Jonathan Babb

Baring it all to software: Raw machines

The most radical of the architectures that appear in this issue are Raw processors-highly parallel architectures with hundreds of very simple processors coupled to a small portion of the on-chip memory. Each processor, or tile, also contains a small bank of configurable logic, allowing synthesis of complex operations directly in configurable hardware. Unlike the others, this architecture does not use a traditional instruction set architecture. Instead, programs are compiled directly onto the Raw hardware, with all units told explicitly what to do by the compiler. The compiler even schedules most of the intertile communication. The real limitation to this architecture is the efficacy of the compiler. The authors demonstrate impressive speedups for simple algorithms that lend themselves well to this architectural model, but whether this architecture will be effective for future workloads is an open question.

Space-time scheduling of instruction-level parallelism on a raw machine

Increasing demand for both greater parallelism and faster clocks dictate that future generation architectures will need to decentralize their resources and eliminate primitives that require single cycle global communication. A Raw microprocessor distributes all of its resources, including instruction streams, register files, memory ports, and ALUs, over a pipelined two-dimensional mesh interconnect, and exposes them fully to the compiler. Because communication in Raw machines is distributed, compiling for instruction-level parallelism (ILP) requires both spatial instruction partitioning as well as traditional temporal instruction scheduling. In addition, the compiler must explicitly manage all communication through the interconnect, including the global synchronization required at branch points. This paper describes RAWCC, the compiler we have developed for compiling general-purpose sequential programs to the distributed Raw architecture. We present performance results that demonstrate that although Raw machines provide no mechanisms for global communication the Raw compiler can schedule to achieve speedups that scale with the number of available functional units.

Bidwidth analysis with application to silicon compilation

This paper introduces Bitwise, a compiler that minimizes the bitwidth the number of bits used to represent each operand for both integers and pointers in a program. By propagating 70static information both forward and backward in the program dataflow graph, Bitwise frees the programmer from declaring bitwidth invariants in cases where the compiler can determine bitwidths automatically. Because loop instructions comprise the bulk of dynamically executed instructions, Bitwise incorporates sophisticated loop analysis techniques for identifying bitwidths. We find a rich opportunity for bitwidth reduction in modern multimedia and streaming application workloads. For new architectures that support sub-word data-types, we expect that our bitwidth reductions will save power and increase processor performance. This paper also applies our analysis to silicon compilation, thetranslation of programs into custom hardware, to realize the full benefits of bitwidth reduction. We describe our integration of Bitwise with the DeepC Silicon Compiler. By taking advantage of bitwidth information during architectural synthesis, we reduce silicon real estate by 15 - 86%, improve clock speed by 3 - 249%, and reduce power by 46 - 73%. The next era of general purpose and reconfigurable architectures should strive to capture a portion of these gains.

Logic emulation with virtual wires

Logic emulation enables designers to functionally verify complex integrated circuits prior to chip fabrication. However, traditional FPGA-based logic emulators have poor inter-chip communication bandwidth, commonly limiting gate utilization to less than 20%. Global routing contention mandates the use of expensive crossbar and PC-board technology in a system of otherwise low-cost commodity parts. Even with crossbar technology, current emulators only use a fraction of potential communication bandwidth because they dedicate each FPGA pin (physical wire) to a single emulated signal (logical wire). Virtual wires overcome pin limitations by intelligently multiplexing each physical wire among multiple logical wires, and pipelining these connections at the maximum clocking frequency of the FPGA. The resulting increase in bandwidth allows effective use of low-dimension direct interconnect. The size of the FPGA array can be decreased as well, resulting in low-cost logic emulation. This paper covers major contributions of the MIT Virtual Wires project. In the context of a complete emulation system, we analyze phase-based static scheduling and routing algorithms, present virtual wires synthesis methodologies, and overview an operational prototype with 20 K-gate boards. Results, including in-circuit emulation of a SPARC microprocessor, indicate that virtual wires eliminate the need for expensive crossbar technology while increasing FPGA utilization beyond 45%. Theoretical analysis predicts that virtual wires emulation scales with FPGA size and average routing distance, while traditional emulation does not.

Parallelizing applications into silicon

The next decade of computing will be dominated by embedded systems, information appliances and application-specific computers. In order to build these systems, designers will need high-level compilation and CAD tools that generate architectures that effectively meet the needs of each application. In this paper we present a novel compilation system that allows sequential programs, written in C or FORTRAN, to be compiled directly into custom silicon or reconfigurable architectures. This capability is also interesting because trends in computer architecture are moving towards more reconfigurable hardware-like substrates, such as FPGA based systems. Our system works by successfully combining two resource-efficient computing disciplines: Small Memories and Virtual Wires. For a given application, the compiler first analyzes the memory access patterns of pointers and arrays in the program and constructs a partitioned memory system made up of many small memories. The computation is implemented by active computing elements that are spatially distributed within the memory array. A space-time scheduler assigns instructions to the computing elements in a way that maximizes locality and minimizes physical communication distance. It also generates an efficient static schedule for the interconnect. Finally, specialized hardware for the resulting schedule of memory accesses, wires, and computation is generated as a multi-process state machine in synthesizable Verilog. With this system, implemented as a set of SUIF compiler passes, we have successfully compiled programs into hardware and achieve specialization performance enhancements by up to an order of magnitude versus a single general purpose processor. We also achieve additional parallelization speedups similar to those obtainable using a tightly-interconnected multiprocessor.

The GreenDroid Mobile Application Processor: An Architecture for Silicon's Dark Future

This article discusses about Greendroid mobile Application Processor. Dark silicon has emerged as the fundamental limiter in modern processor design. The Greendroid mobile application processor demonstrates an approach that uses dark silicon to execute general-purpose smart phone applications with less energy than todays most energy efficient designs.

The RAW benchmark suite: computation structures for general purpose computing

The RAW benchmark suite consists of twelve programs designed to facilitate comparing, validating, and improving reconfigurable computing systems. These benchmarks run the gamut of algorithms found in general purpose computing, including sorting, matrix operations, and graph algorithms. The suite includes an architecture-independent compilation framework, Raw Computation Structures (RawCS), to express each algorithms dependencies and to support automatic synthesis, partitioning, and mapping to a reconfigurable computer. Within this framework, each benchmark is portably designed in both C and Behavioral Verilog and scalably parameterized to consume a range of hardware resource capacities. To establish initial benchmark ratings, we have targeted a commercial logic emulation system based on virtual wires technology to automatically generate designs up to millions of gates (14 to 379 FPGAs). Because the virtual wires techniques abstract away machine-level details like FPGA capacity and interconnect, our hardware target for this system is an abstract reconfigurable logic fabric with memory-mapped host I/O. We report initial speeds in the range of 2X to 1800X faster than a 2.82 SPECint95 SparcStation 20 and encourage others in the field to run these benchmarks on other systems to provide a standard comparison.

An End-to-End Workflow for Engineering of Biological Networks from High-Level Specifications

We present a workflow for the design and production of biological networks from high-level program specifications. The workflow is based on a sequence of intermediate models that incrementally translate high-level specifications into DNA samples that implement them. We identify algorithms for translating between adjacent models and implement them as a set of software tools, organized into a four-stage toolchain: Specification, Compilation, Part Assignment, and Assembly. The specification stage begins with a Boolean logic computation specified in the Proto programming language. The compilation stage uses a library of network motifs and cellular platforms, also specified in Proto, to transform the program into an optimized Abstract Genetic Regulatory Network (AGRN) that implements the programmed behavior. The part assignment stage assigns DNA parts to the AGRN, drawing the parts from a database for the target cellular platform, to create a DNA sequence implementing the AGRN. Finally, the assembly stage computes an optimized assembly plan to create the DNA sequence from available part samples, yielding a protocol for producing a sample of engineered plasmids with robotics assistance. Our workflow is the first to automate the production of biological networks from a high-level program specification. Furthermore, the workflows modular design allows the same program to be realized on different cellular platforms simply by swapping workflow configurations. We validated our workflow by specifying a small-molecule sensor-reporter program and verifying the resulting plasmids in both HEK 293 mammalian cells and in E. coli bacterial cells.

Emulation of the Sparcle microprocessor with the MIT Virtual Wires emulation system

Describes a complete FPGA-based emulation software system using Virtual Wires technology and present the results of emulating an 18K-gate ASIC implementation of a modified Sparc microprocessor. Virtual Wires overcomes the pin-count limitation that formerly restricted the efficiency of FPGA-based logic emulators. The MIT Virtual Wires softwire compiler accepts a netlist description of the system to be emulated and produces programming information for the FPGA hardware, an inexpensive (

Solving graph problems with dynamic computation structures

3000) board designed for Virtual Wires in-circuit emulation. The compiler also provides an interface to standard logic simulator tools for hardware accelerated simulation. We discuss innovative features of the compiler system and knowledge gained during its construction. A comparison is made of different implementations of the on-chip Virtual Wires circuitry synthesized by the compiler. Several enhancements to the original Virtual Wires concept are presented that improve the emulation speed and FPGA utilization.<<ETX>>