Instruction Scheduling

Govindarajan, Raghav

doi:10.1201/9781420040579.ch17

Cited by 2 publications

(4 citation statements)

References 98 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ranking can be used as a guide for hand-crafted heuristics and also for our automated machine learning approach, as we expect to see at least one of the top-ranked features in any heuristic. A surprise is that critical-path distance to the leaf node, commonly used as the primary feature (Govindarajan 2003;Muchnick 1997), is ranked only in 5th place. Also somewhat surprising is that the lowest ranked features, features 14-17, are dynamic features.…”

Section: Feature Filteringmentioning

confidence: 99%

“…Solving the basic block instruction scheduling problem exactly is known to be difficult, and most compilers use a greedy list scheduling algorithm together with a heuristic for choosing which instruction to schedule next (Govindarajan 2003;Muchnick 1997). Such a heuristic usually consists of a set of features and a priority or order in which to test the features.…”

Section: Introductionmentioning

confidence: 99%

“…In this section, we define the instruction scheduling problem studied in this paper followed by a brief review of the list scheduling algorithm and the heuristics used in the algorithm (for more background on these topics see, for example, Govindarajan 2003;Hennessy and Patterson 2003;Muchnick 1997).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Learning heuristics for basic block instruction scheduling

et al. 2007

View full text Add to dashboard Cite

Instruction scheduling is an important step for improving the performance of object code produced by a compiler. A fundamental problem that arises in instruction scheduling is to find a minimum length schedule for a basic block-a straightline sequence of code with a single entry point and a single exit point-subject to precedence, latency, and resource constraints. Solving the problem exactly is known to be difficult, and most compilers use a greedy list scheduling algorithm coupled with a heuristic. The heuristic is usually hand-crafted, a potentially time-consuming process. In contrast, we present a study on automatically learning good heuristics using techniques from machine learning. In our study, a recently proposed optimal basic block scheduler was used to generate the machine learning training data. A decision tree learning algorithm was then used to induce a simple heuristic from the training data. The automatically constructed decision tree heuristic was compared against a popular critical-path heuristic on the SPEC 2000 benchmarks. On this benchmark suite, the decision tree heuristic reduced the number of basic blocks that were not optimally scheduled by up to 55% compared to the critical-path heuristic, and gave improved performance guarantees in terms of the worst-case factor from optimality.

show abstract

Section: Feature Filteringmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Learning heuristics for basic block instruction scheduling

et al. 2007

View full text Add to dashboard Cite

show abstract

“…Register allocation and coding. Allocate registers in addition and doubling of formulae 27) by as-late-as-possible (ALAP) scheduling policy 24) . The formulae do not consider the registers' allocation, and many registers are used wastefully.…”

Section: Indistinguishable Hyperellipticcurve Addition Formulaementioning

confidence: 99%

Fixed-Hamming-Weight Representation for Indistinguishable Addition Formulae

Mamiya

Miyaji

2006

ipsjdc

View full text Add to dashboard Cite

In the execution of signature on a smart card, side channel attacks such as simple power analysis (SPA) have become serious threat 12) . There are the fixed procedure method and the indistinguishable method for SPA resistant methods. The indistinguishable method conceals all branch instructions by using indistinguishable addition formulae but may reveal the hamming-weight when an addition chain with the un-fixed-hamming-weight is used. In the case of hyper-elliptic curve, the indistinguishable method has not been proposed yet. In this paper, we give an indistinguishable addition formulae of hyper-elliptic curve. We also give algorithms which output the fixed-hamming-weight representation for indistinguishable addition formulae and works with or without computation table, which can dissolve the above mentioned problem on the indistinguishable method and are also applied to an elliptic curve scalar multiplication.

show abstract

Instruction Scheduling

Cited by 2 publications

References 98 publications

Learning heuristics for basic block instruction scheduling

Learning heuristics for basic block instruction scheduling

Fixed-Hamming-Weight Representation for Indistinguishable Addition Formulae

Contact Info

Product

Resources

About