ddidderr/zstd-rs
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

decomp: add prefetch for matched seq on aarch64 (#3164)

Browse Source 
match is used for following sequence copy. It is
only updated when extDict is needed, which is a
low probability case. So it can be prefetched to
reduce cache miss.
The benchmarks on various Arm platforms showed
uplift from 1% ~ 14% with gcc-11/clang-14.

Signed-off-by: Jun He <jun.he@arm.com>
Change-Id: If201af4799d2455d74c79f8387404439d7f684ae
This commit is contained in:
Jun He
2022-07-29 10:27:20 -07:00
committed by GitHub
parent 85d633042d
commit 558cf20d0d
1 changed files with 5 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
lib/decompress/zstd_decompress_block.c
+5
View File
@@ -967,6 +967,11 @@ size_t ZSTD_execSequence(BYTE* op,
assert(op != NULL /* Precondition */); assert(op != NULL /* Precondition */);
assert(oend_w < oend /* No underflow */); assert(oend_w < oend /* No underflow */);
#if defined(__aarch64__)
/* prefetch sequence starting from match that will be used for copy later */
PREFETCH_L1(match);
#endif
/* Handle edge cases in a slow path: /* Handle edge cases in a slow path:
* - Read beyond end of literals * - Read beyond end of literals
* - Match end is within WILDCOPY_OVERLIMIT of oend * - Match end is within WILDCOPY_OVERLIMIT of oend