mirrors/xmrig
1
0
Fork 1
mirror of https://github.com/xmrig/xmrig.git synced 2026-06-18 10:22:39 -04:00
Code Issues Projects Releases Wiki Activity

Merge pull request #3820 from aa022/dev

Browse Source 
ARM64 RandomX JIT: dataset prefetch + non-temporal loads (+~8% on M4 base)
This commit is contained in:
xmrig
2026-05-26 00:21:52 +07:00
committed by GitHub
parent 7eadfdc9c6 9ac373fea5
commit 3fb851d91d
1 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
src/crypto/randomx/jit_compiler_a64_static.S
View File

@@ -303,7 +303,7 @@ DECL(randomx_program_aarch64_cacheline_align_mask1):
add x20, x20, x1 add x20, x20, x1
# Prefetch dataset data # Prefetch dataset data
prfm pldl2strm, [x20] prfm pldl1strm, [x20]
DECL(randomx_program_aarch64_cacheline_align_mask2): DECL(randomx_program_aarch64_cacheline_align_mask2):
# Actual mask will be inserted by JIT compiler # Actual mask will be inserted by JIT compiler
@@ -312,16 +312,16 @@ DECL(randomx_program_aarch64_cacheline_align_mask2):
DECL(randomx_program_aarch64_xor_with_dataset_line): DECL(randomx_program_aarch64_xor_with_dataset_line):
# xor integer registers with dataset data # xor integer registers with dataset data
ldp x20, x19, [x10] ldnp x20, x19, [x10]
eor x4, x4, x20 eor x4, x4, x20
eor x5, x5, x19 eor x5, x5, x19
ldp x20, x19, [x10, 16] ldnp x20, x19, [x10, 16]
eor x6, x6, x20 eor x6, x6, x20
eor x7, x7, x19 eor x7, x7, x19
ldp x20, x19, [x10, 32] ldnp x20, x19, [x10, 32]
eor x12, x12, x20 eor x12, x12, x20
eor x13, x13, x19 eor x13, x13, x19
ldp x20, x19, [x10, 48] ldnp x20, x19, [x10, 48]
eor x14, x14, x20 eor x14, x14, x20
eor x15, x15, x19 eor x15, x15, x19