From mboxrd@z Thu Jan  1 00:00:00 1970
From: erik quanstrom <quanstro@quanstro.net>
Date: Thu, 22 Aug 2013 12:54:11 -0400
To: 9fans@9fans.net
Message-ID: <28376249a60c1da8f7f8956eb942eb02@brasstown.quanstro.net>
In-Reply-To: <20130822153243.A567AB827@mail.bitblocks.com>
References: <2332222c9f75f30c6395f16787280535@brasstown.quanstro.net>
	<20130821184909.51FA2B827@mail.bitblocks.com>
	<d92931b41d270e71c61f582b9860649c@brasstown.quanstro.net>
	<0A2E2FB2-B2F1-444E-AF62-85FAC05335EA@bitblocks.com>
	<1c77ed407dc1ed28544e2033df7088ce@brasstown.quanstro.net>
	<20130822153243.A567AB827@mail.bitblocks.com>
MIME-Version: 1.0
Content-Type: text/plain; charset="US-ASCII"
Content-Transfer-Encoding: 7bit
Subject: Re: [9fans] more on why vc can't produce amd64 executables
Topicbox-Message-UUID: 7408d176-ead8-11e9-9d60-3106f5b1d025

> > i think a bug is setting inuxi8[i+4] = inuxi8[i] for 0<=i<4.
> > mikro; diffy -c *.c
> > diff -c /n/dump/2013/0821/sys/src/cmd/6l/obj.c obj.c
> > /n/dump/2013/0821/sys/src/cmd/6l/obj.c:1455,1471 - obj.c:1455,1471
> >   	int i, c;
> >
> >   	for(i=0; i<4; i++) {
> > - 		c = find1(0x04030201L, i+1);
> > + 		c = find1(0x0807060504030201ULL, i+1);
>
> Why not
> 	for(i=0; i<8; i++) {
> Else what is the point of
> 		c = find1(0x0807060504030201ULL, i+1);
> Just eyeballing. I haven't looked at the actual code.

as it turns out, floating point is already swapped by Ieee, and
anything less than or equal to 4 bytes is cast uprated to a ulong,
not a uvlong.

this version produces the same output with -a as on amd64.

i think it's a little more clear to straightforwardly set up the nuxi,
and special case the word-swapping in the floating point.
ideally, the low and high words would be merged to a vlong.

this fix likely won't survive its encounter with review intact, but
at least for now i can compile amd64 binaries on mips.
once a final form is in place a fix should be applied to all
compilers.

- erik

----
/n/atom/plan9/sys/src/cmd/6l/obj.c:1449,1472 - obj.c:1449,1482
  	}
  }

+ static uvlong lorder = 0x0706050403020100ull;
+
  void
+ letab(uchar *t, int w, int n)
+ {
+ 	uchar *o;
+ 	uint i;
+
+ 	o = (uchar*)&lorder;
+ 	o += (o[0]!=0)*(8-w);		/* if big endian, use tail not head */
+ 	for(i = 0; i < n; i++)
+ 		t[i] = o[i];
+ }
+
+ void
  nuxiinit(void)
  {
- 	int i, c;
+ 	int i;

- 	for(i=0; i<4; i++) {
- 		c = find1(0x04030201L, i+1);
- 		if(i < 2)
- 			inuxi2[i] = c;
- 		if(i < 1)
- 			inuxi1[i] = c;
- 		inuxi4[i] = c;
- 		inuxi8[i] = c;
- 		inuxi8[i+4] = c+4;
- 		fnuxi4[i] = c;
- 		fnuxi8[i] = c;
- 		fnuxi8[i+4] = c+4;
- 	}
+ 	letab(inuxi1, 4, 1);			/* cast to 4 bytes, 1 byte tab */
+ 	letab(inuxi2, 4, 2);
+ 	letab(inuxi4, 4, 4);
+ 	letab(inuxi8, 8, 8);
+ 	letab(fnuxi4, 4, 4);
+ 	letab(fnuxi8, 4, 4);		/* undo Ieee swapping. */
+ 	for(i = 4; i < 8; i++)
+ 		fnuxi8[i] = fnuxi8[i-4]+4;
+
  	if(debug['v']) {
  		Bprint(&bso, "inuxi = ");
  		for(i=0; i<1; i++)
/n/atom/plan9/sys/src/cmd/6l/obj.c:1489,1523 - obj.c:1499,1504
  		Bprint(&bso, "\n");
  	}
  	Bflush(&bso);
- }
-
- int
- find1(long l, int c)
- {
- 	char *p;
- 	int i;
-
- 	p = (char*)&l;
- 	for(i=0; i<4; i++)
- 		if(*p++ == c)
- 			return i;
- 	return 0;
- }
-
- int
- find2(long l, int c)
- {
- 	short *p;
- 	int i;
-
- 	p = (short*)&l;
- 	for(i=0; i<4; i+=2) {
- 		if(((*p >> 8) & 0xff) == c)
- 			return i;
- 		if((*p++ & 0xff) == c)
- 			return i+1;
- 	}
- 	return 0;
  }

  long