Estimating interlock and improving balance for pipelined architectures

Callahan, David; Cocke, John; Kennedy, Ken

doi:10.1016/0743-7315(88)90002-0

Cited by 123 publications

(89 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dependence profiling is used in [23] to help the optimizations for hyper-blocks. The profiling is supported by a special hardware structure called the conflict buffer.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Data Dependence Profiling for Speculative Optimizations

Chen

Lin

Dai

et al. 2004

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Data dependence analysis is the foundation to many reordering related compiler optimizations and loop parallelization. Traditional data dependence analysis algorithms are developed primarily for Fortran-like subscripted array variables. They are not very effective for pointer-based references in C or C++. With more advanced hardware support for speculative execution, such as the advanced load instructions in Intel's IA64 architecture, some data dependences with low probability can be speculatively ignored. However, such speculative optimizations must be carefully applied to avoid excessive cost associated with potential mis-speculations. Data dependence profiling is one way to provide probabilistic information on data dependences to guide such speculative optimizations and speculative thread generation.

show abstract

“…Dependence profiling is used in [23] to help the optimizations for hyper-blocks. The profiling is supported by a special hardware structure called the conflict buffer.…”

Section: Related Workmentioning

confidence: 99%

“…Data speculation has been used to move loads speculatively so that the length of a critical path can be reduced [23]. In the ORC compiler, the speculation is based on heuristic rules.…”

Section: Speculative Code Schedulingmentioning

confidence: 99%

Data Dependence Profiling for Speculative Optimizations

Chen

Lin

Dai

et al. 2004

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…In this case, the improvements in cache performance far outweigh the potential loss in low-level parallelism when the recurrence is carried by the innermost loop. To regain any lost parallelism, unroll-and-jam can be applied to the outermost loop [Callahan et al 1988;Carr and Kennedy 1994a]. Finally, it is important to note that the programmer was allowed to write the code in a form for one type of machine and still attain machine-independent performance through the use of compiler optimization.…”

Section: Analysis Of Individual Programsmentioning

confidence: 99%

Improving data locality with loop transformations

McKinley

Carr

Tseng

1996

ACM Trans. Program. Lang. Syst.

412

301

View full text Add to dashboard Cite

In the past decade, processor speed has become significantly faster than memory speed. Small, fast cache memories are designed to overcome this discrepancy, but they are only effective when programs exhibit data locality. In this article, we present compiler optimizations to improve data locality based on a simple yet accurate cost model. The model computes both temporal and spatial reuse of cache lines to find desirable loop organizations. The cost model drives the application of compound transformations consisting of loop permutation, loop fusion, loop distribution, and loop reversal. We demonstrate that these program transformations are useful for optimizing many programs. To validate our optimization strategy, we implemented our algorithms and ran experiments on a large collection of scientific programs and kernels. Experiments illustrate that for kernels our model and algorithm can select and achieve the best loop structure for a nest. For over 30 complete applications, we executed the original and transformed versions and simulated cache hit rates. We collected statistics about the inherent characteristics of these programs and our ability to improve their data locality. To our knowledge, these studies are the first of such breadth and depth. We found performance improvements were difficult to achieve because benchmark programs typically have high hit rates even for small data caches; however, our optimizations significantly improved several programs.

show abstract

“…Callahan et al described the transformation as unroll-and-jam and gave its legality test [6], which allows a compiler implementation [8]. The later studies, for examples Wolf and Lam [39], Cierniak and Li [9], and Kodukula et al [24], modeled tiling as an optimization problem in the (highdimensional) iteration space and approximated the optimal solution in various ways.…”

Section: Related Workmentioning

confidence: 99%

“…In 1988, Callahan, Cocke, and Kennedy gave a model called balance to measure the match between the memory demand of a program and the data bandwidth of a machine [6]. Some programs run well on machines with a memory hierarchy, and some need the high-bandwidth vector memory.…”

Section: Potential Uses Of the Systemmentioning

confidence: 99%

The Potential of Computation Regrouping for Improving Locality

Ding

Orlovich

Proceedings of the ACM/IEEE SC2004 Conference

View full text Add to dashboard Cite

Improving program locality has become increasingly important on modern computer systems. An effective strategy is to group computations on the same data so that once the data are loaded into cache, the program performs all their operations before the data are evicted. However, computation regrouping is difficult to automate for programs with complex data and control structures.This paper studies the potential of locality improvement through trace-driven computation regrouping. First, it shows that maximizing the locality is different from maximizing the parallelism or maximizing the cache utilization. The problem is NP-hard even without considering data dependences and cache organization. Then the paper describes a tool that performs constrained computation regrouping on program traces. The new tool is unique because it measures the exact control dependences and applies complete memory renaming and re-allocation. Using the tool, the paper measures the potential locality improvement in a set of commonly used benchmark programs written in C.

show abstract

Estimating interlock and improving balance for pipelined architectures

Cited by 123 publications

References 5 publications

Data Dependence Profiling for Speculative Optimizations

Data Dependence Profiling for Speculative Optimizations

Improving data locality with loop transformations

The Potential of Computation Regrouping for Improving Locality

Contact Info

Product

Resources

About