Improving cache locking performance of modern embedded systems via the addition of a miss table at the L2 cache level

To confer the robustness and high quality of service, modern computing architectures running real-time applications should provide high system performance and high timing predictability. Cache memory is used to improve performance by bridging the speed gap between the main memory and CPU. However, the cache introduces timing unpredictability creating serious challenges for real-time applications. Herein, we introduce a miss table (MT) based cache locking scheme at level-2 (L2) cache to further improve the timing predictability and system performance/power ratio. The MT holds information of block addresses related to the application being processed which cause most cache misses if not locked. Information in MT is used for efficient selection of the blocks to be locked and victim blocks to be replaced. This MT based approach improves timing predictability by locking important blocks with the highest number of misses inside the cache for the entire execution time. In addition, this technique decreases the average delay per task and total power consumption by reducing cache misses and avoiding unnecessary data transfers. This MT based solution is effective for both uniprocessors and multicores. We evaluate the proposed MT-based cache locking scheme by simulating an 8-core processor with 2 levels of caches using MPEG4 decoding, H.264/AVC decoding, FFT, and MI workloads. Experimental results show that in addition to improving the predictability, a reduction of 21% in mean delay per task and a reduction of 18% in total power consumption are achieved for MPEG4 (and H.264/AVC) by using MT and locking 25% of the L2. The MT results in about 5% delay and power reductions on these video applications, possibly more on applications with worse cache behavior. For the FFT and MI (and other) applications whose code fits inside the level-1 instruction (I1) cache, the mean delay per task increases only by 3% and total power consumption increases by 2% due to the addition of the MT.     

Organization of the lamprey striatum - transmitters and projections

The purpose of the present study is to characterize the striatum of the lamprey by immunohistochemical and tracing techniques. Cells immunoreactive for GABA and substance P (SP), and positive for acetylcholinesterase, are present in the lamprey striatum. Immunoreactive (ir) fibers were detected by antisera raised against SP, dopamine, enkephalin and serotonin. These immunoreactive fibers were mainly located in the periventricular neuropil that borders the striatum and in which GABAergic striatal neurons distributed their dendritic arbors. Putative connections between the striatum, the ventral part of the lateral pallium, and the diencephalic motor centers involved in the control of locomotion were studied by using fluorescein-coupled dextran amines (FDA) as a tracer. The striatum projects to the ventral part of the lateral pallium (lpv), where GABA-ir cells and SP-ir fibers were also present. The lpv in turn projects to the ventral thalamus, which has descending connections to the reticulospinal cells involved in the control of locomotion. These results, together with previous findings of histaminergic and neurotensin projections, suggest that the lamprey striatum and its inputs with regard to neurotransmitters/modulators are very similar to those of modem amniotes, including primates, and are thus conserved to a high degree.     

Intrinsic function of a neuronal network - a vertebrate central pattern generator

The cellular bases of vertebrate locomotor behaviour is reviewed using the lamprey as a model system. Forebrain and brainstem cell populations initiate locomotor activity via reticulospinal fibers activating a spinal network comprised of glutamatergic and glycinergic interneurons. The role of different subtypes of Ca2+ channels, Ca2+ dependent K+ channels and voltage dependent NMDA channels at the neuronal and network level is in focus as well as the effects of different metabotropic, aminergic and peptidergic modulators that target these ion channels. This is one of the few vertebrate networks that is understood at a cellular level.     

Impact of level-2 cache sharing on the performance and power requirements of homogeneous multicore embedded systems

In order to satisfy the needs for increasing computer processing power, there are significant changes in the design process of modern computing systems. Major chip-vendors are deploying multicore or manycore processors to their product lines. Multicore architectures offer a tremendous amount of processing speed. At the same time, they bring challenges for embedded systems which suffer from limited resources. Various cache memory hierarchies have been proposed to satisfy the requirements for different embedded systems. Normally, a level-1 cache (CL1) memory is dedicated to each core. However, the level-2 cache (CL2) can be shared (like Intel Xeon and IBM Cell) or distributed (like AMD Athlon). In this paper, we investigate the impact of the CL2 organization type (shared Vs distributed) on the performance and power consumption of homogeneous multicore embedded systems. We use VisualSim and Heptane tools to model and simulate the target architectures running FFT, MI, and DFT applications. Experimental results show that by replacing a single-core system with an 8-core system, reductions in mean delay per core of 64% for distributed CL2 and 53% for shared CL2 are possible with little additional power (15% for distributed CL2 and 18% for shared CL2) for FFT. Results also reveal that the distributed CL2 hierarchy outperforms the shared CL2 hierarchy for all three applications considered and for other applications with similar code characteristics.     

Endogenous activation of metabotropic glutamate receptors contributes to burst frequency regulation in the lamprey locomotor network

The effect of metabotropic glutamate receptor (mGluR) agonists and antagonists on the spinal cord network underlying locomotion in the lamprey has been analysed. The specific group I mGluR agonist (R,S)-3,5-dihydroxyphenylglycine (DHPG) and the broad-spectrum mGluR agonist (1S,3R)-1-aminocyclopentane-1,3-dicarboxylic acid (1S,3R-ACPD) both increased the burst frequency of N-methyl-D-aspartic acid (NMDA)-induced fictive locomotion and depolarized grey matter neurons. The burst frequency increase induced by the mGluR agonists was counteracted by the mGluR antagonists (+)-alpha-methyl-4-carboxyphenylglycine ((+)-MCPG), cyclopropan[b]chromen-1a-carboxylic acid ethylester (CPCCOEt) and (RS)-1-aminoindan-1,5-dicarboxylic acid (AIDA). Application of CPCCOEt alone reduced the locomotor burst frequency, indicating that mGluRs are endogenously activated during fictive locomotion. The mGluR antagonist CPCCOEt had no effect on NMDA-, or (S)-alpha-amino-3-hydroxy-5-methyl-4-isoazolepropionic acid (AMPA)-induced depolarizations. The mGluR agonists 1S,3R-ACPD and DHPG increased the amplitude of NMDA-induced depolarizations, a mechanism which could account for the increase in burst frequency. The group III mGluR agonist L-2-amino-4-phosphonobutyric acid reduced intraspinal synaptic transmission and burst frequency.     

Cellular Interaction of Human Skin Cells towards Natural Bioink via 3D-Bioprinting Technologies for Chronic Wound: A Comprehensive Review

Skin substitutes can provide a temporary or permanent treatment option for chronic wounds. The selection of skin substitutes depends on several factors, including the type of wound and its severity. Full-thickness skin grafts (SGs) require a well-vascularised bed and sometimes will lead to contraction and scarring formation. Besides, donor sites for full-thickness skin grafts are very limited if the wound area is big, and it has been proven to have the lowest survival rate compared to thick- and thin-split thickness. Tissue engineering technology has introduced new advanced strategies since the last decades to fabricate the composite scaffold via the 3D-bioprinting approach as a tissue replacement strategy. Considering the current global donor shortage for autologous split-thickness skin graft (ASSG), skin 3D-bioprinting has emerged as a potential alternative to replace the ASSG treatment. The three-dimensional (3D)-bioprinting technique yields scaffold fabrication with the combination of biomaterials and cells to form bioinks. Thus, the essential key factor for success in 3D-bioprinting is selecting and developing suitable bioinks to maintain the mechanisms of cellular activity. This crucial stage is vital to mimic the native extracellular matrix (ECM) for the sustainability of cell viability before tissue regeneration. This comprehensive review outlined the application of the 3D-bioprinting technique to develop skin tissue regeneration. The cell viability of human skin cells, dermal fibroblasts (DFs), and keratinocytes (KCs) during in vitro testing has been further discussed prior to in vivo application. It is essential to ensure the printed tissue/organ constantly allows cellular activities, including cell proliferation rate and migration capacity. Therefore, 3D-bioprinting plays a vital role in developing a complex skin tissue structure for tissue replacement approach in future precision medicine.     

Calcium channel subtypes in lamprey sensory and motor neurons

Pharmacologically distinct calcium channels have been characterized in dissociated cutaneous sensory neurons and motoneurons of the larval lamprey spinal cord. To enable cell identification, sensory dorsal cells and motoneurons were selectively labeled with fluorescein-coupled dextran amine in the intact spinal cord in vitro before dissociation. Calcium channels present in sensory dorsal cells, motoneurons, and other spinal cord neurons were characterized with the use of whole cell voltage-clamp recordings and specific calcium channel agonist and antagonists. The results show that a transient low-voltage-activated (LVA) calcium current was present in a proportion of sensory dorsal cells but not in motoneurons, whereas high-voltage-activated (HVA) calcium currents were seen in all neurons recorded. The different components of HVA current were dissected pharmacologically and similar results were obtained for both dorsal cells and motoneurons. The N-type calcium channel antagonist omega-conotoxin-GVIA (omega-CgTx) blocked >70% of the HVA current. A large part of the omega-CgTx block was reversed after washout of the toxin. The L-type calcium channel antagonist nimodipine blocked approximately 15% of the total HVA current. The dihydropyridine agonist (+/-)-BayK 8644 markedly increased the amplitude of the calcium channel current. The BayK-potentiated current was not affected by omega-CgTx, indicating that the reversibility of the omega-CgTx effect is not due to a blockade of L-type channels. Simultaneous application of omega-CgTx and nimodipine left approximately 15% of the HVA calcium channel current, a small part of which was blocked by the P/Q-type channel antagonist omega-agatoxin-IVA. In the presence of the three antagonists, the persistent residual current (approximately 10%) was completely blocked by cadmium. Our results provide evidence for the existence of HVA calcium channels of the N, L, and P/Q types and other HVA calcium channels in lamprey sensory neurons and motoneurons. In addition, certain types of neurons express LVA calcium channels.