Instruction Assignment for Clustered VLIW DSP Compilers: A New Approach
نویسنده
چکیده
VLIW, clustering, assignment, ILP, DSP This report proposes a new heuristic/model driven approach to assign nodes of a computational DAG to clusters for a VLIW machine with a partitioned register file. Our approach exploits a heuristically found initial clustering to speed up the convergence of a deterministic descent algorithm. The initial configuration is determined through a longest path driven strategy that collects a number of paths or sub-dags starting from the DAG's leaves. The initial node assignment problem is then simplified to the assignment of these partial components to one of the k clusters.
منابع مشابه
Register Allocation for VLIW DSP Processors with Irregular Register Files
A variety of new register file architectures have been developed for embedded processors in recent years, promoting hardware design to achieve low-power dissipation and reduced die size over traditional unified register file structures. This paper presents a novel register allocation scheme for a clustered VLIW DSP processor which is designed with distinctively banked register files in which po...
متن کاملA Study of Loop Unrolling for VLIW-based DSP Processors
With the growing popularity of DSPs and their associated applications, cost-effective software development has become a major issue. High-level language compilers are becoming more commonplace in the DSP world. While these compilers can generate correct code for DSP architectures, there remains considerable room for performance improvements. This paper addresses issues related to DSP compilatio...
متن کاملPALF: compiler supports for irregular register files in clustered VLIW DSP processors
Wide varieties of register file architectures — developed for embedded processors — have turned to aim at reducing the power dissipation and die size these years, by contrast with the traditional unified register file structures. This article presents a novel register allocation scheme for a clustered VLIW DSP, which is designed with distinctively banked register files in which port access is h...
متن کاملEffective Code Generation for Distributed and Ping-Pong Register Files: A Case Study on PAC VLIW DSP Cores
The compiler is generally regarded as the most important software component that supports a processor design to achieve success. This paper describes our application of the open research compiler infrastructure to a novel VLIW DSP (known as the PAC DSP core) and the specific design of code generation for its register file architecture. The PAC DSP utilizes port-restricted, distributed, and part...
متن کاملORC2DSP: Compiler Infrastructure Supports for VLIW DSP Processors
In this paper, we describe our experiences in deploying ORC infrastructures for a novel 32-bit VLIW DSP processor (known as PAC core), which equips with new architectural features, such as distributed and ‘ping-pong’ register files. We also present methods in retargeting ORC compilers for PAC VLIW DSP processors. In addition, mechanisms are proposed to incorporate register allocation policies i...
متن کامل