Searched refs:four (Results 1 – 23 of 23) sorted by relevance
45 2: EX( stq_u $31, 0($16) ) # e0 : zero four words
34 # see if the region parameters are four-byte aligned
35 # see if the three parameters are all four-byte aligned
41 # see if the three parameters are all four-byte aligned
29 # in four SSE registers. It performs matrix operation on four words in150 # This function encrypts four consecutive ChaCha20 blocks by loading the151 # the state matrix in SSE registers four times. As we need some scratch152 # registers, we save the first four registers on the stack. The
91 # This four-block variant uses loop unrolled block processing. It
33 # scratch registers, we save the first four registers on the stack. The
155 ## compute s0 four at a time and s1 two at a time
148 ## compute s0 four at a time and s1 two at a time
145 cmovne four(%rip), idx320 four: label
64 @ four bits, since this is the amount of unwinding in the main151 @ four bits, since this is the amount of unwinding in the main
75 Support boards with upto four XLPs connected over ICI.
46 | ;four word frame
73 keycode 59 = four dollar
89 * handling the four disks.
726 * The ROM checks the first four physical blocks
670 * The ROM checks the first four physical blocks
129 are nested four deep.
242 Select one of the four serial ports as a rescue port. The default
449 ! We could do this with the four scratch registers, but if src
291 # In the general case, four quotient words would be created by
516 product. The product is broken into four 64-bit pieces which are stored at
13 @ This code is ~4.5 (four and a half) times faster than code generated