# HG changeset patch
# User Tassilo Philipp
# Date 1646090210 -3600
# Node ID 6c72cb768099e2844ad8c187acf89ac5dd0f6086
# Parent  75c19f11b86a652e1a28289f86ec30dfed9e244e
callconv doc:
- mips o32 update w/ regards to aggregates
- mips o32 disas examples
- sparc64 doc fixes

diff -r 75c19f11b86a -r 6c72cb768099 doc/disas_examples/mips.o32.disas
--- a/doc/disas_examples/mips.o32.disas	Sun Feb 27 13:53:18 2022 +0100
+++ b/doc/disas_examples/mips.o32.disas	Tue Mar 01 00:16:50 2022 +0100
@@ -217,5 +217,1542 @@
  168:   03e00008        jr      ra
  16c:   00000000        nop
 
+
+
+; ---------- structs by value ---------->
+;
+; struct A { int i, j; long long l; };
+;
+; void leaf_call(int b, int c, int d, int e, struct A f, int g, int h)
+; {
+; }
+;
+; void nonleaf_call(int a, int b, int c, int d, int e, struct A f, int g, int h)
+; {
+;     /* use some local data */
+;     char l[100] ={ 'L'};
+;     leaf_call(b, c, d, e, f, g, h);
+; }
+;
+; int main()
+; {
+;     nonleaf_call(0, 1, 2, 3, 4, (struct A){5, 6, 7ll}, 8, 9);
+;     return 0;
+; }
+
+
+
+; output from freebsd-12.0_r333647-malta_mipsebhf 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:   27bdff60        addiu   sp,sp,-160
+  48:   afbf009c        sw      ra,156(sp)
+  4c:   afbe0098        sw      s8,152(sp)
+  50:   03a0f021        move    s8,sp
+  54:   afbc0028        sw      gp,40(sp)
+  58:   afc400a0        sw      a0,160(s8)
+  5c:   afc500a4        sw      a1,164(s8)
+  60:   afc600a8        sw      a2,168(s8)
+  64:   afc700ac        sw      a3,172(s8)
+  68:   27c20030        addiu   v0,s8,48
+  6c:   24030064        li      v1,100
+  70:   00402021        move    a0,v0
+  74:   00002821        move    a1,zero
+  78:   00603021        move    a2,v1
+  7c:   8f990000        lw      t9,0(gp)
+  80:   0320f809        jalr    t9
+  84:   00000000        nop
+  88:   8fdc0028        lw      gp,40(s8)
+  8c:   2402004c        li      v0,76
+  90:   a3c20030        sb      v0,48(s8)
+  94:   8fc200b8        lw      v0,184(s8)
+  98:   8fc300bc        lw      v1,188(s8)
+  9c:   8fc400c0        lw      a0,192(s8)
+  a0:   8fc500c4        lw      a1,196(s8)
+  a4:   afa20010        sw      v0,16(sp)
+  a8:   afa30014        sw      v1,20(sp)
+  ac:   afa40018        sw      a0,24(sp)
+  b0:   afa5001c        sw      a1,28(sp)
+  b4:   8fc200c8        lw      v0,200(s8)
+  b8:   afa20020        sw      v0,32(sp)
+  bc:   8fc200cc        lw      v0,204(s8)
+  c0:   afa20024        sw      v0,36(sp)
+  c4:   8fc400a4        lw      a0,164(s8)
+  c8:   8fc500a8        lw      a1,168(s8)
+  cc:   8fc600ac        lw      a2,172(s8)
+  d0:   8fc700b0        lw      a3,176(s8)
+  d4:   8f990000        lw      t9,0(gp)
+  d8:   0320f809        jalr    t9
+  dc:   00000000        nop
+  e0:   8fdc0028        lw      gp,40(s8)
+  e4:   03c0e821        move    sp,s8
+  e8:   8fbf009c        lw      ra,156(sp)
+  ec:   8fbe0098        lw      s8,152(sp)
+  f0:   03e00008        jr      ra
+  f4:   27bd00a0        addiu   sp,sp,160
+
+000000f8 <main>:
+  f8:   3c1c0000        lui     gp,0x0    ; |
+  fc:   279c0000        addiu   gp,gp,0   ; |
+ 100:   0399e021        addu    gp,gp,t9  ; |
+ 104:   27bdffb0        addiu   sp,sp,-80 ; | prolog
+ 108:   afbf004c        sw      ra,76(sp) ; |
+ 10c:   afbe0048        sw      s8,72(sp) ; |
+ 110:   03a0f021        move    s8,sp     ; |         frame pointer (note: with offset to frame start, but static compared to sp)
+ 114:   afbc0030        sw      gp,48(sp) ; /
+ 118:   8f820000        lw      v0,0(gp)  ; \                               \
+ 11c:   24420000        addiu   v0,v0,0   ; |                               | field j -> v0
+ 120:   8c420000        lw      v0,0(v0)  ; |                               /
+ 124:   8f830000        lw      v1,0(gp)  ; |                               \
+ 128:   24630000        addiu   v1,v1,0   ; |                               | field j -> v1
+ 12c:   8c630004        lw      v1,4(v1)  ; | prep local struct A data ...  /
+ 130:   8f840000        lw      a0,0(gp)  ; |                               \
+ 134:   24840000        addiu   a0,a0,0   ; |                               |
+ 138:   8c840008        lw      a0,8(a0)  ; |                               | field l -> a0 & a1
+ 13c:   8f850000        lw      a1,0(gp)  ; |                               |
+ 140:   24a50000        addiu   a1,a1,0   ; |                               |
+ 144:   8ca5000c        lw      a1,12(a1) ; /                               /
+ 148:   afc20038        sw      v0,56(s8) ; \
+ 14c:   afc3003c        sw      v1,60(s8) ; | ... and write to local area
+ 150:   afc40040        sw      a0,64(s8) ; |
+ 154:   afc50044        sw      a1,68(s8) ; /
+ 158:   24020004        li      v0,4      ; push arg 4 ...
+ 15c:   afa20010        sw      v0,16(sp) ; ... onto stack
+ 160:   8fc20038        lw      v0,56(s8) ; \
+ 164:   8fc3003c        lw      v1,60(s8) ; |
+ 168:   8fc40040        lw      a0,64(s8) ; | prep arg 5 (struct A) ...
+ 16c:   8fc50044        lw      a1,68(s8) ; /
+ 170:   afa20018        sw      v0,24(sp) ; \
+ 174:   afa3001c        sw      v1,28(sp) ; | ... and push onto stack
+ 178:   afa40020        sw      a0,32(sp) ; |
+ 17c:   afa50024        sw      a1,36(sp) ; /
+ 180:   24020008        li      v0,8      ; push arg 6 ...
+ 184:   afa20028        sw      v0,40(sp) ; ... onto stack
+ 188:   24020009        li      v0,9      ; push arg 7 ...
+ 18c:   afa2002c        sw      v0,44(sp) ; ... onto stack
+ 190:   00002021        move    a0,zero   ; arg 0
+ 194:   24050001        li      a1,1      ; arg 1
+ 198:   24060002        li      a2,2      ; arg 2
+ 19c:   24070003        li      a3,3      ; arg 3
+ 1a0:   8f990000        lw      t9,0(gp)  ; func to call -> t9
+ 1a4:   0320f809        jalr    t9        ; call and ret addr -> ra
+ 1a8:   00000000        nop               ; branch delay slot
+ 1ac:   8fdc0030        lw      gp,48(s8) ; |
+ 1b0:   00001021        move    v0,zero   ; :        return value: not part of epilog, but unordered (branch delay slot style)
+ 1b4:   03c0e821        move    sp,s8     ; |
+ 1b8:   8fbf004c        lw      ra,76(sp) ; | epilog
+ 1bc:   8fbe0048        lw      s8,72(sp) ; |
+ 1c0:   03e00008        jr      ra        ; |
+ 1c4:   27bd0050        addiu   sp,sp,80  ; |
+        ...
+
+
+
+; output from freebsd-12.0_r333647-malta_mipsebhf w/ gcc 4.2.1 *and* -mhard-float ----->
+
+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:   27bdff60        addiu   sp,sp,-160
+  48:   afbf009c        sw      ra,156(sp)
+  4c:   afbe0098        sw      s8,152(sp)
+  50:   03a0f021        move    s8,sp
+  54:   afbc0028        sw      gp,40(sp)
+  58:   afc400a0        sw      a0,160(s8)
+  5c:   afc500a4        sw      a1,164(s8)
+  60:   afc600a8        sw      a2,168(s8)
+  64:   afc700ac        sw      a3,172(s8)
+  68:   27c20030        addiu   v0,s8,48
+  6c:   24030064        li      v1,100
+  70:   00402021        move    a0,v0
+  74:   00002821        move    a1,zero
+  78:   00603021        move    a2,v1
+  7c:   8f990000        lw      t9,0(gp)
+  80:   0320f809        jalr    t9
+  84:   00000000        nop
+  88:   8fdc0028        lw      gp,40(s8)
+  8c:   2402004c        li      v0,76
+  90:   a3c20030        sb      v0,48(s8)
+  94:   8fc200b8        lw      v0,184(s8)
+  98:   8fc300bc        lw      v1,188(s8)
+  9c:   8fc400c0        lw      a0,192(s8)
+  a0:   8fc500c4        lw      a1,196(s8)
+  a4:   afa20010        sw      v0,16(sp)
+  a8:   afa30014        sw      v1,20(sp)
+  ac:   afa40018        sw      a0,24(sp)
+  b0:   afa5001c        sw      a1,28(sp)
+  b4:   8fc200c8        lw      v0,200(s8)
+  b8:   afa20020        sw      v0,32(sp)
+  bc:   8fc200cc        lw      v0,204(s8)
+  c0:   afa20024        sw      v0,36(sp)
+  c4:   8fc400a4        lw      a0,164(s8)
+  c8:   8fc500a8        lw      a1,168(s8)
+  cc:   8fc600ac        lw      a2,172(s8)
+  d0:   8fc700b0        lw      a3,176(s8)
+  d4:   8f990000        lw      t9,0(gp)
+  d8:   0320f809        jalr    t9
+  dc:   00000000        nop
+  e0:   8fdc0028        lw      gp,40(s8)
+  e4:   03c0e821        move    sp,s8
+  e8:   8fbf009c        lw      ra,156(sp)
+  ec:   8fbe0098        lw      s8,152(sp)
+  f0:   03e00008        jr      ra
+  f4:   27bd00a0        addiu   sp,sp,160
+
+000000f8 <main>:
+  f8:   3c1c0000        lui     gp,0x0    ; |
+  fc:   279c0000        addiu   gp,gp,0   ; |
+ 100:   0399e021        addu    gp,gp,t9  ; |
+ 104:   27bdffb0        addiu   sp,sp,-80 ; | prolog
+ 108:   afbf004c        sw      ra,76(sp) ; |
+ 10c:   afbe0048        sw      s8,72(sp) ; |
+ 110:   03a0f021        move    s8,sp     ; |         frame pointer (note: with offset to frame start, but static compared to sp)
+ 114:   afbc0030        sw      gp,48(sp) ; /
+ 118:   8f820000        lw      v0,0(gp)  ; \                               \
+ 11c:   24420000        addiu   v0,v0,0   ; |                               | field j -> v0
+ 120:   8c420000        lw      v0,0(v0)  ; |                               /
+ 124:   8f830000        lw      v1,0(gp)  ; |                               \
+ 128:   24630000        addiu   v1,v1,0   ; |                               | field j -> v1
+ 12c:   8c630004        lw      v1,4(v1)  ; | prep local struct A data ...  /
+ 130:   8f840000        lw      a0,0(gp)  ; |                               \
+ 134:   24840000        addiu   a0,a0,0   ; |                               |
+ 138:   8c840008        lw      a0,8(a0)  ; |                               | field l -> a0 & a1
+ 13c:   8f850000        lw      a1,0(gp)  ; |                               |
+ 140:   24a50000        addiu   a1,a1,0   ; |                               |
+ 144:   8ca5000c        lw      a1,12(a1) ; /                               /
+ 148:   afc20038        sw      v0,56(s8) ; \
+ 14c:   afc3003c        sw      v1,60(s8) ; | ... and write to local area
+ 150:   afc40040        sw      a0,64(s8) ; |
+ 154:   afc50044        sw      a1,68(s8) ; /
+ 158:   24020004        li      v0,4      ; push arg 4 ...
+ 15c:   afa20010        sw      v0,16(sp) ; ... onto stack
+ 160:   8fc20038        lw      v0,56(s8) ; \
+ 164:   8fc3003c        lw      v1,60(s8) ; |
+ 168:   8fc40040        lw      a0,64(s8) ; | prep arg 5 (struct A) ...
+ 16c:   8fc50044        lw      a1,68(s8) ; /
+ 170:   afa20018        sw      v0,24(sp) ; \
+ 174:   afa3001c        sw      v1,28(sp) ; | ... and push onto stack
+ 178:   afa40020        sw      a0,32(sp) ; |
+ 17c:   afa50024        sw      a1,36(sp) ; /
+ 180:   24020008        li      v0,8      ; push arg 6 ...
+ 184:   afa20028        sw      v0,40(sp) ; ... onto stack
+ 188:   24020009        li      v0,9      ; push arg 7 ...
+ 18c:   afa2002c        sw      v0,44(sp) ; ... onto stack
+ 190:   00002021        move    a0,zero   ; arg 0
+ 194:   24050001        li      a1,1      ; arg 1
+ 198:   24060002        li      a2,2      ; arg 2
+ 19c:   24070003        li      a3,3      ; arg 3
+ 1a0:   8f990000        lw      t9,0(gp)  ; func to call -> t9
+ 1a4:   0320f809        jalr    t9        ; call and ret addr -> ra
+ 1a8:   00000000        nop               ; branch delay slot
+ 1ac:   8fdc0030        lw      gp,48(s8) ; |
+ 1b0:   00001021        move    v0,zero   ; :        return value: not part of epilog, but unordered (branch delay slot style)
+ 1b4:   03c0e821        move    sp,s8     ; |
+ 1b8:   8fbf004c        lw      ra,76(sp) ; | epilog
+ 1bc:   8fbe0048        lw      s8,72(sp) ; |
+ 1c0:   03e00008        jr      ra        ; |
+ 1c4:   27bd0050        addiu   sp,sp,80  ; |
+        ...
+
+
+
+; ---------- structs by value, complex example (multiple structs) ---------->
+;
+; struct A { int i, j; float f; };
+; struct B { double d; long long l; };
+;
+; void leaf_call(int b, struct A c, struct B d, int e, int f, struct A g, struct B h, int i, int j)
+; {
+; }
+;
+; void nonleaf_call(int a, int b, struct A c, struct B d, int e, int f, struct A g, struct B h, int i, int j)
+; {
+;     /* use some local data */
+;     char l[100] ={ 'L'};
+;     leaf_call(b, c, d, e, f, g, h, i, j);
+; }
+;
+; int main()
+; {
+;     nonleaf_call(0, 1, (struct A){2, 3, 4.f}, (struct B){5., 6ll}, 7, 8, (struct A){9, 10, 11.f}, (struct B){12., 13ll}, 14, 15);
+;     return 0;
+; }
+
+
+
+; output from freebsd-12.0_r333647-malta_mipsebhf 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:   27bdff38        addiu   sp,sp,-200
+  48:   afbf00c4        sw      ra,196(sp)
+  4c:   afbe00c0        sw      s8,192(sp)
+  50:   03a0f021        move    s8,sp
+  54:   afbc0050        sw      gp,80(sp)
+  58:   afc400c8        sw      a0,200(s8)
+  5c:   afc500cc        sw      a1,204(s8)
+  60:   afc600d0        sw      a2,208(s8)
+  64:   afc700d4        sw      a3,212(s8)
+  68:   27c20058        addiu   v0,s8,88
+  6c:   24030064        li      v1,100
+  70:   00402021        move    a0,v0
+  74:   00002821        move    a1,zero
+  78:   00603021        move    a2,v1
+  7c:   8f990000        lw      t9,0(gp)
+  80:   0320f809        jalr    t9
+  84:   00000000        nop
+  88:   8fdc0050        lw      gp,80(s8)
+  8c:   2402004c        li      v0,76
+  90:   a3c20058        sb      v0,88(s8)
+  94:   8fc200e0        lw      v0,224(s8)
+  98:   8fc300e4        lw      v1,228(s8)
+  9c:   8fc400e8        lw      a0,232(s8)
+  a0:   8fc500ec        lw      a1,236(s8)
+  a4:   afa20010        sw      v0,16(sp)
+  a8:   afa30014        sw      v1,20(sp)
+  ac:   afa40018        sw      a0,24(sp)
+  b0:   afa5001c        sw      a1,28(sp)
+  b4:   8fc200f0        lw      v0,240(s8)
+  b8:   afa20020        sw      v0,32(sp)
+  bc:   8fc200f4        lw      v0,244(s8)
+  c0:   afa20024        sw      v0,36(sp)
+  c4:   8fc200f8        lw      v0,248(s8)
+  c8:   8fc300fc        lw      v1,252(s8)
+  cc:   8fc40100        lw      a0,256(s8)
+  d0:   afa20028        sw      v0,40(sp)
+  d4:   afa3002c        sw      v1,44(sp)
+  d8:   afa40030        sw      a0,48(sp)
+  dc:   8fc20108        lw      v0,264(s8)
+  e0:   8fc3010c        lw      v1,268(s8)
+  e4:   8fc40110        lw      a0,272(s8)
+  e8:   8fc50114        lw      a1,276(s8)
+  ec:   afa20038        sw      v0,56(sp)
+  f0:   afa3003c        sw      v1,60(sp)
+  f4:   afa40040        sw      a0,64(sp)
+  f8:   afa50044        sw      a1,68(sp)
+  fc:   8fc20118        lw      v0,280(s8)
+ 100:   afa20048        sw      v0,72(sp)
+ 104:   8fc2011c        lw      v0,284(s8)
+ 108:   afa2004c        sw      v0,76(sp)
+ 10c:   8fc400cc        lw      a0,204(s8)
+ 110:   8fc500d0        lw      a1,208(s8)
+ 114:   8fc600d4        lw      a2,212(s8)
+ 118:   8fc700d8        lw      a3,216(s8)
+ 11c:   8f990000        lw      t9,0(gp)
+ 120:   0320f809        jalr    t9
+ 124:   00000000        nop
+ 128:   8fdc0050        lw      gp,80(s8)
+ 12c:   03c0e821        move    sp,s8
+ 130:   8fbf00c4        lw      ra,196(sp)
+ 134:   8fbe00c0        lw      s8,192(sp)
+ 138:   03e00008        jr      ra
+ 13c:   27bd00c8        addiu   sp,sp,200
+
+00000140 <main>:
+ 140:   3c1c0000        lui     gp,0x0     ; |
+ 144:   279c0000        addiu   gp,gp,0    ; |
+ 148:   0399e021        addu    gp,gp,t9   ; |
+ 14c:   27bdff58        addiu   sp,sp,-168 ; | prolog
+ 150:   afbf00a4        sw      ra,164(sp) ; |
+ 154:   afbe00a0        sw      s8,160(sp) ; |
+ 158:   03a0f021        move    s8,sp      ; |         frame pointer (note: with offset to frame start, but static compared to sp)
+ 15c:   afbc0058        sw      gp,88(sp)  ; /
+ 160:   8f820000        lw      v0,0(gp)   ; \                                       |
+ 164:   24420030        addiu   v0,v0,48   ; |                                       | field j -> v0
+ 168:   8c420000        lw      v0,0(v0)   ; |                                       /
+ 16c:   8f830000        lw      v1,0(gp)   ; | prep (first) local struct A data ...  \
+ 170:   24630030        addiu   v1,v1,48   ; |                                       | field j -> v1
+ 174:   8c630004        lw      v1,4(v1)   ; |                                       /
+ 178:   8f840000        lw      a0,0(gp)   ; |                                       \
+ 17c:   24840030        addiu   a0,a0,48   ; |                                       | field f -> a0
+ 180:   8c840008        lw      a0,8(a0)   ; /                                       |
+ 184:   afc20090        sw      v0,144(s8) ; \
+ 188:   afc30094        sw      v1,148(s8) ; | ... and write to local area
+ 18c:   afc40098        sw      a0,152(s8) ; /
+ 190:   8f820000        lw      v0,0(gp)   ; \                                       |
+ 194:   24420020        addiu   v0,v0,32   ; |                                       |
+ 198:   8c420000        lw      v0,0(v0)   ; |                                       |
+ 19c:   8f830000        lw      v1,0(gp)   ; |                                       | field d -> v0 & v1
+ 1a0:   24630020        addiu   v1,v1,32   ; |                                       |
+ 1a4:   8c630004        lw      v1,4(v1)   ; | prep (first) local struct B data ...  /
+ 1a8:   8f840000        lw      a0,0(gp)   ; |                                       \
+ 1ac:   24840020        addiu   a0,a0,32   ; |                                       |
+ 1b0:   8c840008        lw      a0,8(a0)   ; |                                       |
+ 1b4:   8f850000        lw      a1,0(gp)   ; |                                       | field l -> a0 & a1
+ 1b8:   24a50020        addiu   a1,a1,32   ; |                                       |
+ 1bc:   8ca5000c        lw      a1,12(a1)  ; /                                       |
+ 1c0:   afc20080        sw      v0,128(s8) ; \
+ 1c4:   afc30084        sw      v1,132(s8) ; |
+ 1c8:   afc40088        sw      a0,136(s8) ; | ... and write to local area
+ 1cc:   afc5008c        sw      a1,140(s8) ; /
+ 1d0:   8f820000        lw      v0,0(gp)   ; \                                        |
+ 1d4:   24420010        addiu   v0,v0,16   ; |                                        | field j -> v0
+ 1d8:   8c420000        lw      v0,0(v0)   ; |                                        /
+ 1dc:   8f830000        lw      v1,0(gp)   ; | prep (second) local struct A data ...  \
+ 1e0:   24630010        addiu   v1,v1,16   ; |                                        | field j -> v1
+ 1e4:   8c630004        lw      v1,4(v1)   ; |                                        /
+ 1e8:   8f840000        lw      a0,0(gp)   ; |                                        \
+ 1ec:   24840010        addiu   a0,a0,16   ; |                                        | field f -> a0
+ 1f0:   8c840008        lw      a0,8(a0)   ; /                                        |
+ 1f4:   afc20070        sw      v0,112(s8) ; \
+ 1f8:   afc30074        sw      v1,116(s8) ; | ... and write to local area
+ 1fc:   afc40078        sw      a0,120(s8) ; /
+ 200:   8f820000        lw      v0,0(gp)   ; \                                        |
+ 204:   24420000        addiu   v0,v0,0    ; |                                        |
+ 208:   8c420000        lw      v0,0(v0)   ; |                                        |
+ 20c:   8f830000        lw      v1,0(gp)   ; |                                        | field d -> v0 & v1
+ 210:   24630000        addiu   v1,v1,0    ; |                                        |
+ 214:   8c630004        lw      v1,4(v1)   ; | prep (second) local struct B data ...  /
+ 218:   8f840000        lw      a0,0(gp)   ; |                                        \
+ 21c:   24840000        addiu   a0,a0,0    ; |                                        |
+ 220:   8c840008        lw      a0,8(a0)   ; |                                        |
+ 224:   8f850000        lw      a1,0(gp)   ; |                                        | field l -> a0 & a1
+ 228:   24a50000        addiu   a1,a1,0    ; |                                        |
+ 22c:   8ca5000c        lw      a1,12(a1)  ; /                                        |
+ 230:   afc20060        sw      v0,96(s8)  ; \
+ 234:   afc30064        sw      v1,100(s8) ; |
+ 238:   afc40068        sw      a0,104(s8) ; | ... and write to local area
+ 23c:   afc5006c        sw      a1,108(s8) ; /
+ 240:   8fc20080        lw      v0,128(s8) ; \
+ 244:   8fc30084        lw      v1,132(s8) ; |
+ 248:   8fc40088        lw      a0,136(s8) ; |
+ 24c:   8fc5008c        lw      a1,140(s8) ; |
+ 250:   afa20018        sw      v0,24(sp)  ; |                         | d
+ 254:   afa3001c        sw      v1,28(sp)  ; | arg 3 (first struct B)  /
+ 258:   afa40020        sw      a0,32(sp)  ; |                         \
+ 25c:   afa50024        sw      a1,36(sp)  ; /                         | l
+ 260:   24020007        li      v0,7       ; \
+ 264:   afa20028        sw      v0,40(sp)  ; / arg 4
+ 268:   24020008        li      v0,8       ; \
+ 26c:   afa2002c        sw      v0,44(sp)  ; / arg 5
+ 270:   8fc20070        lw      v0,112(s8) ; \
+ 274:   8fc30074        lw      v1,116(s8) ; |
+ 278:   8fc40078        lw      a0,120(s8) ; | arg 6 (second struct A, note that 60(sp) isn't used, so sizeof(struct A) is probably a padded 16)
+ 27c:   afa20030        sw      v0,48(sp)  ; |                          i
+ 280:   afa30034        sw      v1,52(sp)  ; |                          j
+ 284:   afa40038        sw      a0,56(sp)  ; /                          f   
+ 288:   8fc20060        lw      v0,96(s8)  ; \
+ 28c:   8fc30064        lw      v1,100(s8) ; |
+ 290:   8fc40068        lw      a0,104(s8) ; |
+ 294:   8fc5006c        lw      a1,108(s8) ; |
+ 298:   afa20040        sw      v0,64(sp)  ; |                          | d
+ 29c:   afa30044        sw      v1,68(sp)  ; | arg 7 (second struct B)  /
+ 2a0:   afa40048        sw      a0,72(sp)  ; |                          \
+ 2a4:   afa5004c        sw      a1,76(sp)  ; |                          | l
+ 2a8:   2402000e        li      v0,14      ; arg 8 pushed ...
+ 2ac:   afa20050        sw      v0,80(sp)  ; ... onto stack
+ 2b0:   2402000f        li      v0,15      ; arg 9 pushed ...
+ 2b4:   afa20054        sw      v0,84(sp)  ; ... onto stack
+ 2b8:   8fc20098        lw      v0,152(s8) ; |                          | f (via stack, first slot after save area)
+ 2bc:   afa20010        sw      v0,16(sp)  ; |                          |   note that 20(sp) isn't used, so sizeof(struct A) is probably a padded 16
+ 2c0:   8fc60090        lw      a2,144(s8) ; | arg 2 (first struct A)     i (via reg)
+ 2c4:   8fc70094        lw      a3,148(s8) ; |                            j (via reg)
+ 2c8:   00002021        move    a0,zero    ; arg 0
+ 2cc:   24050001        li      a1,1       ; arg 1
+ 2d0:   8f990000        lw      t9,0(gp)   ; func to call -> t9
+ 2d4:   0320f809        jalr    t9         ; call and ret addr -> ra
+ 2d8:   00000000        nop                ; branch delay slot
+ 2dc:   8fdc0058        lw      gp,88(s8)  ; |
+ 2e0:   00001021        move    v0,zero    ; :        return value: not part of epilog, but unordered (branch delay slot style)
+ 2e4:   03c0e821        move    sp,s8      ; |
+ 2e8:   8fbf00a4        lw      ra,164(sp) ; | epilog
+ 2ec:   8fbe00a0        lw      s8,160(sp) ; |
+ 2f0:   03e00008        jr      ra         ; |
+ 2f4:   27bd00a8        addiu   sp,sp,168  ; |
+        ...
+
+
+
+; output from freebsd-12.0_r333647-malta_mipsebhf w/ gcc 4.2.1 *and* -mhard-float ----->
+
+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:   27bdff38        addiu   sp,sp,-200
+  48:   afbf00c4        sw      ra,196(sp)
+  4c:   afbe00c0        sw      s8,192(sp)
+  50:   03a0f021        move    s8,sp
+  54:   afbc0050        sw      gp,80(sp)
+  58:   afc400c8        sw      a0,200(s8)
+  5c:   afc500cc        sw      a1,204(s8)
+  60:   afc600d0        sw      a2,208(s8)
+  64:   afc700d4        sw      a3,212(s8)
+  68:   27c20058        addiu   v0,s8,88
+  6c:   24030064        li      v1,100
+  70:   00402021        move    a0,v0
+  74:   00002821        move    a1,zero
+  78:   00603021        move    a2,v1
+  7c:   8f990000        lw      t9,0(gp)
+  80:   0320f809        jalr    t9
+  84:   00000000        nop
+  88:   8fdc0050        lw      gp,80(s8)
+  8c:   2402004c        li      v0,76
+  90:   a3c20058        sb      v0,88(s8)
+  94:   8fc200e0        lw      v0,224(s8)
+  98:   8fc300e4        lw      v1,228(s8)
+  9c:   8fc400e8        lw      a0,232(s8)
+  a0:   8fc500ec        lw      a1,236(s8)
+  a4:   afa20010        sw      v0,16(sp)
+  a8:   afa30014        sw      v1,20(sp)
+  ac:   afa40018        sw      a0,24(sp)
+  b0:   afa5001c        sw      a1,28(sp)
+  b4:   8fc200f0        lw      v0,240(s8)
+  b8:   afa20020        sw      v0,32(sp)
+  bc:   8fc200f4        lw      v0,244(s8)
+  c0:   afa20024        sw      v0,36(sp)
+  c4:   8fc200f8        lw      v0,248(s8)
+  c8:   8fc300fc        lw      v1,252(s8)
+  cc:   8fc40100        lw      a0,256(s8)
+  d0:   afa20028        sw      v0,40(sp)
+  d4:   afa3002c        sw      v1,44(sp)
+  d8:   afa40030        sw      a0,48(sp)
+  dc:   8fc20108        lw      v0,264(s8)
+  e0:   8fc3010c        lw      v1,268(s8)
+  e4:   8fc40110        lw      a0,272(s8)
+  e8:   8fc50114        lw      a1,276(s8)
+  ec:   afa20038        sw      v0,56(sp)
+  f0:   afa3003c        sw      v1,60(sp)
+  f4:   afa40040        sw      a0,64(sp)
+  f8:   afa50044        sw      a1,68(sp)
+  fc:   8fc20118        lw      v0,280(s8)
+ 100:   afa20048        sw      v0,72(sp)
+ 104:   8fc2011c        lw      v0,284(s8)
+ 108:   afa2004c        sw      v0,76(sp)
+ 10c:   8fc400cc        lw      a0,204(s8)
+ 110:   8fc500d0        lw      a1,208(s8)
+ 114:   8fc600d4        lw      a2,212(s8)
+ 118:   8fc700d8        lw      a3,216(s8)
+ 11c:   8f990000        lw      t9,0(gp)
+ 120:   0320f809        jalr    t9
+ 124:   00000000        nop
+ 128:   8fdc0050        lw      gp,80(s8)
+ 12c:   03c0e821        move    sp,s8
+ 130:   8fbf00c4        lw      ra,196(sp)
+ 134:   8fbe00c0        lw      s8,192(sp)
+ 138:   03e00008        jr      ra
+ 13c:   27bd00c8        addiu   sp,sp,200
+
+00000140 <main>:
+ 140:   3c1c0000        lui     gp,0x0     ; |
+ 144:   279c0000        addiu   gp,gp,0    ; |
+ 148:   0399e021        addu    gp,gp,t9   ; |
+ 14c:   27bdff58        addiu   sp,sp,-168 ; | prolog
+ 150:   afbf00a4        sw      ra,164(sp) ; |
+ 154:   afbe00a0        sw      s8,160(sp) ; |
+ 158:   03a0f021        move    s8,sp      ; |         frame pointer (note: with offset to frame start, but static compared to sp)
+ 15c:   afbc0058        sw      gp,88(sp)  ; /
+ 160:   8f820000        lw      v0,0(gp)   ; \                                       |
+ 164:   24420030        addiu   v0,v0,48   ; |                                       | field j -> v0
+ 168:   8c420000        lw      v0,0(v0)   ; |                                       /
+ 16c:   8f830000        lw      v1,0(gp)   ; | prep (first) local struct A data ...  \
+ 170:   24630030        addiu   v1,v1,48   ; |                                       | field j -> v1
+ 174:   8c630004        lw      v1,4(v1)   ; |                                       /
+ 178:   8f840000        lw      a0,0(gp)   ; |                                       \
+ 17c:   24840030        addiu   a0,a0,48   ; |                                       | field f -> a0
+ 180:   8c840008        lw      a0,8(a0)   ; /                                       |
+ 184:   afc20090        sw      v0,144(s8) ; \
+ 188:   afc30094        sw      v1,148(s8) ; | ... and write to local area
+ 18c:   afc40098        sw      a0,152(s8) ; /
+ 190:   8f820000        lw      v0,0(gp)   ; \                                       |
+ 194:   24420020        addiu   v0,v0,32   ; |                                       |
+ 198:   8c420000        lw      v0,0(v0)   ; |                                       |
+ 19c:   8f830000        lw      v1,0(gp)   ; |                                       | field d -> v0 & v1
+ 1a0:   24630020        addiu   v1,v1,32   ; |                                       |
+ 1a4:   8c630004        lw      v1,4(v1)   ; | prep (first) local struct B data ...  /
+ 1a8:   8f840000        lw      a0,0(gp)   ; |                                       \
+ 1ac:   24840020        addiu   a0,a0,32   ; |                                       |
+ 1b0:   8c840008        lw      a0,8(a0)   ; |                                       |
+ 1b4:   8f850000        lw      a1,0(gp)   ; |                                       | field l -> a0 & a1
+ 1b8:   24a50020        addiu   a1,a1,32   ; |                                       |
+ 1bc:   8ca5000c        lw      a1,12(a1)  ; /                                       |
+ 1c0:   afc20080        sw      v0,128(s8) ; \
+ 1c4:   afc30084        sw      v1,132(s8) ; |
+ 1c8:   afc40088        sw      a0,136(s8) ; | ... and write to local area
+ 1cc:   afc5008c        sw      a1,140(s8) ; /
+ 1d0:   8f820000        lw      v0,0(gp)   ; \                                        |
+ 1d4:   24420010        addiu   v0,v0,16   ; |                                        | field j -> v0
+ 1d8:   8c420000        lw      v0,0(v0)   ; |                                        /
+ 1dc:   8f830000        lw      v1,0(gp)   ; | prep (second) local struct A data ...  \
+ 1e0:   24630010        addiu   v1,v1,16   ; |                                        | field j -> v1
+ 1e4:   8c630004        lw      v1,4(v1)   ; |                                        /
+ 1e8:   8f840000        lw      a0,0(gp)   ; |                                        \
+ 1ec:   24840010        addiu   a0,a0,16   ; |                                        | field f -> a0
+ 1f0:   8c840008        lw      a0,8(a0)   ; /                                        |
+ 1f4:   afc20070        sw      v0,112(s8) ; \
+ 1f8:   afc30074        sw      v1,116(s8) ; | ... and write to local area
+ 1fc:   afc40078        sw      a0,120(s8) ; /
+ 200:   8f820000        lw      v0,0(gp)   ; \                                        |
+ 204:   24420000        addiu   v0,v0,0    ; |                                        |
+ 208:   8c420000        lw      v0,0(v0)   ; |                                        |
+ 20c:   8f830000        lw      v1,0(gp)   ; |                                        | field d -> v0 & v1
+ 210:   24630000        addiu   v1,v1,0    ; |                                        |
+ 214:   8c630004        lw      v1,4(v1)   ; | prep (second) local struct B data ...  /
+ 218:   8f840000        lw      a0,0(gp)   ; |                                        \
+ 21c:   24840000        addiu   a0,a0,0    ; |                                        |
+ 220:   8c840008        lw      a0,8(a0)   ; |                                        |
+ 224:   8f850000        lw      a1,0(gp)   ; |                                        | field l -> a0 & a1
+ 228:   24a50000        addiu   a1,a1,0    ; |                                        |
+ 22c:   8ca5000c        lw      a1,12(a1)  ; /                                        |
+ 230:   afc20060        sw      v0,96(s8)  ; \
+ 234:   afc30064        sw      v1,100(s8) ; |
+ 238:   afc40068        sw      a0,104(s8) ; | ... and write to local area
+ 23c:   afc5006c        sw      a1,108(s8) ; /
+ 240:   8fc20080        lw      v0,128(s8) ; \
+ 244:   8fc30084        lw      v1,132(s8) ; |
+ 248:   8fc40088        lw      a0,136(s8) ; |
+ 24c:   8fc5008c        lw      a1,140(s8) ; |
+ 250:   afa20018        sw      v0,24(sp)  ; |                         | d
+ 254:   afa3001c        sw      v1,28(sp)  ; | arg 3 (first struct B)  /
+ 258:   afa40020        sw      a0,32(sp)  ; |                         \
+ 25c:   afa50024        sw      a1,36(sp)  ; /                         | l
+ 260:   24020007        li      v0,7       ; \
+ 264:   afa20028        sw      v0,40(sp)  ; / arg 4
+ 268:   24020008        li      v0,8       ; \
+ 26c:   afa2002c        sw      v0,44(sp)  ; / arg 5
+ 270:   8fc20070        lw      v0,112(s8) ; \
+ 274:   8fc30074        lw      v1,116(s8) ; |
+ 278:   8fc40078        lw      a0,120(s8) ; | arg 6 (second struct A, note that 60(sp) isn't used, so sizeof(struct A) is probably a padded 16)
+ 27c:   afa20030        sw      v0,48(sp)  ; |                          i
+ 280:   afa30034        sw      v1,52(sp)  ; |                          j
+ 284:   afa40038        sw      a0,56(sp)  ; /                          f   
+ 288:   8fc20060        lw      v0,96(s8)  ; \
+ 28c:   8fc30064        lw      v1,100(s8) ; |
+ 290:   8fc40068        lw      a0,104(s8) ; |
+ 294:   8fc5006c        lw      a1,108(s8) ; |
+ 298:   afa20040        sw      v0,64(sp)  ; |                          | d
+ 29c:   afa30044        sw      v1,68(sp)  ; | arg 7 (second struct B)  /
+ 2a0:   afa40048        sw      a0,72(sp)  ; |                          \
+ 2a4:   afa5004c        sw      a1,76(sp)  ; |                          | l
+ 2a8:   2402000e        li      v0,14      ; arg 8 pushed ...
+ 2ac:   afa20050        sw      v0,80(sp)  ; ... onto stack
+ 2b0:   2402000f        li      v0,15      ; arg 9 pushed ...
+ 2b4:   afa20054        sw      v0,84(sp)  ; ... onto stack
+ 2b8:   8fc20098        lw      v0,152(s8) ; |                          | f (via stack, first slot after save area)
+ 2bc:   afa20010        sw      v0,16(sp)  ; |                          |   note that 20(sp) isn't used, so sizeof(struct A) is probably a padded 16
+ 2c0:   8fc60090        lw      a2,144(s8) ; | arg 2 (first struct A)     i (via reg)
+ 2c4:   8fc70094        lw      a3,148(s8) ; |                            j (via reg)
+ 2c8:   00002021        move    a0,zero    ; arg 0
+ 2cc:   24050001        li      a1,1       ; arg 1
+ 2d0:   8f990000        lw      t9,0(gp)   ; func to call -> t9
+ 2d4:   0320f809        jalr    t9         ; call and ret addr -> ra
+ 2d8:   00000000        nop                ; branch delay slot
+ 2dc:   8fdc0058        lw      gp,88(s8)  ; |
+ 2e0:   00001021        move    v0,zero    ; :        return value: not part of epilog, but unordered (branch delay slot style)
+ 2e4:   03c0e821        move    sp,s8      ; |
+ 2e8:   8fbf00a4        lw      ra,164(sp) ; | epilog
+ 2ec:   8fbe00a0        lw      s8,160(sp) ; |
+ 2f0:   03e00008        jr      ra         ; |
+ 2f4:   27bd00a8        addiu   sp,sp,168  ; |
+        ...
+
+
+
+; ---------- returning structs by value ---------->
+; 
+; struct Small { char x; };
+; struct Big { long long i,j,k,l; long m; }; /* bigger than 16b */
+;
+; struct Small f0()
+; {
+;     struct Small s = { 132 };
+;     return s;
+; }
+;
+; struct Big f1()
+; {
+;     struct Big b = { 7171LL, 99LL, -99LL, -3102LL, 32 };
+;     return b;
+; }
+;
+; int main()
+; {
+;     struct Small s = f0();
+;     struct Big b = f1();
+;     return b.j + b.k + b.m + s.x;
+; }
+
+
+
+; output from freebsd-12.0_r333647-malta_mipsebhf w/ gcc 4.2.1 ----->
+
+00000000 <f0>:
+   0:   3c1c0000        lui     gp,0x0    ; |
+   4:   279c0000        addiu   gp,gp,0   ; |
+   8:   0399e021        addu    gp,gp,t9  ; | prolog
+   c:   27bdffe8        addiu   sp,sp,-24 ; |
+  10:   afbe0010        sw      s8,16(sp) ; |
+  14:   03a0f021        move    s8,sp     ; |
+  18:   00801021        move    v0,a0     ; hidden first arg (ptr to struct ret) -> v0
+  1c:   2403ff84        li      v1,-124   ; | put together local struct
+  20:   a3c30008        sb      v1,8(s8)  ; /
+  24:   93c30008        lbu     v1,8(s8)  ; read struct data from local area ...
+  28:   a0430000        sb      v1,0(v0)  ; ... and write to return value area
+  2c:   03c0e821        move    sp,s8     ; \
+  30:   8fbe0010        lw      s8,16(sp) ; |
+  34:   03e00008        jr      ra        ; | epilog
+  38:   27bd0018        addiu   sp,sp,24  ; |
+
+0000003c <f1>:
+  3c:   3c1c0000        lui     gp,0x0    ; |
+  40:   279c0000        addiu   gp,gp,0   ; |
+  44:   0399e021        addu    gp,gp,t9  ; |
+  48:   27bdffb0        addiu   sp,sp,-80 ; |
+  4c:   afbf0048        sw      ra,72(sp) ; | prolog
+  50:   afbe0044        sw      s8,68(sp) ; |
+  54:   afb00040        sw      s0,64(sp) ; |
+  58:   03a0f021        move    s8,sp     ; |
+  5c:   afbc0010        sw      gp,16(sp) ; |
+  60:   00808021        move    s0,a0     ; hidden first arg (ptr to struct ret) -> s0
+  64:   27c20018        addiu   v0,s8,24  ;
+  68:   8f830000        lw      v1,0(gp)  ;
+  6c:   24630000        addiu   v1,v1,0   ;
+  70:   24060028        li      a2,40     ;
+  74:   00402021        move    a0,v0     ;
+  78:   00602821        move    a1,v1     ;
+  7c:   8f990000        lw      t9,0(gp)  ;
+  80:   0320f809        jalr    t9        ;
+  84:   00000000        nop               ;        @@@ unsure why those two jumps, but seems to put return value data together
+  88:   8fdc0010        lw      gp,16(s8) ;
+  8c:   02001021        move    v0,s0     ;
+  90:   27c30018        addiu   v1,s8,24  ;
+  94:   24060028        li      a2,40     ;
+  98:   00402021        move    a0,v0     ;
+  9c:   00602821        move    a1,v1     ;
+  a0:   8f990000        lw      t9,0(gp)  ;
+  a4:   0320f809        jalr    t9        ;
+  a8:   00000000        nop               ;
+  ac:   8fdc0010        lw      gp,16(s8) ; |
+  b0:   02001021        move    v0,s0     ; :        return value (hidden ptr): not part of epilog, but unordered (branch delay slot style)
+  b4:   03c0e821        move    sp,s8     ; |
+  b8:   8fbf0048        lw      ra,72(sp) ; |
+  bc:   8fbe0044        lw      s8,68(sp) ; | epilog
+  c0:   8fb00040        lw      s0,64(sp) ; |
+  c4:   03e00008        jr      ra        ; |
+  c8:   27bd0050        addiu   sp,sp,80  ; |
+
+000000cc <main>:
+  cc:   3c1c0000        lui     gp,0x0    ; |
+  d0:   279c0000        addiu   gp,gp,0   ; |
+  d4:   0399e021        addu    gp,gp,t9  ; |
+  d8:   27bdffb0        addiu   sp,sp,-80 ; |
+  dc:   afbf004c        sw      ra,76(sp) ; | prolog
+  e0:   afbe0048        sw      s8,72(sp) ; |
+  e4:   03a0f021        move    s8,sp     ; |
+  e8:   afbc0010        sw      gp,16(sp) ; /
+  ec:   27c20018        addiu   v0,s8,24  ; \
+  f0:   00402021        move    a0,v0     ; | hidden first arg (ptr to space for ret val)
+  f4:   8f990000        lw      t9,0(gp)  ; func to call (f0) -> t9
+  f8:   0320f809        jalr    t9        ; call and ret addr -> ra
+  fc:   00000000        nop               ; branch delay slot
+ 100:   8fdc0010        lw      gp,16(s8) ; restore gp @@@ unsure why?
+ 104:   27c20020        addiu   v0,s8,32  ; |
+ 108:   00402021        move    a0,v0     ; | hidden first arg (ptr to space for ret val)
+ 10c:   8f990000        lw      t9,0(gp)  ; func to call (f1) -> t9
+ 110:   0320f809        jalr    t9        ; call and ret addr -> ra
+ 114:   00000000        nop               ; branch delay slot
+ 118:   8fdc0010        lw      gp,16(s8) ; restore gp @@@ unsure why?
+ 11c:   8fc3002c        lw      v1,44(s8) ; |                |
+ 120:   8fc20028        lw      v0,40(s8) ; |                | b.j -> v0 & v1
+ 124:   00602021        move    a0,v1     ; |                a0 = (int)b.j
+ 128:   8fc30034        lw      v1,52(s8) ; |                |
+ 12c:   8fc20030        lw      v0,48(s8) ; |                | b.j -> v0 & v1
+ 130:   00601021        move    v0,v1     ; | return value   v0 = (int)b.k
+ 134:   00821821        addu    v1,a0,v0  ; |                (int)b.j + (int)b.k -> v1
+ 138:   8fc20040        lw      v0,64(s8) ; |                b.m -> v0
+ 13c:   00621821        addu    v1,v1,v0  ; |                ((int)b.j + (int)b.k) + b.m -> v1
+ 140:   83c20018        lb      v0,24(s8) ; |                s.x -> v0
+ 144:   00621021        addu    v0,v1,v0  ; /                (((int)b.j + (int)b.k) + b.m) + s.x -> v0
+ 148:   03c0e821        move    sp,s8     ; \
+ 14c:   8fbf004c        lw      ra,76(sp) ; |
+ 150:   8fbe0048        lw      s8,72(sp) ; | epilog
+ 154:   03e00008        jr      ra        ; |
+ 158:   27bd0050        addiu   sp,sp,80  ; |
+ 15c:   00000000        nop               ; |
+
+
+
+; output from freebsd-12.0_r333647-malta_mipsebhf w/ gcc 4.2.1 *and* -mhard-float ----->
+
+00000000 <f0>:
+   0:   3c1c0000        lui     gp,0x0
+   4:   279c0000        addiu   gp,gp,0
+   8:   0399e021        addu    gp,gp,t9
+   c:   27bdffe8        addiu   sp,sp,-24
+  10:   afbe0010        sw      s8,16(sp)
+  14:   03a0f021        move    s8,sp
+  18:   00801021        move    v0,a0
+  1c:   2403ff84        li      v1,-124
+  20:   a3c30008        sb      v1,8(s8)
+  24:   93c30008        lbu     v1,8(s8)
+  28:   a0430000        sb      v1,0(v0)
+  2c:   03c0e821        move    sp,s8
+  30:   8fbe0010        lw      s8,16(sp)
+  34:   03e00008        jr      ra
+  38:   27bd0018        addiu   sp,sp,24
+
+0000003c <f1>:
+  3c:   3c1c0000        lui     gp,0x0
+  40:   279c0000        addiu   gp,gp,0
+  44:   0399e021        addu    gp,gp,t9
+  48:   27bdffb0        addiu   sp,sp,-80
+  4c:   afbf0048        sw      ra,72(sp)
+  50:   afbe0044        sw      s8,68(sp)
+  54:   afb00040        sw      s0,64(sp)
+  58:   03a0f021        move    s8,sp
+  5c:   afbc0010        sw      gp,16(sp)
+  60:   00808021        move    s0,a0
+  64:   27c20018        addiu   v0,s8,24
+  68:   8f830000        lw      v1,0(gp)
+  6c:   24630000        addiu   v1,v1,0
+  70:   24060028        li      a2,40
+  74:   00402021        move    a0,v0
+  78:   00602821        move    a1,v1
+  7c:   8f990000        lw      t9,0(gp)
+  80:   0320f809        jalr    t9
+  84:   00000000        nop
+  88:   8fdc0010        lw      gp,16(s8)
+  8c:   02001021        move    v0,s0
+  90:   27c30018        addiu   v1,s8,24
+  94:   24060028        li      a2,40
+  98:   00402021        move    a0,v0
+  9c:   00602821        move    a1,v1
+  a0:   8f990000        lw      t9,0(gp)
+  a4:   0320f809        jalr    t9
+  a8:   00000000        nop
+  ac:   8fdc0010        lw      gp,16(s8)
+  b0:   02001021        move    v0,s0
+  b4:   03c0e821        move    sp,s8
+  b8:   8fbf0048        lw      ra,72(sp)
+  bc:   8fbe0044        lw      s8,68(sp)
+  c0:   8fb00040        lw      s0,64(sp)
+  c4:   03e00008        jr      ra
+  c8:   27bd0050        addiu   sp,sp,80
+
+000000cc <main>:
+  cc:   3c1c0000        lui     gp,0x0
+  d0:   279c0000        addiu   gp,gp,0
+  d4:   0399e021        addu    gp,gp,t9
+  d8:   27bdffb0        addiu   sp,sp,-80
+  dc:   afbf004c        sw      ra,76(sp)
+  e0:   afbe0048        sw      s8,72(sp)
+  e4:   03a0f021        move    s8,sp
+  e8:   afbc0010        sw      gp,16(sp)
+  ec:   27c20018        addiu   v0,s8,24
+  f0:   00402021        move    a0,v0
+  f4:   8f990000        lw      t9,0(gp)
+  f8:   0320f809        jalr    t9
+  fc:   00000000        nop
+ 100:   8fdc0010        lw      gp,16(s8)
+ 104:   27c20020        addiu   v0,s8,32
+ 108:   00402021        move    a0,v0
+ 10c:   8f990000        lw      t9,0(gp)
+ 110:   0320f809        jalr    t9
+ 114:   00000000        nop
+ 118:   8fdc0010        lw      gp,16(s8)
+ 11c:   8fc3002c        lw      v1,44(s8)
+ 120:   8fc20028        lw      v0,40(s8)
+ 124:   00602021        move    a0,v1
+ 128:   8fc30034        lw      v1,52(s8)
+ 12c:   8fc20030        lw      v0,48(s8)
+ 130:   00601021        move    v0,v1
+ 134:   00821821        addu    v1,a0,v0
+ 138:   8fc20040        lw      v0,64(s8)
+ 13c:   00621821        addu    v1,v1,v0
+ 140:   83c20018        lb      v0,24(s8)
+ 144:   00621021        addu    v0,v1,v0
+ 148:   03c0e821        move    sp,s8
+ 14c:   8fbf004c        lw      ra,76(sp)
+ 150:   8fbe0048        lw      s8,72(sp)
+ 154:   03e00008        jr      ra
+ 158:   27bd0050        addiu   sp,sp,80
+ 15c:   00000000        nop
+
+
+
+; ---------- returning long long ---------->
+;
+; long long f()
+; {
+;     return 7171LL;
+; }
+;
+; int main()
+; {
+;     return (int)f();
+; }
+
+
+
+; output from freebsd-12.0_r333647-malta_mipsebhf w/ gcc 4.2.1 ----->
+
+00000000 <f>:
+   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:   24031c03        li      v1,7171  ; | return value
+  1c:   00001021        move    v0,zero  ; |
+  20:   03c0e821        move    sp,s8    ;
+  24:   8fbe0000        lw      s8,0(sp) ;
+  28:   03e00008        jr      ra       ;
+  2c:   27bd0008        addiu   sp,sp,8  ;
+
+00000030 <main>:
+  30:   3c1c0000        lui     gp,0x0
+  34:   279c0000        addiu   gp,gp,0
+  38:   0399e021        addu    gp,gp,t9
+  3c:   27bdffe0        addiu   sp,sp,-32
+  40:   afbf001c        sw      ra,28(sp)
+  44:   afbe0018        sw      s8,24(sp)
+  48:   03a0f021        move    s8,sp
+  4c:   afbc0010        sw      gp,16(sp)
+  50:   8f990000        lw      t9,0(gp)
+  54:   0320f809        jalr    t9
+  58:   00000000        nop
+  5c:   8fdc0010        lw      gp,16(s8)
+  60:   00601021        move    v0,v1
+  64:   03c0e821        move    sp,s8
+  68:   8fbf001c        lw      ra,28(sp)
+  6c:   8fbe0018        lw      s8,24(sp)
+  70:   03e00008        jr      ra
+  74:   27bd0020        addiu   sp,sp,32
+        ...
+
+
+
+; output from freebsd-12.0_r333647-malta_mipsebhf w/ gcc 4.2.1 *and* -mhard-float ----->
+
+00000000 <f>:
+   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:   24031c03        li      v1,7171  ; | return value
+  1c:   00001021        move    v0,zero  ; |
+  20:   03c0e821        move    sp,s8    ;
+  24:   8fbe0000        lw      s8,0(sp) ;
+  28:   03e00008        jr      ra       ;
+  2c:   27bd0008        addiu   sp,sp,8  ;
+
+00000030 <main>:
+  30:   3c1c0000        lui     gp,0x0
+  34:   279c0000        addiu   gp,gp,0
+  38:   0399e021        addu    gp,gp,t9
+  3c:   27bdffe0        addiu   sp,sp,-32
+  40:   afbf001c        sw      ra,28(sp)
+  44:   afbe0018        sw      s8,24(sp)
+  48:   03a0f021        move    s8,sp
+  4c:   afbc0010        sw      gp,16(sp)
+  50:   8f990000        lw      t9,0(gp)
+  54:   0320f809        jalr    t9
+  58:   00000000        nop
+  5c:   8fdc0010        lw      gp,16(s8)
+  60:   00601021        move    v0,v1
+  64:   03c0e821        move    sp,s8
+  68:   8fbf001c        lw      ra,28(sp)
+  6c:   8fbe0018        lw      s8,24(sp)
+  70:   03e00008        jr      ra
+  74:   27bd0020        addiu   sp,sp,32
+        ...
+
+
+
+; ---------- passing structs with only fp parts ---------->
+;
+; struct A { float a; };
+; struct B { float a, b; };
+; struct C { float a, b, c; };
+; struct D { double a; };
+; struct E { double a, b; };
+; struct F { double a, b, c; };
+;
+; void leaf_call(struct A a, struct B b, struct C c, struct D d, struct E e, struct F f)
+; {
+; }
+;
+; int main()
+; {
+;     leaf_call((struct A){1.f}, (struct B){2.f,3.f}, (struct C){4.f,5.f,6.f}, (struct D){1.}, (struct E){2.,3.}, (struct F){4.,5.,6.});
+;     return 0;
+; }
+
+
+
+; output from freebsd-12.0_r333647-malta_mipsebhf 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 <main>:
+  38:   3c1c0000        lui     gp,0x0     ; |
+  3c:   279c0000        addiu   gp,gp,0    ; |
+  40:   0399e021        addu    gp,gp,t9   ; |
+  44:   27bdff60        addiu   sp,sp,-160 ; | prolog
+  48:   afbf009c        sw      ra,156(sp) ; |
+  4c:   afbe0098        sw      s8,152(sp) ; |
+  50:   03a0f021        move    s8,sp      ; |         frame pointer (note: with offset to frame start, but static compared to sp)
+  54:   afbc0048        sw      gp,72(sp)  ; /
+  58:   8f820000        lw      v0,0(gp)   ; \
+  5c:   24420044        addiu   v0,v0,68   ; | prep local struct A data ...
+  60:   8c420000        lw      v0,0(v0)   ; /
+  64:   afc20094        sw      v0,148(s8) ; ... and write to local area
+  68:   8f820000        lw      v0,0(gp)   ; \
+  6c:   2442003c        addiu   v0,v0,60   ; |
+  70:   8c420000        lw      v0,0(v0)   ; |
+  74:   8f830000        lw      v1,0(gp)   ; | prep local struct B data ...
+  78:   2463003c        addiu   v1,v1,60   ; |
+  7c:   8c630004        lw      v1,4(v1)   ; /
+  80:   afc2008c        sw      v0,140(s8) ; \ ... and write to local area   a
+  84:   afc30090        sw      v1,144(s8) ; /                               b
+  88:   8f820000        lw      v0,0(gp)   ; \
+  8c:   24420030        addiu   v0,v0,48   ; |
+  90:   8c420000        lw      v0,0(v0)   ; |
+  94:   8f830000        lw      v1,0(gp)   ; |
+  98:   24630030        addiu   v1,v1,48   ; | prep local struct C data ...
+  9c:   8c630004        lw      v1,4(v1)   ; |
+  a0:   8f840000        lw      a0,0(gp)   ; |
+  a4:   24840030        addiu   a0,a0,48   ; |
+  a8:   8c840008        lw      a0,8(a0)   ; /
+  ac:   afc20080        sw      v0,128(s8) ; \                               a
+  b0:   afc30084        sw      v1,132(s8) ; | ... and write to local area   b
+  b4:   afc40088        sw      a0,136(s8) ; /                               c
+  b8:   8f830000        lw      v1,0(gp)   ; \
+  bc:   24630028        addiu   v1,v1,40   ; |
+  c0:   8c630004        lw      v1,4(v1)   ; |
+  c4:   8f820000        lw      v0,0(gp)   ; | prep local struct D data ...
+  c8:   24420028        addiu   v0,v0,40   ; |
+  cc:   8c420000        lw      v0,0(v0)   ; /
+  d0:   afc3007c        sw      v1,124(s8) ; \ ... and write to local area
+  d4:   afc20078        sw      v0,120(s8) ; /
+  d8:   8f820000        lw      v0,0(gp)   ; \
+  dc:   24420018        addiu   v0,v0,24   ; |
+  e0:   8c420000        lw      v0,0(v0)   ; |
+  e4:   8f830000        lw      v1,0(gp)   ; |
+  e8:   24630018        addiu   v1,v1,24   ; |
+  ec:   8c630004        lw      v1,4(v1)   ; | prep local struct E data ...
+  f0:   8f840000        lw      a0,0(gp)   ; |
+  f4:   24840018        addiu   a0,a0,24   ; |
+  f8:   8c840008        lw      a0,8(a0)   ; |
+  fc:   8f850000        lw      a1,0(gp)   ; |
+ 100:   24a50018        addiu   a1,a1,24   ; |
+ 104:   8ca5000c        lw      a1,12(a1)  ; /
+ 108:   afc20068        sw      v0,104(s8) ; \                               | a
+ 10c:   afc3006c        sw      v1,108(s8) ; | ... and write to local area   /
+ 110:   afc40070        sw      a0,112(s8) ; |                               \
+ 114:   afc50074        sw      a1,116(s8) ; /                               | b
+ 118:   8f820000        lw      v0,0(gp)   ; \
+ 11c:   24420000        addiu   v0,v0,0    ; |
+ 120:   8c420000        lw      v0,0(v0)   ; |
+ 124:   8f830000        lw      v1,0(gp)   ; |
+ 128:   24630000        addiu   v1,v1,0    ; |
+ 12c:   8c630004        lw      v1,4(v1)   ; |
+ 130:   8f840000        lw      a0,0(gp)   ; |
+ 134:   24840000        addiu   a0,a0,0    ; |
+ 138:   8c840008        lw      a0,8(a0)   ; |
+ 13c:   8f850000        lw      a1,0(gp)   ; | prep local struct F data ...
+ 140:   24a50000        addiu   a1,a1,0    ; |
+ 144:   8ca5000c        lw      a1,12(a1)  ; |
+ 148:   8f860000        lw      a2,0(gp)   ; |
+ 14c:   24c60000        addiu   a2,a2,0    ; |
+ 150:   8cc60010        lw      a2,16(a2)  ; |
+ 154:   8f870000        lw      a3,0(gp)   ; |
+ 158:   24e70000        addiu   a3,a3,0    ; |
+ 15c:   8ce70014        lw      a3,20(a3)  ; /
+ 160:   afc20050        sw      v0,80(s8)  ; \                               | a
+ 164:   afc30054        sw      v1,84(s8)  ; |                               /
+ 168:   afc40058        sw      a0,88(s8)  ; |                               \ b
+ 16c:   afc5005c        sw      a1,92(s8)  ; | ... and write to local area   /
+ 170:   afc60060        sw      a2,96(s8)  ; |                               \
+ 174:   afc70064        sw      a3,100(s8) ; /                               | c
+ 178:   8fc3007c        lw      v1,124(s8) ; \
+ 17c:   8fc20078        lw      v0,120(s8) ; |
+ 180:   afa3001c        sw      v1,28(sp)  ; | arg 3 (struct D)
+ 184:   afa20018        sw      v0,24(sp)  ; /
+ 188:   8fc20068        lw      v0,104(s8) ; \
+ 18c:   8fc3006c        lw      v1,108(s8) ; |
+ 190:   8fc40070        lw      a0,112(s8) ; |
+ 194:   8fc50074        lw      a1,116(s8) ; |
+ 198:   afa20020        sw      v0,32(sp)  ; | arg 4 (struct E)
+ 19c:   afa30024        sw      v1,36(sp)  ; |
+ 1a0:   afa40028        sw      a0,40(sp)  ; |
+ 1a4:   afa5002c        sw      a1,44(sp)  ; /
+ 1a8:   8fc20050        lw      v0,80(s8)  ; \
+ 1ac:   8fc30054        lw      v1,84(s8)  ; |
+ 1b0:   8fc40058        lw      a0,88(s8)  ; |
+ 1b4:   8fc5005c        lw      a1,92(s8)  ; |
+ 1b8:   8fc60060        lw      a2,96(s8)  ; |
+ 1bc:   8fc70064        lw      a3,100(s8) ; |
+ 1c0:   afa20030        sw      v0,48(sp)  ; | arg 5 (struct F)
+ 1c4:   afa30034        sw      v1,52(sp)  ; |
+ 1c8:   afa40038        sw      a0,56(sp)  ; |
+ 1cc:   afa5003c        sw      a1,60(sp)  ; |
+ 1d0:   afa60040        sw      a2,64(sp)  ; |
+ 1d4:   afa70044        sw      a3,68(sp)  ; /
+ 1d8:   8fc20084        lw      v0,132(s8) ; \
+ 1dc:   8fc30088        lw      v1,136(s8) ; |
+ 1e0:   afa20010        sw      v0,16(sp)  ; | arg 2 (struct C)            b (via stack)
+ 1e4:   afa30014        sw      v1,20(sp)  ; |                             c (via stack)
+ 1e8:   8fc70080        lw      a3,128(s8) ; |                             a (via reg)
+ 1ec:   8fc40094        lw      a0,148(s8) ; arg 0 (struct A, via reg)
+ 1f0:   8fc5008c        lw      a1,140(s8) ; | arg 1 (struct B, via regs)  a
+ 1f4:   8fc60090        lw      a2,144(s8) ; |                             b
+ 1f8:   8f990000        lw      t9,0(gp)   ; func to call -> t9
+ 1fc:   0320f809        jalr    t9         ; call and ret addr -> ra
+ 200:   00000000        nop                ; branch delay slot
+ 204:   8fdc0048        lw      gp,72(s8)  ; |
+ 208:   00001021        move    v0,zero    ; :        return value: not part of epilog, but unordered (branch delay slot style)
+ 20c:   03c0e821        move    sp,s8      ; |
+ 210:   8fbf009c        lw      ra,156(sp) ; | epilog
+ 214:   8fbe0098        lw      s8,152(sp) ; |
+ 218:   03e00008        jr      ra         ; |
+ 21c:   27bd00a0        addiu   sp,sp,160  ; |
+
+
+
+; output from freebsd-12.0_r333647-malta_mipsebhf w/ gcc 4.2.1 *and* -mhard-float ----->
+
+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 <main>:
+  38:   3c1c0000        lui     gp,0x0      ; |
+  3c:   279c0000        addiu   gp,gp,0     ; |
+  40:   0399e021        addu    gp,gp,t9    ; |
+  44:   27bdff60        addiu   sp,sp,-160  ; | prolog
+  48:   afbf009c        sw      ra,156(sp)  ; |
+  4c:   afbe0098        sw      s8,152(sp)  ; |
+  50:   03a0f021        move    s8,sp       ; |         frame pointer (note: with offset to frame start, but static compared to sp)
+  54:   afbc0048        sw      gp,72(sp)   ; /
+  58:   8f810000        lw      at,0(gp)    ; \
+  5c:   24210044        addiu   at,at,68    ; | prep local struct A (single float field) data ...
+  60:   c4200000        lwc1    $f0,0(at)   ; /
+  64:   e7c00094        swc1    $f0,148(s8) ; ... and write to local area
+  68:   8f820000        lw      v0,0(gp)    ; \
+  6c:   2442003c        addiu   v0,v0,60    ; |
+  70:   8c420000        lw      v0,0(v0)    ; |
+  74:   8f830000        lw      v1,0(gp)    ; | prep local struct B data ...
+  78:   2463003c        addiu   v1,v1,60    ; |
+  7c:   8c630004        lw      v1,4(v1)    ; /
+  80:   afc2008c        sw      v0,140(s8)  ; \ ... and write to local area   a
+  84:   afc30090        sw      v1,144(s8)  ; /                               b
+  88:   8f820000        lw      v0,0(gp)    ; \
+  8c:   24420030        addiu   v0,v0,48    ; |
+  90:   8c420000        lw      v0,0(v0)    ; |
+  94:   8f830000        lw      v1,0(gp)    ; |
+  98:   24630030        addiu   v1,v1,48    ; | prep local struct C data ...
+  9c:   8c630004        lw      v1,4(v1)    ; |
+  a0:   8f840000        lw      a0,0(gp)    ; |
+  a4:   24840030        addiu   a0,a0,48    ; |
+  a8:   8c840008        lw      a0,8(a0)    ; /
+  ac:   afc20080        sw      v0,128(s8)  ; \                               a
+  b0:   afc30084        sw      v1,132(s8)  ; | ... and write to local area   b
+  b4:   afc40088        sw      a0,136(s8)  ; /                               c
+  b8:   8f810000        lw      at,0(gp)    ; \
+  bc:   24210028        addiu   at,at,40    ; | prep local struct D (single double field) data ...
+  c0:   d4200000        ldc1    $f0,0(at)   ; /
+  c4:   f7c00078        sdc1    $f0,120(s8) ; ... and write to local area
+  c8:   8f820000        lw      v0,0(gp)    ; \
+  cc:   24420018        addiu   v0,v0,24    ; |
+  d0:   8c420000        lw      v0,0(v0)    ; |
+  d4:   8f830000        lw      v1,0(gp)    ; |
+  d8:   24630018        addiu   v1,v1,24    ; |
+  dc:   8c630004        lw      v1,4(v1)    ; | prep local struct E data ...
+  e0:   8f840000        lw      a0,0(gp)    ; |
+  e4:   24840018        addiu   a0,a0,24    ; |
+  e8:   8c840008        lw      a0,8(a0)    ; |
+  ec:   8f850000        lw      a1,0(gp)    ; |
+  f0:   24a50018        addiu   a1,a1,24    ; |
+  f4:   8ca5000c        lw      a1,12(a1)   ; /
+  f8:   afc20068        sw      v0,104(s8)  ; \                               | a
+  fc:   afc3006c        sw      v1,108(s8)  ; | ... and write to local area   /
+ 100:   afc40070        sw      a0,112(s8)  ; |                               \
+ 104:   afc50074        sw      a1,116(s8)  ; /                               | b
+ 108:   8f820000        lw      v0,0(gp)    ; \
+ 10c:   24420000        addiu   v0,v0,0     ; |
+ 110:   8c420000        lw      v0,0(v0)    ; |
+ 114:   8f830000        lw      v1,0(gp)    ; |
+ 118:   24630000        addiu   v1,v1,0     ; |
+ 11c:   8c630004        lw      v1,4(v1)    ; |
+ 120:   8f840000        lw      a0,0(gp)    ; |
+ 124:   24840000        addiu   a0,a0,0     ; |
+ 128:   8c840008        lw      a0,8(a0)    ; |
+ 12c:   8f850000        lw      a1,0(gp)    ; | prep local struct F data ...
+ 130:   24a50000        addiu   a1,a1,0     ; |
+ 134:   8ca5000c        lw      a1,12(a1)   ; |
+ 138:   8f860000        lw      a2,0(gp)    ; |
+ 13c:   24c60000        addiu   a2,a2,0     ; |
+ 140:   8cc60010        lw      a2,16(a2)   ; |
+ 144:   8f870000        lw      a3,0(gp)    ; |
+ 148:   24e70000        addiu   a3,a3,0     ; |
+ 14c:   8ce70014        lw      a3,20(a3)   ; /
+ 150:   afc20050        sw      v0,80(s8)   ; \                               | a
+ 154:   afc30054        sw      v1,84(s8)   ; |                               /
+ 158:   afc40058        sw      a0,88(s8)   ; |                               \ b
+ 15c:   afc5005c        sw      a1,92(s8)   ; | ... and write to local area   /
+ 160:   afc60060        sw      a2,96(s8)   ; |                               \
+ 164:   afc70064        sw      a3,100(s8)  ; /                               | c
+ 168:   d7c00078        ldc1    $f0,120(s8) ; \
+ 16c:   f7a00018        sdc1    $f0,24(sp)  ; / arg 3 (struct D)
+ 170:   8fc20068        lw      v0,104(s8)  ; \
+ 174:   8fc3006c        lw      v1,108(s8)  ; |
+ 178:   8fc40070        lw      a0,112(s8)  ; |
+ 17c:   8fc50074        lw      a1,116(s8)  ; |
+ 180:   afa20020        sw      v0,32(sp)   ; | arg 4 (struct E)
+ 184:   afa30024        sw      v1,36(sp)   ; |
+ 188:   afa40028        sw      a0,40(sp)   ; |
+ 18c:   afa5002c        sw      a1,44(sp)   ; /
+ 190:   8fc20050        lw      v0,80(s8)   ; \
+ 194:   8fc30054        lw      v1,84(s8)   ; |
+ 198:   8fc40058        lw      a0,88(s8)   ; |
+ 19c:   8fc5005c        lw      a1,92(s8)   ; |
+ 1a0:   8fc60060        lw      a2,96(s8)   ; |
+ 1a4:   8fc70064        lw      a3,100(s8)  ; |
+ 1a8:   afa20030        sw      v0,48(sp)   ; | arg 5 (struct F)
+ 1ac:   afa30034        sw      v1,52(sp)   ; |
+ 1b0:   afa40038        sw      a0,56(sp)   ; |
+ 1b4:   afa5003c        sw      a1,60(sp)   ; |
+ 1b8:   afa60040        sw      a2,64(sp)   ; |
+ 1bc:   afa70044        sw      a3,68(sp)   ; /
+ 1c0:   8fc20084        lw      v0,132(s8)  ; \
+ 1c4:   8fc30088        lw      v1,136(s8)  ; |
+ 1c8:   afa20010        sw      v0,16(sp)   ; | arg 2 (struct C)            b (via stack)
+ 1cc:   afa30014        sw      v1,20(sp)   ; |                             c (via stack)
+ 1d0:   8fc70080        lw      a3,128(s8)  ; |                             a (via reg)
+ 1d4:   8fc40094        lw      a0,148(s8)  ; arg 0 (struct A, via reg)
+ 1d8:   8fc5008c        lw      a1,140(s8)  ; | arg 1 (struct B, via regs)  a
+ 1dc:   8fc60090        lw      a2,144(s8)  ; |                             b
+ 1e0:   8f990000        lw      t9,0(gp)    ; func to call -> t9
+ 1e4:   0320f809        jalr    t9          ; call and ret addr -> ra
+ 1e8:   00000000        nop                 ; branch delay slot
+ 1ec:   8fdc0048        lw      gp,72(s8)   ; |
+ 1f0:   00001021        move    v0,zero     ; :        return value: not part of epilog, but unordered (branch delay slot style)
+ 1f4:   03c0e821        move    sp,s8       ; |
+ 1f8:   8fbf009c        lw      ra,156(sp)  ; | epilog
+ 1fc:   8fbe0098        lw      s8,152(sp)  ; |
+ 200:   03e00008        jr      ra          ; |
+ 204:   27bd00a0        addiu   sp,sp,160   ; |
+        ...                                  
+                                             
+                                             
+                                             
+; ---------- single-field structs by values (and small array fields) ---------->
+;
+; struct C { char c; };
+; struct S { short s; };
+; struct I { int i; };
+; struct F { float f; };
+; struct D { double d; };
+;
+; struct C2 { char c[2]; };
+; struct C3 { char c[3]; };
+;
+; void leaf_call(struct C2 a, struct C b, struct S c, struct I d, struct F e, struct D f, struct C3 g)
+; {
+; }
+;
+; int main()
+; {
+;     leaf_call((struct C2){{0,1}}, (struct C){2}, (struct S){3}, (struct I){4}, (struct F){5.f}, (struct D){6.}, (struct C3){{7,8,9}});
+;     return 0;
+; }
+
+
+
+; output from freebsd-12.0_r333647-malta_mipsebhf 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 <main>:
+  38:   3c1c0000        lui     gp,0x0
+  3c:   279c0000        addiu   gp,gp,0
+  40:   0399e021        addu    gp,gp,t9
+  44:   27bdffa0        addiu   sp,sp,-96
+  48:   afbf005c        sw      ra,92(sp)
+  4c:   afbe0058        sw      s8,88(sp)
+  50:   03a0f021        move    s8,sp
+  54:   afbc0028        sw      gp,40(sp)
+  58:   8f820000        lw      v0,0(gp)
+  5c:   24420010        addiu   v0,v0,16
+  60:   90420000        lbu     v0,0(v0)
+  64:   a3c2004b        sb      v0,75(s8)
+  68:   8f820000        lw      v0,0(gp)
+  6c:   24420010        addiu   v0,v0,16
+  70:   90420001        lbu     v0,1(v0)
+  74:   a3c2004c        sb      v0,76(s8)
+  78:   24020002        li      v0,2
+  7c:   a3c2004a        sb      v0,74(s8)
+  80:   24020003        li      v0,3
+  84:   a7c20048        sh      v0,72(s8)
+  88:   24020004        li      v0,4
+  8c:   afc20044        sw      v0,68(s8)
+  90:   8f820000        lw      v0,0(gp)
+  94:   24420014        addiu   v0,v0,20
+  98:   8c420000        lw      v0,0(v0)
+  9c:   afc20040        sw      v0,64(s8)
+  a0:   8f830000        lw      v1,0(gp)
+  a4:   24630008        addiu   v1,v1,8
+  a8:   8c630004        lw      v1,4(v1)
+  ac:   8f820000        lw      v0,0(gp)
+  b0:   24420008        addiu   v0,v0,8
+  b4:   8c420000        lw      v0,0(v0)
+  b8:   afc3003c        sw      v1,60(s8)
+  bc:   afc20038        sw      v0,56(s8)
+  c0:   8f820000        lw      v0,0(gp)
+  c4:   24420000        addiu   v0,v0,0
+  c8:   94420000        lhu     v0,0(v0)
+  cc:   a7c20030        sh      v0,48(s8)
+  d0:   8f820000        lw      v0,0(gp)
+  d4:   24420000        addiu   v0,v0,0
+  d8:   90420002        lbu     v0,2(v0)
+  dc:   a3c20032        sb      v0,50(s8)
+  e0:   8fc20040        lw      v0,64(s8)
+  e4:   afa20010        sw      v0,16(sp)
+  e8:   8fc3003c        lw      v1,60(s8)
+  ec:   8fc20038        lw      v0,56(s8)
+  f0:   afa3001c        sw      v1,28(sp)
+  f4:   afa20018        sw      v0,24(sp)
+  f8:   97c20030        lhu     v0,48(s8)
+  fc:   a7a20020        sh      v0,32(sp)
+ 100:   93c20032        lbu     v0,50(s8)
+ 104:   a3a20022        sb      v0,34(sp)
+ 108:   93c2004b        lbu     v0,75(s8)
+ 10c:   00021a00        sll     v1,v0,0x8
+ 110:   93c2004c        lbu     v0,76(s8)
+ 114:   00431025        or      v0,v0,v1
+ 118:   afc00050        sw      zero,80(s8)
+ 11c:   00021c00        sll     v1,v0,0x10
+ 120:   8fc40050        lw      a0,80(s8)
+ 124:   3082ffff        andi    v0,a0,0xffff
+ 128:   00431025        or      v0,v0,v1
+ 12c:   afc20050        sw      v0,80(s8)
+ 130:   8fc40050        lw      a0,80(s8)
+ 134:   93c5004a        lbu     a1,74(s8)
+ 138:   00052e00        sll     a1,a1,0x18
+ 13c:   97c60048        lhu     a2,72(s8)
+ 140:   00063400        sll     a2,a2,0x10
+ 144:   8fc70044        lw      a3,68(s8)
+ 148:   8f990000        lw      t9,0(gp)
+ 14c:   0320f809        jalr    t9
+ 150:   00000000        nop
+ 154:   8fdc0028        lw      gp,40(s8)
+ 158:   00001021        move    v0,zero
+ 15c:   03c0e821        move    sp,s8
+ 160:   8fbf005c        lw      ra,92(sp)
+ 164:   8fbe0058        lw      s8,88(sp)
+ 168:   03e00008        jr      ra
+ 16c:   27bd0060        addiu   sp,sp,96
+
+
+
+; output from freebsd-12.0_r333647-malta_mipsebhf w/ gcc 4.2.1 *and* -mhard-float ----->
+
+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 <main>:
+  38:   3c1c0000        lui     gp,0x0
+  3c:   279c0000        addiu   gp,gp,0
+  40:   0399e021        addu    gp,gp,t9
+  44:   27bdffa0        addiu   sp,sp,-96
+  48:   afbf005c        sw      ra,92(sp)
+  4c:   afbe0058        sw      s8,88(sp)
+  50:   03a0f021        move    s8,sp
+  54:   afbc0028        sw      gp,40(sp)
+  58:   8f820000        lw      v0,0(gp)
+  5c:   24420010        addiu   v0,v0,16
+  60:   90420000        lbu     v0,0(v0)
+  64:   a3c2004b        sb      v0,75(s8)
+  68:   8f820000        lw      v0,0(gp)
+  6c:   24420010        addiu   v0,v0,16
+  70:   90420001        lbu     v0,1(v0)
+  74:   a3c2004c        sb      v0,76(s8)
+  78:   24020002        li      v0,2
+  7c:   a3c2004a        sb      v0,74(s8)
+  80:   24020003        li      v0,3
+  84:   a7c20048        sh      v0,72(s8)
+  88:   24020004        li      v0,4
+  8c:   afc20044        sw      v0,68(s8)
+  90:   8f810000        lw      at,0(gp)
+  94:   24210014        addiu   at,at,20
+  98:   c4200000        lwc1    $f0,0(at)
+  9c:   e7c00040        swc1    $f0,64(s8)
+  a0:   8f810000        lw      at,0(gp)
+  a4:   24210008        addiu   at,at,8
+  a8:   d4200000        ldc1    $f0,0(at)
+  ac:   f7c00038        sdc1    $f0,56(s8)
+  b0:   8f820000        lw      v0,0(gp)
+  b4:   24420000        addiu   v0,v0,0
+  b8:   94420000        lhu     v0,0(v0)
+  bc:   a7c20030        sh      v0,48(s8)
+  c0:   8f820000        lw      v0,0(gp)
+  c4:   24420000        addiu   v0,v0,0
+  c8:   90420002        lbu     v0,2(v0)
+  cc:   a3c20032        sb      v0,50(s8)
+  d0:   c7c00040        lwc1    $f0,64(s8)
+  d4:   e7a00010        swc1    $f0,16(sp)
+  d8:   d7c00038        ldc1    $f0,56(s8)
+  dc:   f7a00018        sdc1    $f0,24(sp)
+  e0:   97c20030        lhu     v0,48(s8)
+  e4:   a7a20020        sh      v0,32(sp)
+  e8:   93c20032        lbu     v0,50(s8)
+  ec:   a3a20022        sb      v0,34(sp)
+  f0:   93c2004b        lbu     v0,75(s8)
+  f4:   00021a00        sll     v1,v0,0x8
+  f8:   93c2004c        lbu     v0,76(s8)
+  fc:   00431025        or      v0,v0,v1
+ 100:   afc00050        sw      zero,80(s8)
+ 104:   00021c00        sll     v1,v0,0x10
+ 108:   8fc40050        lw      a0,80(s8)
+ 10c:   3082ffff        andi    v0,a0,0xffff
+ 110:   00431025        or      v0,v0,v1
+ 114:   afc20050        sw      v0,80(s8)
+ 118:   8fc40050        lw      a0,80(s8)
+ 11c:   93c5004a        lbu     a1,74(s8)
+ 120:   00052e00        sll     a1,a1,0x18
+ 124:   97c60048        lhu     a2,72(s8)
+ 128:   00063400        sll     a2,a2,0x10
+ 12c:   8fc70044        lw      a3,68(s8)
+ 130:   8f990000        lw      t9,0(gp)
+ 134:   0320f809        jalr    t9
+ 138:   00000000        nop
+ 13c:   8fdc0028        lw      gp,40(s8)
+ 140:   00001021        move    v0,zero
+ 144:   03c0e821        move    sp,s8
+ 148:   8fbf005c        lw      ra,92(sp)
+ 14c:   8fbe0058        lw      s8,88(sp)
+ 150:   03e00008        jr      ra
+ 154:   27bd0060        addiu   sp,sp,96
+        ...
+
+
+
 ; vim: ft=asm
 
diff -r 75c19f11b86a -r 6c72cb768099 doc/manual/callconvs/callconv_mips32.tex
--- a/doc/manual/callconvs/callconv_mips32.tex	Sun Feb 27 13:53:18 2022 +0100
+++ b/doc/manual/callconvs/callconv_mips32.tex	Tue Mar 01 00:16:50 2022 +0100
@@ -1,6 +1,6 @@
 %//////////////////////////////////////////////////////////////////////////////
 %
-% Copyright (c) 2007-2019 Daniel Adler <dadler@uni-goettingen.de>, 
+% Copyright (c) 2007-2022 Daniel Adler <dadler@uni-goettingen.de>, 
 %                         Tassilo Philipp <tphilipp@potion-studios.com>
 %
 % Permission to use, copy, modify, and distribute this software for any
@@ -88,6 +88,11 @@
 \item if either integer or float registers are used up, the stack is used
 \item if the callee takes the address of one of the parameters and uses it to address other unnamed parameters (e.g. varargs) it has to copy - in its prolog - the the argument registers to a reserved stack area adjacent to the other parameters on the stack (only the unnamed integer parameters require saving, though) % @@@ seems to *ONLY* spill with varargs, never for any other reason
 \item float registers don't seem to ever need to be saved that way, because floats passed to an ellipsis function are promoted to doubles, which in turn are passed in a? register pairs, so only \$a0-\$a7 are need to be spilled
+\end{itemize}
+
+\paragraph{Return values}
+
+\begin{itemize}
 \item results are returned in \$v0 (32-bit), \$v0 and \$v1 (64-bit), \$f0 or \$f0 and \$f2 (2 $\times$ 32 bit float e.g. complex)
 \end{itemize}
 
@@ -168,9 +173,17 @@
 \item only on hard-float targets: if the very first call argument is a float, up to 2 floats or doubles can be passed via \$f12 and \$f14, respectively, for first and second argument
 \item only on hard-float targets: if any arguments are passed via float registers, skip \$a0-\$a3 for subsequent arguments as if the values were passed via them
 \item only on hard-float targets: note that if the first argument is not a float, but the second, it'll get passed via the \$a? registers
+\item single precision float parameters (32 bit) are right-justified in their 8-byte slot on the stack on big endian targets, as they aren't promoted % @@@ verify
+\item aggregates (struct, union) are passed as a sequence of words like integers, no matter the fields or if hard-float target (splitting across registers and stack is allowed)
+\end{itemize}
+
+\paragraph{Return values}
+
+\begin{itemize}
 \item results are returned in \$v0 and \$v1, with \$v0 for all values \textless\ 64bit (only integer on hard-float targets)
 \item only on hard-float targets: floating point results are returned in \$f0 (32-bit float), or \$f0 and \$f3 (64bit float)
-\item single precision float parameters (32 bit) are right-justified in their 8-byte slot on the stack on big endian targets, as they aren't promoted @@@
+\item aggregates (struct, union) of any size are returned in a space allocated by the caller, with a pointer to it
+passed as first parameter to the function called (meaning in \%a0)
 \end{itemize}
 
 \paragraph{Stack layout}
diff -r 75c19f11b86a -r 6c72cb768099 doc/manual/callconvs/callconv_ppc32.tex
--- a/doc/manual/callconvs/callconv_ppc32.tex	Sun Feb 27 13:53:18 2022 +0100
+++ b/doc/manual/callconvs/callconv_ppc32.tex	Tue Mar 01 00:16:50 2022 +0100
@@ -1,6 +1,6 @@
 %//////////////////////////////////////////////////////////////////////////////
 %
-% Copyright (c) 2007-2019 Daniel Adler <dadler@uni-goettingen.de>, 
+% Copyright (c) 2007-2022 Daniel Adler <dadler@uni-goettingen.de>, 
 %                         Tassilo Philipp <tphilipp@potion-studios.com>
 %
 % Permission to use, copy, modify, and distribute this software for any
diff -r 75c19f11b86a -r 6c72cb768099 doc/manual/callconvs/callconv_sparc64.tex
--- a/doc/manual/callconvs/callconv_sparc64.tex	Sun Feb 27 13:53:18 2022 +0100
+++ b/doc/manual/callconvs/callconv_sparc64.tex	Tue Mar 01 00:16:50 2022 +0100
@@ -112,9 +112,9 @@
 \begin{itemize}
 \item results are expected by caller to be returned in \%o0-\%o3 (after reg window restore, meaning callee writes to \%i0-\%i3) for integers
 \item \%d0,\%d2,\%d4,\%d6 are used for floating point values
-\item the fields of aggregates (struct, union) \textless 32 bytes are returned via registers registers mentioned above (which are
+\item the fields of aggregates (struct, union) \textless= 32 bytes are returned via registers mentioned above (which are
 assigned following the same logic as when passing the aggregate as a first argument to a function)
-\item aggregates (struct, union) \textgreater= 32 bytes are returned in a space allocated by the caller, with a pointer to it
+\item aggregates (struct, union) \textgreater 32 bytes are returned in a space allocated by the caller, with a pointer to it
 passed as first parameter to the function called (meaning in \%o0)
 % from spec:
 %Structure and union return types up to thirty-two bytes in size are returned in registers. The registers are assigned as if