Evaluation of the raw microprocessor: an exposed-wire-delay architecture for ILP and streams

Abstract

This paper evaluates the Raw microprocessor. Raw addresses the challenge of building a general-purpose architecture that performs well on a larger class of stream and embedded computing applications than existing microprocessors, while still running existing ILP-based sequential programs with reasonable performance in the face of increasing wire delays. Raw approaches this challenge by implementing plenty of on-chip resources -including logic, wires, and pins -in a tiled arrangement, and exposing them through a new ISA, so that the software can take advantage of these resources for parallel applications. Raw supports both ILP and streams by routing operands between architecturally-exposed functional units over a point-to-point scalar operand network. This network offers low latency for scalar data transport. Raw manages the effect of wire delays by exposing the interconnect and using software to orchestrate both scalar and stream data transport.We have implemented a prototype Raw microprocessor in IBM's 180 nm, 6-layer copper, CMOS 7SF standard-cell ASIC process. We have also implemented ILP and stream compilers. Our evaluation attempts to determine the extent to which Raw succeeds in meeting its goal of serving as a more versatile, general-purpose processor. Central to achieving this goal is Raw's ability to exploit all forms of parallelism, including ILP, DLP, TLP, and Stream parallelism. Specifically, we evaluate the performance of Raw on a diverse set of codes including traditional sequential programs, streaming applications, server workloads and bit-level embedded computation. Our experimental methodology makes use of a cycle-accurate simulator validated against our real hardware. Compared to a 180 nm Pentium-III, using commodity PC memory system components, Raw performs within a factor of 2x for sequential applications with a very low degree of ILP, about 2x to 9x better for higher levels of ILP, and 10x-100x better when highly parallel applications are coded in a stream language or optimized by hand. The paper also proposes a new versatility metric and uses it to discuss the generality of Raw.Clearly, the ALU area is not a significant constraint on the execution width of a modern-day wide-issue microprocessor. On the other hand, the presence of many physical execution units is a minimum prerequisite to the exploitation of the same massive parallelism that ASICs are able to exploit.3. Management of Wires and Wire Delay: ASIC designers can place and wire communicating operations in ways that minimize wire delay, minimize latency, and maximize bandwidth. In contrast, it is now well known that the delay of the interconnect inside traditional microprocessors limits scalability [36,1,15,38,45]. Itanium II's 6-way integer execution unit presents evidence for this -it spends over half of its critical path in the bypass paths of the ALUs. ASIC designers manage wire delay inherent in large distributed arrays of function units in multiple steps. First, they place close together operations that need to communicate fre...

Reducing the Energy Cost of Irregular Code Bases in Soft Processor Systems

“…We use a cycle-accurate simulation infrastructure based on btl [17]. When the toolchain generates ICERs it also generates models of the new hardware for the cycleaccurate system simulator.…”

“…The MIPS processor core derives from the MIT Raw [17] processor and has an eight stage, in-order, single-issue pipeline. The core includes an L1 data cache, instruction memory, and the Raw networkon-chip router for one Raw tile.…”

Reconciling performance and predictability on a many-core through off-line mapping

“…The RAW architecture was the first to employ communication programs to control on-chip communications. There are several fundamental differences between this work and the work presented in this paper: The objective of RAW is to allow the many-core-wide use of compilation techniques that exploit Instruction Level Parallelism [14] and a very fine grain scheduling of computations and communications. We aim for a coarser level of control in both the NoC (transmission of packets instead of RAW's scalar values), and the software control of the NoC (which is performed through standard components such as caches and DMA units).…”

Adaptive Vision Leveraging Digital Retinas: Extracting Meaningful Segments

“…The latter issue is addressed for more general reasons by the computer architecture community (e.g. [14]). But, in this paper, we focus on artificial retinas (also known as vision chips [11]), which mix processor and memory in an extreme way.…”