Lines Matching +full:4 +full:b

30 	mov		dg2v.16b, dg0v.16b
32 	add		t1.4s, v\s0\().4s, \rc\().4s
33 	sha256h		dg0q, dg1q, t0.4s
34 	sha256h2	dg1q, dg2q, t0.4s
37 	add		t0.4s, v\s0\().4s, \rc\().4s
39 	sha256h		dg0q, dg1q, t1.4s
40 	sha256h2	dg1q, dg2q, t1.4s
45 	sha256su0	v\s0\().4s, v\s1\().4s
47 	sha256su1	v\s0\().4s, v\s2\().4s, v\s3\().4s
54 	.align		4
75 	ld1		{ v0.4s- v3.4s}, [\tmp], #64
76 	ld1		{ v4.4s- v7.4s}, [\tmp], #64
77 	ld1		{ v8.4s-v11.4s}, [\tmp], #64
78 	ld1		{v12.4s-v15.4s}, [\tmp]
91 	ld1		{dgav.4s, dgbv.4s}, [x0]
94 0:	ld1		{v16.4s-v19.4s}, [x1], #64
97 CPU_LE(	rev32		v16.16b, v16.16b	)
98 CPU_LE(	rev32		v17.16b, v17.16b	)
99 CPU_LE(	rev32		v18.16b, v18.16b	)
100 CPU_LE(	rev32		v19.16b, v19.16b	)
102 	add		t0.4s, v16.4s, v0.4s
103 	mov		dg0v.16b, dgav.16b
104 	mov		dg1v.16b, dgbv.16b
127 	add		dgav.4s, dgav.4s, dg0v.4s
128 	add		dgbv.4s, dgbv.4s, dg1v.4s
134 	cbnz		x2, 0b
137 1:	st1		{dgav.4s, dgbv.4s}, [x0]
193 	// Do 4 rounds of SHA-256 for each of two messages (interleaved).  m0_a
194 	// and m0_b contain the current 4 message schedule words for the first
198 	// this also computes 4 more message schedule words for each message.
199 	// m1_a-m3_a contain the next 3 groups of 4 message schedule words for
208 	add		t0_a\().4s, \m0_a\().4s, \k\().4s
209 	add		t0_b\().4s, \m0_b\().4s, \k\().4s
211 	sha256su0	\m0_a\().4s, \m1_a\().4s
212 	sha256su0	\m0_b\().4s, \m1_b\().4s
213 	sha256su1	\m0_a\().4s, \m2_a\().4s, \m3_a\().4s
214 	sha256su1	\m0_b\().4s, \m2_b\().4s, \m3_b\().4s
216 	mov		t1_a.16b, state0_a.16b
217 	mov		t1_b.16b, state0_b.16b
218 	sha256h		state0_a_q, state1_a_q, t0_a\().4s
219 	sha256h		state0_b_q, state1_b_q, t0_b\().4s
220 	sha256h2	state1_a_q, t1_a_q, t0_a\().4s
221 	sha256h2	state1_b_q, t1_b_q, t0_b\().4s
226 	do_4rounds_2x	\i + 4,  \k1,  v17, v18, v19, v16,  v21, v22, v23, v20
251 	ld1		{state0_a.4s-state1_a.4s}, [ctx]
266 	ld1		{v16.16b-v19.16b}, [x9]
267 	st1		{v16.16b-v19.16b}, [sp]
269 	ld1		{v16.16b-v19.16b}, [data1], #64
271 	st1		{v16.16b-v19.16b}, [x9]
272 	ld1		{v16.4s-v19.4s}, [sp]
274 	ld1		{v20.16b-v23.16b}, [data2], #64
275 	st1		{v20.16b-v23.16b}, [x9]
276 	ld1		{v20.4s-v23.4s}, [sp]
282 	mov		state0_b.16b, state0_a.16b
283 	mov		state1_b.16b, state1_a.16b
284 	b		.Lfinup2x_loop_have_data
288 	mov		state0_b.16b, state0_a.16b
289 	mov		state1_b.16b, state1_a.16b
292 	ld1		{v16.4s-v19.4s}, [data1], #64
293 	ld1		{v20.4s-v23.4s}, [data2], #64
296 CPU_LE(	rev32		v16.16b, v16.16b	)
297 CPU_LE(	rev32		v17.16b, v17.16b	)
298 CPU_LE(	rev32		v18.16b, v18.16b	)
299 CPU_LE(	rev32		v19.16b, v19.16b	)
300 CPU_LE(	rev32		v20.16b, v20.16b	)
301 CPU_LE(	rev32		v21.16b, v21.16b	)
302 CPU_LE(	rev32		v22.16b, v22.16b	)
303 CPU_LE(	rev32		v23.16b, v23.16b	)
307 	st1		{state0_a.4s-state1_b.4s}, [sp]
316 	ld1		{v16.4s-v19.4s}, [sp]
317 	add		state0_a.4s, state0_a.4s, v16.4s
318 	add		state1_a.4s, state1_a.4s, v17.4s
319 	add		state0_b.4s, state0_b.4s, v18.4s
320 	add		state1_b.4s, state1_b.4s, v19.4s
345 CPU_BE(	movi		v16.16b, #0		)
348 	movi		v17.16b, #0
353 	b.ge		1f		// will count spill into its own block?
358 	b		2f
362 	ld1		{v16.16b-v19.16b}, [data1]
363 	st1		{v16.16b-v19.16b}, [sp]
364 	ld1		{v16.4s-v19.4s}, [x9]
365 	ld1		{v20.16b-v23.16b}, [data2]
366 	st1		{v20.16b-v23.16b}, [sp]
367 	ld1		{v20.4s-v23.4s}, [x9]
368 	b		.Lfinup2x_loop_have_data
381 	b		1f
391 	mov		v20.16b, v16.16b
394 	mov		v23.16b, v19.16b
396 	b		.Lfinup2x_loop_have_bswapped_data
400 CPU_LE(	rev32		state0_a.16b, state0_a.16b	)
401 CPU_LE(	rev32		state1_a.16b, state1_a.16b	)
402 CPU_LE(	rev32		state0_b.16b, state0_b.16b	)
403 CPU_LE(	rev32		state1_b.16b, state1_b.16b	)
404 	st1		{state0_a.4s-state1_a.4s}, [out1]
405 	st1		{state0_b.4s-state1_b.4s}, [out2]