Commit Graph

8 Commits

Author SHA1 Message Date
Marcel Cornu
671e67b62d crc: reformat using new code style
Signed-off-by: Marcel Cornu <marcel.d.cornu@intel.com>
2024-04-22 11:35:03 +02:00
Taiju Yamada
1187583a97 Fixes for aarch64 mac
- It should be fine to enable pmull always on Apple Silicon
- macOS 12+ is required for PMULL instruction.
- Changed the conditional macro to __APPLE__
- Rewritten dispatcher using sysctlbyname
- Use __USER_LABEL_PREFIX__
- Use __TEXT,__const as readonly section
- use ASM_DEF_RODATA macro
- fix func decl

Change-Id: I800593f21085d8187b480c8bb3ab2bd70c4a6974
Signed-off-by: Taiju Yamada <tyamada@bi.a.u-tokyo.ac.jp>
2022-10-28 08:27:26 -07:00
Jerry Yu
1c71f9c0ae crc32: tweak performance of crc32/crc32c
Tweak performances with prefetch instructions.

Below is the test results:
- Neoverse N1: ~30%
- Cortex-A72: ~3%
- Cortex-A57: ~90%
- Others: 50% - 5x

Change-Id: I3ab292a953043dbaea98af3c66778f57da3a1331
Signed-off-by: Jerry Yu <jerry.h.yu@arm.com>
2020-07-09 17:37:00 +08:00
Zhiyuan Zhu
031450f697 crc32: Implement default mix mode optimization
Change-Id: Ib3bf04215cca491db522ec33905fe48df173cc2f
Signed-off-by: Zhiyuan Zhu <zhiyuan.zhu@arm.com>
2020-05-09 08:10:34 +00:00
Jerry Yu
9bcd6768fd crc32:Adjust hardware folding algorithm flags
Hardware folding algorithm depend on CRC32 and PMULL instruction.
And it should match both flags .

Change-Id: I361068402db1fe6d7c0bd8d2c7048f1d94880233
Signed-off-by: Jerry Yu <jerry.h.yu@arm.com>
2020-04-08 13:50:15 +08:00
Jerry Yu
0033f42189 crc32:Optimize crc32/c for cortex-a72
Change-Id: Ib1658fd4b87b31d8ea6c93f697b50d9b409c186e
Signed-off-by: Jerry Yu <jerry.h.yu@arm.com>
2020-04-08 13:49:38 +08:00
Jerry Yu
a2fc2c000d crc32:Add optimization implementation for Neoverse N1
This patch is base on reference(1) algorithm with some changes.
- Redefine the block number to two.
  - That's due to only two pipe-line can be used in CRC32 calculate.
- Redefine the block size:
  - The block size of CRC is 1536B and PMULL is 512B
- Interleave CRC and PMULL instructions.
The optimization parameters are calculated base on reference(2)

References:
- https://www.intel.com/content/dam/www/public/us/en/documents/white-papers/fast-crc-computation-generic-polynomials-pclmulqdq-paper.pdf
- https://developer.arm.com/docs/swog309707/a

Change-Id: I1c9e593d59b521f56e4b3c807b396c083c181636
Signed-off-by: Jerry Yu <jerry.h.yu@arm.com>
2020-03-30 09:20:29 -07:00
Jerry Yu
183385f02f multibinary: Add run-time cpu feature detect for aarch64
Some CPUs  report "illegal instruction" error for the crc test because
they do not support the relevant optional feature . This can be fixed by
introducing CPU feature detection for AArch64 .

The difference with the x86 implementation is the dispatcher . It is based
on the glibc function `getauxval(AT_HWCAP)` and `getauxval(AT_HWCAP2)` , not
registers or instructions .

On a  heterogeneous system (big.LITTLE) , it is dangerous to detect CPU
features using identification registers . And while it is possible to use
architectural feature registers from userspace on recent kernels, this
won't necessarily work with older platforms . Thus we use the HW_CAPs
exported from the kernel (and visible in getauxval) as the solution.

- According to kernel suggestion , getauxval should be used for this purpose .
  - [CPU Feature detection](https://github.com/torvalds/linux/blob/master/Documentation/arm64/cpu-feature-registers.rst)
- According to  AAPCS result/paramter registers should be saved/restore for function call
  - [AAPCS](http://infocenter.arm.com/help/topic/com.arm.doc.ihi0055b/IHI0055B_aapcs64.pdf)
  - [GLibc](https://sourceware.org/git/gitweb.cgi?p=glibc.git;a=blob;f=sysdeps/aarch64/dl-trampoline.S)

Signed-off-by: Jerry Yu <jerry.h.yu@arm.com>
Change-Id: Ic9abe0d2268ac95537e1abf10acc642fc58a5054
2019-08-26 17:58:42 +08:00