Reliability-Aware Instruction Set Customization for ASIPs with Hardened Logic

The application specific instruction-set processor (ASIP) offers better computing performance and efficiency by exploiting a set of specific custom instructions (CI) in the processor. However, traditional approaches suffer from the problem that it costs so much computational resource to enumerate and select the optimal custom instructions. In this paper, instead of generating the custom instructions by enumerating all sub-graphs in the data flow graph, we propose a novel custom instruction generation algorithm based on analyzing the basic blocks (BB) which are the smallest execution units of the program. On the basis of characterizing the logic information and structure of basic blocks, both the identification and selection processes could be more efficient by focusing on the feasible candidates with better benefits. A Maximal Weight Independent Set-based formulation is set up to select the final custom instructions based on the efficient identification of candidate custom instructions with logic information of BBs. The experimental result shows that our algorithm can identify 55% more feasible CIs compared with the previous approach. With efficient identification process, we can finally get better CI designs with about 3.27X performance gain of the whole system.

This article discusses a MATLAB-to-C vectorizing compiler that exploits custom instructions, for example, for Single Instruction Multiple Data (SIMD) processing and instructions for complex arithmetic present in Application-Specific Instruction Set Processors (ASIPs). Custom instructions are represented via specialized intrinsic functions in the generated code, and the generated code can be used as input to any C/C++ compiler supporting the target processor. Furthermore, the specialized instruction set of the target processor is described in a parameterized way using a target processor-independent architecture description approach, thus allowing the support of any processor. The compiler has been used for the generation of application code for two different ASIPs for several benchmarks. The code generated by the compiler achieves a speedup between 2× --74× and 2× --97× compared to the code generated by the MathWorks MATLAB-to-C compiler. Experimental results also prove that the compiler efficiently exploits SIMD custom instructions achieving a 3.3 factor speedup compared to cases where no SIMD processing is used. Thus the compiler can be employed to reduce the development time/effort/cost and time to market through raising the abstraction of application design in an embedded systems/system-on-chip development context.

In recent years, the use of extensible processors has been increased. Extensible processors extend the base instruction set of a general-purpose processor with a set of custom instructions. Custom instructions that can be implemented in special hardware units make it possible to improve performance and decrease power consumption in extensible processors. The key issue involved is to generate and select automatically custom instructions from a high-level application code. In this paper, we propose an efficient and flexible algorithm for the exact enumeration of custom instructions. The algorithm can be tuned to generate all possible patterns or only connected patterns. Compared to a previously proposed well-known algorithm, our algorithm can achieve orders of magnitude speedup.

We describe a new approach for creating hardware description language (HDL) specifications for custom instructions, to form part of the instruction-set architecture (ISA) of an application specific instruction set processor (ASIP). Our approach integrates fully into the traditional C development process, binding tightly with software source code and simplifying the ASIP optimisation process. Our tool is also free software, facilitating its use in future research.KeywordsClock CycleIntegrate Development EnvironmentBenchmark ProgramManual ImplementationCustom UnitThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

In this paper, a flexible HW architecture for video-based driver assistance applications is presented. It comprises a customizable and extensible processor template and several task-specific HW accelerators. The proposed heterogeneous architecture allows utilization of the programmable processor core for control and low data rate tasks. For the acceleration of computationally intensive tasks of the application, special functional units and custom instructions can be added to the processor template to form an application specific instruction set processor (ASIP). Moreover, dedicated HW accelerators can be attached to the ASIP. To compare the diverse design options, a shape detection application for traffic sign detection is utilized as case study. It is shown that single tasks of a pure software implementation can be significantly accelerated by usage of special functional units by a factor of up to 35 and by usage of HW accelerators of up to 243. The proposed architecture has been mapped onto an FPGA and it could be shown that a realtime capable system can be realized.

Several techniques have been proposed to reduce the energy consumption of ASIPs (Application-Specific Instruction set Processors). While those techniques can reduce the energy consumption with minimal change in the instruction set (IS), they often fail to exploit the opportunity of designing the entire IS from the energy-efficiency perspective. In this chapter we present an energy-efficient IS synthesis that can comprehensively reduce the energy-delay product (EDP) of ASIPs through optimal instruction encoding, considering both the instruction bitwidth and the dynamic instruction fetch count. Experimental results with a typical embedded RISC processor show that the proposed energy-efficient IS synthesis technique can generate application-specific ISs that are up to 40% more energy-efficient over the native IS for several application benchmarks.

This chapter presents the novel adaptive low-power reconfigurable processor architecture with a run-time adaptive energy management scheme. It exploits the novel concept of Selective Instruction Set Muting with multiple muting modes. The first section analyzes different scenarios, while motivating the need for run-time energy management. Afterwards, the adaptive energy management scheme with the novel concept of Custom Instruction (CI) Set Muting is discussed in Sect. 5.2. In this section different CI muting modes are explained along with the corresponding configuration of sleep transistors for different parts of the reconfigurable fabric. Afterwards, the required power-shutdown infrastructure is discussed. In Sect. 5.2.3 an overview of the energy management scheme is provided highlighting different requirements and steps considered at design-, compile-, and run-time.

In this paper, we propose a parallel systematic resampling (PSR) algorithm for particle filters, which is a new form of systematic resampling (SR). The PSR algorithm makes iterations independent, thus allowing the resampling algorithm to perform loop iterations in parallel. A fixed-point version of the PSR algorithm is also proposed, with a modification to ensure that a correct number of particles is generated. Experiments show that the fixed-point implementation of the PSR algorithm can use as few as 22 bits for representing the weights, when processing 512 particles, while achieving results equivalent to a floating-point SR implementation. Four customized instructions were designed to accelerate the proposed PSR algorithm in Application-Specific Instruction-set Processors. These four custom instructions, when configured to support four weight inputs in parallel, lead to a 73.7 $$\times $$ × speedup over a floating-point SR implementation on a general-purpose processor at a cost of 47.3 K additional gates.

Particle filters (PFs) are computationally intensive, which prevents them from being widely used in some real-time applications with high throughput requirements. A parallel implementation is a feasible approach to enable using PFs in these applications. However, effective resampling algorithms such as the Systematic Resampling (SR) algorithm are sequential in nature. In this paper, we propose a new form of the SR algorithm suitable for parallel implementation in an Application-Specific Instruction-set Processor (ASIP). Six custom instructions were designed for this reformulated SR algorithm. Experimental results show that the ASIP implementation of the reformulated SR algorithm, with four weights calculated in parallel, and eight categories defined by uniformly distributed numbers that are compared simultaneously to achieve a 30.6× speedup over the serial SR algorithm in a general-purpose processor. This comes at a cost of only 54K additional gates, or 68% overhead to be added to a base processor with 79K gates.

This paper proposes a LDPC (Low Density Parity Check Codes) encoder architecture for DMB-TH based on ASIP (Application Specific Instruction Set Processor). The encoding algorithm is first analyzed and optimized for the ASIP encode, And then the special instruction sets are extracted according to the optimized algorithm. The ASIP architecture uses main processor and coprocessor to get high throughput. This ASIP encoder can support three different code rates (0.4, 0.6 and 0.8) just by different programs and thus is more flexible than other ASIC implementations. Based on XC2V6000, at the max frequency of 117MHz, the max throughput of the encoder can deliver 187Mbps, 206Mbps and 232Mbps for 0.4, 0.6 and 0.8 code rates, respectively.

Area cost estimation model is important for accurate measurement of area on reconfigurable processor. However, in the process of CI (Custom Instruction), traditional model can’t accurately estimate area cost of CI candidates. In the paper, we propose a novel strategy of area cost estimation. According to island-style FPGA (Field Programmable Gate Array) structure, the strategy firstly enumerated all BCs (Basic Cells) from data-path of CI candidates. Then checked all the validity of BCs enumerated, and selected the unique BC set to overlap original data-paths. We lastly used the effective estimation model based on BC to accurately measure area cost of candidates. Experimental results show that novel strategy can accurately estimate area cost of CI candidates, which is very close to actual result from a HLS (High Level Synthesis) tool, and deviation is less than 6%.

Implementation-aware selection of the custom instruction set for extensible processors

This work proposes a hierarchical Design Space Exploration (DSE) for the design of multi-processor platforms targeted to specific applications with strict timing and area constraints. In particular, it considers platforms integrating multiple Application Specific Instruction Set Processors (ASIPs) and each ASIP is automatically synthesized and tuned for a specific set of tasks. The definition of the platform (number of processors and their interconnection) and of the micro-architecture of each single ASIP are tightly coupled. Tasks can be allocated to the different ASIPs only knowing their performance and therefore the ASIP micro-architecture. At the same time an ASIP can be derived only knowing the functionality that it has to implement, i.e. the tasks that are assigned. We break this circular dependency with an iterative hierarchical DSE, applied at platform and micro-architecture level. We evaluate different platforms and micro-architecture alternatives to find a multi-ASIP platform targeted to the input application and able to meet the design constraints. We evaluate our design flow using a MJPEG encoder application.

In this paper we research an FPGA based application specific instruction set processor (ASIP) tailored to the needs of a flow aware Ethernet access node using a retargetable compilation flow. The toolchain is used to develop an initial processor design, asses the performance and identify the potential bottlenecks. A second design iteration results in a fully optimized ASIP with a VLIW instruction set which allows for high degree of parallelism among the functional units inside the ASIP and has dedicated instructions to accelerate typical packet processing tasks. This way, a single processor is capable of handling the complete throughput of a gigabit Ethernet link. To reach the target of a 10 Gbit/s Ethernet access node several processors operate in parallel in a multicore environment

Chapter 14 - Application Specific Instruction Set Processor for UMTS-FDD Cell Search