Search

High performance architectures depend heavily on efficient multi-level memory hierarchies to minimize the cost of accessing data. This dependence will increase with the expected increases in relative distance to main memory. There have been a number of published proposals for cache conflict-avoidance schemes. We investigate the design and performance of conflict-avoiding cache architectures based on polynomial modulus functions, which earlier research has shown to be highly effective at reducing conflict miss ratios. We examine a number of practical implementation issues and present experimental evidence to support the claim that pseudo-randomly indexed caches are both effective in performance terms and practical from an implementation viewpoint.

Scalability analysis provides information about the effectiveness of increasing the number of resources of a parallel system. Several methods have been proposed which use different approaches to provide this information. This paper presents a family of analysis methods oriented to the user. The methods in this family should assist the user in estimating the benefits when increasing the system size. The key issue in the proposal is the appropriate combination of a scaling model, which reflects the way the users utilize an increasing number of resources, and a figure of merit that the user wants to improve with the larger system. Another important element in the proposal is the approach to characterize the scalability, which enables quick visual analyses and comparisons. Finally, three concrete examples of methods belonging to the proposed family are introduced in this paper.

Software pipelining is a loop scheduling technique that extracts parallelism from loops by overlapping the execution of several consecutive iterations. Most prior scheduling research has focused on achieving minimum execution time, without regarding register requirements. Most strategies tend to stretch operand lifetimes because they schedule some operations too early or too late. The paper presents a novel strategy that simultaneously schedules some operations late and other operations early, minimizing all the stretchable dependencies and therefore reducing the registers required by the loop. The key of this strategy is a pre-ordering that selects the order in which the operations will be scheduled. The results show that the method described in this paper performs better than other heuristic methods and almost as well as a linear programming method but requiring much less time to produce the schedules.

This paper presents a novel parallel implementation of Prolog. The system is based on Multipath, a novel execution model for Prolog that implements a partial breadth-first search of the SLD-tree. The paper focusses on the type of parallelism inherent to the execution model, which is called path parallelism. This is a particular case of data parallelism that can be efficiently exploited in a SPMD architecture. A SPMD architecture oriented to the Multipath execution model is presented. A simulator of such system has been developed and used to assess the performance of path parallelism. Performance figures show that path parallelism is effective for non-deterministic programs.

A mechanism to reduce the cost of branches in pipelined processors is described and evaluated. It is based on the use of multiple prefetch, early computation of the target address, delayed branch, and parallel execution of branches. The implementation of this mechanism using a branch target instruction memory is described. An analytical model of the performance of this implementation makes it possible to measure the efficiency of the mechanism with a very low computational cost. The model is used to determine the size of cache lines that maximizes the processor performance, to compare the performance of the mechanism with that of other schemes, and to analyze the performance of the mechanism with two alternative cache organizations.

Many parallel algorithms use hypercubes as the communication topology among processes, which make them suitable to be executed on a hypercube multicomputer. In this way the communication cost is kept to a minimum since processes can be allocated to processors in such a way that only communication between neighbor processors is required. However, the scalability of hypercube multicomputer is constrained by the fact that the interconnection cost per node increases with the total number of nodes. From the point of view of scalability, meshes and toruses are a more interesting class of interconnection topologies. In this paper the authors propose an embedding of hypercubes onto toruses of any given dimension, incuding one-dimensional toruses which are also called rings. They also prove that the embedding is optimal in the sense that it minimizes the execution time on a ring of a class of parallel algorithms frequently found in real applications, such as FFT and some class of sorting algorithms.

The dependence of the characteristics of the light curves of Type Ia supernovae on the ignition density of the progenitor white dwarf is studied with the aid of two models of propagation of the thermonuclear burning front: as a deflagration and as a delayed detonation. The light curve is computed from opacities which take into account the velocity gradients. The results show that in all cases the resulting light curves roughly agree with observations and that they are not sensitive to the ignition density of the white dwarf. Only the model corresponding to a deflagration starting at a density of 8 x 10 exp 9 g/cu cm shows a deviation from the general behavior, having a significantly lower luminosity at maximum. A dispersion of about 1000 km/s is found in the computed expansion velocities at maximum, which compares well with that found in the observations.

Automatic Speech Recognition (ASR) has experienced a dramatic evolution since pioneer development of Bell Lab’s single-digit recognizer more than 50 years ago. Current ASR systems have taken advantage of the tremendous improvements in AI during the past decade by incorporating Deep Neural Networks into the system and pushing their accuracy to levels comparable to that of humans. This article describes and characterizes a representative ASR system with state-of-the-art accuracy and proposes a hardware platform capable of decoding speech in real-time with a power dissipation close to 1 Watt. The software is based on the so-called hybrid approach with a vocabulary of 200K words and RNN-based language model re-scoring, whereas the hardware consists of a commercially available low-power processor along with two accelerators used for the most compute-intensive tasks. The article shows that high performance can be obtained with very low power, enabling the deployment of these systems in extremely power-constrained environments such as mobile and IoT devices. This work has been supported by the CoCoUnit ERC Advanced Grant of the EU’s Horizon 2020 program (grant No. 833057), the Spanish State Research Agency under grant TIN2016-75344-R (AEI/FEDER, EU), the ICREA Academia program, and the Spanish MICINN Ministry under grant BES-2017-080605.

This work was funded by the Ministry of Education CAICYT under contract Number 314-85 The execution of branch instructions involves a loss of performance in pipelined processors. In this paper we present a mechanism for executing this kind of instruction with a zero delay. This mechanism has been proposed for architectures without condition codes.

Register windows is an architectural technique that reduces memory operations required to save and restore registers across procedure calls. Its effectiveness depends on the size of the register file. Such register requirements are normally increased for out-of-order execution because it requires registers for the in-flight instructions, in addition to the architectural ones. However, a large register file has an important cost in terms of area and power and may even affect the cycle time. In this paper we propose two early register release techniques that leverages register windows to drastically reduce the register requirements, and hence reduce the register file cost. Contrary to the common belief that out-of-order processors with register windows would need a large physical register file, this paper shows that the physical register file size may be reduced to the bare minimum by using this novel microarchitecture. Moreover, our proposal has much lower hardware complexity than previous approaches, and requires minimal changes to a conventional register window scheme. Performance studies show that the proposed technique can reduce the number of physical registers to the same number as logical registers plus one (minimum number to guarantee forward progress) and still achieve almost the same performance as an unbounded register file.

In this paper we show that value prediction can be used to avoid the penalty of long wire delays by predicting the data that is communicated through these long wires and validating the prediction locally where the value is produced. Only in the case of misprediction, the long wire delay is experienced. We apply this concept to a clustered microarchitecture in order to reduce inter-cluster communication. The predictability of values provides the dynamic instruction partitioning hardware with less constraints to optimize the trade-off between communication requirements and workload balance, which is the most critical issue of the partitioning scheme. We show that value prediction reduces the penalties caused by inter-cluster communication by 18% on average for a realistic implementation of a 4-cluster microarchitecture.

In this paper, we propose a dynamically tunable fine-grain body biasing mechanism to reduce active & standby leakage power in caches under process variations.

The final publication is available at ACM via http://dx.doi.org/10.1145/3352460.3358309 Recurrent Neural Networks (RNNs) are a key technology for applications such as automatic speech recognition or machine translation. Unlike conventional feed-forward DNNs, RNNs remember past information to improve the accuracy of future predictions and, therefore, they are very effective for sequence processing problems. For each application run, each recurrent layer is executed many times for processing a potentially large sequence of inputs (words, images, audio frames, etc.). In this paper, we make the observation that the output of a neuron exhibits small changes in consecutive invocations. We exploit this property to build a neuron-level fuzzy memoization scheme, which dynamically caches the output of each neuron and reuses it whenever it is predicted that the current output will be similar to a previously computed result, avoiding in this way the output computations. The main challenge in this scheme is determining whether the new neuron's output for the current input in the sequence will be similar to a recently computed result. To this end, we extend the recurrent layer with a much simpler Bitwise Neural Network (BNN), and show that the BNN and RNN outputs are highly correlated: if two BNN outputs are very similar, the corresponding outputs in the original RNN layer are likely to exhibit negligible changes. The BNN provides a low-cost and effective mechanism for deciding when fuzzy memoization can be applied with a small impact on accuracy. We evaluate our memoization scheme on top of a state-of-the-art accelerator for RNNs, for a variety of different neural networks from multiple application domains. We show that our technique avoids more than 24.2% of computations, resulting in 18.5% energy savings and 1.35x speedup on average.

Instruction-based or software-based self-testing (SBST) is a scalable functional testing paradigm that has gained increasing acceptance in testing of single-threaded uniprocessors. Recent computer architecture trends towards chip multiprocessing and multithreading have raised new challenges in the test process. In this paper, we present a novel self-test optimization strategy for multithreaded, multicore microprocessor architectures and apply it to both manufacturing testing (execution from on-chip cache memory) and post-silicon validation (execution from main memory) setups. The proposed self-test program execution optimization aims to: (a) take maximum advantage of the available execution parallelism provided by multiple threads and multiple cores, (b) preserve the high fault coverage that single-thread execution provides for the processor components, and (c) enhance the fault coverage of the thread-specific control logic of the multithreaded multiprocessor. The proposed multithreaded (MT) SBST methodology generates an efficient multithreaded version of the test program and schedules the resulting test threads into the hardware threads of the processor to reduce the overall test execution time and on the same time to increase the overall fault coverage. We demonstrate our methodology in the OpenSPARC T1 processor model which integrates eight CPU cores, each one supporting four hardware threads. MT-SBST methodology and scheduling algorithm significantly speeds up self-test time at both the core level (3.6 times) and the processor level (6.0 times) against single-threaded execution, while at the same time it improves the overall fault coverage. Compared with straightforward multithreaded execution, it reduces the self-test time at both the core level and the processor level by 33% and 20%, respectively. Overall, MT-SBST reaches more than 91% stuck-at fault coverage for the functional units and 88% for the entire chip multiprocessor, a total of more than 1.5M logic gates.

Clustered microarchitectures provide a promising paradigm to solve or alleviate the problems of increasing microprocessor complexity and wire delays. High- performance out-of-order processors rely on hardware-only steering mechanisms to achieve balanced workload distribution among clusters. However, the additional steering logic results in a significant increase on complexity, which actually decreases the benefits of the clustered design. In this paper, we address this complexity issue and present a novel software-hardware hybrid steering mechanism for out-of-order processors. The proposed software- hardware cooperative scheme makes use of the concept of virtual clusters. Instructions are distributed to virtual clusters at compile time using static properties of the program such as data dependences. Then, at runtime, virtual clusters are mapped into physical clusters by considering workload information. Experiments using SPEC CPU2000 benchmarks show that our hybrid approach can achieve almost the same performance as a state-of-the-art hardware-only steering scheme, while requiring low hardware complexity. In addition, the proposed mechanism outperforms state-of-the-art software-only steering mechanisms by 5% and 10% on average for 2-cluster and 4-cluster machines, respectively.

Estimating extremely low SRAM failure-probabilities by conventional Monte Carlo (MC) approach requires hundreds-of-thousands simulations making it an impractical approach. To alleviate this problem, failure-probability estimation methods with a smaller number of simulations have recently been proposed, most notably variants of consecutive mean-shift based Importance Sampling (IS). In this method, a large amount of time is spent simulating data points that will eventually be discarded in favor of other data-points with minimum norm. This can potentially increase the simulation time by orders of magnitude. To solve this very important limitation, in this paper, we introduce SSFB: A novel SRAM failure-probability estimation method that has much better cognizance of the data points compared to conventional approaches. The proposed method starts with radial simulation of a single point and reduces discarded simulations by: a) random sampling-only-when it reaches a failure boundary and after that continues again with radial simulation of a chosen point, and b) random sampling is performed-only-within a specific failure-range which decreases in each iteration. The proposed method is also scalable to higher dimensions (more input variables) as sampling is done on the surface of the hyper-sphere, rather than within-the-hypersphere as other techniques do. Our results show that using our method we can achieve an overall 40x reduction in simulations compared to consecutive mean-shift IS methods while remaining within the 0.01-Sigma accuracy. © 2014 EDAA.

This study focuses on the importance of quantifying the effect of prefetching on the interconnection network of a multiprocessor chip. This kind of microarchitectural effects are often quantified using simulators. However, if prefetching traffic in a CMP (Chip MultiProcessor) system is to be accurately evaluated, simulators should simulate not only the memory hierarchy module and the multicore system, but also the network-on-chip. Unfortunately, no open-source simulator is able to evaluate all these elements at the same time. This paper describes how to develop a prefetching module for the gem5 CMP simulator and how to integrate this into the Ruby memory system. Moreover, by using the infrastructure developed in this study, this paper shows the importance of taking the network effect in prefetching-related studies into account, in order for accurate results to be obtained: not doing so may lead to mistaken conclusions. For this purpose, we have carried out a detailed analysis of the behavior of three different prefetching engines, providing not only the typical statistics for instructions per cycle and the miss rate, but also specific network and prefetching statistics.

Dynamic Binary Translators and Optimizers (DBTOs) have been established as a hot research topic. They are used in many different systems, such as emulation, instrumentation tools and innovative HW/SW co-designed microarchitectures. Although many researchers worked on characterizing and reducing the emulation overhead, to the best of our knowledge, there are no published results that explain how the microarchitectural behavior of the emulation software is affected by the guest application which is emulated. In this paper we study the DBTO as an independent application, which is divided into the modules with specific functionality. We show the variance in microarchitectural behavior of DBTO among 48 applications. Moreover, we locate and explain the sources of variance. The results show that the variance is caused by interaction with the code cache (emulated application) and non uniform module execution characteristics. The insights presented in this paper can be exploited towards the design of more efficient DBTOs

This paper presents a mechanism to dynamically detect the loops that are executed in a program. This technique detects the beginning and the termination of the iterations and executions of the loops without compiler/user intervention. We propose to apply this dynamic loop detection to the speculation of multiple threads of control dynamically obtained from a sequential program. Based an the highly predictable behavior of the loops, the history of the past executed loops is used to speculate the future instruction sequence. The overall objective is to dynamically obtain coarse grain parallelism (at the thread level) that can be exploited by a multithreaded architecture. We show that for a 4-context multithreaded processor the speculation mechanism provides around 2.6 concurrent threads in average.

With chip temperature being a major hurdle in microprocessor design, techniques to recover the performance loss due to thermal emergency mechanisms are crucial in order to sustain performance growth. Many techniques for power reduction in the past and some on thermal management more recently have contributed to alleviate this problem. Probably the most important thermal control technique is dynamic voltage and frequency scaling (DVS) which allows for almost cubic reduction in power with worst-case performance penalty only linear. So far, DVS techniques for temperature control have been studied at the chip level. Finer grain DVS is feasible if a globally-asynchronous locally-synchronous (GALS) design style is employed. GALS, also known as multiple-clock domain (MCD), allows for an independent voltage and frequency control for each one of the clock domains that are part of the chip. There are several studies on DVS for GALS that aim to improve energy and power efficiency but not temperature. This paper proposes and analyses the usage of DVS at the domain level to control temperature in a clustered MCD microarchitecture with the goal of improving the performance of applications that do not meet the thermal constraints imposed by the designers.

In this paper, we provide an insight on the different proactive read/write assist methods (wordline boosting & adaptive body biasing) that help in preventing (and reducing) parametric failures when coupled with reactive techniques like ECC and redundancy which cope with already existent failures. While proactive and reactive have been previously viewed as complementary techniques, we show that it is not necessarily the case when considering the benefits of such hybrid schemes.

In this paper, we take a MIPS-based open-source uniprocessor soft core, Plasma, and extend it to obtain the Beefarm infrastructure for FPGA-based multiprocessor emulation, a popular research topic of the last few years both in the FPGA and the computer architecture communities. We discuss various design tradeo s and we demonstrate superior scalability through experimental results compared to traditional software instruction set simulators. Based on our experience of designing and building a complete FPGA-based multiprocessor emulation system that supports runtime and compiler infrastructure and on the actual executions of our experiments running Software Transactional Memory (STM) benchmarks, we comment on the pros, cons and future trends of using hardware-based emulation for research.

The number of physical registers is one of the critical issues of current superscalar out-of-order processors. Conventional architectures allocate, in the decoding stage, a new storage location (e.g. a physical register) for each operation that has a destination register. When an instruction is committed, it frees the physical register allocated to the previous instruction that had the same destination logical register. Thus, an additional register (i.e. in addition to the number of logical registers) is used for each instruction with a destination register from the time it is decoded until it is committed. In this paper, we propose a novel register organization that allocates physical registers when instructions complete their execution. In this way, the register pressure is significantly reduced, since the additional register is only used from the time execution completes until the instruction is committed. For some long-latency instructions (e.g. load with a cache miss) and for parts of the code with a small amount of parallelism, the savings could be very high. We have evaluated the new scheme for a superscalar processor and obtained a significant speedup.

This paper presents a tool based on a new approach for analyzing the locality exhibited by data memory references. The tool is very fast because it is based on a static locality analysis enhanced with very simple profiling information, which results in a negligible slowdown. This feature allows the tool to be used for highly time-consuming applications and to include it as a step in a typical iterative analysis-optimization process. The tool can provide a detailed evaluation of the reuse exhibited by a program, quantifying and qualifying the different types of misses either globally or detailed by program sections, data structures, memory instructions, etc. The accuracy of the tool is validated by comparing its results with those provided by a simulator.

The document is part of deliverable D3.6 of the TRAMS Project (EU FP7 248789), of public nature, and shows and justifies the levels of variability used in the research project for sub-18nm bulk CMOS technologies.

Wire delays are a major concern for current and forthcoming processors. One approach to deal with this problem is to divide the processor into semi-independent units referred to as clusters. A cluster usually consists of a local register file and a subset of the functional units, while the L1 data cache typically remains centralized in What we call partially distributed architectures. However, as technology evolves, the relative latency of such a centralized cache will increase, leading to an important impact on performance. In this paper, we propose partitioning the L1 data cache among clusters for clustered VLIW processors. We refer to this kind of design as fully distributed processors. In particular; we propose and evaluate three different configurations: a snoop-based cache coherence scheme, a word-interleaved cache, and flexible LO-buffers managed by the compiler. For each alternative, instruction scheduling techniques targeted to cyclic code are developed. Results for the Mediabench suite'show that the performance of such fully distributed architectures is always better than the performance of a partially distributed one with the same amount of resources. In addition, the key aspects of each fully distributed configuration are explored.

Intrusion Detection Systems (IDS) have emerged as one of the most promising ways to secure systems in the network. To be effective against evasion attempts, the IDS must provide tight bounds on performance. Otherwise an adversary can bypass the IDS by carefully crafting and sending packets that throttle it. This can render the IDS ineffective, thus resulting in the network becoming vulnerable. We present a performance throttling attack mounted against the computationally intensive string matching algorithm. This algorithm performs string matching by traversing a finite-state-machine (FSM). We observe that there are some input bytes that sequentially traverse a chain of 30 pointers. This chain of traversal drastically degrades performance, and we observe a 22X performance drop in comparison to the average case performance. We investigate hardware and software mechanisms to counter this performance degradation. The software mechanism is targeted for commodity general purpose CPUs. While the hardware-based mechanism uses a parallel traversal suitable for network processor architectures. Our results show that our proposed mechanisms significantly improves (by over 3X magnitude) string matching algorithm’s worst performing cases.

Aggressive voltage scaling needed for low power in each new process generation causes large deviations in the threshold voltage of minimally sized devices of the 6T SRAM cell. Gate oxide scaling can cause large transient gate leakage (a trap in the gate oxide), which is known as the erratic bits phenomena. Register file protection is necessary to prevent errors from quickly spreading to different parts of the system, which may cause applications to crash or silent data corruption. This paper proposes a simple and cost-effective mechanism that increases the resiliency of the register files to erratic bits. Our mechanism detects those registers that have erratic bits, recovers from the error and quarantines the faulty register. After the quarantine period, it is able to detect whether they are fully operational with low overhead.

The speculative multithreading paradigm (speculative thread-level parallelism) is based on the concurrent execution of control-speculative threads. The efficiency of microarchitectures that adopt this paradigm strongly depends on the performance of the control and data speculation techniques. While control speculation is used to predict the most effective points where a thread can be spawned, data speculation is required to eliminate the serialization imposed by inter-thread dependences. This work studies the performance of different value predictors for speculative multithreaded processors. We propose a value predictor, the increment predictor, and evaluate its performance for a particular microarchitecture that implements this execution paradigm (Clustered Speculative Multithreaded architecture). The proposed trace-oriented increment predictor clearly outperforms trace-adapted versions of the last value, stride and context-based predictors, specially for small-sized history tables. A 1-KB increment predictor achieves a 73% prediction accuracy and a performance that is just 13% lower than that of a perfect value predictor.

The growing influence of wire delay in cache design has meant that access latencies to last-level cache banks are no longer constant. Non-Uniform Cache Architectures (NUCAs)have been proposed to address this problem. Furthermore, an efficient last-level cache is crucial in chip multiprocessors (CMP) architectures to reduce requests to the offchip memory, because of the significant speed gap between processor and memory and the limited memory bandwidth. Therefore, a bank replacement policy that efficiently manages the NUCA cache is desirable. However, the decentralized nature of NUCA has prevented previously proposed replacement policies from being effective in this kind of caches. As banks operate independently of each other, their replacement decisions are restricted to a single NUCA bank. We propose a novel mechanism based on the bank replacement policy for NUCA caches on CMP, called The Auction. This mechanism enables the replacement decisions taken in a single bank to be spread to the whole NUCA cache. Thus, global replacement policies that rely on the current state of the NUCA cache, such as evicting the least frequently accessed data in the whole NUCA cache, are now feasible. Moreover, The Auction adapts to current program behaviour in order to relocate a line that is being evicted from a bank in the NUCA cache to the most suitable position in the whole cache. We propose, implement and evaluate three approaches of The Auction mechanism.We also show that The Auction manages the cache efficiently and significantly reduces the requests to the off-chip memory by increasing the hit ratio in the NUCA cache. This translates into an average IPC improvement of 8%, and reduces energy consumed by the memory system by 4%.

This paper presents a novel software pipelining approach, which is called Swing Modulo Scheduling (SMS). It generates schedules that are near optimal in terms of initiation interval, register requirements and stage count. Swing Modulo Scheduling is an heuristic approach that has a low computational cost. The paper describes the technique and evaluates it for the Perfect Club benchmark suite. SMS is compared with other heuristic methods showing that it outperforms them in terms of the quality of the obtained schedules and compilation time. SMS is also compared with an integer linear programming approach that generates optimum schedules but with a huge computational cost, which makes it feasible only for very small loops. For a set of small loops, SMS obtained the optimum initiation interval in all the cases and its schedules required only 5% more registers and a 1% higher stage count than the optimum

The increasing hardware complexity of dynamically scheduled superscalar processors may compromise the scalability of this organization to make an efficient use of future increases in transistor budget. SMT processors, designed over a superscalar core, are therefore directly concerned by this problem. The article presents and evaluates a novel processor microarchitecture which combines two paradigms: simultaneous multithreading and access/execute decoupling. Since its decoupled units issue instructions in order, this architecture is significantly less complex, in terms of critical path delays, than a centralized out-of-order design, and it is more effective for future growth in issue-width and clock speed. We investigate how both techniques complement each other. Since decoupling features an excellent memory latency hiding efficiency, the large amount of parallelism exploited by multithreading may be used to hide the latency of functional units and keep them fully utilized. The study shows that, by adding decoupling to a multithreaded architecture, fewer threads are needed to achieve maximum throughput. Therefore, in addition to the obvious hardware complexity reduction, it places lower demands on the memory system. The study also reveals that multithreading by itself exhibits little memory latency tolerance. Results suggest that most of the latency hiding effectiveness of SMT architectures comes from the dynamic scheduling. On the other hand, decoupling is very effective at hiding memory latency. An increase in the cache miss penalty from 1 to 32 cycles reduces the performance of a 4-context multithreaded decoupled processor by less than 2 percent. For the nondecoupled multithreaded processor, the loss of performance is about 23 percent.

Time-to-market is a critical issue for nowadays integrated circuits manufacturers. In this paper the Via-Configurable Transistor Array regular layout fabric (VCTA), which aims to minimize the time-to-market and its associated costs, is studied for a Delay-Locked Loop design (DLL). The comparison with a full custom design demonstrates that VCTA can be used without loss of functionality while accelerating the design time. Layout implementations, in 90 nm CMOS process, as well as the delay, energy and jitter electrical simulations are provided.

Process variations are a major bottleneck for digital CMOS integrated circuits manufacturability and yield. That is why regular techniques with different degrees of regularity are emerging as possible solutions. Our proposal is a new regular layout design technique called Via-Configurable Transistors Array (VCTA) that pushes to the limit circuit layout regularity for devices and interconnects in order to maximize regularity benefits. VCTA is predicted to perform worse than the Standard Cell approach designs for a certain technology node but it will allow the use of a future technology on an earlier time. Our objective is to optimize VCTA for it to be comparable to the Standard Cell design in an older technology. Simulations for the first unoptimized version of our VCTA of delay and energy consumption for a Full Adder circuit in the 90 nm technology node are presented and also the extrapolation for Carry-Ripple Adders from 4 bits to 64 bits.

Clustered microarchitectures are an effective approach to reducing the penalties caused by wire delays inside a chip. Current superscalar processors have in fact a two-cluster microarchitecture with a naive code partitioning approach: integer instructions are allocated to one cluster and floating-point instructions to the other. This partitioning scheme is simple and results in no communications between the two clusters (just through memory) but it is in general far from optimal because she workload is not evenly distributed most of the time. In fact, when the processor is running integer programs, the workload is extremely unbalanced since the FP cluster is not used at all. In this work we investigate run-time mechanisms that dynamically distribute the instructions of a program among these two clusters. By optimizing the trade-off between inter-cluster communication penalty and workload balance, the proposed schemes can achieve an average speed-up of 36% for the SpecInt95 benchmark suite.

We investigate some power efficient data cache designs that try to significantly reduce the cache energy consumption, both static and dynamic, with a minimal impact in performance. The basic idea is to combine different threshold voltages with different cache organizations that provide different levels of performance. Multibanked organizations in combination with different approaches to allocate data to cache banks are explored. Some of the resulting cache architectures are shown to provide a good tradeoff between power and performance.

Caches have become increasingly important with the widening gap between main memory and processor speeds. Small and fast cache memories are designed to bridge this discrepancy. However, they are only effective when programs exhibit sufficient data locality. Performance of memory hierarchy can be improved by means of data and loop transformations. Tiling is a loop transformation that aims at reducing capacity misses by exploiting reuse at the lower levels of cache. Padding is a data transformation targeted to reduce conflict misses. We present an accurate cost model which makes use of the cache miss equations (CMEs) to guide tiling and padding transformations. It describes misses across different hierarchy levels and considers the effects of other hardware components such as branch predictors. We combine the cost model with a genetic algorithm (GA) to select the tile and pad factors that enhance the program. Our results show that this scheme is useful to optimize programs' performance. When compared to previous works, we observe that with a reasonable compile-time overhead, our approach obtains significant performance improvements for all studied kernels on a variety of architectures.

In this paper, we propose a novel programmable functional unit (PFU) to accelerate general purpose application execution on a modern out-of-order x86 processor in a complexity-effective way. Code is transformed and instructions are generated that run on the PFU using a co-designed virtual machine (Cd-VM). Groups of frequently executed micro-operations (micro-ops) are identified and fused into a macro-op (MOP) by the Cd-VM. The MOPs are executed on PFU. Results presented in this paper show that this HW/SW co-designed approach produces average speedups in performance of 17% in SPECFP and 10% in SPECINT, and up-to 33%, over modern out-of-order processor. Moreover, we also show that the proposed scheme not only out-performs dynamic vectorization using SIMD accelerators but also outperforms an 8-wide issue out-of-order processor.

As technology evolves, power density significantly increases and cooling systems become more complex and expensive. The issue logic is one of the processor hotspots and, at the same time, its latency is crucial for the processor performance. We present a low-complexity FP issue logic (MB/spl I.bar/distr) that achieves high performance with small energy requirements. The MB/spl I.bar/distr scheme is based on classifying instructions and dispatching them into a set of queues depending on their data dependences. These instructions are selected for issuing based on an estimation of when their operands will be available, so the conventional wakeup activity is not required. Additionally, the functional units are distributed across the different queues. The energy required by the proposed scheme is substantially lower than that required by a conventional issue design, even if the latter has the ability of waking-up only unready operands. MB/spl I.bar/distr scheme reduces the energy-delay product by 35% and the energy-delay product by 18% with respect to a state-of-the-art approach.

3T1D cell has been stated as a valid alternative to be implemented on L1 memory cache to substitute 6T, highly affected by device variability as technology dimensions are reduced. In this work, we have shown that 22 nm 3T1D memory cells present significant tolerance to high levels of device parameter fluctuation. Moreover, we have observed that when variability is considered the write access transistor becomes a significant detrimental element on the 3T1D cell performance. Furthermore, resizing and temperature control have been presented as some valid strategies in order to mitigate the 3T1D cell variability.

Transistors per area unit double in every new technology node. However, the electric field density and power demand grow if Vcc is not scaled. Therefore, Vcc must be scaled in pace with new technology nodes to prevent excessive degradation and keep power demand within reasonable limits. Unfortunately, low Vcc operation exacerbates the effect of variations and decreases noise and stability margins, increasing the likelihood of errors in SRAM memories such as caches. Those errors translate into performance loss and performance variation across different cores, which is especially undesirable in a multi-core processor. This paper presents (i) a novel scheme to tolerate high faulty bit rates in caches by disabling only faulty subblocks, (ii) a dynamic address remapping scheme to reduce performance variation across different cores, which is key for performance predictability, and (iii) a comparison with state-of-the-art techniques for faulty bit tolerance in caches. Results for some typical first level data cache configurations show 15% average performance increase and standard deviation reduction from 3.13% down to 0.55% when compared to cache line disabling schemes.

Clustering is an approach that many microprocessors are adopting in recent times in order to mitigate the increasing penalties of wire delays. We propose a novel clustered VLIW architecture which has all its resources partitioned among clusters, including the cache memory. A modulo scheduling scheme for this architecture is also proposed. This algorithm takes into account both register and memory inter-cluster communications so that the final schedule results in a cluster assignment that favors cluster locality in cache references and register accesses. It has been evaluated for both 2- and 4-cluster configurations and for differing numbers and latencies of inter-cluster buses. The proposed algorithm produces schedules with very low communication requirements and outperforms previous cluster-oriented schedulers.

Industry is moving towards multi-core designs as we have hit the memory and power walls. Multi-core designs are very effective to exploit thread-level parallelism (TLP) but do not provide benefits when executing serial code (applications with low TLP, serial parts of a parallel application and legacy code). In this paper we propose Anaphase, a novel approach for speculative multithreading to improve single-thread performance in a multi-core design. The proposed technique is based on a graph partitioning technique which performs a decomposition of applications into speculative threads at instruction granularity. Moreover, the proposed technique leverages communications and pre-computation slices to deal with inter-thread dependences. Results presented in this paper show that this approach improves single-thread performance by 32% on average and up to 2.15x for some selected applications of the Spec2006 suite. In addition, the proposed technique outperforms by 21% on average schemes in which thread decomposition is performed at a coarser granularity.

During real-time graphics rendering, objects are processed by the GPU in the order they are submitted by the CPU, and occluded surfaces are often processed even though they will end up not being part of the final image, thus wasting precious time and energy. To help discard occluded surfaces, most current GPUs include an Early-Depth test before the fragment processing stage. However, to be effective it requires that opaque objects are processed in a front-to-back order. Depth sorting and other occlusion culling techniques at the object level incur overheads that are only offset for applications having substantial depth and/or fragment shading complexity, which is often not the case in mobile workloads. We propose a novel architectural technique for mobile GPUs, Visibility Rendering Order (VRO), which reorders objects front-to-back entirely in hardware by exploiting the fact that the objects in graphics animated applications tend to keep its relative depth order across consecutive frames (temporal coherence). Since order relationships are already tested by the Depth Test, VRO incurs minimal energy overheads because it just requires adding a small hardware to capture that information and use it later to guide the rendering of the following frame. Moreover, unlike other approaches, this unit works in parallel with the graphics pipeline without any performance overhead. We illustrate the benefits of VRO using various unmodified commercial 3D applications for which VRO achieves 27% speed-up and 14.8% energy reduction on average over a state-of-the-art mobile GPU.

System reliability has become a key design aspect for computer systems due to the aggressive technology miniaturization. Errors are typically dominated by transient faults due to radiation and are strongly related to the technology used to build hardware. However, there is a lack of detailed methodologies to model and fairly compare Soft Error Rates (SER) across different advanced technologies. This work first describes a common methodology that from (1) technology models, (2) location (latitude, longitude and altitude), (3) operating conditions and (4) circuit descriptions (i.e. SRAM, latches, logic gates) can obtain accurate Soft Error Rates. Then, we use it to characterize soft errors through current and future technologies. Results at the technology layer show that new technologies, such as FinFET and SOI, can reduce SER up to 100x while the location can increase SER up to 650x. © 2016 EDAA. This work has been partially supported by the Spanish Ministry of Education and Science under grant TIN2013-44375-R and the FP7 program of the EU under contract FP7-611404 (CLERECO). Jaume Abella has been partially supported by the Ministry of Economy and Competitiveness under Ramon y Cajal postdoctoral fellowship number RYC-2013-14717.

The thermonuclear explosion of a mass-accreting white dwarf in a close binary system is thought to be at the origin of Type Ia supernovae. Standard models, which ignite carbon at densities higher than 2-4 x 10 exp 9 g/cu cm, give, however, a large production of species like Fe-54, Ni-58, and Cr-54, which has been regarded as incompatible with the solar system abundances. In this paper we analyze the weight of the constraints imposed by nucleosynthesis of the Fe-peak nuclides to the aforementioned scenario for Type Ia supernovae when the contribution of Type II and Type Ib supernovae to the galactic iron abundances is also taken into account. We find that the production of the aforementioned nuclides predicted by standard SNIa models is in fact compatible with the solar system abundances when the yields from gravitational-collapse supernovae are adjusted to reproduce the Ni abundances in low-metallicity stars.

© 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes,creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. In this work, we propose Locality-AWare-Scheme (LAWS) for an Automatic Speech Recognition (ASR) accelerator in order to significantly reduce its energy consumption and memory requirements, by leveraging the locality among consecutive segments of the speech signal. LAWS diminishes ASR's workload by up to 60% by removing most of the off-chip accesses during the ASR's decoding process. We furthermore improve LAWS's effectiveness by selectively adapting the amount of ASR's workload, based on run-time feedback. In particular, we exploit the fact that the confidence of the ASR system varies along the recognition process. When confidence is high, the ASR system can be more restrictive and reduce the amount of work. The end design provides a saving of 87% in memory requests, 2.3x reduction in energy consumption, and a speedup of 2.1x with respect to the state-of-the-art ASR accelerator.

Wire delays are a major concern for current and forthcoming processors. One approach to attack this problem is to divide the processor into semi-independent units referred to as clusters. A cluster usually consists of a local register file and a subset of the functional units, while the data cache remains centralized. However, as technology evolves, the latency of such a centralized cache increase leading to an important performance impact. In this paper, we propose to include flexible low-latency buffers in each cluster in order to reduce the performance impact of higher cache latencies. The reduced number of entries in each buffer permits the design of flexible ways to map data from L1 to these buffers. The proposed L0 buffers are managed by the compiler, which is responsible to decide which memory instructions make us of them. Effective instruction scheduling techniques are proposed to generate code that exploits these buffers. Results for the Mediabench benchmark suite show that the performance of a clustered VLIW processor with a unified L1 data cache is improved by 16% when such buffers are used. In addition, the proposed architecture also shows significant advantages over both MultiVLIW processors and clustered processors with a word-interleaved cache, two state-of-the-art designs with a distributed L1 data cache.

Modern microprocessors are increasingly power-constrained as a result of slowed supply voltage scaling (end of Dennard scaling) in conjunction with the transistor density scaling (Moore's Law). Existing many-core power management techniques such as chip-wide/per-core DVFS, and core and cache adaptation are quite effective in isolation at moderate to high power budgets. However, for future many-core chip, the existing techniques do not scale well to large core counts, small time slices and stringent power budgets. We need a new solution that combines different adaptation and reconfiguration techniques. In this paper, we present Chrysso, an integrated, scalable and low-overhead power management framework. Chrysso consists of a three-step process: leveraging simple analytical performance and power models, pruning the search space early using local Pareto front generation, followed by global utility-based power allocation. This ensures scalable and effective dynamic adaptation of many-core processors at short time scales along multiple axes, including core, cache and per-core DVFS adaptations. By integrating multiple power management techniques into a common methodology, Chrysso provides significant performance improvements over isolated mechanisms within a given power budget without power-gating cores. On a 64-core system, Chrysso improves system throughput by 1.6× and 1.9× over core-gating at stringent power envelops for multi-program (SPEC) and multi-threaded (PARSEC) workloads, respectively.

Accurate, real-time Automatic Speech Recognition (ASR) comes at a high energy cost, so accuracy has often to be sacrificed in order to fit the strict power constraints of mobile systems. However, accuracy is extremely important for the end-user, and today's systems are still unsatisfactory for many applications. The most critical component of an ASR system is the acoustic scoring, as it has a large impact on the accuracy of the system and takes up the bulk of execution time. The vast majority of ASR systems implement the acoustic scoring by means of Gaussian Mixture Models (GMMs), where the acoustic scores are obtained by evaluating multidimensional Gaussian distributions.In this paper, we propose a hardware accelerator for GMM evaluation that reduces the energy required for acoustic scoring by three orders of magnitude compared to solutions based on CPUs and GPUs. Our accelerator implements a lazy evaluation scheme where Gaussians are computed on demand, avoiding 50% of the computations. Furthermore, it employs a novel clustering scheme to reduce the size of the acoustic model, which results in 8x memory bandwidth savings with a negligible impact on accuracy. Finally, it includes a novel memoization scheme that avoids 74.88% of floating-point operations. The end design provides a 164x speedup and 3532x energy reduction when compared with a highly-tuned implementation running on a modern mobile CPU. Compared to a state-of-the-art mobile GPU, the GMM accelerator achieves 5.89x speedup over a highly optimized CUDA implementation, while reducing energy by 241x.