Lines Matching +full:non +full:- +full:zero

6  * and re-licensed under GPLv2 for the Linux kernel. The original code can
9  * http://bazaar.launchpad.net/~linaro-toolchain-dev/cortex-strings/trunk/
32  *	x0 - const string 1 pointer
33  *    x1 - const string 2 pointer
35  * x0 - an integer less than, equal to, or greater than zero
72 	* NUL detection works on the principle that (X - 1) & (~X) & 0x80
73 	* (=> (X - 1) & ~(X | 0x7f)) is non-zero iff a byte is zero, and
82 	eor	diff, data1, data2	/* Non-zero if differences found.  */
83 	bic	has_nul, tmp1, tmp2	/* Non-zero if NUL terminator.  */
96 	lsl	tmp1, tmp1, #3		/* Bytes beyond alignment -> bits.  */
98 	neg	tmp1, tmp1		/* Bits to alignment -64.  */
101 	/* Big-endian.  Early bytes are at MSB.  */
103 	/* Little-endian.  Early bytes are at LSB.  */
144 	/*load 8 bytes from aligned str1 and non-aligned str2..*/
151 	eor	diff, data1, data2 /* Non-zero if differences found.  */
173 	eor	diff, data1, data2  /* Non-zero if differences found.  */
183 	eor	diff, data1, data2  /* Non-zero if differences found.  */
189 	* reversed the byte-order as big-endian,then CLZ can find the most
190 	* significant zero bits.
197 	* For big-endian we cannot use the trick with the syndrome value
198 	* as carry-propagation can corrupt the upper bits if the trailing
210 	/*Re-compute the NUL-byte detection, using a byte-reversed value. */
220 	* The MS-non-zero bit of the syndrome marks either the first bit
221 	* that is different, or the top bit of the first zero byte.
228 	* But we need to zero-extend (char is unsigned) the value and then
229 	* perform a signed 32-bit subtraction.