- use c89-style comments

  Closes issue #5194

25 files changed, 854 insertions, 853 deletions

diff --git a/libc/string/bfin/memchr.S b/libc/string/bfin/memchr.S
index 88e46bef6..26d419f7c 100644
--- a/libc/string/bfin/memchr.S
+++ b/libc/string/bfin/memchr.S
@@ -25,8 +25,8 @@
 
 .weak _memchr
 ENTRY(_memchr)
-	P0 = R0;             // P0 = address
-	P2 = R2;             // P2 = count
+	P0 = R0;             /* P0 = address */
+	P2 = R2;             /* P2 = count */
 	R1 = R1.B(Z);
 	CC = R2 == 0;
 	IF CC JUMP .Lfailed;
diff --git a/libc/string/bfin/strcmp.S b/libc/string/bfin/strcmp.S
index 12e8c53c6..ef23aa9ab 100644
--- a/libc/string/bfin/strcmp.S
+++ b/libc/string/bfin/strcmp.S
@@ -29,66 +29,66 @@ ENTRY(_strcmp)
 	p1 = r0;
 	p2 = r1;
 
-	p0 = -1;	// (need for loop counter init)
+	p0 = -1;	/* (need for loop counter init) */
 
-	  // check if byte aligned
-	r0 = r0 | r1;	// check both pointers at same time
-	r0 <<= 30;	// dump all but last 2 bits
-	cc = az;	// are they zero?
-	if !cc jump .Lunaligned;	// no; use unaligned code.
-			// fall-thru for aligned case..
+	  /* check if byte aligned */
+	r0 = r0 | r1;	/* check both pointers at same time */
+	r0 <<= 30;	/* dump all but last 2 bits */
+	cc = az;	/* are they zero? */
+	if !cc jump .Lunaligned;	/* no; use unaligned code. */
+			/* fall-thru for aligned case.. */
 
-	  // note that r0 is zero from the previous...
-	  //           p0 set to -1
+	  /* note that r0 is zero from the previous... */
+	  /*           p0 set to -1 */
 
 	LSETUP (.Lbeginloop, .Lendloop) lc0=p0;
-	  // pick up first words
+	  /* pick up first words */
 	r1 = [p1++];
 	r2 = [p2++];
-	  // make up mask:  0FF0FF
+	  /* make up mask:  0FF0FF */
 	r7 = 0xFF;
 	r7.h = 0xFF;
-		// loop : 9 cycles to check 4 characters
+		/* loop : 9 cycles to check 4 characters */
 	cc = r1 == r2;
 .Lbeginloop:
-	if !cc jump .Lnotequal4;	// compare failure, exit loop
+	if !cc jump .Lnotequal4;	/* compare failure, exit loop */
 
-	  // starting with   44332211
-	  // see if char 3 or char 1 is 0
-	r3 = r1 & r7;		// form 00330011
-	  // add to zero, and (r2 is free, reload)
+	  /* starting with   44332211 */
+	  /* see if char 3 or char 1 is 0 */
+	r3 = r1 & r7;		/* form 00330011 */
+	  /* add to zero, and (r2 is free, reload) */
 	r6 = r3 +|+ r0 || r2 = [p2++] || nop;
-	cc = az;	// true if either is zero
-	r3 = r1 ^ r3;	        // form 44002200 (4321^0301 => 4020)
-				// (trick, saves having another mask)
-	// add to zero,  and  (r1 is free, reload)
+	cc = az;	/* true if either is zero */
+	r3 = r1 ^ r3;	        /* form 44002200 (4321^0301 => 4020) */
+				/* (trick, saves having another mask) */
+	/* add to zero,  and  (r1 is free, reload) */
 	r6 = r3 +|+ r0 || r1 = [p1++] || nop;
-	cc |= az;	// true if either is zero
-	if cc jump .Lzero4;	// leave if a zero somewhere
+	cc |= az;	/* true if either is zero */
+	if cc jump .Lzero4;	/* leave if a zero somewhere */
 .Lendloop:
 	cc = r1 == r2;
 
- // loop exits
-.Lnotequal4:		// compare failure on 4-char compare
-			// address pointers are one word ahead;
-			// faster to use zero4 exit code
+ /* loop exits */
+.Lnotequal4:		/* compare failure on 4-char compare */
+			/* address pointers are one word ahead; */
+			/* faster to use zero4 exit code */
 	p1 += 4;
 	p2 += 4;
 
-.Lzero4:			// one of the bytes in word 1 is zero
-			// but we've already fetched the next word; so
-			// backup two to look at failing word again
+.Lzero4:			/* one of the bytes in word 1 is zero */
+			/* but we've already fetched the next word; so */
+			/* backup two to look at failing word again */
 	p1 += -8;
 	p2 += -8;
 
 
 
-		// here when pointers are unaligned: checks one
-		// character at a time.  Also use at the end of
-		// the word-check algorithm to figure out what happened
+		/* here when pointers are unaligned: checks one */
+		/* character at a time.  Also use at the end of */
+		/* the word-check algorithm to figure out what happened */
 .Lunaligned:
-	  //	R0 is non-zero from before.
-	  //           p0 set to -1
+	  /*	R0 is non-zero from before. */
+	  /*           p0 set to -1 */
 
 	r0 = 0 (Z);
 	r1 = B[p1++] (Z);
@@ -96,18 +96,18 @@ ENTRY(_strcmp)
 	LSETUP (.Lbeginloop1, .Lendloop1) lc0=p0;
 
 .Lbeginloop1:
-	cc = r1;	// first char must be non-zero
-	// chars must be the same
+	cc = r1;	/* first char must be non-zero */
+	/* chars must be the same */
 	r3 = r2 - r1 (NS) || r1 = B[p1++] (Z) || nop;
 	cc &= az;
-	r3 = r0 - r2;	// second char must be non-zero
+	r3 = r0 - r2;	/* second char must be non-zero */
 	cc &= an;
 	if !cc jump .Lexitloop1;
 .Lendloop1:
 	r2 = B[p2++] (Z);
 
-.Lexitloop1: // here means we found a zero or a difference.
-	   // we have r2(N), p2(N), r1(N+1), p1(N+2)
+.Lexitloop1: /* here means we found a zero or a difference. */
+	   /* we have r2(N), p2(N), r1(N+1), p1(N+2) */
 	r1=B[p1+ -2] (Z);
 	r0 = r1 - r2;
 	(r7:4) = [sp++];
diff --git a/libc/string/generic/strtok_r.c b/libc/string/generic/strtok_r.c
index d082d226e..7648212f7 100644
--- a/libc/string/generic/strtok_r.c
+++ b/libc/string/generic/strtok_r.c
@@ -29,17 +29,17 @@
 # define __rawmemchr strchr
 /* Experimentally off - libc_hidden_proto(strchr) */
 #endif
-
-/* Parse S into tokens separated by characters in DELIM.
+#if 0
+   Parse S into tokens separated by characters in DELIM.
    If S is NULL, the saved pointer in SAVE_PTR is used as
    the next starting point.  For example:
 	char s[] = "-abc-=-def";
 	char *sp;
-	x = strtok_r(s, "-", &sp);	// x = "abc", sp = "=-def"
-	x = strtok_r(NULL, "-=", &sp);	// x = "def", sp = NULL
-	x = strtok_r(NULL, "=", &sp);	// x = NULL
-		// s = "abc\0-def\0"
-*/
+	x = strtok_r(s, "-", &sp);	/* x = "abc", sp = "=-def" */
+	x = strtok_r(NULL, "-=", &sp);	/* x = "def", sp = NULL */
+	x = strtok_r(NULL, "=", &sp);	/* x = NULL */
+		/* s = "abc\0-def\0" */
+#endif
 char *strtok_r (char *s, const char *delim, char **save_ptr)
 {
   char *token;
diff --git a/libc/string/ia64/bzero.S b/libc/string/ia64/bzero.S
index d390838a6..1f0f8b7ac 100644
--- a/libc/string/ia64/bzero.S
+++ b/libc/string/ia64/bzero.S
@@ -47,13 +47,13 @@
 #define ptr1		r28
 #define ptr2		r27
 #define ptr3		r26
-#define ptr9 		r24
+#define ptr9		r24
 #define	loopcnt		r23
 #define linecnt		r22
 #define bytecnt		r21
 
-// This routine uses only scratch predicate registers (p6 - p15)
-#define p_scr		p6	// default register for same-cycle branches
+/* This routine uses only scratch predicate registers (p6 - p15) */
+#define p_scr		p6	/* default register for same-cycle branches */
 #define p_unalgn	p9
 #define p_y		p11
 #define p_n		p12
@@ -65,7 +65,7 @@
 #define MIN1		15
 #define MIN1P1HALF	8
 #define LINE_SIZE	128
-#define LSIZE_SH        7			// shift amount
+#define LSIZE_SH        7			/* shift amount */
 #define PREF_AHEAD	8
 
 #define USE_FLP
@@ -87,49 +87,49 @@ ENTRY(bzero)
 	movi0	save_lc = ar.lc
 } { .mmi
 	.body
-	mov	ret0 = dest		// return value
+	mov	ret0 = dest		/* return value */
 	nop.m	0
 	cmp.eq	p_scr, p0 = cnt, r0
 ;; }
 { .mmi
-	and	ptr2 = -(MIN1+1), dest	// aligned address
-	and	tmp = MIN1, dest	// prepare to check for alignment
-	tbit.nz p_y, p_n = dest, 0	// Do we have an odd address? (M_B_U)
+	and	ptr2 = -(MIN1+1), dest	/* aligned address */
+	and	tmp = MIN1, dest	/* prepare to check for alignment */
+	tbit.nz p_y, p_n = dest, 0	/* Do we have an odd address? (M_B_U) */
 } { .mib
 	mov	ptr1 = dest
 	nop.i	0
-(p_scr)	br.ret.dpnt.many rp		// return immediately if count = 0
+(p_scr)	br.ret.dpnt.many rp		/* return immediately if count = 0 */
 ;; }
 { .mib
 	cmp.ne	p_unalgn, p0 = tmp, r0
-} { .mib					// NB: # of bytes to move is 1
-	sub	bytecnt = (MIN1+1), tmp		//     higher than loopcnt
-	cmp.gt	p_scr, p0 = 16, cnt		// is it a minimalistic task?
-(p_scr)	br.cond.dptk.many .move_bytes_unaligned	// go move just a few (M_B_U)
+} { .mib					/* NB: # of bytes to move is 1 */
+	sub	bytecnt = (MIN1+1), tmp		/*     higher than loopcnt */
+	cmp.gt	p_scr, p0 = 16, cnt		/* is it a minimalistic task? */
+(p_scr)	br.cond.dptk.many .move_bytes_unaligned	/* go move just a few (M_B_U) */
 ;; }
 { .mmi
-(p_unalgn) add	ptr1 = (MIN1+1), ptr2		// after alignment
-(p_unalgn) add	ptr2 = MIN1P1HALF, ptr2		// after alignment
-(p_unalgn) tbit.nz.unc p_y, p_n = bytecnt, 3	// should we do a st8 ?
+(p_unalgn) add	ptr1 = (MIN1+1), ptr2		/* after alignment */
+(p_unalgn) add	ptr2 = MIN1P1HALF, ptr2		/* after alignment */
+(p_unalgn) tbit.nz.unc p_y, p_n = bytecnt, 3	/* should we do a st8 ? */
 ;; }
 { .mib
 (p_y)	add	cnt = -8, cnt
-(p_unalgn) tbit.nz.unc p_yy, p_nn = bytecnt, 2	// should we do a st4 ?
+(p_unalgn) tbit.nz.unc p_yy, p_nn = bytecnt, 2	/* should we do a st4 ? */
 } { .mib
 (p_y)	st8	[ptr2] = r0,-4
 (p_n)	add	ptr2 = 4, ptr2
 ;; }
 { .mib
 (p_yy)	add	cnt = -4, cnt
-(p_unalgn) tbit.nz.unc p_y, p_n = bytecnt, 1	// should we do a st2 ?
+(p_unalgn) tbit.nz.unc p_y, p_n = bytecnt, 1	/* should we do a st2 ? */
 } { .mib
 (p_yy)	st4	[ptr2] = r0,-2
 (p_nn)	add	ptr2 = 2, ptr2
 ;; }
 { .mmi
-	mov	tmp = LINE_SIZE+1		// for compare
+	mov	tmp = LINE_SIZE+1		/* for compare */
 (p_y)	add	cnt = -2, cnt
-(p_unalgn) tbit.nz.unc p_yy, p_nn = bytecnt, 0	// should we do a st1 ?
+(p_unalgn) tbit.nz.unc p_yy, p_nn = bytecnt, 0	/* should we do a st1 ? */
 } { .mmi
 	nop.m	0
 (p_y)	st2	[ptr2] = r0,-1
@@ -138,44 +138,44 @@ ENTRY(bzero)
 
 { .mmi
 (p_yy)	st1	[ptr2] = r0
-  	cmp.gt	p_scr, p0 = tmp, cnt		// is it a minimalistic task?
+	cmp.gt	p_scr, p0 = tmp, cnt		/* is it a minimalistic task? */
 } { .mbb
 (p_yy)	add	cnt = -1, cnt
-(p_scr)	br.cond.dpnt.many .fraction_of_line	// go move just a few
+(p_scr)	br.cond.dpnt.many .fraction_of_line	/* go move just a few */
 ;; }
 { .mib
-	nop.m 	0
+	nop.m	0
 	shr.u	linecnt = cnt, LSIZE_SH
 	nop.b	0
 ;; }
 
 	.align 32
-.l1b:	// ------------------//  L1B: store ahead into cache lines; fill later
+.l1b:	/* ------------------  L1B: store ahead into cache lines; fill later */
 { .mmi
-	and	tmp = -(LINE_SIZE), cnt		// compute end of range
-	mov	ptr9 = ptr1			// used for prefetching
-	and	cnt = (LINE_SIZE-1), cnt	// remainder
+	and	tmp = -(LINE_SIZE), cnt		/* compute end of range */
+	mov	ptr9 = ptr1			/* used for prefetching */
+	and	cnt = (LINE_SIZE-1), cnt	/* remainder */
 } { .mmi
-	mov	loopcnt = PREF_AHEAD-1		// default prefetch loop
-	cmp.gt	p_scr, p0 = PREF_AHEAD, linecnt	// check against actual value
+	mov	loopcnt = PREF_AHEAD-1		/* default prefetch loop */
+	cmp.gt	p_scr, p0 = PREF_AHEAD, linecnt	/* check against actual value */
 ;; }
 { .mmi
 (p_scr)	add	loopcnt = -1, linecnt
-	add	ptr2 = 16, ptr1	// start of stores (beyond prefetch stores)
-	add	ptr1 = tmp, ptr1	// first address beyond total range
+	add	ptr2 = 16, ptr1	/* start of stores (beyond prefetch stores) */
+	add	ptr1 = tmp, ptr1	/* first address beyond total range */
 ;; }
 { .mmi
-	add	tmp = -1, linecnt	// next loop count
+	add	tmp = -1, linecnt	/* next loop count */
 	movi0	ar.lc = loopcnt
 ;; }
 .pref_l1b:
 { .mib
-	stf.spill [ptr9] = f0, 128	// Do stores one cache line apart
+	stf.spill [ptr9] = f0, 128	/* Do stores one cache line apart */
 	nop.i   0
 	br.cloop.dptk.few .pref_l1b
 ;; }
 { .mmi
-	add	ptr0 = 16, ptr2		// Two stores in parallel
+	add	ptr0 = 16, ptr2		/* Two stores in parallel */
 	movi0	ar.lc = tmp
 ;; }
 .l1bx:
@@ -190,7 +190,7 @@ ENTRY(bzero)
  { .mmi
 	stf.spill [ptr2] = f0, 32
 	stf.spill [ptr0] = f0, 64
- 	cmp.lt	p_scr, p0 = ptr9, ptr1	// do we need more prefetching?
+	cmp.lt	p_scr, p0 = ptr9, ptr1	/* do we need more prefetching? */
  ;; }
 { .mmb
 	stf.spill [ptr2] = f0, 32
@@ -198,14 +198,14 @@ ENTRY(bzero)
 	br.cloop.dptk.few .l1bx
 ;; }
 { .mib
-	cmp.gt  p_scr, p0 = 8, cnt	// just a few bytes left ?
+	cmp.gt  p_scr, p0 = 8, cnt	/* just a few bytes left ? */
 (p_scr)	br.cond.dpnt.many  .move_bytes_from_alignment
 ;; }
 
 .fraction_of_line:
 { .mib
 	add	ptr2 = 16, ptr1
-	shr.u	loopcnt = cnt, 5   	// loopcnt = cnt / 32
+	shr.u	loopcnt = cnt, 5	/* loopcnt = cnt / 32 */
 ;; }
 { .mib
 	cmp.eq	p_scr, p0 = loopcnt, r0
@@ -213,11 +213,11 @@ ENTRY(bzero)
 (p_scr)	br.cond.dpnt.many .store_words
 ;; }
 { .mib
-	and	cnt = 0x1f, cnt		// compute the remaining cnt
+	and	cnt = 0x1f, cnt		/* compute the remaining cnt */
 	movi0   ar.lc = loopcnt
 ;; }
 	.align 32
-.l2:	// -----------------------------//  L2A:  store 32B in 2 cycles
+.l2:	/* -----------------------------  L2A:  store 32B in 2 cycles */
 { .mmb
 	store	[ptr1] = myval, 8
 	store	[ptr2] = myval, 8
@@ -228,38 +228,38 @@ ENTRY(bzero)
 ;; }
 .store_words:
 { .mib
-	cmp.gt	p_scr, p0 = 8, cnt	// just a few bytes left ?
-(p_scr)	br.cond.dpnt.many .move_bytes_from_alignment	// Branch
+	cmp.gt	p_scr, p0 = 8, cnt	/* just a few bytes left ? */
+(p_scr)	br.cond.dpnt.many .move_bytes_from_alignment	/* Branch */
 ;; }
 
 { .mmi
-	store	[ptr1] = myval, 8	// store
-	cmp.le	p_y, p_n = 16, cnt	//
-	add	cnt = -8, cnt		// subtract
+	store	[ptr1] = myval, 8	/* store */
+	cmp.le	p_y, p_n = 16, cnt	/* */
+	add	cnt = -8, cnt		/* subtract */
 ;; }
 { .mmi
-(p_y)	store	[ptr1] = myval, 8	// store
+(p_y)	store	[ptr1] = myval, 8	/* store */
 (p_y)	cmp.le.unc p_yy, p_nn = 16, cnt
-(p_y)	add	cnt = -8, cnt		// subtract
+(p_y)	add	cnt = -8, cnt		/* subtract */
 ;; }
-{ .mmi					// store
+{ .mmi					/* store */
 (p_yy)	store	[ptr1] = myval, 8
-(p_yy)	add	cnt = -8, cnt		// subtract
+(p_yy)	add	cnt = -8, cnt		/* subtract */
 ;; }
 
 .move_bytes_from_alignment:
 { .mib
 	cmp.eq	p_scr, p0 = cnt, r0
-	tbit.nz.unc p_y, p0 = cnt, 2	// should we terminate with a st4 ?
+	tbit.nz.unc p_y, p0 = cnt, 2	/* should we terminate with a st4 ? */
 (p_scr)	br.cond.dpnt.few .restore_and_exit
 ;; }
 { .mib
 (p_y)	st4	[ptr1] = r0,4
-	tbit.nz.unc p_yy, p0 = cnt, 1	// should we terminate with a st2 ?
+	tbit.nz.unc p_yy, p0 = cnt, 1	/* should we terminate with a st2 ? */
 ;; }
 { .mib
 (p_yy)	st2	[ptr1] = r0,2
-	tbit.nz.unc p_y, p0 = cnt, 0	// should we terminate with a st1 ?
+	tbit.nz.unc p_y, p0 = cnt, 0	/* should we terminate with a st1 ? */
 ;; }
 
 { .mib
@@ -281,38 +281,38 @@ ENTRY(bzero)
 (p_n)	add	ptr2 = 2, ptr1
 } { .mmi
 (p_y)	add	ptr2 = 3, ptr1
-(p_y)	st1	[ptr1] = r0, 1		// fill 1 (odd-aligned) byte
-(p_y)	add	cnt = -1, cnt		// [15, 14 (or less) left]
+(p_y)	st1	[ptr1] = r0, 1		/* fill 1 (odd-aligned) byte */
+(p_y)	add	cnt = -1, cnt		/* [15, 14 (or less) left] */
 ;; }
 { .mmi
 (p_yy)	cmp.le.unc p_y, p0 = 8, cnt
-	add	ptr3 = ptr1, cnt	// prepare last store
+	add	ptr3 = ptr1, cnt	/* prepare last store */
 	movi0	ar.lc = save_lc
 } { .mmi
-(p_yy)	st2	[ptr1] = r0, 4		// fill 2 (aligned) bytes
-(p_yy)	st2	[ptr2] = r0, 4		// fill 2 (aligned) bytes
-(p_yy)	add	cnt = -4, cnt		// [11, 10 (o less) left]
+(p_yy)	st2	[ptr1] = r0, 4		/* fill 2 (aligned) bytes */
+(p_yy)	st2	[ptr2] = r0, 4		/* fill 2 (aligned) bytes */
+(p_yy)	add	cnt = -4, cnt		/* [11, 10 (o less) left] */
 ;; }
 { .mmi
 (p_y)	cmp.le.unc p_yy, p0 = 8, cnt
-	add	ptr3 = -1, ptr3		// last store
-	tbit.nz p_scr, p0 = cnt, 1	// will there be a st2 at the end ?
+	add	ptr3 = -1, ptr3		/* last store */
+	tbit.nz p_scr, p0 = cnt, 1	/* will there be a st2 at the end ? */
 } { .mmi
-(p_y)	st2	[ptr1] = r0, 4		// fill 2 (aligned) bytes
-(p_y)	st2	[ptr2] = r0, 4		// fill 2 (aligned) bytes
-(p_y)	add	cnt = -4, cnt		// [7, 6 (or less) left]
+(p_y)	st2	[ptr1] = r0, 4		/* fill 2 (aligned) bytes */
+(p_y)	st2	[ptr2] = r0, 4		/* fill 2 (aligned) bytes */
+(p_y)	add	cnt = -4, cnt		/* [7, 6 (or less) left] */
 ;; }
 { .mmi
-(p_yy)	st2	[ptr1] = r0, 4		// fill 2 (aligned) bytes
-(p_yy)	st2	[ptr2] = r0, 4		// fill 2 (aligned) bytes
-					// [3, 2 (or less) left]
-	tbit.nz p_y, p0 = cnt, 0	// will there be a st1 at the end ?
+(p_yy)	st2	[ptr1] = r0, 4		/* fill 2 (aligned) bytes */
+(p_yy)	st2	[ptr2] = r0, 4		/* fill 2 (aligned) bytes */
+					/* [3, 2 (or less) left] */
+	tbit.nz p_y, p0 = cnt, 0	/* will there be a st1 at the end ? */
 } { .mmi
 (p_yy)	add	cnt = -4, cnt
 ;; }
 { .mmb
-(p_scr)	st2	[ptr1] = r0		// fill 2 (aligned) bytes
-(p_y)	st1	[ptr3] = r0		// fill last byte (using ptr3)
+(p_scr)	st2	[ptr1] = r0		/* fill 2 (aligned) bytes */
+(p_y)	st1	[ptr3] = r0		/* fill last byte (using ptr3) */
 	br.ret.sptk.many rp
 ;; }
 END(bzero)
diff --git a/libc/string/ia64/memccpy.S b/libc/string/ia64/memccpy.S
index 1afba3637..259d680bc 100644
--- a/libc/string/ia64/memccpy.S
+++ b/libc/string/ia64/memccpy.S
@@ -23,7 +23,7 @@
    Inputs:
         in0:    dest
         in1:    src
-  	in2:	char
+	in2:	char
         in3:    byte count
 
    This implementation assumes little endian mode (UM.be = 0).
@@ -69,75 +69,75 @@ ENTRY(memccpy)
 	.rotr	r[MEMLAT + 7], tmp1[4], tmp2[4], val[4], tmp3[2], pos0[2]
 	.rotp	p[MEMLAT + 6 + 1]
 
-	mov	ret0 = r0		// return NULL if no match
+	mov	ret0 = r0		/* return NULL if no match */
 	.save pr, saved_pr
-	mov	saved_pr = pr		// save the predicate registers
-	mov 	dest = in0		// dest
+	mov	saved_pr = pr		/* save the predicate registers */
+	mov 	dest = in0		/* dest */
 	.save ar.lc, saved_lc
-        mov 	saved_lc = ar.lc	// save the loop counter
-        mov 	saved_ec = ar.ec	// save the loop counter
+        mov 	saved_lc = ar.lc	/* save the loop counter */
+        mov 	saved_ec = ar.ec	/* save the loop counter */
 	.body
-	mov 	src = in1		// src
-	extr.u	char = in2, 0, 8	// char
-	mov	len = in3		// len
-	sub	tmp = r0, in0		// tmp = -dest
-	cmp.ne	p7, p0 = r0, r0		// clear p7
+	mov 	src = in1		/* src */
+	extr.u	char = in2, 0, 8	/* char */
+	mov	len = in3		/* len */
+	sub	tmp = r0, in0		/* tmp = -dest */
+	cmp.ne	p7, p0 = r0, r0		/* clear p7 */
 	;;
-	and	loopcnt = 7, tmp	// loopcnt = -dest % 8
-	cmp.ge	p6, p0 = OP_T_THRES, len	// is len <= OP_T_THRES
-	mov	ar.ec = 0		// ec not guaranteed zero on entry
-(p6)	br.cond.spnt	.cpyfew		// copy byte by byte
+	and	loopcnt = 7, tmp	/* loopcnt = -dest % 8 */
+	cmp.ge	p6, p0 = OP_T_THRES, len	/* is len <= OP_T_THRES */
+	mov	ar.ec = 0		/* ec not guaranteed zero on entry */
+(p6)	br.cond.spnt	.cpyfew		/* copy byte by byte */
 	;;
 	cmp.eq	p6, p0 = loopcnt, r0
 	mux1	charx8 = char, @brcst
 (p6)	br.cond.sptk .dest_aligned
-	sub	len = len, loopcnt	// len -= -dest % 8
-	adds	loopcnt = -1, loopcnt	// --loopcnt
+	sub	len = len, loopcnt	/* len -= -dest % 8 */
+	adds	loopcnt = -1, loopcnt	/* --loopcnt */
 	;;
 	mov	ar.lc = loopcnt
-.l1:					// copy -dest % 8 bytes
-	ld1	value = [src], 1	// value = *src++
+.l1:					/* copy -dest % 8 bytes */
+	ld1	value = [src], 1	/* value = *src++ */
 	;;
-	st1	[dest] = value, 1	// *dest++ = value
+	st1	[dest] = value, 1	/* *dest++ = value */
 	cmp.eq	p6, p0 = value, char
 (p6)	br.cond.spnt .foundit
 	br.cloop.dptk .l1
 .dest_aligned:
-	and	sh1 = 7, src 		// sh1 = src % 8
-	and	tmp = -8, len   	// tmp = len & -OPSIZ
-	and	asrc = -8, src		// asrc = src & -OPSIZ  -- align src
-	shr.u	loopcnt = len, 3	// loopcnt = len / 8
-	and	len = 7, len ;;		// len = len % 8
-	shl	sh1 = sh1, 3		// sh1 = 8 * (src % 8)
-	adds	loopcnt = -1, loopcnt	// --loopcnt
-	mov     pr.rot = 1 << 16 ;;	// set rotating predicates
-	sub	sh2 = 64, sh1		// sh2 = 64 - sh1
-	mov	ar.lc = loopcnt		// set LC
-	cmp.eq  p6, p0 = sh1, r0 	// is the src aligned?
+	and	sh1 = 7, src 		/* sh1 = src % 8 */
+	and	tmp = -8, len   	/* tmp = len & -OPSIZ */
+	and	asrc = -8, src		/* asrc = src & -OPSIZ  -- align src */
+	shr.u	loopcnt = len, 3	/* loopcnt = len / 8 */
+	and	len = 7, len ;;		/* len = len % 8 */
+	shl	sh1 = sh1, 3		/* sh1 = 8 * (src % 8) */
+	adds	loopcnt = -1, loopcnt	/* --loopcnt */
+	mov     pr.rot = 1 << 16 ;;	/* set rotating predicates */
+	sub	sh2 = 64, sh1		/* sh2 = 64 - sh1 */
+	mov	ar.lc = loopcnt		/* set LC */
+	cmp.eq  p6, p0 = sh1, r0 	/* is the src aligned? */
 (p6)    br.cond.sptk .src_aligned ;;
-	add	src = src, tmp		// src += len & -OPSIZ
-	mov	ar.ec = MEMLAT + 6 + 1 	// six more passes needed
-	ld8	r[1] = [asrc], 8 	// r[1] = w0
-	cmp.ne	p6, p0 = r0, r0	;;	// clear p6
+	add	src = src, tmp		/* src += len & -OPSIZ */
+	mov	ar.ec = MEMLAT + 6 + 1 	/* six more passes needed */
+	ld8	r[1] = [asrc], 8 	/* r[1] = w0 */
+	cmp.ne	p6, p0 = r0, r0	;;	/* clear p6 */
 	ALIGN(32)
 .l2:
-(p[0])		ld8.s	r[0] = [asrc], 8		// r[0] = w1
-(p[MEMLAT])	shr.u	tmp1[0] = r[1 + MEMLAT], sh1	// tmp1 = w0 >> sh1
-(p[MEMLAT])	shl	tmp2[0] = r[0 + MEMLAT], sh2  	// tmp2 = w1 << sh2
+(p[0])		ld8.s	r[0] = [asrc], 8		/* r[0] = w1 */
+(p[MEMLAT])	shr.u	tmp1[0] = r[1 + MEMLAT], sh1	/* tmp1 = w0 >> sh1 */
+(p[MEMLAT])	shl	tmp2[0] = r[0 + MEMLAT], sh2  	/* tmp2 = w1 << sh2 */
 (p[MEMLAT+4])	xor	tmp3[0] = val[1], charx8
 (p[MEMLAT+5])	czx1.r	pos0[0] = tmp3[1]
-(p[MEMLAT+6])	chk.s	r[6 + MEMLAT], .recovery1	// our data isn't
-							// valid - rollback!
+(p[MEMLAT+6])	chk.s	r[6 + MEMLAT], .recovery1	/* our data isn't */
+							/* valid - rollback! */
 (p[MEMLAT+6])	cmp.ne	p6, p0 = 8, pos0[1]
 (p6)		br.cond.spnt	.gotit
-(p[MEMLAT+6])	st8	[dest] = val[3], 8		// store val to dest
-(p[MEMLAT+3])	or	val[0] = tmp1[3], tmp2[3] 	// val = tmp1 | tmp2
+(p[MEMLAT+6])	st8	[dest] = val[3], 8		/* store val to dest */
+(p[MEMLAT+3])	or	val[0] = tmp1[3], tmp2[3] 	/* val = tmp1 | tmp2 */
 		br.ctop.sptk    .l2
 		br.cond.sptk .cpyfew
 
 .src_aligned:
-		cmp.ne  p6, p0 = r0, r0			// clear p6
-		mov     ar.ec = MEMLAT + 2 + 1 ;;	// set EC
+		cmp.ne  p6, p0 = r0, r0			/* clear p6 */
+		mov     ar.ec = MEMLAT + 2 + 1 ;;	/* set EC */
 .l3:
 (p[0])		ld8.s	r[0] = [src], 8
 (p[MEMLAT])	xor	tmp3[0] = r[MEMLAT], charx8
@@ -149,8 +149,8 @@ ENTRY(memccpy)
 (p[MEMLAT+2])	st8	[dest] = r[MEMLAT+2], 8
 		br.ctop.dptk .l3
 .cpyfew:
-	cmp.eq	p6, p0 = len, r0	// is len == 0 ?
-	adds	len = -1, len		// --len;
+	cmp.eq	p6, p0 = len, r0	/* is len == 0 ? */
+	adds	len = -1, len		/* --len; */
 (p6)	br.cond.spnt	.restore_and_exit ;;
 	mov	ar.lc = len
 .l4:
@@ -163,14 +163,14 @@ ENTRY(memccpy)
 .foundit:
 (p6)	mov	ret0 = dest
 .restore_and_exit:
-	mov     pr = saved_pr, -1    	// restore the predicate registers
-	mov 	ar.lc = saved_lc	// restore the loop counter
-	mov 	ar.ec = saved_ec ;;	// restore the epilog counter
+	mov     pr = saved_pr, -1    	/* restore the predicate registers */
+	mov 	ar.lc = saved_lc	/* restore the loop counter */
+	mov 	ar.ec = saved_ec ;;	/* restore the epilog counter */
 	br.ret.sptk.many b0
 .gotit:
 	.pred.rel "mutex" p6, p7
-(p6)	mov	value = val[3]		// if coming from l2
-(p7)	mov	value = r[MEMLAT+2]	// if coming from l3
+(p6)	mov	value = val[3]		/* if coming from l2 */
+(p7)	mov	value = r[MEMLAT+2]	/* if coming from l3 */
 	mov	ar.lc = pos0[1] ;;
 .l5:
 	extr.u	tmp = value, 0, 8 ;;
diff --git a/libc/string/ia64/memchr.S b/libc/string/ia64/memchr.S
index 2bf078fe6..0246b5997 100644
--- a/libc/string/ia64/memchr.S
+++ b/libc/string/ia64/memchr.S
@@ -62,18 +62,18 @@ ENTRY(__memchr)
 	.rotr	value[MEMLAT+1], addr[MEMLAT+3], aux[2], poschr[2]
 	.rotp	p[MEMLAT+3]
 	.save ar.lc, saved_lc
-        mov 	saved_lc = ar.lc 	// save the loop counter
+        mov 	saved_lc = ar.lc 	/* save the loop counter */
 	.save pr, saved_pr
-	mov	saved_pr = pr		// save the predicates
+	mov	saved_pr = pr		/* save the predicates */
 	.body
 	mov 	ret0 = str
-	and 	tmp = 7, str		// tmp = str % 8
-	cmp.ne	p7, p0 = r0, r0		// clear p7
-	extr.u	chr = in1, 0, 8		// chr = (unsigned char) in1
+	and 	tmp = 7, str		/* tmp = str % 8 */
+	cmp.ne	p7, p0 = r0, r0		/* clear p7 */
+	extr.u	chr = in1, 0, 8		/* chr = (unsigned char) in1 */
 	mov	len = in2
-	cmp.gtu	p6, p0 = 16, in2	// use a simple loop for short
-(p6)	br.cond.spnt .srchfew ;;	// searches
-	sub	loopcnt = 8, tmp	// loopcnt = 8 - tmp
+	cmp.gtu	p6, p0 = 16, in2	/* use a simple loop for short */
+(p6)	br.cond.spnt .srchfew ;;	/* searches */
+	sub	loopcnt = 8, tmp	/* loopcnt = 8 - tmp */
 	cmp.eq	p6, p0 = tmp, r0
 (p6)	br.cond.sptk	.str_aligned;;
 	sub	len = len, loopcnt
@@ -86,12 +86,12 @@ ENTRY(__memchr)
 (p6)	br.cond.spnt	.foundit
 	br.cloop.sptk	.l1 ;;
 .str_aligned:
-	cmp.ne	p6, p0 = r0, r0		// clear p6
-	shr.u	loopcnt = len, 3	// loopcnt = len / 8
-	and 	len = 7, len ;;		// remaining len = len & 7
+	cmp.ne	p6, p0 = r0, r0		/* clear p6 */
+	shr.u	loopcnt = len, 3	/* loopcnt = len / 8 */
+	and 	len = 7, len ;;		/* remaining len = len & 7 */
 	adds	loopcnt = -1, loopcnt
 	mov	ar.ec = MEMLAT + 3
-	mux1	chrx8 = chr, @brcst ;;	// get a word full of chr
+	mux1	chrx8 = chr, @brcst ;;	/* get a word full of chr */
 	mov	ar.lc = loopcnt
 	mov	pr.rot = 1 << 16 ;;
 .l2:
@@ -114,12 +114,12 @@ ENTRY(__memchr)
 (p6)	br.cond.dpnt	.foundit
 	br.cloop.sptk	.l3 ;;
 .notfound:
-	cmp.ne	p6, p0 = r0, r0	// clear p6 (p7 was already 0 when we got here)
-	mov	ret0 = r0 ;;	// return NULL
+	cmp.ne	p6, p0 = r0, r0	/* clear p6 (p7 was already 0 when we got here) */
+	mov	ret0 = r0 ;;	/* return NULL */
 .foundit:
 	.pred.rel "mutex" p6, p7
-(p6)	adds	ret0 = -1, ret0 		   // if we got here from l1 or l3
-(p7)	add	ret0 = addr[MEMLAT+2], poschr[1]   // if we got here from l2
+(p6)	adds	ret0 = -1, ret0 		   /* if we got here from l1 or l3 */
+(p7)	add	ret0 = addr[MEMLAT+2], poschr[1]   /* if we got here from l2 */
 	mov	pr = saved_pr, -1
 	mov	ar.lc = saved_lc
 	br.ret.sptk.many b0
diff --git a/libc/string/ia64/memcmp.S b/libc/string/ia64/memcmp.S
index 8b0c096ce..adb1a20de 100644
--- a/libc/string/ia64/memcmp.S
+++ b/libc/string/ia64/memcmp.S
@@ -28,7 +28,7 @@
    In this form, it assumes little endian mode.  For big endian mode, the
    the two shifts in .l2 must be inverted:
 
-	shl   	tmp1[0] = r[1 + MEMLAT], sh1   // tmp1 = w0 << sh1
+	shl	tmp1[0] = r[1 + MEMLAT], sh1   // tmp1 = w0 << sh1
 	shr.u   tmp2[0] = r[0 + MEMLAT], sh2   // tmp2 = w1 >> sh2
 
    and all the mux1 instructions should be replaced by plain mov's.  */
@@ -36,8 +36,8 @@
 #include "sysdep.h"
 #undef ret
 
-#define OP_T_THRES 	16
-#define OPSIZ 		8
+#define OP_T_THRES	16
+#define OPSIZ		8
 #define MEMLAT		2
 
 #define start		r15
@@ -56,85 +56,85 @@
 
 ENTRY(memcmp)
 	.prologue
-	alloc 	r2 = ar.pfs, 3, 37, 0, 40
+	alloc	r2 = ar.pfs, 3, 37, 0, 40
 
 	.rotr	r[MEMLAT + 2], q[MEMLAT + 5], tmp1[4], tmp2[4], val[2]
 	.rotp	p[MEMLAT + 4 + 1]
 
-	mov	ret0 = r0		// by default return value = 0
+	mov	ret0 = r0		/* by default return value = 0 */
 	.save pr, saved_pr
-	mov	saved_pr = pr		// save the predicate registers
+	mov	saved_pr = pr		/* save the predicate registers */
 	.save ar.lc, saved_lc
-        mov 	saved_lc = ar.lc	// save the loop counter
+        mov	saved_lc = ar.lc	/* save the loop counter */
 	.body
-	mov 	dest = in0		// dest
-	mov 	src = in1		// src
-	mov	len = in2		// len
-	sub	tmp = r0, in0		// tmp = -dest
+	mov	dest = in0		/* dest */
+	mov	src = in1		/* src */
+	mov	len = in2		/* len */
+	sub	tmp = r0, in0		/* tmp = -dest */
 	;;
-	and	loopcnt = 7, tmp		// loopcnt = -dest % 8
-	cmp.ge	p6, p0 = OP_T_THRES, len	// is len <= OP_T_THRES
-(p6)	br.cond.spnt	.cmpfew			// compare byte by byte
+	and	loopcnt = 7, tmp		/* loopcnt = -dest % 8 */
+	cmp.ge	p6, p0 = OP_T_THRES, len	/* is len <= OP_T_THRES */
+(p6)	br.cond.spnt	.cmpfew			/* compare byte by byte */
 	;;
 	cmp.eq	p6, p0 = loopcnt, r0
 (p6)	br.cond.sptk .dest_aligned
-	sub	len = len, loopcnt	// len -= -dest % 8
-	adds	loopcnt = -1, loopcnt	// --loopcnt
+	sub	len = len, loopcnt	/* len -= -dest % 8 */
+	adds	loopcnt = -1, loopcnt	/* --loopcnt */
 	;;
 	mov	ar.lc = loopcnt
-.l1:					// copy -dest % 8 bytes
-	ld1	value1 = [src], 1	// value = *src++
+.l1:					/* copy -dest % 8 bytes */
+	ld1	value1 = [src], 1	/* value = *src++ */
 	ld1	value2 = [dest], 1
 	;;
 	cmp.ne	p6, p0 = value1, value2
 (p6)	br.cond.spnt .done
 	br.cloop.dptk .l1
 .dest_aligned:
-	and	sh1 = 7, src 		// sh1 = src % 8
-	and	tmp = -8, len   	// tmp = len & -OPSIZ
-	and	asrc = -8, src		// asrc = src & -OPSIZ  -- align src
-	shr.u	loopcnt = len, 3	// loopcnt = len / 8
-	and	len = 7, len ;;		// len = len % 8
-	shl	sh1 = sh1, 3		// sh1 = 8 * (src % 8)
-	adds	loopcnt = -1, loopcnt	// --loopcnt
-	mov     pr.rot = 1 << 16 ;;	// set rotating predicates
-	sub	sh2 = 64, sh1		// sh2 = 64 - sh1
-	mov	ar.lc = loopcnt		// set LC
-	cmp.eq  p6, p0 = sh1, r0 	// is the src aligned?
+	and	sh1 = 7, src		/* sh1 = src % 8 */
+	and	tmp = -8, len		/* tmp = len & -OPSIZ */
+	and	asrc = -8, src		/* asrc = src & -OPSIZ  -- align src */
+	shr.u	loopcnt = len, 3	/* loopcnt = len / 8 */
+	and	len = 7, len ;;		/* len = len % 8 */
+	shl	sh1 = sh1, 3		/* sh1 = 8 * (src % 8) */
+	adds	loopcnt = -1, loopcnt	/* --loopcnt */
+	mov     pr.rot = 1 << 16 ;;	/* set rotating predicates */
+	sub	sh2 = 64, sh1		/* sh2 = 64 - sh1 */
+	mov	ar.lc = loopcnt		/* set LC */
+	cmp.eq  p6, p0 = sh1, r0	/* is the src aligned? */
 (p6)    br.cond.sptk .src_aligned
-	add	src = src, tmp		// src += len & -OPSIZ
-	mov	ar.ec = MEMLAT + 4 + 1 	// four more passes needed
-	ld8	r[1] = [asrc], 8 ;;	// r[1] = w0
+	add	src = src, tmp		/* src += len & -OPSIZ */
+	mov	ar.ec = MEMLAT + 4 + 1	/* four more passes needed */
+	ld8	r[1] = [asrc], 8 ;;	/* r[1] = w0 */
 	.align	32
 
-// We enter this loop with p6 cleared by the above comparison
+/* We enter this loop with p6 cleared by the above comparison */
 
 .l2:
-(p[0])		ld8	r[0] = [asrc], 8		// r[0] = w1
+(p[0])		ld8	r[0] = [asrc], 8		/* r[0] = w1 */
 (p[0])		ld8	q[0] = [dest], 8
-(p[MEMLAT])	shr.u	tmp1[0] = r[1 + MEMLAT], sh1	// tmp1 = w0 >> sh1
-(p[MEMLAT])	shl	tmp2[0] = r[0 + MEMLAT], sh2  	// tmp2 = w1 << sh2
+(p[MEMLAT])	shr.u	tmp1[0] = r[1 + MEMLAT], sh1	/* tmp1 = w0 >> sh1 */
+(p[MEMLAT])	shl	tmp2[0] = r[0 + MEMLAT], sh2	/* tmp2 = w1 << sh2 */
 (p[MEMLAT+4])	cmp.ne	p6, p0 = q[MEMLAT + 4], val[1]
-(p[MEMLAT+3])	or	val[0] = tmp1[3], tmp2[3] 	// val = tmp1 | tmp2