Mercurial > pub > dyncall > dyncall

view doc/disas_examples/mips.o32.disas @ 357:d982a00c2177

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
- PPC64 asm syntax fix, specifying explicitly comparison mode for cmpi (newer toolchains complain, older ones took optional field of instruction which happened to be same value)
author Tassilo Philipp
date Tue, 25 Feb 2020 18:16:13 +0100
parents c0390dc85a07
children 6c72cb768099
line wrap: on
line source

; #include <stdlib.h>
; 
; void leaf_call(int b, int c, int d, int e, int f, int g, int h)
; {
; }
; 
; void nonleaf_call(int a, int b, int c, int d, int e, int f, int g, int h)
; {
; 	/* use some local data */
; 	*(char*)alloca(220) = 'L';
; 	leaf_call(b, c, d, e, f, g, h);
; }
; 
; int main()
; {
; 	nonleaf_call(0, 1, 2, 3, 4, 5, 6, 7);
; 	return 0;
; }



; output from freebsd-12.0_r333647-malta_mipselhf w/ gcc 4.2.1 ----->

00000000 <leaf_call>:
   0:   3c1c0000        lui     gp,0x0
   4:   279c0000        addiu   gp,gp,0
   8:   0399e021        addu    gp,gp,t9
   c:   27bdfff8        addiu   sp,sp,-8
  10:   afbe0000        sw      s8,0(sp)
  14:   03a0f021        move    s8,sp
  18:   afc40008        sw      a0,8(s8)
  1c:   afc5000c        sw      a1,12(s8)
  20:   afc60010        sw      a2,16(s8)
  24:   afc70014        sw      a3,20(s8)
  28:   03c0e821        move    sp,s8
  2c:   8fbe0000        lw      s8,0(sp)
  30:   03e00008        jr      ra
  34:   27bd0008        addiu   sp,sp,8

00000038 <nonleaf_call>:
  38:   3c1c0000        lui     gp,0x0     ; |
  3c:   279c0000        addiu   gp,gp,0    ; |
  40:   0399e021        addu    gp,gp,t9   ; |
  44:   27bdffc8        addiu   sp,sp,-56  ; | prolog
  48:   afbf0034        sw      ra,52(sp)  ; |
  4c:   afbe0030        sw      s8,48(sp)  ; |
  50:   03a0f021        move    s8,sp      ; |         frame pointer (note: with offset to frame start, but static compared to sp)
  54:   afbc0020        sw      gp,32(sp)  ; /
  58:   afc40038        sw      a0,56(s8)  ; \
  5c:   afc5003c        sw      a1,60(s8)  ; |
  60:   afc60040        sw      a2,64(s8)  ; | spill first 4 args into prev frame's reserved spill space in param area (although not actually needing to spill, here but just do a temp copy, but space is reserved for them anyways)
  64:   afc70044        sw      a3,68(s8)  ; |
  68:   27bdff18        addiu   sp,sp,-232 ; alloca(220) - with padding to guarantee alignment
  6c:   27a20020        addiu   v0,sp,32   ; |
  70:   afc20028        sw      v0,40(s8)  ; |
  74:   8fc30028        lw      v1,40(s8)  ; | start of alloca()'d memory -> v1, by ...
  78:   24620007        addiu   v0,v1,7    ; | ... using v0 as helper to align to 8b
  7c:   000210c2        srl     v0,v0,0x3  ; |    @@@ unsure about use of helper space at 40(s8) in prev frame..?
  80:   000210c0        sll     v0,v0,0x3  ; |
  84:   afc20028        sw      v0,40(s8)  ; |
  88:   8fc30028        lw      v1,40(s8)  ; |
  8c:   2402004c        li      v0,76      ; 'L' -> v0, and...
  90:   a0620000        sb      v0,0(v1)   ; ... store in local area (of alloca()'d space)
  94:   8fc2004c        lw      v0,76(s8)  ; arg 4 (fetched from prev frame's param area), and ...
  98:   afa20010        sw      v0,16(sp)  ; ... "pushed" onto stack
  9c:   8fc20050        lw      v0,80(s8)  ; arg 5 (fetched from prev frame's param area), and ...
  a0:   afa20014        sw      v0,20(sp)  ; ... "pushed" onto stack
  a4:   8fc20054        lw      v0,84(s8)  ; arg 6 (fetched from prev frame's param area), and ...
  a8:   afa20018        sw      v0,24(sp)  ; ... "pushed" onto stack
  ac:   8fc4003c        lw      a0,60(s8)  ; arg 0 (fetched from spill area of prev frame)
  b0:   8fc50040        lw      a1,64(s8)  ; arg 1 (fetched from spill area of prev frame)
  b4:   8fc60044        lw      a2,68(s8)  ; arg 2 (fetched from spill area of prev frame)
  b8:   8fc70048        lw      a3,72(s8)  ; arg 3 (fetched from prev frame's param area)
  bc:   8f990000        lw      t9,0(gp)   ; func to call -> t9
  c0:   0320f809        jalr    t9         ; call and ret addr -> ra
  c4:   00000000        nop                ; branch delay slot
  c8:   8fdc0020        lw      gp,32(s8)  ; |
  cc:   03c0e821        move    sp,s8      ; |
  d0:   8fbf0034        lw      ra,52(sp)  ; |
  d4:   8fbe0030        lw      s8,48(sp)  ; | epilog
  d8:   03e00008        jr      ra         ; |
  dc:   27bd0038        addiu   sp,sp,56   ; |

000000e0 <main>:
  e0:   3c1c0000        lui     gp,0x0     ; |
  e4:   279c0000        addiu   gp,gp,0    ; |
  e8:   0399e021        addu    gp,gp,t9   ; |
  ec:   27bdffd0        addiu   sp,sp,-48  ; | prolog
  f0:   afbf002c        sw      ra,44(sp)  ; |
  f4:   afbe0028        sw      s8,40(sp)  ; |
  f8:   03a0f021        move    s8,sp      ; |         frame pointer (note: with offset to frame start, but static compared to sp)
  fc:   afbc0020        sw      gp,32(sp)  ; |
 100:   24020004        li      v0,4       ; arg 4, and ...
 104:   afa20010        sw      v0,16(sp)  ; ... "pushed" onto stack
 108:   24020005        li      v0,5       ; arg 5, and ...
 10c:   afa20014        sw      v0,20(sp)  ; ... "pushed" onto stack
 110:   24020006        li      v0,6       ; arg 6, and ...
 114:   afa20018        sw      v0,24(sp)  ; ... "pushed" onto stack
 118:   24020007        li      v0,7       ; arg 7, and ...
 11c:   afa2001c        sw      v0,28(sp)  ; ... "pushed" onto stack
 120:   00002021        move    a0,zero    ; arg 0
 124:   24050001        li      a1,1       ; arg 1
 128:   24060002        li      a2,2       ; arg 2
 12c:   24070003        li      a3,3       ; arg 3
 130:   8f990000        lw      t9,0(gp)   ; func to call -> t9
 134:   0320f809        jalr    t9         ; call and ret addr -> ra
 138:   00000000        nop                ; branch delay slot
 13c:   8fdc0020        lw      gp,32(s8)  ; |
 140:   00001021        move    v0,zero    ; :        return value: not part of epilog, but unordered (branch delay slot style)
 144:   03c0e821        move    sp,s8      ; |
 148:   8fbf002c        lw      ra,44(sp)  ; | epilog
 14c:   8fbe0028        lw      s8,40(sp)  ; |
 150:   03e00008        jr      ra         ; |
 154:   27bd0030        addiu   sp,sp,48   ; |



; output from netbsd-5.0.2-pmax_mipsel_o32 w/ gcc 4.1.3 ----->
; nearly the same, equivalent to above except non-optimal use of branch delay slots and $gp preserving in leaf call

00000000 <leaf_call>:
   0:   27bdfff8        addiu   sp,sp,-8
   4:   afbe0000        sw      s8,0(sp)
   8:   03a0f021        move    s8,sp
   c:   afc40008        sw      a0,8(s8)
  10:   afc5000c        sw      a1,12(s8)
  14:   afc60010        sw      a2,16(s8)
  18:   afc70014        sw      a3,20(s8)
  1c:   03c0e821        move    sp,s8
  20:   8fbe0000        lw      s8,0(sp)
  24:   27bd0008        addiu   sp,sp,8
  28:   03e00008        jr      ra
  2c:   00000000        nop

00000030 <nonleaf_call>:
  30:   3c1c0000        lui     gp,0x0
  34:   279c0000        addiu   gp,gp,0
  38:   0399e021        addu    gp,gp,t9
  3c:   27bdffc8        addiu   sp,sp,-56
  40:   afbf0034        sw      ra,52(sp)
  44:   afbe0030        sw      s8,48(sp)
  48:   03a0f021        move    s8,sp
  4c:   afbc0020        sw      gp,32(sp)
  50:   afc40038        sw      a0,56(s8)
  54:   afc5003c        sw      a1,60(s8)
  58:   afc60040        sw      a2,64(s8)
  5c:   afc70044        sw      a3,68(s8)
  60:   27bdff18        addiu   sp,sp,-232
  64:   27a20020        addiu   v0,sp,32
  68:   afc20028        sw      v0,40(s8)
  6c:   8fc30028        lw      v1,40(s8)
  70:   00000000        nop

  74:   24620007        addiu   v0,v1,7
  78:   000210c2        srl     v0,v0,0x3
  7c:   000210c0        sll     v0,v0,0x3
  80:   afc20028        sw      v0,40(s8)
  84:   8fc30028        lw      v1,40(s8)
  88:   2402004c        li      v0,76
  8c:   a0620000        sb      v0,0(v1)
  90:   8fc2004c        lw      v0,76(s8)
  94:   00000000        nop
  98:   afa20010        sw      v0,16(sp)
  9c:   8fc20050        lw      v0,80(s8)
  a0:   00000000        nop
  a4:   afa20014        sw      v0,20(sp)
  a8:   8fc20054        lw      v0,84(s8)
  ac:   00000000        nop
  b0:   afa20018        sw      v0,24(sp)
  b4:   8fc4003c        lw      a0,60(s8)
  b8:   8fc50040        lw      a1,64(s8)
  bc:   8fc60044        lw      a2,68(s8)
  c0:   8fc70048        lw      a3,72(s8)
  c4:   8f990000        lw      t9,0(gp)
  c8:   00000000        nop
  cc:   0320f809        jalr    t9
  d0:   00000000        nop
  d4:   8fdc0020        lw      gp,32(s8)
  d8:   03c0e821        move    sp,s8
  dc:   8fbf0034        lw      ra,52(sp)
  e0:   8fbe0030        lw      s8,48(sp)
  e4:   27bd0038        addiu   sp,sp,56
  e8:   03e00008        jr      ra
  ec:   00000000        nop

000000f0 <main>:
  f0:   3c1c0000        lui     gp,0x0
  f4:   279c0000        addiu   gp,gp,0
  f8:   0399e021        addu    gp,gp,t9
  fc:   27bdffd0        addiu   sp,sp,-48
 100:   afbf002c        sw      ra,44(sp)
 104:   afbe0028        sw      s8,40(sp)
 108:   03a0f021        move    s8,sp
 10c:   afbc0020        sw      gp,32(sp)
 110:   24020004        li      v0,4
 114:   afa20010        sw      v0,16(sp)
 118:   24020005        li      v0,5
 11c:   afa20014        sw      v0,20(sp)
 120:   24020006        li      v0,6
 124:   afa20018        sw      v0,24(sp)
 128:   24020007        li      v0,7
 12c:   afa2001c        sw      v0,28(sp)
 130:   00002021        move    a0,zero
 134:   24050001        li      a1,1
 138:   24060002        li      a2,2
 13c:   24070003        li      a3,3
 140:   8f990000        lw      t9,0(gp)
 144:   00000000        nop
 148:   0320f809        jalr    t9
 14c:   00000000        nop
 150:   8fdc0020        lw      gp,32(s8)
 154:   00001021        move    v0,zero
 158:   03c0e821        move    sp,s8
 15c:   8fbf002c        lw      ra,44(sp)
 160:   8fbe0028        lw      s8,40(sp)
 164:   27bd0030        addiu   sp,sp,48
 168:   03e00008        jr      ra
 16c:   00000000        nop

; vim: ft=asm