diff options
| author | Jakub Jelinek <jakub@redhat.com> | 2023-11-28 13:29:58 +0100 |
|---|---|---|
| committer | Jakub Jelinek <jakub@redhat.com> | 2023-11-28 13:29:58 +0100 |
| commit | 4a50820ee8f153265ec8ffd068618607d4be3a26 (patch) | |
| tree | 680392257eafcb9160a66e62070f802374d2eda6 /include | |
| parent | e5f1ee1832ff9e970833fa5773f46c3e0b93bc04 (diff) | |
| download | binutils-4a50820ee8f153265ec8ffd068618607d4be3a26.zip binutils-4a50820ee8f153265ec8ffd068618607d4be3a26.tar.gz binutils-4a50820ee8f153265ec8ffd068618607d4be3a26.tar.bz2 | |
libiberty, ld: Use x86 HW optimized sha1
The following patch attempts to use x86 SHA ISA if available to speed
up in my testing about 2.5x sha1 build-id processing (in my case on
AMD Ryzen 5 3600) while producing the same result.
I believe AArch64 has similar HW acceleration for SHA1, perhaps it
could be added similarly.
Note, seems lld uses BLAKE3 rather than md5/sha1. I think it would be
a bad idea to lie to users, if they choose --buildid=sha1, we should
be using SHA1, not some other checksum, but perhaps we could add some other
--buildid= styles and perhaps make one of the new the default.
Tested on x86_64-linux, both on Intel i9-7960X (which doesn't have
sha_ni ISA support) without/with the patch and on AMD Ryzen 5 3600
(which does have it) without/with the patch.
2023-11-28 Jakub Jelinek <jakub@redhat.com>
include/
* sha1.h (sha1_process_bytes_fn): New typedef.
(sha1_choose_process_bytes): Declare.
libiberty/
* configure.ac (HAVE_X86_SHA1_HW_SUPPORT): New check.
* sha1.c: If HAVE_X86_SHA1_HW_SUPPORT is defined, include x86intrin.h
and cpuid.h.
(sha1_hw_process_bytes, sha1_hw_process_block,
sha1_choose_process_bytes): New functions.
* config.in: Regenerated.
* configure: Regenerated.
ld/
* ldbuildid.c (generate_build_id): Use sha1_choose_process_bytes ()
instead of &sha1_process_bytes.
Diffstat (limited to 'include')
| -rw-r--r-- | include/ChangeLog | 5 | ||||
| -rw-r--r-- | include/sha1.h | 7 |
2 files changed, 12 insertions, 0 deletions
diff --git a/include/ChangeLog b/include/ChangeLog index dbef999..d9e4dc4 100644 --- a/include/ChangeLog +++ b/include/ChangeLog @@ -1,3 +1,8 @@ +2023-11-28 Jakub Jelinek <jakub@redhat.com> + + * sha1.h (sha1_process_bytes_fn): New typedef. + (sha1_choose_process_bytes): Declare. + 2023-11-10 Simon Marchi <simon.marchi@efficios.com> * elf/amdgpu.h (EF_AMDGPU_MACH_AMDGCN_GFX1100, diff --git a/include/sha1.h b/include/sha1.h index eb86fbb..6c94a47 100644 --- a/include/sha1.h +++ b/include/sha1.h @@ -108,6 +108,13 @@ extern void sha1_process_block (const void *buffer, size_t len, extern void sha1_process_bytes (const void *buffer, size_t len, struct sha1_ctx *ctx); +typedef void (*sha1_process_bytes_fn) (const void *, size_t, + struct sha1_ctx *); + +/* Return sha1_process_bytes or some hardware optimized version thereof + depending on current CPU. */ +extern sha1_process_bytes_fn sha1_choose_process_bytes (void); + /* Process the remaining bytes in the buffer and put result from CTX in first 20 bytes following RESBUF. The result is always in little endian byte order, so that a byte-wise output yields to the wanted |