in a wide range of situations, especially mobile platforms such as autonomous vehicles, cameras, and electronic personal assistants. This paper introduces the Sparse CNN (SCNN) accelerator architecture, which improves performance and energy efficiency by exploiting the zero-valued weights that stem from network pru

As GPU's compute capabilities grow, their memory hierarchy increasingly becomes a bottleneck. Current GPU memory hierarchies use coarse-grained memory accesses to exploit spatial locality, maximize peak bandwidth, simplify control, and reduce cache meta-data storage. These coarse-grained memory accesses, however, are a poor match for emerging GPU applications with irregular control flow and memory access patterns. Meanwhile, the massive multi-threading of GPUs and the simplicity of their cache h

Current graphics processing units (GPUs) utilize the single instruction multiple thread (SIMT) execution model. With SIMT, a group of logical threads executes such that all threads in the group execute a single common instruction on a particular cycle. To enable control flow to diverge within the group of threads, GPUs partially serialize execution and follow a single control flow path at a time. The execution of the threads in the group that are not on the current path is masked. Most current G

Wide SIMD-based GPUs have evolved into a promising platform for running general purpose workloads. Current programmable GPUs allow even code with irregular control to execute well on their SIMD pipelines. To do this, each SIMD lane is considered to execute a logical thread where hardware ensures that control flow is accurate by automatically applying masked execution. The masked execution, however, often degrades performance because the issue slots of masked lanes are wasted. This degradation ca

Current GPUs maintain high programmability by abstracting the SIMD nature of the hardware as independent concurrent threads of control with hardware responsible for generating predicate masks to utilize the SIMD hardware for different flows of control. This dynamic masking leads to poor utilization of SIMD resources when the control of different threads in the same SIMD group diverges. Prior research suggests that SIMD groups be formed dynamically by compacting a large number of threads into gro

Wide SIMD-based GPUs have evolved into a promising platform for running general purpose workloads. Current programmable GPUs allow even code with irregular control to execute well on their SIMD pipelines. To do this, each SIMD lane is considered to execute a logical thread where hardware ensures that control flow is accurate by automatically applying masked execution. The masked execution, however, often degrades performance because the issue slots of masked lanes are wasted. This degradation ca

The most widely used machine learning frameworks require users to carefully tune their memory usage so that the deep neural network (DNN) fits into the DRAM capacity of a GPU. This restriction hampers a researcher's flexibility to study different machine learning algorithms, forcing them to either use a less desirable network architecture or parallelize the processing across multiple GPUs. We propose a runtime memory manager that virtualizes the memory usage of DNNs such that both GPU and CPU me

Embedded block coding with optimized truncation (EBCOT) employed in the JPEG2000 standard accounts for the majority of the processing time, because the EBCOT is full of bit operations that cannot be implemented efficiently in software. The block coder consists of a bit-plane coder (BPC) followed by a binary arithmetic coder (BAC), where the most up-to-date BPC architectures are capable of producing symbols at a much higher rate than the conventional BACs can handle. This letter proposes a novel

Popular deep learning frameworks require users to fine-tune their memory usage so that the training data of a deep neural network (DNN) fits within the GPU physical memory. Prior work tries to address this restriction by virtualizing the memory usage of DNNs, enabling both CPU and GPU memory to be utilized for memory allocations. Despite its merits, virtualizing memory can incur significant performance overheads when the time needed to copy data back and forth from CPU memory is higher than the