Packet Reordering in Network Processors

Network processors today consist of multiple parallel processors (micro engines) with support for multiple threads to exploit packet level parallelism inherent in network workloads. With such concurrency, packet ordering at the output of the network processor cannot be guaranteed. This paper studies the effect of concurrency in network processors on packet ordering. We use a validated Petri net model of a commercial network processor, Intel IXP 2400, to determine the extent of packet reordering for IPv4 forwarding application. Our study indicates that in addition to the parallel processing in the network processor, the allocation scheme for the transmit buffer also adversely impacts packet ordering. In particular, our results reveal that these packet reordering results in a packet retransmission rate of up to 61%. We explore different transmit buffer allocation schemes namely, contiguous, strided, local, and global which reduces the packet retransmission to 24%. We propose an alternative scheme, packet sort, which guarantees complete packet ordering while achieving a throughput of 2.5 Gbps. Further, packet sort outperforms the in-built packet ordering schemes in the IXP processor by up to 35%.

Register Allocation and Optimal Spill code Scheduling in Software Pipelined Loops using 0-1 Integer Linear Programming Formulation

In achieving higher instruction level parallelism, software pipelining increases the register pressure in the loop. The usefulness of the generated schedule may be restricted to cases where the register pressure is less than the available number of registers. Spill instructions need to be introduced otherwise. But scheduling these spill instructions in the compact schedule is a difficult task. Several heuristics have been proposed to schedule spill code. These heuristics may generate more spill code than necessary, and scheduling them may necessitate increasing the initiation interval. We model the problem of register allocation with spill code generation and scheduling in software pipelined loops as a 0-1 integer linear program. The formulation minimizes the increase in initiation interval (II) by optimally placing spill code and simultaneously minimizes the amount of spill code produced. To the best of our knowledge, this is the first integrated formulation for register allocation, optimal spill code generation and scheduling for software pipelined loops. The proposed formulation performs better than the existing heuristics by preventing an increase in II in 11.11% of the loops and generating 18.48% less spill code on average among the loops extracted from Perfect Club and SPEC benchmarks with a moderate increase in compilation time.

Compiler-Directed Dynamic Voltage Scaling using Program Phases

Energy consumption has become a major constraint in providing increased functionality for devices with small form factors. Dynamic voltage and frequency scaling has been identified as an effective approach for reducing the energy consumption of embedded systems. Earlier works on dynamic voltage scaling focused mainly on performing voltage scaling when the CPU is waiting for memory subsystem or concentrated chiefly on loop nests and/or subroutine calls having sufficient number of dynamic instructions. This paper concentrates on coarser program regions and for the first time uses program phase behavior for performing dynamic voltage scaling. Program phases are annotated at compile time with mode switch instructions. Further, we relate the Dynamic Voltage Scaling Problem to the Multiple Choice Knapsack Problem, and use well known heuristics to solve it efficiently. Also, we develop a simple integer linear program formulation for this problem. Experimental evaluation on a set of media applications reveal that our heuristic method obtains a 38% reduction in energy consumption on an average, with a performance degradation of 1% and upto 45% reduction in energy with a performance degradation of 5%. Further, the energy consumed by the heuristic solution is within 1% of the optimal solution obtained from the ILP approach.

Emulating Optimal Replacement with a Shepherd Cache

The inherent temporal locality in memory accesses is filtered out by the L1 cache. As a consequence, an L2 cache with LRU replacement incurs significantly higher misses than the optimal replacement policy (OPT). We propose to narrow this gap through a novel replacement strategy that mimics the replacement decisions of OPT. The L2 cache is logically divided into two components, a Shepherd Cache (SC) with a simple FIFO replacement and a Main Cache (MC) with an emulation of optimal replacement. The SC plays the dual role of caching lines and guiding the replacement decisions in MC. Our pro- posed organization can cover 40% of the gap between OPT and LRU for a 2MB cache resulting in 7% overall speedup. Comparison with the dynamic insertion policy, a victim buffer, a V-Way cache and an LRU based fully associative cache demonstrates that our scheme performs better than all these strategies.

MODLEX: A Multi Objective Data Layout EXploration Framework for Embedded Systems-on-Chip

The memory subsystem is a major contributor to the performance, power, and area of complex SoCs used in feature rich multimedia products. Hence, memory architecture of the embedded DSP is complex and usually custom designed with multiple banks of single-ported or dual ported on-chip scratch pad memory and multiple banks of off-chip memory. Building software for such large complex memories with many of the software components as individually optimized software IPs is a big challenge. In order to obtain good performance and a reduction in memory stalls, the data buffers of the application need to be placed carefully in different types of memory. In this paper we present a unified framework (MODLEX) that combines different data layout optimizations to address the complex DSP memory architectures. Our method models the data layout problem as multi-objective genetic algorithm (GA) with performance and power being the objectives and presents a set of solution points which is attractive from a platform design viewpoint. While most of the work in the literature assumes that performance and power are non-conflicting objectives, our work demonstrates that there is significant trade-off (up to 70%) that is possible between power and performance.

MAX: A Multi Objective Memory Architecture eXploration Framework for Embedded Systems-on-Chip

Today's feature-rich multimedia products require embedded system solution with complex System-on-Chip (SoC) to meet market expectations of high performance at a low cost and lower energy consumption. The memory architecture of the embedded system strongly influences these parameters. Hence the embedded system designer performs a complete memory architecture exploration. This problem is a multi-objective optimization problem and can be tackled as a two-level optimization problem. The outer level explores various memory architecture while the inner level explores placement of data sections (data layout problem) to minimize memory stalls. Further, the designer would be interested in multiple optimal design points to address various market segments. However, tight time-to-market constraints enforces short design cycle time. In this paper we address the multi-level multi-objective memory architecture exploration problem through a combination of Multi-objective Genetic Algorithm (Memory Architecture exploration) and an efficient heuristic data placement algorithm. At the outer level the memory architecture exploration is done by picking memory modules directly from a ASIC memory Library. This helps in performing the memory architecture exploration in a integrated framework, where the memory allocation, memory exploration and data layout works in a tightly coupled way to yield optimal design points with respect to area, power and performance. We experimented our approach for 3 embedded applications and our approach explores several thousand memory architecture for each application, yielding a few hundred optimal design points in a few hours of computation time on a standard desktop.

REDEFINE: Architecture of a SoC Fabric for Runtime Composition of Computation Structures

In this paper we propose the architecture of a SoC fabric onto which applications described in a HLL are synthesized. The fabric is a homogeneous layout of computation, storage and communication resources on silicon. Through a process of composition of resources (as opposed to decomposition of applications), application specific computational structures are defined on the fabric at runtime to realize different modules of the applications in hardware. Applications synthesized on this fabric offers performance comparable to ASICs while retaining the programmability of processing cores. We outline the application synthesis methodology through examples, and compare our results with software implementations on traditional platforms with unbounded resources.

Limits of Data Level Parallelism

Abstract—A new breed of processors like the Cell Broadband Engine, the Imagine stream processor and the various GPU processors emphasize data-level parallelism (DLP) and threadlevel parallelism (TLP) as opposed to traditional instructionlevel parallelism (ILP). This allows them to achieve order-ofmagnitude improvements over conventional superscalar processors for many workloads. However, it is unclear as to how much parallelism of these types exists in current programs. Most earlier studies have largely concentrated on the amount of ILP in a program, without differentiating DLP or TLP. In this study, we investigate the extent of data-level parallelism available in programs in the MediaBench suite. By packing instructions in a SIMD fashion, we observe reductions of up to 91 % (84 % on average) in the number of dynamic instructions, indicating a very high degree of DLP in several applications. I.

An Efficient MPI_Allgather for Grids

Allgather is an important MPI collective communication. Most of the algorithms for allgather have been designed for homogeneous and tightly coupled systems. The existing algorithms for allgather on Gridsystems do not efficiently utilize the bandwidths available on slow wide-area links of the grid. In this paper, we present an algorithm for allgather on grids that efficiently utilizes wide-area bandwidths and is also wide-area optimal. Our algorithm is also adaptive to gridload dynamics since it considers transient network characteristics for dividing the nodes into clusters. Our experiments on a real-grid setup consisting of 3 sites show that our algorithm gives an average performance improvement of 52% over existing strategies.

Coupled Climate Model on Grids

Community Climate System Model (CCSM) is a Multiple Program Multiple Data (MPMD) parallel global climate model comprising atmosphere, ocean, land, ice and coupler components. The simulations have a time-step of the order of tens of minutes and are typically performed for periods of the order of centuries. These climate simulations are highly computationally intensive and can take several days to weeks to complete on most of today’s multi-processor systems. ExecutingCCSM on grids could potentially lead to a significant reduction in simulation times due to the increase in number of processors. However, in order to obtain performance gains on grids, several challenges have to be met. In this work,we describe our load balancing efforts in CCSM to make it suitable for grid enabling.We also identify the various challenges in executing CCSM on grids. Since CCSM is an MPI application, we also describe our current work on building a MPI implementation for grids to grid-enable CCSM.

Two-level Mapping Based Cache Index Selection for Packet Forwarding Engines

Packet forwarding is a memory-intensive application requiring multiple accesses through a trie structure. The efficiency of a cache for this application critically depends on the placement function to reduce conflict misses. Traditional placement functions use a one-level mapping that naively partitions trie-nodes into cache sets. However, as a significant percentage of trie nodes are not useful, these schemes suffer from a non-uniform distribution of useful nodes to sets. This in turn results in increased conflict misses. Newer organizations such as variable associativity caches achieve flexibility in placement at the expense of increased hit-latency. This makes them unsuitable for L1 caches.We propose a novel two-level mapping framework that retains the hit-latency of one-level mapping yet incurs fewer conflict misses. This is achieved by introducing a secondlevel mapping which reorganizes the nodes in the naive initial partitions into refined partitions with near-uniform distribution of nodes. Further as this remapping is accomplished by simply adapting the index bits to a given routing table the hit-latency is not affected. We propose three new schemes which result in up to 16% reduction in the number of misses and 13% speedup in memory access time. In comparison, an XOR-based placement scheme known to perform extremely well for general purpose architectures, can obtain up to 2% speedup in memory access time.

Exploiting Programmable Network Interfaces for Parallel Query Execution in Workstation Clusters

Workstation clusters equipped with high performance interconnect having programmable network processors facilitate interesting opportunities to enhance the performance of parallel application run on them. In this paper, we propose schemes where certain application level processing in parallel database query execution is performed on the network processor. We evaluate the performance of TPC-H queries executing on a high end cluster where all tuple processing is done on the host processor, using a timed Petri net model, and find that tuple processing costs on the host processor dominate the execution time. These results are validated using a small cluster. We therefore propose 4 schemes where certain tuple processing activity is offloaded to the network processor. The first 2 schemes offload the tuple splitting activity - computation to identify the node on which to process the tuples, resulting in an execution time speedup of 1.09 relative to the base scheme, but with I/O bus becoming the bottleneck resource. In the 3rd scheme in addition to offloading tuple processing activity, the disk and network interface are combined to avoid the I/O bus bottleneck, which results in speedups up to 1.16, but with high host processor utilization. Our 4th scheme where the network processor also performs apart of join operation along with the host processor, gives a speedup of 1.47 along with balanced system resource utilizations. Further we observe that the proposed schemes perform equally well even in a scaled architecture i.e., when the number of processors is increased from 2 to 64

Holistic Schema Mappings for XML-on-RDBMS

When hosting XML information on relational backends, a mapping has to be established between the schemas of the information source and the target storage repositories. A rich body of recent literature exists for mapping isolated components of XML Schema to their relational counterparts, especially with regard to table configurations. In this paper, we present the Elixir system for designing industrial-strength mappings for real-world applications. Specifically, it produces an information-preserving holistic mapping that transforms the complete XML world-view (XML schema with constraints, XML documents XQuery queries including triggers and views) into a full-scale relational mapping (table definitions, integrity constraints, indices, triggers and views) that is tuned to the application workload. A key design feature of Elixir is that it performs all its mapping-related optimizations in the XML source space, rather than in the relational target space. Further, unlike the XML mapping tools of commercial database systems, which rely heavily on user inputs, Elixir takes a principled cost-based approach to automatically find an efficient relational mapping. A prototype of Elixir is operational and we quantitatively demonstrate its functionality and efficacy on a variety of real-life XML schemas.