mirror of
https://github.com/wownero/RandomX.git
synced 2026-11-19 06:34:34 +01:00
Optimized dataset read (#211)
* Optimized dataset read There was a false dependency on readReg2 and readReg3 (caused by `xor rbp, rax` instruction) when reading dataset item (see design.md - 4.6.2 Loop execution, steps 5 and 7). This change uses `ma` register to read dataset item before the whole `rbp` (`ma` and `mx`) is changed, so superscalar and out-of-order CPU can start executing it earlier. Results: https://i.imgur.com/Bpeq9mx.png ~1% speedup on modern Intel/AMD CPUs. * ARMv8: optimized dataset read Break dependency from readReg2 and readReg3. * Fixed light mode hashing
This commit is contained in:
@@ -307,6 +307,9 @@ literal_v14: .fill 2,8,0
|
||||
literal_v15: .fill 2,8,0
|
||||
|
||||
DECL(randomx_program_aarch64_vm_instructions_end):
|
||||
# Calculate dataset pointer for dataset read
|
||||
# Do it here to break false dependency from readReg2 and readReg3 (see next line)
|
||||
lsr x10, x9, 32
|
||||
|
||||
# mx ^= r[readReg2] ^ r[readReg3];
|
||||
eor x9, x9, x18
|
||||
@@ -324,8 +327,6 @@ DECL(randomx_program_aarch64_cacheline_align_mask1):
|
||||
# mx <-> ma
|
||||
ror x9, x9, 32
|
||||
|
||||
# Calculate dataset pointer for dataset read
|
||||
mov w10, w9
|
||||
DECL(randomx_program_aarch64_cacheline_align_mask2):
|
||||
# Actual mask will be inserted by JIT compiler
|
||||
and x10, x10, 1
|
||||
|
||||
Reference in New Issue
Block a user