Search

Modern GPGPUs support the concurrent execution of thousands of threads to provide an energy-efficient platform. However, the massive multi-threading of GPGPUs incurs serious cache contention, as the cache lines brought by one thread can easily be evicted by other threads in the small shared cache. In this paper, we propose a software-hardware cooperative approach that exploits the spatial locality among different thread blocks to better utilize the precious cache capacity. Through dynamic locality estimation and thread block scheduling, we can capture more performance improvement opportunities than prior work that only explores the spatial locality between consecutive thread blocks. Evaluations across diverse GPGPU applications show that, on average, our locality-aware scheduler provides 25 and 9 percent performance improvement over the commonly-employed round-robin scheduler and the state-of-the-art scheduler, respectively.

A microalgae-based energy system, which is a combination of different microalgae-to-biodiesel chains and an integrated cogasification combined cycle (ICGCC) system, is presented. To address the low environmental impacts, the electricity is generated from ICGCC to meet the load demand from the microalgae-to-biodiesel chains and the flue gas exits from ICGCC to meet the demand of growing algal culture. To achieve the microalgae-based energy system with minimum life cycle greenhouse gas (GHG) emissions, the first step is to develop the superstructure model based on GAMS, the second step is to use the optimal heat exchanger network to maximize the heat recovery of ICGCC, and the third step is to find the optimal combination of the microalgae-to-biodiesel chain and optimal operating conditions of ICGCC by solving the global optimization of nonconvex mixed-integer nonlinear programming (MINLP) problem. For the scope of well-to-tank (WTT), the optimal microalgae-based energy system reduces 16.80% greenhouse gas (GHG) emissions compared to the other reported microalgae-to-biodiesel chains. For the scope of well-to-wheel (WTW), the optimal microalgae-based energy system reduces 45.77% GHG emissions compared to the conventional diesel process.

Accelerator-rich architectures employ IOMMUs to support unified virtual address, but researches show that they fail to meet the performance and energy requirements of accelerators. Instead of optimizing the speed/energy of IOMMU address translation, this work tackles the issue from a new perspective, eliminating the need for translation with an active forwarding (AF) mechanism that forwards input data of accelerators directly from the CPU cache to the scratchpad memory of the accelerator. Results show that on average, AF can provide 8% performance improvement compared to the state-of-the-art mechanism, hostPageWalk, and reduce 22.1% accelerator power.

To consider QoS for resource-limited mobile systems, we introduce a fast preemption mechanism on GPUs. First, we involve a dual-kernel execution model to support fine-grained preemption, and a resource allocation policy to avoid resource fragmentation problem. Second, we propose a preemption victim selection scheme to reduce the throughput overhead while satisfying a required preemption latency. Evaluations show that we can reach very close to the ideal preemption scheme within 2% difference in terms of deadline violations. Furthermore, on average we improve GPU resource utilization by 2.93× over prior technique during preemption.

Shared last-level cache (LLC) management is a critical design issue for heterogeneous multi-cores. In this paper, we observe two major challenges: the contribution of LLC latency to overall performance varies among applications/cores and also across time; overlooking the off-chip latency factor often leads to adverse effects on overall performance. Hence, we propose a Latency Sensitivity-based Cache Partitioning (LSP) framework, including a lightweight runtime mechanism to quantify the latency-sensitivity and a new cost function to guide the LLC partitioning. Results show that LSP improves the overall throughput by 8% on average (27% at most), compared with the state-of-the-art partitioning mechanism, TAP.

In this work, we report a simple method for solution-processed organic light emitting devices (OLEDs), where single-layer graphene acts as the anode and the hexa-peri-hexabenzocoronene exfoliating agent (HBC-6ImBr) provides surface modification. In SEM images, the PEDOT:PSS solution fully covered the graphene electrode after coating with HBC-6ImBr. The fabricated solution-processed OLEDs with a single-layer graphene anode showed outstanding brightness at 3182 cd/m2 and current efficiency up to 6 cd/A which is comparable to that of indium tin oxide films, and the OLED device brightness performance increases six times compared to tri-layer graphene treated with UV-Ozone at the same driving voltage. This method can be used in a wide variety of solution-processed organic optoelectronics on surface-modified graphene anodes.