about summary refs log tree commit diff
path: root/ports/sysdeps/alpha/alphaev6/stxncpy.S
diff options
context:
space:
mode:
Diffstat (limited to 'ports/sysdeps/alpha/alphaev6/stxncpy.S')
-rw-r--r--ports/sysdeps/alpha/alphaev6/stxncpy.S392
1 files changed, 392 insertions, 0 deletions
diff --git a/ports/sysdeps/alpha/alphaev6/stxncpy.S b/ports/sysdeps/alpha/alphaev6/stxncpy.S
new file mode 100644
index 0000000000..28495df004
--- /dev/null
+++ b/ports/sysdeps/alpha/alphaev6/stxncpy.S
@@ -0,0 +1,392 @@
+/* Copyright (C) 2000-2012 Free Software Foundation, Inc.
+   Contributed by Richard Henderson (rth@tamu.edu)
+   EV6 optimized by Rick Gorton <rick.gorton@alpha-processor.com>.
+   This file is part of the GNU C Library.
+
+   The GNU C Library is free software; you can redistribute it and/or
+   modify it under the terms of the GNU Lesser General Public
+   License as published by the Free Software Foundation; either
+   version 2.1 of the License, or (at your option) any later version.
+
+   The GNU C Library is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+   Lesser General Public License for more details.
+
+   You should have received a copy of the GNU Lesser General Public
+   License along with the GNU C Library.  If not, see
+   <http://www.gnu.org/licenses/>.  */
+
+/* Copy no more than COUNT bytes of the null-terminated string from
+   SRC to DST.
+
+   This is an internal routine used by strncpy, stpncpy, and strncat.
+   As such, it uses special linkage conventions to make implementation
+   of these public functions more efficient.
+
+   On input:
+	t9 = return address
+	a0 = DST
+	a1 = SRC
+	a2 = COUNT
+
+   Furthermore, COUNT may not be zero.
+
+   On output:
+	t0  = last word written
+	t8  = bitmask (with one bit set) indicating the last byte written
+	t10 = bitmask (with one bit set) indicating the byte position of
+	      the end of the range specified by COUNT
+	a0  = unaligned address of the last *word* written
+	a2  = the number of full words left in COUNT
+
+   Furthermore, v0, a3-a5, t11, and t12 are untouched.
+*/
+
+#include <sysdep.h>
+
+	.arch ev6
+	.set noat
+	.set noreorder
+
+	.text
+	.type	__stxncpy, @function
+	.globl	__stxncpy
+	.usepv	__stxncpy, no
+
+	cfi_startproc
+	cfi_return_column (t9)
+
+	/* On entry to this basic block:
+	   t0 == the first destination word for masking back in
+	   t1 == the first source word.  */
+	.align 4
+stxncpy_aligned:
+	/* Create the 1st output word and detect 0's in the 1st input word.  */
+	lda	t2, -1		# E : build a mask against false zero
+	mskqh	t2, a1, t2	# U :   detection in the src word (stall)
+	mskqh	t1, a1, t3	# U :
+	ornot	t1, t2, t2	# E : (stall)
+
+	mskql	t0, a1, t0	# U : assemble the first output word
+	cmpbge	zero, t2, t7	# E : bits set iff null found
+	or	t0, t3, t0	# E : (stall)
+	beq	a2, $a_eoc	# U :
+
+	bne	t7, $a_eos	# U :
+	nop
+	nop
+	nop
+
+	/* On entry to this basic block:
+	   t0 == a source word not containing a null.  */
+
+	/*
+	 * nops here to:
+	 *	separate store quads from load quads
+	 *	limit of 1 bcond/quad to permit training
+	 */
+$a_loop:
+	stq_u	t0, 0(a0)	# L :
+	addq	a0, 8, a0	# E :
+	subq	a2, 1, a2	# E :
+	nop
+
+	ldq_u	t0, 0(a1)	# L :
+	addq	a1, 8, a1	# E :
+	cmpbge	zero, t0, t7	# E :
+	beq	a2, $a_eoc      # U :
+
+	beq	t7, $a_loop	# U :
+	nop
+	nop
+	nop
+
+	/* Take care of the final (partial) word store.  At this point
+	   the end-of-count bit is set in t7 iff it applies.
+
+	   On entry to this basic block we have:
+	   t0 == the source word containing the null
+	   t7 == the cmpbge mask that found it.  */
+$a_eos:
+	negq	t7, t8		# E : find low bit set
+	and	t7, t8, t8	# E : (stall)
+	/* For the sake of the cache, don't read a destination word
+	   if we're not going to need it.  */
+	and	t8, 0x80, t6	# E : (stall)
+	bne	t6, 1f		# U : (stall)
+
+	/* We're doing a partial word store and so need to combine
+	   our source and original destination words.  */
+	ldq_u	t1, 0(a0)	# L :
+	subq	t8, 1, t6	# E :
+	or	t8, t6, t7	# E : (stall)
+	zapnot	t0, t7, t0	# U : clear src bytes > null (stall)
+
+	zap	t1, t7, t1	# .. e1 : clear dst bytes <= null
+	or	t0, t1, t0	# e1    : (stall)
+	nop
+	nop
+
+1:	stq_u	t0, 0(a0)	# L :
+	ret	(t9)		# L0 : Latency=3
+	nop
+	nop
+
+	/* Add the end-of-count bit to the eos detection bitmask.  */
+$a_eoc:
+	or	t10, t7, t7	# E :
+	br	$a_eos		# L0 : Latency=3
+	nop
+	nop
+
+	.align 4
+__stxncpy:
+	/* Are source and destination co-aligned?  */
+	lda	t2, -1		# E :
+	xor	a0, a1, t1	# E :
+	and	a0, 7, t0	# E : find dest misalignment
+	nop			# E :
+
+	srl	t2, 1, t2	# U :
+	and	t1, 7, t1	# E :
+	cmovlt	a2, t2, a2	# E : bound count to LONG_MAX (stall)
+	nop			# E :
+
+	addq	a2, t0, a2	# E : bias count by dest misalignment
+	subq	a2, 1, a2	# E : (stall)
+	and	a2, 7, t2	# E : (stall)
+	lda	t10, 1		# E :
+
+	srl	a2, 3, a2	# U : a2 = loop counter = (count - 1)/8
+	sll	t10, t2, t10	# U : t10 = bitmask of last count byte
+	nop			# E :
+	bne	t1, $unaligned	# U : (stall)
+
+	/* We are co-aligned; take care of a partial first word.  */
+	ldq_u	t1, 0(a1)	# L : load first src word
+	addq	a1, 8, a1	# E :
+	beq	t0, stxncpy_aligned # U : avoid loading dest word if not needed
+	ldq_u	t0, 0(a0)	# L :
+
+	br	stxncpy_aligned	# U :
+	nop
+	nop
+	nop
+
+
+
+/* The source and destination are not co-aligned.  Align the destination
+   and cope.  We have to be very careful about not reading too much and
+   causing a SEGV.  */
+
+	.align 4
+$u_head:
+	/* We know just enough now to be able to assemble the first
+	   full source word.  We can still find a zero at the end of it
+	   that prevents us from outputting the whole thing.
+
+	   On entry to this basic block:
+	   t0 == the first dest word, unmasked
+	   t1 == the shifted low bits of the first source word
+	   t6 == bytemask that is -1 in dest word bytes */
+
+	ldq_u	t2, 8(a1)	# L : Latency=3 load second src word
+	addq	a1, 8, a1	# E :
+	mskql	t0, a0, t0	# U : mask trailing garbage in dst
+	extqh	t2, a1, t4	# U : (3 cycle stall on t2)
+
+	or	t1, t4, t1	# E : first aligned src word complete (stall)
+	mskqh	t1, a0, t1	# U : mask leading garbage in src (stall)
+	or	t0, t1, t0	# E : first output word complete (stall)
+	or	t0, t6, t6	# E : mask original data for zero test (stall)
+
+	cmpbge	zero, t6, t7	# E :
+	beq	a2, $u_eocfin	# U :
+	lda	t6, -1		# E :
+	nop
+
+	bne	t7, $u_final	# U :
+	mskql	t6, a1, t6	# U : mask out bits already seen
+	stq_u	t0, 0(a0)	# L : store first output word
+	or      t6, t2, t2	# E :
+
+	cmpbge	zero, t2, t7	# E : find nulls in second partial
+	addq	a0, 8, a0	# E :
+	subq	a2, 1, a2	# E :
+	bne	t7, $u_late_head_exit	# U :
+
+	/* Finally, we've got all the stupid leading edge cases taken care
+	   of and we can set up to enter the main loop.  */
+	extql	t2, a1, t1	# U : position hi-bits of lo word
+	beq	a2, $u_eoc	# U :
+	ldq_u	t2, 8(a1)	# L : read next high-order source word
+	addq	a1, 8, a1	# E :
+
+	extqh	t2, a1, t0	# U : position lo-bits of hi word (stall)
+	cmpbge	zero, t2, t7	# E :
+	nop
+	bne	t7, $u_eos	# U :
+
+	/* Unaligned copy main loop.  In order to avoid reading too much,
+	   the loop is structured to detect zeros in aligned source words.
+	   This has, unfortunately, effectively pulled half of a loop
+	   iteration out into the head and half into the tail, but it does
+	   prevent nastiness from accumulating in the very thing we want
+	   to run as fast as possible.
+
+	   On entry to this basic block:
+	   t0 == the shifted low-order bits from the current source word
+	   t1 == the shifted high-order bits from the previous source word
+	   t2 == the unshifted current source word
+
+	   We further know that t2 does not contain a null terminator.  */
+
+	.align 4
+$u_loop:
+	or	t0, t1, t0	# E : current dst word now complete
+	subq	a2, 1, a2	# E : decrement word count
+	extql	t2, a1, t1	# U : extract high bits for next time
+	addq	a0, 8, a0	# E :
+
+	stq_u	t0, -8(a0)	# L : save the current word
+	beq	a2, $u_eoc	# U :
+	ldq_u	t2, 8(a1)	# L : Latency=3 load high word for next time
+	addq	a1, 8, a1	# E :
+
+	extqh	t2, a1, t0	# U : extract low bits (2 cycle stall)
+	cmpbge	zero, t2, t7	# E : test new word for eos
+	nop
+	beq	t7, $u_loop	# U :
+
+	/* We've found a zero somewhere in the source word we just read.
+	   If it resides in the lower half, we have one (probably partial)
+	   word to write out, and if it resides in the upper half, we
+	   have one full and one partial word left to write out.
+
+	   On entry to this basic block:
+	   t0 == the shifted low-order bits from the current source word
+	   t1 == the shifted high-order bits from the previous source word
+	   t2 == the unshifted current source word.  */
+$u_eos:
+	or	t0, t1, t0	# E : first (partial) source word complete
+	nop
+	cmpbge	zero, t0, t7	# E : is the null in this first bit? (stall)
+	bne	t7, $u_final	# U : (stall)
+
+	stq_u	t0, 0(a0)	# L : the null was in the high-order bits
+	addq	a0, 8, a0	# E :
+	subq	a2, 1, a2	# E :
+	nop
+
+$u_late_head_exit:
+	extql	t2, a1, t0	# U :
+	cmpbge	zero, t0, t7	# E :
+	or	t7, t10, t6	# E : (stall)
+	cmoveq	a2, t6, t7	# E : Latency=2, extra map slot (stall)
+
+	/* Take care of a final (probably partial) result word.
+	   On entry to this basic block:
+	   t0 == assembled source word
+	   t7 == cmpbge mask that found the null.  */
+$u_final:
+	negq	t7, t6		# E : isolate low bit set
+	and	t6, t7, t8	# E : (stall)
+	and	t8, 0x80, t6	# E : avoid dest word load if we can (stall)
+	bne	t6, 1f		# U : (stall)
+
+	ldq_u	t1, 0(a0)	# L :
+	subq	t8, 1, t6	# E :
+	or	t6, t8, t7	# E : (stall)
+	zapnot	t0, t7, t0	# U : kill source bytes > null
+
+	zap	t1, t7, t1	# U : kill dest bytes <= null
+	or	t0, t1, t0	# E : (stall)
+	nop
+	nop
+
+1:	stq_u	t0, 0(a0)	# L :
+	ret	(t9)		# L0 : Latency=3
+
+        /* Got to end-of-count before end of string.
+           On entry to this basic block:
+           t1 == the shifted high-order bits from the previous source word  */
+$u_eoc:
+	and	a1, 7, t6	# E :
+	sll	t10, t6, t6	# U : (stall)
+	and	t6, 0xff, t6	# E : (stall)
+	bne	t6, 1f		# U : (stall)
+
+	ldq_u	t2, 8(a1)	# L : load final src word
+	nop
+	extqh	t2, a1, t0	# U : extract low bits for last word (stall)
+	or	t1, t0, t1	# E : (stall)
+
+1:	cmpbge	zero, t1, t7	# E :
+	mov	t1, t0
+
+$u_eocfin:			# end-of-count, final word
+	or	t10, t7, t7	# E :
+	br	$u_final	# L0 : Latency=3
+
+	/* Unaligned copy entry point.  */
+	.align 4
+$unaligned:
+
+	ldq_u	t1, 0(a1)	# L : load first source word
+	and	a0, 7, t4	# E : find dest misalignment
+	and	a1, 7, t5	# E : find src misalignment
+	/* Conditionally load the first destination word and a bytemask
+	   with 0xff indicating that the destination byte is sacrosanct.  */
+	mov	zero, t0	# E :
+
+	mov	zero, t6	# E :
+	beq	t4, 1f		# U :
+	ldq_u	t0, 0(a0)	# L :
+	lda	t6, -1		# E :
+
+	mskql	t6, a0, t6	# U :
+	nop
+	nop
+1:	subq	a1, t4, a1	# E : sub dest misalignment from src addr
+
+	/* If source misalignment is larger than dest misalignment, we need
+	   extra startup checks to avoid SEGV.  */
+
+	cmplt	t4, t5, t8	# E :
+	extql	t1, a1, t1	# U : shift src into place
+	lda	t2, -1		# E : for creating masks later
+	beq	t8, $u_head	# U : (stall)
+
+	mskqh	t2, t5, t2	# U : begin src byte validity mask
+	cmpbge	zero, t1, t7	# E : is there a zero?
+	extql	t2, a1, t2	# U :
+	or	t7, t10, t5	# E : test for end-of-count too
+
+	cmpbge	zero, t2, t3	# E :
+	cmoveq	a2, t5, t7	# E : Latency=2, extra map slot
+	nop			# E : keep with cmoveq
+	andnot	t7, t3, t7	# E : (stall)
+
+	beq	t7, $u_head	# U :
+	/* At this point we've found a zero in the first partial word of
+	   the source.  We need to isolate the valid source data and mask
+	   it into the original destination data.  (Incidentally, we know
+	   that we'll need at least one byte of that original dest word.) */
+	ldq_u	t0, 0(a0)	# L :
+	negq	t7, t6		# E : build bitmask of bytes <= zero
+	mskqh	t1, t4, t1	# U :
+
+	and	t6, t7, t8	# E :
+	subq	t8, 1, t6	# E : (stall)
+	or	t6, t8, t7	# E : (stall)
+	zapnot	t2, t7, t2	# U : prepare source word; mirror changes (stall)
+
+	zapnot	t1, t7, t1	# U : to source validity mask
+	andnot	t0, t2, t0	# E : zero place for source to reside
+	or	t0, t1, t0	# E : and put it there (stall both t0, t1)
+	stq_u	t0, 0(a0)	# L : (stall)
+
+	ret	(t9)		# L0 : Latency=3
+
+	cfi_endproc