Profile-guided optimisation for indirect branches in a binary translator
Binary translators, which translate the binary executables from one instruction set to another, are useful tools. Indirect branches are one of the key factors that affect the efficiency of binary translators. In the previous research, our lab developed an LLVM-based binary translation framework, cal...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2022-12-01
|
| Series: | Connection Science |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/09540091.2022.2041555 |
| _version_ | 1797684023609262080 |
|---|---|
| author | Jyun-Siang Huang Wuu Yang Yi-Ping You |
| author_facet | Jyun-Siang Huang Wuu Yang Yi-Ping You |
| author_sort | Jyun-Siang Huang |
| collection | DOAJ |
| description | Binary translators, which translate the binary executables from one instruction set to another, are useful tools. Indirect branches are one of the key factors that affect the efficiency of binary translators. In the previous research, our lab developed an LLVM-based binary translation framework, called Rabbit. Rabbit introduces novel optimisations: platform-dependent hyperchaining and platform-independent hyperchaining for improving the emulation of the indirect branch instructions. Indirect branch instructions may have several destinations, and these destinations are not known until runtime. Both platform-independent and platform-dependent hyperchaining establish a search table for each indirect branch instruction to record the visited branch destinations at runtime. In this work, we focus on the translation from AArch64 binary to RISC-V binary and further develop the profile-guided optimisation for indirect branch, which collects runtime information, including branch destinations and execution frequency of each destination for each indirect branch instruction, and then use the information to improve hyperchaining (i.e. accelerate the process of finding the branch destination). The profile-guided optimisation can be divided to profile-guided platform-independent hyperchaining and profile-guided platform-dependent hyperchaining. We finally use SPEC CPU 2006 CINT benchmark to evaluate the optimisations. The experiment results indicate that compared with (1) no chaining, (2) platform-independent hyperchaining and (3) platform-dependent hyperchaining, profile-guided platform-independent hyperchaining provides 1.123×, 1.066× and 1.098× speedup respectively. Similarly, profile-guided platform-dependent hyperchaining achieves 1.106×, 1.047× and 1.083× speedup with respect to the above three configurations, respectively. |
| first_indexed | 2024-03-12T00:24:34Z |
| format | Article |
| id | doaj.art-b4900e2d532049a2a517f9de615ca564 |
| institution | Directory Open Access Journal |
| issn | 0954-0091 1360-0494 |
| language | English |
| last_indexed | 2024-03-12T00:24:34Z |
| publishDate | 2022-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Connection Science |
| spelling | doaj.art-b4900e2d532049a2a517f9de615ca5642023-09-15T10:48:00ZengTaylor & Francis GroupConnection Science0954-00911360-04942022-12-0134174976510.1080/09540091.2022.20415552041555Profile-guided optimisation for indirect branches in a binary translatorJyun-Siang Huang0Wuu Yang1Yi-Ping You2National Yang–Ming Chiao–Tung UniversityNational Yang–Ming Chiao–Tung UniversityNational Yang–Ming Chiao–Tung UniversityBinary translators, which translate the binary executables from one instruction set to another, are useful tools. Indirect branches are one of the key factors that affect the efficiency of binary translators. In the previous research, our lab developed an LLVM-based binary translation framework, called Rabbit. Rabbit introduces novel optimisations: platform-dependent hyperchaining and platform-independent hyperchaining for improving the emulation of the indirect branch instructions. Indirect branch instructions may have several destinations, and these destinations are not known until runtime. Both platform-independent and platform-dependent hyperchaining establish a search table for each indirect branch instruction to record the visited branch destinations at runtime. In this work, we focus on the translation from AArch64 binary to RISC-V binary and further develop the profile-guided optimisation for indirect branch, which collects runtime information, including branch destinations and execution frequency of each destination for each indirect branch instruction, and then use the information to improve hyperchaining (i.e. accelerate the process of finding the branch destination). The profile-guided optimisation can be divided to profile-guided platform-independent hyperchaining and profile-guided platform-dependent hyperchaining. We finally use SPEC CPU 2006 CINT benchmark to evaluate the optimisations. The experiment results indicate that compared with (1) no chaining, (2) platform-independent hyperchaining and (3) platform-dependent hyperchaining, profile-guided platform-independent hyperchaining provides 1.123×, 1.066× and 1.098× speedup respectively. Similarly, profile-guided platform-dependent hyperchaining achieves 1.106×, 1.047× and 1.083× speedup with respect to the above three configurations, respectively.http://dx.doi.org/10.1080/09540091.2022.2041555binary translationprofile-guided optimisationhyperchainingrisc-vaarch64llvmrabbit |
| spellingShingle | Jyun-Siang Huang Wuu Yang Yi-Ping You Profile-guided optimisation for indirect branches in a binary translator Connection Science binary translation profile-guided optimisation hyperchaining risc-v aarch64 llvm rabbit |
| title | Profile-guided optimisation for indirect branches in a binary translator |
| title_full | Profile-guided optimisation for indirect branches in a binary translator |
| title_fullStr | Profile-guided optimisation for indirect branches in a binary translator |
| title_full_unstemmed | Profile-guided optimisation for indirect branches in a binary translator |
| title_short | Profile-guided optimisation for indirect branches in a binary translator |
| title_sort | profile guided optimisation for indirect branches in a binary translator |
| topic | binary translation profile-guided optimisation hyperchaining risc-v aarch64 llvm rabbit |
| url | http://dx.doi.org/10.1080/09540091.2022.2041555 |
| work_keys_str_mv | AT jyunsianghuang profileguidedoptimisationforindirectbranchesinabinarytranslator AT wuuyang profileguidedoptimisationforindirectbranchesinabinarytranslator AT yipingyou profileguidedoptimisationforindirectbranchesinabinarytranslator |