Practical Data Value Speculation for Future High-end Processors

A fait l'objet d'une publication à "High Performance Computer Architecture (HPCA) 2014" Lien : http://people.irisa.fr/Arthur.Perais/data/HPCA%2714_Practical_VP.pdfDedicating more silicon area to single thread performance will necessarily be considered as worthwhile in future - potentially heterogeneous - multicores. In particular, Value prediction (VP) was proposed in the mid 90's to enhance the performance of high-end uniprocessors by breaking true data dependencies. In this paper, we reconsider the concept of Value Prediction in the contemporary context and show its potential as a direction to improve current single thread performance. First, building on top of research carried out during the previous decade on confidence estimation, we show that every value predictor is amenable to very high prediction accuracy using very simple hardware. This clears the path to an implementation of VP without a complex selective reissue mechanism to absorb mispredictions, where prediction is performed in the in-order pipeline frond-end and validation is performed in the in-order pipeline back-end, while the out-of-order engine is only marginally modified. Second, when predicting back-to-back occurrences of the same instruction, previous context-based value predictors relying on local value history exhibit a complex critical loop that should ideally be implemented in a single cycle. To bypass this requirement, we introduce a new value predictor VTAGE harnessing the global branch history. VTAGE can seamlessly predict back-to-back occurrences, allowing predictions to span over several cycles. It achieves higher performance than previously proposed context-based predictors. Specifically, using SPEC'00 and SPEC'06 benchmarks, our simulations show that combining VTAGE and a Stride-based predictor yields up to 65% speedup on a fairly aggressive pipeline without support for selective reissue.Dédier plus de surface de silicium à la performance séquentielle sera nécessairement considéré comme digne d'interêt dans un futur proche. En particulier, la Prédiction de Valeurs (VP) a été proposée dans les années 90 afin d'améliorer la performance séquentielle des processeurs haute-performance en cassant les dépendances de données entre instructions. Dans ce papier, nous revisitons le concept de Prédiction de Valeurs dans un contexte contemporain et montrons son potentiel d'amélioration de la performance séquentielle. Spécifiquement, utilisant les suites de benchmarks SPEC'00 et SPEC'06, nos simulations montrent qu'en combinant notre prédicteur, VTAGE, avec un prédicteur de type Stride, des gains de performances allant jusqu'à 65% peuvent être observés sur un pipeline relativement agressif mais sans ré-exécution sélective en cas de mauvaise prédiction