Retargetable Compiler Research Articles

Retargetable Optimizing Compilers for Quantum Accelerators via a Multilevel Intermediate Representation

We present a multilevel quantum–classical intermediate representation (IR) that enables an optimizing, retargetable compiler for available quantum languages. Our work builds upon the multilevel intermediate representation (MLIR) framework and leverages its unique progressive lowering capabilities to map quantum languages to the low-level virtual machine (LLVM) machine-level IR. We provide both quantum and classical optimizations via the MLIR pattern rewriting subsystem and standard LLVM optimization passes, and demonstrate the programmability, compilation, and execution of our approach via standard benchmarks and test cases. In comparison to other standalone language and compiler efforts available today, our work results in compile times that are 1,000× faster than standard Pythonic approaches, and 5–10× faster than comparative standalone quantum language compilers. Our compiler provides quantum resource optimizations via standard programming patterns that result in a 10× reduction in entangling operations, a common source of program noise. We see this work as a vehicle for rapid quantum compiler prototyping.

Extending C++ for Heterogeneous Quantum-Classical Computing

We present qcor—a language extension to C++ and compiler implementation that enables heterogeneous quantum-classical programming, compilation, and execution in a single-source context. Our work provides a first-of-its-kind C++ compiler enabling high-level quantum kernel (function) expression in a quantum-language agnostic manner, as well as a hardware-agnostic, retargetable compiler workflow targeting a number of physical and virtual quantum computing backends. qcor leverages novel Clang plugin interfaces and builds upon the XACC system-level quantum programming framework to provide a state-of-the-art integration mechanism for quantum-classical compilation that leverages the best from the community at-large. qcor translates quantum kernels ultimately to the XACC intermediate representation, and provides user-extensible hooks for quantum compilation routines like circuit optimization, analysis, and placement. This work details the overall architecture and compiler workflow for qcor, and provides a number of illuminating programming examples demonstrating its utility for near-term variational tasks, quantum algorithm expression, and feed-forward error correction schemes.

T|ket⟩: a retargetable compiler for NISQ devices

We present t|ket⟩, a quantum software development platform produced by Cambridge Quantum Computing Ltd. The heart of t|ket⟩ is a language-agnostic optimising compiler designed to generate code for a variety of NISQ devices, which has several features designed to minimise the influence of device error. The compiler has been extensively benchmarked and outperforms most competitors in terms of circuit optimisation and qubit routing.

Programmable ASIPs for Multimode MIMO Transceiver

Application specific instruction-set processors (ASIP) are a programmable and flexible alternative of traditional finite state machine (FSM) controlled register-transfer level (RTL) designs for multimode basedband systems. In this paper, we present two ASIPs for small scale multiple-input multiple-output (MIMO) wireless communication systems that demonstrate the soundness and effectiveness of ASIPs for this type of applications. The first ASIP is programmed with multiple MIMO symbol detection algorithms for 4 × 4 systems. The supported detection algorithms are minimum mean-square error (MMSE), two variants of the selective spanning with fast enumeration (SSFE) and K-best list sphere detection (LSD). The second ASIP supports MMSE and zero-forcing dirty paper coding (ZF-DPC) algorithms for a base station (BS) with 4 antennas and for 4 users. Both ASIPs are based on transport triggered architecture (TTA) and are programmed with a retargetable compiler with high level language to meet the time-to-market requirements. The detection and precoding algorithms can be switched in the respective ASIPs based on the error-rate requirements. Depending on the algorithms, MIMO detection ASIP delivers 6.16–66.66 Mbps throughput at a clock frequency of 200 MHz on 90 nm technology. The precoder ASIP provides a throughput of 52.17 and 51.95 Mbps for MMSE and ZF-DPC precoding respectively at a clock frequency of 210 MHz on 90 nm technology.

Effort at Constructing Big Data Sensor Networks for Monitoring Greenhouse Gas Emission

Global warming is an important environment issue rapidly becoming a part of popular culture. Scientists are 95–100% certain that it is primarily caused by increasing concentrations of greenhouse gases produced by human activities. Policies dealing with global warming depend on accurate and precise monitoring of the emissions of greenhouse gases. However, most greenhouse gas emissions management comes from bottom-up reporting, in which a company reports its energy use and other resource consumption metrics and maps out its carbon footprint. This is not a sufficient good way. A big data network of sensors has been constructed by us in Neimenggu province of China, which will gather huge amount of more accurate information on the dynamics of greenhouse gases in local areas and measure changes over time. Application specific instruction set processor is integrated in those sensor devices, to perform preliminary process of collected data. In this work, we have presented our efforts at constructing the big data sensor network for monitoring the greenhouse gases emission and mainly focused on building the ASIP's retargetable compiler framework designed and dedicated for our sensor network.

효율적인 ASIP 설계를 위한 자동 인스트럭션 확장 시스템 구축

본 논문은 어플리케이션에 최적화된 ASIP설계를 하기 위해 MDL을 기반으로 한 Retargetable 컴파일러를 이용한 자동 인스트럭션 확장 시스템을 제안한다. 제안된 시스템은 어플리케이션 프로그램으로부터 얻은 정보를 이용하여 확장 가능한 인스트럭션 후보를 모두 찾는다. 확장 인스트럭션 후보는 하드웨어 라이브러리를 통해 실제 구현 시의 특성에 대한 정보를 얻게 된다. 하드웨어 특성과 수행 속도 향상을 기반으로 주어진 제한 조건에 맞게 인스트럭션 셋을 선택하고 프로세서 구조를 최적화한다. 제안된 시스템의 효용성을 확인하기 위해 다양한 벤치마크 어플리케이션을 이용하여 자동 인스트럭션 확장 시스템을 수행하였다. 제안된 시스템은 기존의 ARM9TDMI의 프로세서로부터 최적화된 인스트럭션 셋과 프로세서 구조를 갖도록 하였다. 제안된 시스템에 의해 설계된 ASIP는 주어진 제한 조건에 따라 기존 프로세서와 비교하면 평균 33.5%의 수행 사이클이 감소하는 것으로 확인되지만, 프로세서의 면적은 증가하는 것으로 측정되었다. This thesis proposes an automatic instruction extension system that utilizes retargetable compiler, based on MDL, to design an ASIP optimized for application. The proposed system uses information gathered from the application program to find all possible expandable instruction candidates. Expandable instruction candidates acquire the realization characteristics through hardware library. The system chooses instruction set and optimizes processor structure satisfying constraints on the bases of hardware characteristics and increase in execution speed. To confirm the efficiency of the proposed system, automatic instruction extension system was performed using various benchmark applications. The proposed system acquired optimized instruction set and processor structure, which are expanded from the commercial version of ARM9TDMI. Experimental results show that number of execution cycle has been reduced by 33.5% when compared to conventional version of ARM9TDMI, while area has been slightly increased.

Design Space Exploration for a Custom VLIW Architecture

The increasing complexity of algorithms and embedded systems constraints has lead to advanced design methodologies. Hardware/Software co-design methodology has made it possible to find an optimal architecture for a given application by exploring the design space before building a real hardware prototype. The Design Space Exploration is basically exploring the various processor architectures in order to search for a processor architecture that satisfies different conflicting criteria such as chip area, speed, power consumption or on-chip memory requirements. The output is a set of different architectures representing the different tradeoffs. Retargetable compiler is an important tool in design space exploration (DSE). Retargetable compiler is capable of generating code for different target processors, by reusing most of the code. The objective of this research is to develop a retargetable compiler that can generate efficient code in terms of code size, cycle count and retargetability efforts for a VLIW processor.

Instruction set architectural guidelines for embedded packet-processing engines

This paper presents instruction set architectural guidelines for improving general-purpose embedded processors to optimally accommodate packet-processing applications. Similar to other embedded processors such as media processors, packet-processing engines are deployed in embedded applications, where cost and power are as important as performance. In this domain, the growing demands for higher bandwidth and performance besides the ongoing development of new networking protocols and applications call for flexible power- and performance-optimized engines. The instruction set architectural guidelines are extracted from an exhaustive simulation-based profile-driven quantitative analysis of different packet-processing workloads on 32-bit versions of two well-known general-purpose processors, ARM and MIPS. This extensive study has revealed the main performance challenges and tradeoffs in development of evolution path for survival of such general-purpose processors with optimum accommodation of packet-processing functions for future switching-intensive applications. Architectural guidelines include types of instructions, branch offset size, displacement and immediate addressing modes for memory access along with the effective size of these fields, data types of memory operations, and also new branch instructions. The effectiveness of the proposed guidelines is evaluated with the development of a retargetable compilation and simulation framework. Developing the HDL model of the optimized base processor for networking applications and using a logic synthesis tool, we show that enhanced area, power, delay, and power per watt measures are achieved.

DisIRer

This article proposes an alternative yet effective way of constructing a multiplatform binary translator, by converting a retargetable compiler into a binary translator. The rationale is that a retargetable compiler usually parses source programs into an Intermediate Representation (IR), and then translates IR into object code of different targets after performing analysis and optimizations. Specifically, the mechanism of code generation for multiple platforms from IR is already in place, and the missing link of building a multiplatform binary translator is a tool to transform binary programs back into IR. In order to fill in this missing link, this article presents a tool, called thedisIRer. Just as a translator from machine language to assembly language is called a disassembler, a tool that translates executable binary programs to IR is called here a disIRer. The unique feature of this approach is that the retargetability of the binary translator is inherited directly from the retargetable compiler. A prototype multiplatform binary translator has been implemented upon GCC (the GNU Compiler Collection). DisIRer first converts binary programs back into GCC IR (Intermediate Representation), and afterward the GCC backend translates the IR to target binary programs of specified platforms. Experimental results show that x86 binary programs can be translated by this technique into ARM and Alpha binaries with reasonable code density and quality.

Automatically generating instruction selectors using declarative machine descriptions

Despite years of work on retargetable compilers, creating a good, reliable back end for an optimizing compiler still entails a lot of hard work. Moreover, a critical component of the back end---the instruction selector---must be written by a person who is expert in both the compiler's intermediate code and the target machine's instruction set. By generating the instruction selector from declarative machine descriptions we have (a) made it unnecessary for one person to be both a compiler expert and a machine expert, and (b) made creating an optimizing back end easier than ever before. Our achievement rests on two new results. First, finding a mapping from intermediate code to machine code is an undecidable problem. Second, using heuristic search, we can find mappings for machines of practical interest in at most a few minutes of CPU time. Our most significant new idea is that heuristic search should be controlled by algebraic laws. Laws are used not only to show when a sequence of instructions implements part of an intermediate code, but also to limit the search: we drop a sequence of instructions not when it gets too long or when it computes too complicated a result, but when too much reasoning will be required to show that the result computed might be useful.

Playing the trade-off game

Modern mobile devices need to be extremely energy efficient. Due to the growing complexity of these devices, energy-aware design exploration has become increasingly important. Current exploration tools often do not support energy estimation, or require the design to be very detailed before estimation is possible. It is important to get early feedback on both performance and energy consumption during all phases of the design and at higher abstraction levels. This article presents a unified optimization and exploration framework to explore source-level transformation to processor architecture design space. The proposed retargetable compiler and simulator framework can map applications to a range of processors and memory configurations, simulate, and report detailed performance and energy estimates. An accurate and consistent energy modeling approach is introduced which can estimate the energy consumption of processor and memories at a component level, which can help to guide the design process. Fast energy-aware architecture exploration is illustrated by modeling both state-of-the-art processors as well as other architectures. Various design trade-offs are also illustrated on different academic as well as industrial benchmarks from both the wireless communication and multimedia domain. We also illustrate a design space exploration on different applications and show that there is large trade-off space between application performance, energy consumption, and area. We show that the proposed framework is consistent, accurate, and covers a large design space including various novel low-power extensions in a unified framework.

A SIMD optimization framework for retargetable compilers

Retargetable C compilers are currently widely used to quickly obtain compiler support for new embedded processors and to perform early processor architecture exploration. A partially inherent problem of the retargetable compilation approach, though, is the limited code quality as compared to hand-written compilers or assembly code due to the lack of dedicated optimizations techniques. This problem can be circumvented by designing flexible, retargetable code optimization techniques that apply to a certain range of target architectures. This article focuses on target machines with SIMD instruction support, a common feature in embedded processors for multimedia applications. However, SIMD optimization is known to be a difficult task since SIMD architectures are largely nonuniform, support only a limited set of data types and impose several memory alignment constraints. Additionally, such techniques require complicated loop transformations, which are tailored to the SIMD architecture in order to exhibit the necessary amount of parallelism in the code. Thus, integrating the SIMD optimization and the required loop transformations together in a single retargeting formalism is an ambitious challenge. In this article, we present an efficient and quickly retargetable SIMD code optimization framework that is integrated into an industrial retargetable C compiler. Experimental results for different processors demonstrate that the proposed technique applies to real-life target machines and that it produces code quality improvements close to the theoretical limit.

최적화된 에너지 소비를 위한 코드 생성 기술

최근 임베디드 시스템의 폭넓은 보급은 응용 소프트웨어 개발과 더불어 임베디드 소프트웨어 개발 도구의 필요성 및 중요성이 강조되고 있으며 임베디드 소프트웨어를 위한 컴파일러의 개발을 동시에 요구하고 있다. 특히, 임베디드 프로세서를 탑재한 모바일 장치에서는 제한된 전력/에너지의 하드웨어적인 관리 못지않게 소프트웨어적인 관리 기술의 중요성이 강조되고 있다. 본 논문에서는 검증된 재목적 컴파일러 후단부 도구인 EXPRESSION을 통해 최적화된 에너지 소비를 고려한 MIPS 코드 생성 기술을 제안하였다. 이를 위해, 효율적인 MIPS 코드 생성을 위한 코드 생성 규칙을 기술하였으며 생성된 코드에 대한 다양한 성능분석 결과를 제시한다. Recently, together with a new advent of embedded processor developed to support specific application area, and it evolution, a new study of software development to support the embedded processor and its commercial use has been revitalized. Specially, In a mobile device that is built-in embedded processor, software management is as important as hardware management for the limited power/energy. In this paper, we suggest that the code generation technique considering the energy dissipation through the verified retargetable compiler backend tool, EXPRESSION. For this goals, we describes the efficient code generation patterns and showed the variable performance results.

The State of ESL Design [Roundtable

This is the first of two roundtables on electronic system-level design in this issue of IEEE Design & Test. ESL design and tools have been present in the design landscape for many years. Significant ESL innovations are now part of most advanced design methodologies, spanning the domains of modeling, simulation, and synthesis. Techniques such as transaction-level modeling, automatic interconnection generation, behavioral synthesis, automatic instruction-set customization, retargetable compilers, and many others are currently used in the design of multimillion-gate chips. Yet, ESL design still seems to struggle to live up to the promise of providing increased productivity and design quality. This roundtable examines these issues and attempts to provide a definite picture of where ESL design is today and where it might be in the next five to 10 years. The participants in this roundtable include well-known experts in ESL design from the user side, universities, and tool providers. IEEE Design & Test thanks the roundtable participants: moderator Reinaldo Bergamaschi (CadComponents), Luca Benini (University of Bologna), Krisztian Flautner (ARM UK), Wido Kruijtzer (NXP Semiconductors), Alberto Sangiovanni-Vincentelli (University of California, Berkeley), and Kazutoshi Wakabayashi (NEC Japan). D&T gratefully acknowledges the help of Roundtables Editor Bill Joyner (Semiconductor Research Corp.), who organized the event.

A Retargetable Compiler Based on Graph Representation for Dynamically Reconfigurable Processor Arrays

For developing design environment of various Dynamically Reconfigurable Processor Arrays (DRPAs), the Graph with Configuration Information (GCI) is proposed to represent configurable resource in the target dynamically reconfigurable architecture. The functional unit, constant unit, register, and routing resource can be represented in the graph as well as the configuration information. The restriction in the hardware is also added in the graph by limiting the possible configuration at a node controlled by the other node. A prototype compiler called Black-Diamond with GCI is now available for three different DRPAs. It translates data-flow graph from C-like front-end description, applies placement and routing by using the GCI, and generates configuration data for each element of the DRPA. Evaluation results of simple applications show that Black-Diamond can generate reasonable designs for all three different architectures. Other target architectures can be easily treated by representing many aspects of architectural property into a GCI.

Automatic Design Space Exploration of Register Bypasses in Embedded Processors

Register bypassing is a popular and powerful architectural feature to improve processor performance in pipelined processors by eliminating certain data hazards. However, extensive bypassing comes with a significant impact on cycle time, area, and power consumption of the processor. Recent research therefore advocates the use of partial bypassing in a processor. However, accurate performance evaluation of partially bypassed processors is still a challenge, primarily due to the lack of bypass-sensitive retargetable compilation techniques. No existing partial bypass exploration framework estimates the power and area overhead of partial bypassing. As a result, the designers end up making suboptimal design decisions during the exploration of partial bypass design space. This paper presents PBExplore - an automatic design-space-exploration framework for register bypasses. PBExplore accurately evaluates the performance of a partially bypassed processor using a bypass-sensitive compilation technique. It synthesizes the bypass control logic and estimates the area and energy overhead of each bypass configuration. PBExplore is thus able to effectively perform multidimensional exploration of the partial bypass design space. We present experimental results of benchmarks from the MiBench suite on the Intel XScale architecture on and demonstrate the need, utility, and exploration capabilities of PBExplore.

An Overview of a Compiler for Mapping Software Binaries to Hardware

As new applications in embedded communications and control systems push the computational limits of digital signal processing (DSP) functions, there will be an increasing need for software applications to be migrated to hardware in the form of a hardware-software codesign system. In many cases, access to the high-level source code may not be available. It is thus desirable to have a technology to translate the software binaries intended for processors to hardware implementations. This paper provides details on the retargetable FREEDOM compiler. The compiler automatically translates DSP software binaries to register-transfer level (RTL) VHDL and Verilog for implementation on field-programmable gate arrays (FPGAs) as standalone or system-on-chip implementations. We describe the underlying optimizations and some novel algorithms for alias analysis, data dependency analysis, memory optimizations, procedure call recovery, and back-end code scheduling. Experimental results on resource usage and performance are shown for several program binaries intended for the Texas Instruments C 6211 DSP (VLIW) and the ARM 922 T reduced instruction set computer (RISC) processors. Implementation results for four kernels from the Simulink demo library and others from commonly used DSP applications, such as MPEG-4, Viterbi, and JPEG are also discussed. The compiler generated RTL code is mapped to Xilinx Virtex II and Altera Stratix FPGAs. We record overall performance gains of 1.5-26.9 for the hardware implementations of the kernels. Comparisons with the power aware compiler techniques (PACT) high-level synthesis compiler are used to show that software binaries can be used as intermediate representations from any high-level language and generate efficient hardware implementations.

응용프로그램에 특화된 명령어를 통한 고정 소수점 오디오 코덱 최적화를 위한 ADL 기반 컴파일러 사용

빠른 디자인 공간 탐색 (Design space exploration)은 응용 프로그램의 동작을 구현하기 위한 임베디드 시스템을 디자인하는데 매우 중요하다. Time-to-market이 디자인의 주관심사가 되어감에 따라 ASIP(Application specific instruction-set processor)에 기반한 접근 방식이 디자인 방법론적으로 중요한 대안이 되고 있다. 이러한 접근 방식에서는 타깃 프로세서의 ISA(Instruction set architecture)를 코드 크기와 실행 속도 측면에서 응용 프로그램에 가장 적합하도록 변경한다. 본 논문의 목적은 우리의 새로운 재겨냥성 컴파일러를 소개하고, 많이 알려진 디지털 신호 처리용 응용 프로그램을 위한 ASIP 기반 디자인 공간 탐색에서 컴파일러가 어떻게 활용될 수 있는지 설명하고자 하는 것이다. 새롭게 개발된 재겨냥성 컴파일러는 이전의 재겨냥성 컴파일러의 기능을 제공할 뿐만 아니라 application 프로그램의 특징을 시각화하고 application 프로그램의 프로파일된 결과를 제공하므로 application의 성능을 증가시키기 위해 어떤 명령어들을 넣어야 하는지를 결정하는데 도움을 준다. 재겨냥성 컴파일러의 ADL(Architecture description language)를 이용하여 타깃 프로세서의 초기 RISC-style ISA을 기술하고, 컴파일러가 응용 프로그램을 위한 어셈블리 코드를 더 최적화할 수 있도록 응용 프로그램에 특화된 명령어를 ISA에 점진적으로 추가해 나간다. AC3 오디오 codec을 위한 실험 결과로부터 우리는 32%의 성능 증가와 20%의 프로그램 크기 감소를 얻을 수 있는 6개의 새로운 특화 명령어를 빠르게 찾을 수 있었다. 따라서 우리는 고성능의 재겨냥성 컴파일러는 특정 응용 프로그램을 위한 새로운 ASIP의 빠른 디자인을 하기 위한 중요한 핵심이라는 것을 확인할 수 있었다. Rapid design space exploration is crucial to customizing embedded system design for exploiting the application behavior. As the time-to-market becomes a key concern of the design, the approach based on an application specific instruction-set processor (ASIP) is considered more seriously as one alternative design methodology. In this approach, the instruction set architecture (ISA) for a target processor is frequently modified to best fit the application with regard to code size and speed. Two goals of this paper is to introduce our new retargetable compiler and how it has been used in ASIP-based design space exploration for a popular digital signal processing (DSP) application. Newly developed retargetable compiler provides not only the functionality of previous retargetable compilers but also visualizes the features of the application program and profiles it so that it can help architecture designers and application programmers to insert new application specific instructions into target architecture for performance increase. Given an initial RISC-style ISA for the target processor, we characterized the application code and incrementally updated the ISA with more application specific instructions to give the compiler a better chance to optimize assembly code for the application. We get 32% performance increase and 20% program size reduction using 6 audio codec specific instructions from retargetable compiler. Our experimental results manifest a glimpse of evidence that a higgly retargetable compiler is essential to rapidly prototype a new ASIP for a specific application.

Retargetable pipeline hazard detection for partially bypassed processors

Register bypassing is a widely used feature in modern processors to eliminate certain data hazards. Although complete bypassing is ideal for performance, it has significant impact on the cycle time, area, and power consumption of the processor. Owing to the strict design constraints on the performance, cost, and the power consumption of embedded processor systems, architects seek a compromise between the design parameters by implementing partial bypassing in processors. However, partial bypassing in processors presents challenges for compilation. Traditional data hazard detection and/or avoidance techniques used in retargetable compilers that assume a constant value of operation latency, break down in the presence of partial bypassing. In this article, we present the concept of operation tables (OTs) that can be used to accurately detect data hazards, even in the presence of incomplete bypassing. OTs integrate the detection of all kinds of pipeline hazards in a unified framework, and can, therefore, be easily deployed in a compiler to generate better schedules. Our experimental results on the popular Intel XScale embedded processor running embedded applications from the MiBench suite, demonstrate that accurate pipeline hazard detection by OTs can result in up to 20% performance improvement over the best performing GCC generated code. Finally, we demonstrate the usefulness of OTs over various bypass configurations of the Intel XScale

Effective compiler generation by architecture description

Embedded systems have an extremely short time to market and therefore require easily retargetable compilers. Architecture description languages (ADLs) provide a single concise architecture specification for the generation of hardware, instruction set simulators and compilers. In this article, we present an ADL for compiler generation. From a specification, we can derive an optimized tree pattern matching instruction selector, a register allocator and an instruction scheduler. Compared to a hand-crafted back end, the generated compiler produces smaller and faster code.The ADL is rich enough that other tools, such as assemblers, linkers, simulators and documentation, can all be obtained from a single specification.