Jun HeandGitHub 558cf20d0d decomp: add prefetch for matched seq on aarch64 (#3164) ...

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

2022-07-29 10:27:20 -07:00

..

huf_decompress_amd64.S

Simplify HUF_decompress4X2_usingDTable_internal_bmi2_asm_loop

2022-01-19 18:38:46 +01:00

huf_decompress.c

Fix nits

2022-02-14 14:24:50 -05:00

zstd_ddict.c

renamed HufLog into ZSTD_HUFFDTABLE_CAPACITY_LOG

2022-01-26 14:47:24 -08:00

zstd_ddict.h

[copyright][license] Switch to yearless copyright and some cleanup in the linux-kernel files

2021-03-30 10:30:43 -07:00

zstd_decompress_block.c

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

2022-07-29 10:27:20 -07:00

zstd_decompress_block.h

Reduce bit tables to 8bit

2021-12-14 23:47:57 +01:00

zstd_decompress_internal.h

renamed HufLog into ZSTD_HUFFDTABLE_CAPACITY_LOG

2022-01-26 14:47:24 -08:00

zstd_decompress.c

Streaming decompression can detect incorrect header ID sooner

2022-06-21 23:09:03 -07:00