21 March 2025 in ACM Transactions on Architecture and Code Optimization
Today, GPUs significantly boost rendering performance. However, the high memory requirements limit their use, especially on low-end mobile platforms. Compression techniques have been widely adopted to reduce memory consumption but face two primary issues when applied to mobile GPUs: (1) low repetition ratio caused by small raw data sizes and concurrency, and (2) low locality caused by unpredictable rendering behaviors. These two limitations result in a low compression ratio when compressors are applied to low-end mobile devices. This article introduces gCom , a fine-grained rendering compressor accelerated by GPUs. To improve the compression ratio, gCom incorporates the following innovations. First, unlike other compression techniques that use frames or tiles as basic processing units, gCom is the first to employ a fine-grained processing unit (i.e., the color channel), enhancing repetition amplification without increasing raw data. Second, gCom introduces two key features— Hierarchical Delta and Channel Decorrelator —which maximize the locality of adjacent channels and reduce raw data size. Third, to maintain the original GPU throughput, gCom revolutionizes the Golomb-Rice algorithm and proposes a new compression approach, the Parallel-Oriented Golomb-Rice algorithm, enabling parallel execution of both decompression and compression processes. The entire design of gCom utilizes only idle resources and existing commands on mobile GPUs, thus keeping purchasing costs low. To date, gCom has improved the channel locality by nearly 50%. The best compression achievement received by gCom has reached around 20%.
18 August 2025 in IEEE Transactions on Parallel and Distributed Systems
Resource underutilization has troubled data centers for several decades. On the CPU front, live migration plays a crucial role in reallocating CPU resources. Nevertheless, contemporary Virtual Machine (VM) live migration methods are burdened by substantial resource consumption. In terms of memory management, disaggregated memory offers an effective solution to enhance memory utilization, but leaves a gap in addressing CPU underutilization. Our findings highlight a considerable opportunity to optimize live migration in the context of disaggregated memory systems. We introduce Anemoi, a resource management system that seamlessly integrates VM live migration with memory disaggregation to address the aforementioned gap. In the context of disaggregated memory, remote memory becomes accessible from destination nodes, effectively eliminating the need for extensive network transmission of memory pages, and thereby significantly reducing migration time. In addition, we propose using memory replicas as an optimization to the live migration system. To mitigate the overhead of potential excessive memory consumption, we develop a dedicated compression algorithm. Our evaluations demonstrate that Anemoi leads to a notable 69% reduction in network bandwidth utilization and an impressive 83% reduction in migration time compared to traditional VM live migration. Additionally, our compression algorithm achieves an outstanding space-saving rate of 83.6%.
21 March 2026 in ACM Transactions on Architecture and Code Optimization
WebAssembly (WASM) is emerging as an alternative to containers in serverless computing due to its lightweight memory isolation and secure language semantics. However, the WASM System Interface (WASI) does not guarantee isolation from the host kernel. Secure containers reduce exposure to the host kernel API, but they do not match WASM’s memory efficiency or startup latency. In this article, we introduce WaSC , a secure container runtime that hardens WASM system isolation by decoupling the system interface used by sandbox functions into a virtualization-based daemon. WASM functions connect to this daemon transparently; the daemon protects the system interface with machine-level isolation while preserving function-level startup times and memory footprints. Our evaluation shows that WaSC achieves a 99th-percentile startup latency of 15 ms and maintains a memory footprint of \(\sim\) 10 MB. Compared to Firecracker, a state-of-the-art secure container runtime, WaSC achieves 3× memory density on a single physical machine. We present microbenchmarks and application benchmarks that characterize WaSC ’s performance and inform performance tuning for serverless applications ported to WaSC . WaSC incurs a 3.2× slowdown for WASI calls along the virtualization-based daemon path, and SQLite speedtest1 indicates an average 80% increase in runtime.
29 September 2021 in Thrombosis and Haemostasis
Platelet-targeted FVIII gene therapy can efficiently recover bleeding phenotype for hemophilia A (HA), yet characteristics of thrombus formation with this ectopic expression of factor VIII (FVIII) in platelets remain unclear. Here, we generated 2bF8trans mice restrictively expressing human B-domain–deleted FVIII (hBDD FVIII) in platelets on a hemophilic (FVIIInull) mice background. The results showed no statistical difference in clot strength and stability between wild-type (WT) and 2bF8trans mice, but with a prolonged reaction time (R-time), by thromboelastography. Fluid dynamics analysis showed that at the shear rates of 500 to 1,500 s−1, where physiological hemostasis often develops, the thrombi formed in 2bF8trans mice were more stable than those in FVIIInull mice, while at high pathological shear rates (2,500 s−1), mimicking atherosclerosis, thrombus size and fibrin deposition in 2bF8trans mice were less than those in WT mice. Thrombus morphology analysis showed that there was a locally concentrated deposition of fibrin in thrombus at the injured site and fibrin co-localized with activated platelets in 2bF8trans mice. Moreover, a higher ratio of fibrin to platelets was found in thrombus from 2bF8trans mice following laser-induced injury in cremaster arterioles, which might be the underlying mechanism of thrombus stability in 2bF8trans mice at physiological arterial circumstance. These observations suggest that specific morphological features of the thrombi might contribute to the efficacy and safety of platelet-targeted FVIII gene therapy for HA. * These authors contributed equally to this article. Received: 26 March 2021 Accepted: 31 July 2021 Publication Date: 29 September 2021 (online) © 2021. Thieme. All rights reserved. Georg Thieme Verlag KG Rüdigerstraße 14, 70469 Stuttgart, Germany
1 October 2026 in IEEE Transactions on Parallel and Distributed Systems