mirror/gmsm
1
0
Fork 0
mirror of https://github.com/emmansun/gmsm.git synced 2025-04-26 20:26:19 +08:00
Code Issues Packages Projects Releases Wiki Activity

optimize the memory loading

Browse Source
This commit is contained in:
Emman 2021-12-27 16:11:23 +08:00
parent ced4631f5f
commit cb8862bd6c
1 changed files with 26 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

49
sm3/sm3block_arm64.s
View File

@ -152,14 +152,14 @@
COPYRESULT(b, d, f, h) COPYRESULT(b, d, f, h)
// func block(dig *digest, p []byte) // func block(dig *digest, p []byte)
TEXT ·block(SB), 0, $1048-32 TEXT ·block(SB), 0, $272-32
MOVD dig+0(FP), hlp1 MOVD dig+0(FP), hlp1
MOVD p_base+8(FP), SI MOVD p_base+8(FP), SI
MOVD p_len+16(FP), DX MOVD p_len+16(FP), DX
MOVD RSP, BP MOVD RSP, BP
AND $~63, DX AND $~63, DX
CBZ DX, end CBZ DX, end
ADD SI, DX, DI ADD SI, DX, DI
@ -169,6 +169,15 @@ TEXT ·block(SB), 0, $1048-32
LDPW (3*8)(hlp1), (R25, R26) LDPW (3*8)(hlp1), (R25, R26)
loop: loop:
MOVW R19, R10
MOVW R20, R11
MOVW R21, R12
MOVW R22, R13
MOVW R23, R14
MOVW R24, R15
MOVW R25, R16
MOVW R26, R17
MSGSCHEDULE0(0) MSGSCHEDULE0(0)
MSGSCHEDULE0(1) MSGSCHEDULE0(1)
MSGSCHEDULE0(2) MSGSCHEDULE0(2)
@ -241,29 +250,23 @@ loop:
SM3ROUND2(62, 0x9ea1e762, R21, R22, R23, R24, R25, R26, R19, R20) SM3ROUND2(62, 0x9ea1e762, R21, R22, R23, R24, R25, R26, R19, R20)
SM3ROUND2(63, 0x3d43cec5, R20, R21, R22, R23, R24, R25, R26, R19) SM3ROUND2(63, 0x3d43cec5, R20, R21, R22, R23, R24, R25, R26, R19)
LDPW (0*8)(hlp1), (AX, BX) EORW R10, R19 // H0 = a XOR H0
EORW AX, R19 // H0 = a XOR H0 EORW R11, R20 // H1 = b XOR H1
EORW BX, R20 // H1 = b XOR H1 EORW R12, R21 // H0 = a XOR H0
STPW (R19, R20), (0*8)(hlp1) EORW R13, R22 // H1 = b XOR H1
EORW R14, R23 // H0 = a XOR H0
LDPW (1*8)(hlp1), (AX, BX) EORW R15, R24 // H1 = b XOR H1
EORW AX, R21 // H2 = c XOR H2 EORW R16, R25 // H0 = a XOR H0
EORW BX, R22 // H3 = d XOR H3 EORW R17, R26 // H1 = b XOR H1
STPW (R21, R22), (1*8)(hlp1)
LDPW (2*8)(hlp1), (AX, BX)
EORW AX, R23 // H4 = e XOR H4
EORW BX, R24 // H5 = f XOR H5
STPW (R23, R24), (2*8)(hlp1)
LDPW (3*8)(hlp1), (AX, BX)
EORW AX, R25 // H6 = g XOR H6
EORW BX, R26 // H7 = h XOR H7
STPW (R25, R26), (3*8)(hlp1)
ADD $64, SI ADD $64, SI
CMP SI, DI CMP SI, DI
BNE loop BNE loop
STPW (R19, R20), (0*8)(hlp1)
STPW (R21, R22), (0*8)(hlp1)
STPW (R23, R24), (0*8)(hlp1)
STPW (R25, R26), (0*8)(hlp1)
end: end:
RET RET