diff options
| author | Andy Chiu <tchiu@tenstorrent.com> | 2026-09-01 14:23:32 -0500 |
|---|---|---|
| committer | Paul Walmsley <pjw@kernel.org> | 2026-09-02 11:47:08 -0600 |
| commit | b94cec5761d22624d109d859467d7d4ce0a1b88b (patch) | |
| tree | 395e80008be8e80a0939d56c4aab118a6e555882 /scripts/Makefile.thinlto | |
| parent | 2464ac8a6ff8d8a18b50088eb1d1d638f9cee2f1 (diff) | |
| download | linux-b94cec5761d22624d109d859467d7d4ce0a1b88b.tar.gz linux-b94cec5761d22624d109d859467d7d4ce0a1b88b.zip | |
riscv: skip software algning code for HAVE_EFFICIENT_UNALIGNED_ACCESS
We can jump straight into the copy loop if the kernel is compiled for a
hardware that natively supports misaligned access. The user copy
bandwidth improvement on K3 and Ascaolon is shown as below:
Misaligned user copy, size: 512B (offset: [0:15] except 0, 8)
BW Improvement | Write | Read |
K3 | 6.19% | 3.43% |
Ascalon | 10.0% | 11.4% |
Aligned user copy, size: 512B (offset: 0, 8)
BW Improvement | Write | Read |
K3 | 1.69% | 0.90% |
Ascalon | 1.25% | 3.32% |
Suggested-by: Anton Blanchard <antonb@tenstorrent.com>
Signed-off-by: Andy Chiu <tchiu@tenstorrent.com>
Link: https://patch.msgid.link/20260901192334.3543340-1-tchiu@tenstorrent.com
Signed-off-by: Paul Walmsley <pjw@kernel.org>
Diffstat (limited to 'scripts/Makefile.thinlto')
0 files changed, 0 insertions, 0 deletions