Merge pull request #3820 from aa022/dev

ARM64 RandomX JIT: dataset prefetch + non-temporal loads (+~8% on M4 base)
ARM64 RandomX JIT: drop early dataset prefetch
2026-06-20 03:24:37 -04:00 · 2026-05-26 00:21:52 +07:00 · 2026-05-25 18:05:50 +02:00 · 2026-05-25 13:46:41 +02:00
1 changed files with 5 additions and 5 deletions
--- a/src/crypto/randomx/jit_compiler_a64_static.S
+++ b/src/crypto/randomx/jit_compiler_a64_static.S
@@ -303,7 +303,7 @@ DECL(randomx_program_aarch64_cacheline_align_mask1):
 	add	x20, x20, x1
 	# Prefetch dataset data
-	prfm	pldl2strm, [x20]
+	prfm	pldl1strm, [x20]
 DECL(randomx_program_aarch64_cacheline_align_mask2):
 	# 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):
 	# xor integer registers with dataset data
-	ldp	x20, x19, [x10]
+	ldnp	x20, x19, [x10]
 	eor	x4, x4, x20
 	eor	x5, x5, x19
-	ldp	x20, x19, [x10, 16]
+	ldnp	x20, x19, [x10, 16]
 	eor	x6, x6, x20
 	eor	x7, x7, x19
-	ldp	x20, x19, [x10, 32]
+	ldnp	x20, x19, [x10, 32]
 	eor	x12, x12, x20
 	eor	x13, x13, x19
-	ldp	x20, x19, [x10, 48]
+	ldnp	x20, x19, [x10, 48]
 	eor	x14, x14, x20
 	eor	x15, x15, x19