Evaluation and Benefit of Imprecise Value Prediction for Certain Types of Instructions
Based on branch prediction, value prediction has emerged as a solution for problems caused by true data dependencies in pipelined processors. While branch predictors have binary outcomes (taken/not taken), value predictors face a challenging task as their outcomes can take any value. Because of that...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/12/17/3568 |
| _version_ | 1797582677160755200 |
|---|---|
| author | Uroš Radenković Marko Mićović Zaharije Radivojević |
| author_facet | Uroš Radenković Marko Mićović Zaharije Radivojević |
| author_sort | Uroš Radenković |
| collection | DOAJ |
| description | Based on branch prediction, value prediction has emerged as a solution for problems caused by true data dependencies in pipelined processors. While branch predictors have binary outcomes (taken/not taken), value predictors face a challenging task as their outcomes can take any value. Because of that, coverage is reduced to enhance high accuracy and minimise costly recovery from misprediction. This paper evaluates value prediction, focusing on instruction execution with imprecisely predicted operands whose result can still be correct. Two analytical models are introduced to represent instruction execution with value prediction. One model focuses on correctly predicted operands, while the other allows for imprecisely predicted operands as long as the instruction results remain correct. A trace-driven simulator was developed for simulation purposes, implementing well-known predictors and some of the predictors presented at the latest Championship Value Prediction. The gem5 simulator was upgraded to generate program traces of SPEC and EEMBC benchmarks that were used in simulations. Based on the simulation result, proposed analytical models were compared to reveal the conditions under which a model with imprecisely predicted operands, but still correct results, achieved better execution time than a model with correctly predicted operands. Analysis revealed that the accuracy of the correct instruction result based on the predicted operand, even when the predicted operand is imprecise, is higher than the accuracy of the correctly predicted operand. The accuracy improvement ranges from 0.8% to 44%, depending on the specific predictor used. |
| first_indexed | 2024-03-10T23:25:53Z |
| format | Article |
| id | doaj.art-90f6d314143a400ea9581e976b7c043c |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T23:25:53Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-90f6d314143a400ea9581e976b7c043c2023-11-19T08:01:01ZengMDPI AGElectronics2079-92922023-08-011217356810.3390/electronics12173568Evaluation and Benefit of Imprecise Value Prediction for Certain Types of InstructionsUroš Radenković0Marko Mićović1Zaharije Radivojević2School of Electrical Engineering, University of Belgrade, Bulevar kralja Aleksandra 73, 11000 Belgrade, SerbiaSchool of Electrical Engineering, University of Belgrade, Bulevar kralja Aleksandra 73, 11000 Belgrade, SerbiaSchool of Electrical Engineering, University of Belgrade, Bulevar kralja Aleksandra 73, 11000 Belgrade, SerbiaBased on branch prediction, value prediction has emerged as a solution for problems caused by true data dependencies in pipelined processors. While branch predictors have binary outcomes (taken/not taken), value predictors face a challenging task as their outcomes can take any value. Because of that, coverage is reduced to enhance high accuracy and minimise costly recovery from misprediction. This paper evaluates value prediction, focusing on instruction execution with imprecisely predicted operands whose result can still be correct. Two analytical models are introduced to represent instruction execution with value prediction. One model focuses on correctly predicted operands, while the other allows for imprecisely predicted operands as long as the instruction results remain correct. A trace-driven simulator was developed for simulation purposes, implementing well-known predictors and some of the predictors presented at the latest Championship Value Prediction. The gem5 simulator was upgraded to generate program traces of SPEC and EEMBC benchmarks that were used in simulations. Based on the simulation result, proposed analytical models were compared to reveal the conditions under which a model with imprecisely predicted operands, but still correct results, achieved better execution time than a model with correctly predicted operands. Analysis revealed that the accuracy of the correct instruction result based on the predicted operand, even when the predicted operand is imprecise, is higher than the accuracy of the correctly predicted operand. The accuracy improvement ranges from 0.8% to 44%, depending on the specific predictor used.https://www.mdpi.com/2079-9292/12/17/3568value predictionspeculative executioncomputer architectureperformance evaluation |
| spellingShingle | Uroš Radenković Marko Mićović Zaharije Radivojević Evaluation and Benefit of Imprecise Value Prediction for Certain Types of Instructions Electronics value prediction speculative execution computer architecture performance evaluation |
| title | Evaluation and Benefit of Imprecise Value Prediction for Certain Types of Instructions |
| title_full | Evaluation and Benefit of Imprecise Value Prediction for Certain Types of Instructions |
| title_fullStr | Evaluation and Benefit of Imprecise Value Prediction for Certain Types of Instructions |
| title_full_unstemmed | Evaluation and Benefit of Imprecise Value Prediction for Certain Types of Instructions |
| title_short | Evaluation and Benefit of Imprecise Value Prediction for Certain Types of Instructions |
| title_sort | evaluation and benefit of imprecise value prediction for certain types of instructions |
| topic | value prediction speculative execution computer architecture performance evaluation |
| url | https://www.mdpi.com/2079-9292/12/17/3568 |
| work_keys_str_mv | AT urosradenkovic evaluationandbenefitofimprecisevaluepredictionforcertaintypesofinstructions AT markomicovic evaluationandbenefitofimprecisevaluepredictionforcertaintypesofinstructions AT zaharijeradivojevic evaluationandbenefitofimprecisevaluepredictionforcertaintypesofinstructions |