Optimize 64-bit unsigned shifts.

They now try to shift 16 bits at a time and only go bit-by-bit for the last 15 or fewer bit positions.
This commit is contained in:
Stephen Heumann 2021-02-12 15:58:27 -06:00
parent 7ad54827a3
commit 91f0dcbdb9
1 changed files with 36 additions and 6 deletions

View File

@ -349,14 +349,29 @@ num1 equ 4
phd
tcd
loop1 lsr num1+6 do the shift
txa
loop0 cmp #16 shift by 16s first
blt loop1
ldy num1+2
sty num1
ldy num1+4
sty num1+2
ldy num1+6
sty num1+4
stz num1+6
; sec
sbc #16
bne loop0
bra rt0
loop1 lsr num1+6 do the remaining shift
ror num1+4
ror num1+2
ror num1
dex
dec a
bne loop1
pld
rt0 pld
rtl rtl
end
@ -419,14 +434,29 @@ num1 equ 4
phd
tcd
loop1 asl num1 do the shift
txa
loop0 cmp #16 shift by 16s first
blt loop1
ldy num1+4
sty num1+6
ldy num1+2
sty num1+4
ldy num1
sty num1+2
stz num1
; sec
sbc #16
bne loop0
bra rt0
loop1 asl num1 do the remaining shift
rol num1+2
rol num1+4
rol num1+6
dex
dec a
bne loop1
pld
rt0 pld
rtl rtl
end