Author(s): Asanovic, K; Bodik, R; Catanzaro, B; Gebis, J; Husbands, P; Keutzer, K; Patterson, D; Plishker, W; Shalf, J; Williams, SW | Abstract: The recent switch to parallel microprocessors is a milestone in the history of computing. Industry has laid out a roadmap for multicore designs that preserves the programming paradigm of the past via binary compatibility and cache coherence. Conventional wisdom is now to double the number of cores on a chip with each silicon generation. A multidisciplinary group of Berkeley researchers met nearly two years to discuss this change. Our view is that this evolutionary approach to parallel hardware and software may work from 2 or 8 processor systems, but is likely to face diminishing returns as 16 and 32 processor systems are realized, just as returns fell with greater instruction-level parallelism. We believe that much can be learned by examining the success of parallelism at the extremes of the computing spectrum, namely embedded computing and high performance computing. This led us to frame the parallel landscape with seven questions, and to recommend the following: • The overarching goal should be to make it easy to write programs that execute efficiently on highly parallel computing systems • The target should be 1000s of cores per chip, as these chips are built from processing elements that are the most efficient in MIPS (Million Instructions per Second) per watt, MIPS per area of silicon, and MIPS per development dollar. • Instead of traditional benchmarks, use 13 “Dwarfs” to design and evaluate parallel programming models and architectures. (A dwarf is an algorithmic method that captures a pattern of computation and communication.) • “Autotuners” should play a larger role than conventional compilers in translating parallel programs. • To maximize programmer productivity, future programming models must be more human-centric than the conventional focus on hardware or applications. • To be successful, programming models should be independent of the number of processors. • To maximize application efficiency, programming models should support a wide range of data types and successful models of parallelism: task-level parallelism, word-level parallelism, and bit-level parallelism. 1 The Landscape of Parallel Computing Research: A View From Berkeley • Architects should not include features that significantly affect performance or energy if programmers cannot accurately measure their impact via performance counters and energy counters. • Traditional operating systems will be deconstructed and operating system functionality will be orchestrated using libraries and virtual machines. • To explore the design space rapidly, use system emulators based on Field Programmable Gate Arrays (FPGAs) that are highly scalable and low cost. Since real world applications are naturally parallel and hardware is naturally parallel, what we need is a programming model, system software, and a supporting architecture that are naturally parallel. Researchers have the rare opportunity to re-invent these cornerstones of computing, provided they simplify the efficient programming of highly parallel systems.

/pdf/the-landscape-of-parallel-computing-research-a-view-from-1i5pswggnf.pdf

The Landscape of Parallel Computing Research: A View from Berkeley

Concern about the performance of wires wires in scaled technologies has led to research exploring other communication methods. This paper examines wire and gate delays as technologies migrate from 0.18-/spl mu/m to 0.035-/spl mu/m feature sizes to better understand the magnitude of the the wiring problem. Wires that shorten in length as technologies scale have delays that either track gate delays or grow slowly relative to gate delays. This result is good news since these "local" wires dominate chip wiring. Despite this scaling of local wire performance, computer-aided design (CAD) tools must still become move sophisticated in dealing with these wires. Under scaling, the total number of wires grows exponentially, so CAD tools will need to handle an ever-growing percentage of all the wires in order to keep designer workloads constant. Global wires present a more serious problem to designers. These are wires that do not scale in length since they communicate signals across the chip. The delay of these wives will remain constant if repeaters are used meaning that relative to gate delays, their delays scale upwards. These increased delays for global communication will drive architectures toward modular designs with explicit global latency mechanisms.

The future of wires

We characterize high-performance streaming applications as a new and distinct domain of programs that is becoming increasingly important. The StreamIt language provides novel high-level representations to improve programmer productivity and program robustness within the streaming domain. At the same time, the StreamIt compiler aims to improve the performance of streaming applications via stream-specific analyses and optimizations. In this paper, we motivate, describe and justify the language features of StreamIt, which include: a structured model of streams, a messaging system for control, a re-initialization mechanism, and a natural textual syntax.

/pdf/streamit-a-language-for-streaming-applications-il2k3rjwwy.pdf

StreamIt: A Language for Streaming Applications

On-chip caches represent a sizable fraction of the total power consumption of microprocessors. Although large caches can significantly improve performance, they have the potential to increase power consumption. As feature sizes shrink, the dominant component of this power loss will be leakage. However, during a fixed period of time the activity in a cache is only centered on a small subset of the lines. This behavior can be exploited to cut the leakage power of large caches by putting the cold cache lines into a state preserving, low-power drowsy mode. Moving lines into and out of drowsy state incurs a slight performance loss. In this paper we investigate policies and circuit techniques for implementing drowsy caches. We show that with simple architectural techniques, about 80%-90% of the cache lines can be maintained in a drowsy state without affecting performance by more than 1%. According to our projections, in a 0.07um CMOS process, drowsy caches will be able to reduce the total energy (static and dynamic) consumed in the caches by 50%-75%. We also argue that the use of drowsy caches can simplify the design and control of low-leakage caches, and avoid the need to completely turn off selected cache lines and lose their state.

Drowsy caches: simple techniques for reducing leakage power

Growing wire delays will force substantive changes in the designs of large caches. Traditional cache architectures assume that each level in the cache hierarchy has a single, uniform access time. Increases in on-chip communication delays will make the hit time of large on-chip caches a function of a line's physical location within the cache. Consequently, cache access times will become a continuum of latencies rather than a single discrete latency. This non-uniformity can be exploited to provide faster access to cache lines in the portions of the cache that reside closer to the processor. In this paper, we evaluate a series of cache designs that provides fast hits to multi-megabyte cache memories. We first propose physical designs for these Non-Uniform Cache Architectures (NUCAs). We extend these physical designs with logical policies that allow important data to migrate toward the processor within the same level of the cache. We show that, for multi-megabyte level-two caches, an adaptive, dynamic NUCA design achieves 1.5 times the IPC of a Uniform Cache Architecture of any size, outperforms the best static NUCA scheme by 11%, outperforms the best three-level hierarchy--while using less silicon area--by 13%, and comes within 13% of an ideal minimal hit latency solution.

/pdf/an-adaptive-non-uniform-cache-structure-for-wire-delay-1ylutc2xsf.pdf

An adaptive, non-uniform cache structure for wire-delay dominated on-chip caches

The doubling of microprocessor performance every three years has been the result of two factors: more transistors per chip and superlinear scali ng of the processor clock with technology generation. Our results show that, due to both diminishing improvements in clock rates and poor wire scaling as semiconductor devices shrink, the achievable performance growth of conventional microarchitectures will slow substantially. In this paper, we describe technology-driven models for wire capacitance, wire delay, and microarchitectural component delay. Using the results of these models, we measure the simulated performance—estimating both clock rate and IPC —of an aggressive out-of-order microarchitecture as it is scaled from a 250nm technology to a 35nm technology. We perform this analysis for three clock scaling targets and two microarchitecture scaling strategies: pipeline scaling and capacity scaling. We find that no scaling strategy permits annual performance improvements of better than 12.5%, which is far worse than the annual 50-60% to which we have grown accustomed.

/pdf/clock-rate-versus-ipc-the-end-of-the-road-for-conventional-54d15znbzi.pdf

Clock rate versus IPC: the end of the road for conventional microarchitectures

Microprocessor clock frequency has improved by nearly 40% annually over the past decade. This improvement has been provided, in equal measure, by smaller technologies and deeper pipelines. From our study of the SPEC 2000 benchmarks, we find that for a high-performance architecture implemented in 100nm technology, the optimal clock period is approximately 8 fan-out-of-four (FO4) inverter delays for integer benchmarks, comprised of 6 FO4 of useful work and an overhead of about 2 FO4. The optimal clock period for floating-point benchmarks is 6 FO4. We find these optimal points to be insensitive to latch and clock skew overheads. Our study indicates that further pipelining can at best improve performance of integer programs by a factor of 2 over current designs. At these high clock frequencies it will be difficult to design the instruction issue window to operate in a single cycle. Consequently, we propose and evaluate a high-frequency design called a segmented instruction window.

/pdf/the-optimal-logic-depth-per-pipeline-stage-is-6-to-8-fo4-3b8bnsx9kr.pdf

The optimal logic depth per pipeline stage is 6 to 8 FO4 inverter delays

Microprocessor performance has been improved by increasing the capacity of on-chip caches. However, the performance gain comes at the price of increased static energy consumption due to sub-threshold leakage current. This paper compares three techniques for reducing static energy consumption in on-chip level-1 and level-2 caches. One technique employs low-leakage transistors in the memory cell. Another technique, power supply switching can be used to turn off the memory cells and discard their contents. A third alternative is dynamic threshold modulation, which places the memory cells in a standby state that preserves cell contents. In our experiments, we explore the energy/performance trade-offs of these techniques and find that the dynamic threshold modulation achieves the best results for level-1 caches, improving the energy-delay product by 2% in a level-1 instruction cache and 7% in a level-1 data cache. Low-leakage transistors perform best for the level-2 cache as they reduce the static energy by up to 98% and improve the energy-delay product by more than a factor of 50.

/pdf/static-energy-reduction-techniques-for-microprocessor-caches-gx6m03boeo.pdf

Static energy reduction techniques for microprocessor caches

This scalable processor architecture consists of chained ALUs to minimize the physical distance between dependent instructions, thus mitigating the effect of long on-chip wire delays. Simulation studies demonstrate 1.3-15/spl times/ more instructions per clock than conventional superscalar architectures.

M. S. Hrishikesh

Papers

Clock rate versus IPC: the end of the road for conventional microarchitectures

The optimal logic depth per pipeline stage is 6 to 8 FO4 inverter delays

Static energy reduction techniques for microprocessor caches

A wire-delay scalable microprocessor architecture for high performance systems