Compiler-directed soft error resilience for lightweight GPU register file protection
| Autor: | Qingrui Liu, Changhee Jung, Jianping Zeng, Mohammad Abdel-Majeed, Jaejin Lee, Hong-June Kim |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
010302 applied physics
business.industry Computer science Register file Optimizing compiler 02 engineering and technology computer.software_genre 01 natural sciences 020202 computer hardware & architecture Soft error Embedded system 0103 physical sciences 0202 electrical engineering electronic engineering information engineering Overhead (computing) Compiler Pruning (decision trees) Error detection and correction Resilience (network) business computer |
| Zdroj: | PLDI |
| DOI: | 10.1145/3385412.3386033 |
| Popis: | This paper presents Penny, a compiler-directed resilience scheme for protecting GPU register files (RF) against soft errors. Penny replaces the conventional error correction code (ECC) based RF protection by using less expensive error detection code (EDC) along with idempotence based recovery. Compared to the ECC protection, Penny can achieve either the same level of RF resilience yet with significantly lower hardware costs or stronger resilience using the same ECC due to its ability to detect multi-bit errors when it is used solely for detection. In particular, to address the lack of store buffers in GPUs, which causes both checkpoint storage overwriting and the high cost of checkpointing stores, Penny provides several compiler optimizations such as storage coloring and checkpoint pruning. Across 25 benchmarks, Penny causes only ≈3% run-time overhead on average. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|