diff options
| author | Juzhe-Zhong <juzhe.zhong@rivai.ai> | 2023-06-02 14:31:40 +0800 |
|---|---|---|
| committer | Pan Li <pan2.li@intel.com> | 2023-06-02 15:11:02 +0800 |
| commit | 265357d401fb7215e8fea820d29a48eacdd75ad1 (patch) | |
| tree | 4cbd588a63e9908baf853c566fe0a27bcdd4962f /gcc/rtl.h | |
| parent | 37ff12b96d7c1ee5fe135253c7b9db7e2ba61b71 (diff) | |
| download | gcc-265357d401fb7215e8fea820d29a48eacdd75ad1.zip gcc-265357d401fb7215e8fea820d29a48eacdd75ad1.tar.gz gcc-265357d401fb7215e8fea820d29a48eacdd75ad1.tar.bz2 | |
RISC-V: Optimize reverse series index vector
This patch optimizes the following seriese vector:
[nunits - 1, nunits - 2, ...., 0]
Before this patch:
vid
vmul
vadd
After this patch:
vid
vrsub
This patch is an obvious and simple optimization, ok for trunk?
gcc/ChangeLog:
* config/riscv/riscv-v.cc (expand_vec_series): Optimize reverse series index vector.
gcc/testsuite/ChangeLog:
* gcc.target/riscv/rvv/autovec/vls-vlmax/perm-4.c: Add assembly check.
Diffstat (limited to 'gcc/rtl.h')
0 files changed, 0 insertions, 0 deletions