Code optimization

It is a long time since someone mentioned ASM coding on MRC.

Time to repair this issue.
Can this code be optimized ?

The two functions are supposed to copy from and to a "room" of size map_w X map_h (height do not care)
the background under a frame taken from external data and store the tiles in a buffer.

The position in the room and the address of the buffer that stores the background are passed
as parameters in registers BC and DE.

The frame number is passed on the stack.

;de   source_addr;
;bc   dest_addr;
;ix+4 e ix+5 nframe
    global _npctgrab
_npctgrab:
    push    ix
    ld  ix,0
    add ix,sp

    push    de
    ld  e,(ix+4)
    ld  d,(ix+5)
    ld  hl,_frames
    add hl,de
    add hl,de
    ld  e,(hl)
    inc hl
    ld  d,(hl)  ; de punta alla frame corrente
    push    de
    pop     ix  ; ora ix punta alla frame corrente

    pop hl      ; hl punta alla source in room

    ld d,b      ; bc puntava alla destination in frame buffer
    ld e,c      ; ora de punta alla destination in frame buffer

1:  ld  a,(ix+0)      ; 127 == fine

    cp 127
    jp z,3f

    ld  c,a
    ld  b,0
    push hl
    add hl,bc       ; source

    ld  c,(ix+1)    ; len
    inc ix
    inc ix
    add ix,bc

    ldir

    pop hl

    ld  bc,(_map_w)
    add hl,bc

    jp  1b

3:  pop ix
    pop hl
    pop af
    jp  (hl)



;de   source_addr;
;bc   dest_addr;
;ix+4 e ix+5 nframe
    global _npctrest
_npctrest:
    push    ix
    ld  ix,0
    add ix,sp

    push    de
    ld  e,(ix+4)
    ld  d,(ix+5)
    ld  hl,_frames
    add hl,de
    add hl,de
    ld  e,(hl)
    inc hl
    ld  d,(hl)  ; de punta alla frame corrente
    push    de
    pop     ix  ; ora ix punta alla frame corrente

    pop hl      ; hl punta alla source in room

    ld d,b      ; bc puntava alla destination in frame buffer
    ld e,c      ; ora de punta alla destination in frame buffer

1:  ld  a,(ix+0)      ; 127 == fine

    cp 127
    jp z,3f

    ld  c,a
    ld  b,0
    push de
    ex de,hl
    add hl,bc       ; source
    ex de,hl

    ld  c,(ix+1)    ; len
    inc ix
    inc ix
    add ix,bc

    ldir
    pop de

    ld  bc,(_map_w)
    ex de,hl      
    add hl,bc
    ex de,hl  
    jp  1b

3:  pop ix
    pop hl
    pop af
    jp  (hl)

The frame data are structured like this

framex1:
db 0,2,18,19 ; X offset of line 0, length of line 0, data, data ect
db 0,2,20,21;  X offset of line 1, length of line 1, data, data ect
db 127         ; end of the frame

frame0:
db 5,1,147
db 4,1,147
db 3,1,147
db 2,1,147
db 1,1,147
db 127

etc

_frames:
    dw  framex1,frame0,frame1,frame2,frame3,frame4,frame5, etc etc