https://gcc.gnu.org/bugzilla/show_bug.cgi?id=117722
--- Comment #8 from Robin Dapp <rdapp at gcc dot gnu.org> --- So the difference is (usad expansion) vmax vmin vsub vsext vadd vs (right now) vwsub vneg vmax vwadd Why is that preferable?
[Bug target/117722] RISC-V: Failed to vectorize x264_pixel_sad_4x4
rdapp at gcc dot gnu.org via Gcc-bugs Thu, 21 Nov 2024 05:46:20 -0800
- [Bug c/117722] New: RISC-V: Faile... juzhe.zhong at rivai dot ai via Gcc-bugs
- [Bug tree-optimization/11772... juzhe.zhong at rivai dot ai via Gcc-bugs
- [Bug tree-optimization/11772... pan2.li at intel dot com via Gcc-bugs
- [Bug tree-optimization/11772... pinskia at gcc dot gnu.org via Gcc-bugs
- [Bug target/117722] RISC-V: ... rdapp at gcc dot gnu.org via Gcc-bugs
- [Bug target/117722] RISC-V: ... juzhe.zhong at rivai dot ai via Gcc-bugs
- [Bug target/117722] RISC-V: ... rdapp at gcc dot gnu.org via Gcc-bugs
- [Bug target/117722] RISC-V: ... pan2.li at intel dot com via Gcc-bugs
- [Bug target/117722] RISC-V: ... pan2.li at intel dot com via Gcc-bugs
- [Bug target/117722] RISC-V: ... rdapp at gcc dot gnu.org via Gcc-bugs
- [Bug target/117722] RISC-V: ... pan2.li at intel dot com via Gcc-bugs
- [Bug target/117722] RISC-V: ... law at gcc dot gnu.org via Gcc-bugs
- [Bug target/117722] RISC-V: ... rdapp at gcc dot gnu.org via Gcc-bugs
- [Bug target/117722] RISC-V: ... pan2.li at intel dot com via Gcc-bugs
- [Bug target/117722] RISC-V: ... rdapp at gcc dot gnu.org via Gcc-bugs
- [Bug target/117722] RISC-V: ... vineetg at gcc dot gnu.org via Gcc-bugs
- [Bug target/117722] RISC-V: ... rdapp at gcc dot gnu.org via Gcc-bugs
- [Bug target/117722] RISC-V: ... vineetg at gcc dot gnu.org via Gcc-bugs
- [Bug target/117722] RISC-V: ... pan2.li at intel dot com via Gcc-bugs
- [Bug target/117722] RISC-V: ... rdapp at gcc dot gnu.org via Gcc-bugs
