Register File Capacity Satisfaction during Scheduling
نویسندگان
چکیده
In code generation of DSP code for distributed register files architectures the register binding, if not treated properly, becomes a complex problem to be solved. This is also the case for high level synthesis of DSP circuits with limited number of registers. A better way to deal with register file capacity constraints is to alternate between register binding and scheduling in a way that a decision made in one prunes the search space for the other. In this paper we present a method to handle register file capacity constraints during scheduling together with tight resourceand timing constraints. The characteristics of the exact coloring of conflict graphs, representing the relative overlap of values lifetimes, are analyzed in order to identify the values that are a bottleneck for register binding, and serialize their productions and consumptions. This is done with pairs of values until it can be guaranteed that the register file capacity constraints will be satisfied. Experiments in the FACTS environment show that we efficiently obtain high quality schedules for DSP kernels and inner loops. Keywords— Code generation; High Level Synthesis; Scheduling; Register binding; Constraint analysis.
منابع مشابه
Register Files Constraint Satisfaction during Scheduling of DSP Code
Algorithms in digital signal processing (DSP) impose tight timing constraints that the compiler has to respect while considering the limited capacity of the available register files in a target DSP processor. Traditional code generation methods that schedule spill code to satisfy storage capacity may take many iterations and are usually not capable of satisfying the timing constraints. In this ...
متن کاملCLUSTERED MULTI-PORTED REGISTER FILE WITH BUILT-IN-SELF- TEST CIRCUTRIES IN 90nm CMOS TECHNOLOGY
Requirement on number of register file (RF) ports in parallel processors poses a stringent challenge on RF design. Access time, power consumption and silicon area of the RF are strongly related to the micro-architecture and the number of access ports. A clustered register file with global registers is presented in this paper. Circuit techniques and scheduling sequences are also presented to enh...
متن کاملGuaranteeing Forward Progress of Unified Register Allocation and Instruction Scheduling
Increasingly demanding computation requirements and tighter energy constraints have motivated distributed and/or hierarchical register file (dhrf) organizations as a mean to efficiently sustain a sufficient alu utilization in processors targeting embedded applications with many alus. Compared to conventional centralized register file organizations, dhrfs lead to tighter coupling between registe...
متن کاملHierarchical Clustered Register File Organization for VLIW Processors
Technology projections indicate that wire delays will become one of the biggest constraints in future microprocessor designs. To avoid long wire delays and therefore long cycle times, processor cores must be partitioned into components so that most of the communication is done locally. In this paper, we propose a novel register file organization for VLIW cores that combines clustering with a hi...
متن کاملCompiler-assisted power optimization for clustered VLIW architectures
Clustered VLIW architectures solve the scalability problem associated with flat VLIW architectures by partitioning the register file and connecting only a subset of the functional units to a register file. However, inter-cluster communication in clustered architectures leads to increased leakage in functional components and a high number of register accesses. In this paper, we propose compiler ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1999