Convert to chacha bencher

10 files changed, 2197 insertions, 3925 deletions

diff --git a/Makefile b/Makefile
index 8287c4a..b3dcaf7 100644
--- a/Makefile
+++ b/Makefile
@@ -1,5 +1,5 @@
 ifneq ($(KERNELRELEASE),)
-kbench9000-y := main.o curve25519-neon.o curve25519-donna32.o curve25519-fiat32.o
+kbench9000-y := main.o generic.o openssl.o ard.o ard-glue.o
 obj-m := kbench9000.o
 ccflags-y += -O3
 ccflags-y += -D'pr_fmt(fmt)=KBUILD_MODNAME ": " fmt'
diff --git a/ard-glue.c b/ard-glue.c
new file mode 100644
index 0000000..9e7d585
--- /dev/null
+++ b/ard-glue.c
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: MIT
+ *
+ * Copyright (C) 2015-2018 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ */
+
+#include <linux/kernel.h>
+#include <linux/string.h>
+
+asmlinkage void chacha20_ard_block_xor_neon(u32 *state, u8 *dst, const u8 *src);
+asmlinkage void chacha20_ard_4block_xor_neon(u32 *state, u8 *dst, const u8 *src);
+
+enum {
+	CHACHA20_IV_SIZE = 16,
+	CHACHA20_KEY_SIZE = 32,
+	CHACHA20_BLOCK_SIZE = 64,
+	CHACHA20_BLOCK_WORDS = CHACHA20_BLOCK_SIZE / sizeof(u32)
+};
+
+#define EXPAND_32_BYTE_K 0x61707865U, 0x3320646eU, 0x79622d32U, 0x6b206574U
+
+void chacha20_ard_neon(u8 *dst, const u8 *src, u32 len, const u32 key[8], const u32 counter[4])
+{
+	u32 state[] = {
+		EXPAND_32_BYTE_K,
+		key[0], key[1], key[2], key[3],
+		key[4], key[5], key[6], key[7],
+		counter[0], counter[1], counter[2], counter[3]
+	};
+	u8 buf[CHACHA20_BLOCK_SIZE];
+	unsigned int bytes = len;
+
+	while (bytes >= CHACHA20_BLOCK_SIZE * 4) {
+		chacha20_ard_4block_xor_neon(state, dst, src);
+		bytes -= CHACHA20_BLOCK_SIZE * 4;
+		src += CHACHA20_BLOCK_SIZE * 4;
+		dst += CHACHA20_BLOCK_SIZE * 4;
+		state[12] += 4;
+	}
+	while (bytes >= CHACHA20_BLOCK_SIZE) {
+		chacha20_ard_block_xor_neon(state, dst, src);
+		bytes -= CHACHA20_BLOCK_SIZE;
+		src += CHACHA20_BLOCK_SIZE;
+		dst += CHACHA20_BLOCK_SIZE;
+		state[12]++;
+	}
+	if (bytes) {
+		memcpy(buf, src, bytes);
+		chacha20_ard_block_xor_neon(state, buf, buf);
+		memcpy(dst, buf, bytes);
+	}
+}
diff --git a/ard.S b/ard.S
new file mode 100644
index 0000000..c5168a4
--- /dev/null
+++ b/ard.S
@@ -0,0 +1,521 @@
+/*
+ * ChaCha20 256-bit cipher algorithm, RFC7539, ARM NEON functions
+ *
+ * Copyright (C) 2016 Linaro, Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Based on:
+ * ChaCha20 256-bit cipher algorithm, RFC7539, x64 SSE3 functions
+ *
+ * Copyright (C) 2015 Martin Willi
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/linkage.h>
+
+	.text
+	.fpu		neon
+	.align		5
+
+ENTRY(chacha20_ard_block_xor_neon)
+	// r0: Input state matrix, s
+	// r1: 1 data block output, o
+	// r2: 1 data block input, i
+
+	//
+	// This function encrypts one ChaCha20 block by loading the state matrix
+	// in four NEON registers. It performs matrix operation on four words in
+	// parallel, but requireds shuffling to rearrange the words after each
+	// round.
+	//
+
+	// x0..3 = s0..3
+	add		ip, r0, #0x20
+	vld1.32		{q0-q1}, [r0]
+	vld1.32		{q2-q3}, [ip]
+
+	vmov		q8, q0
+	vmov		q9, q1
+	vmov		q10, q2
+	vmov		q11, q3
+
+	mov		r3, #10
+
+.Ldoubleround:
+	// x0 += x1, x3 = rotl32(x3 ^ x0, 16)
+	vadd.i32	q0, q0, q1
+	veor		q3, q3, q0
+	vrev32.16	q3, q3
+
+	// x2 += x3, x1 = rotl32(x1 ^ x2, 12)
+	vadd.i32	q2, q2, q3
+	veor		q4, q1, q2
+	vshl.u32	q1, q4, #12
+	vsri.u32	q1, q4, #20
+
+	// x0 += x1, x3 = rotl32(x3 ^ x0, 8)
+	vadd.i32	q0, q0, q1
+	veor		q4, q3, q0
+	vshl.u32	q3, q4, #8
+	vsri.u32	q3, q4, #24
+
+	// x2 += x3, x1 = rotl32(x1 ^ x2, 7)
+	vadd.i32	q2, q2, q3
+	veor		q4, q1, q2
+	vshl.u32	q1, q4, #7
+	vsri.u32	q1, q4, #25
+
+	// x1 = shuffle32(x1, MASK(0, 3, 2, 1))
+	vext.8		q1, q1, q1, #4
+	// x2 = shuffle32(x2, MASK(1, 0, 3, 2))
+	vext.8		q2, q2, q2, #8
+	// x3 = shuffle32(x3, MASK(2, 1, 0, 3))
+	vext.8		q3, q3, q3, #12
+
+	// x0 += x1, x3 = rotl32(x3 ^ x0, 16)
+	vadd.i32	q0, q0, q1
+	veor		q3, q3, q0
+	vrev32.16	q3, q3
+
+	// x2 += x3, x1 = rotl32(x1 ^ x2, 12)
+	vadd.i32	q2, q2, q3
+	veor		q4, q1, q2
+	vshl.u32	q1, q4, #12
+	vsri.u32	q1, q4, #20
+
+	// x0 += x1, x3 = rotl32(x3 ^ x0, 8)
+	vadd.i32	q0, q0, q1
+	veor		q4, q3, q0
+	vshl.u32	q3, q4, #8
+	vsri.u32	q3, q4, #24
+
+	// x2 += x3, x1 = rotl32(x1 ^ x2, 7)
+	vadd.i32	q2, q2, q3
+	veor		q4, q1, q2
+	vshl.u32	q1, q4, #7
+	vsri.u32	q1, q4, #25
+
+	// x1 = shuffle32(x1, MASK(2, 1, 0, 3))
+	vext.8		q1, q1, q1, #12
+	// x2 = shuffle32(x2, MASK(1, 0, 3, 2))
+	vext.8		q2, q2, q2, #8
+	// x3 = shuffle32(x3, MASK(0, 3, 2, 1))
+	vext.8		q3, q3, q3, #4
+
+	subs		r3, r3, #1
+	bne		.Ldoubleround
+
+	add		ip, r2, #0x20
+	vld1.8		{q4-q5}, [r2]
+	vld1.8		{q6-q7}, [ip]
+
+	// o0 = i0 ^ (x0 + s0)
+	vadd.i32	q0, q0, q8
+	veor		q0, q0, q4
+
+	// o1 = i1 ^ (x1 + s1)
+	vadd.i32	q1, q1, q9
+	veor		q1, q1, q5
+
+	// o2 = i2 ^ (x2 + s2)
+	vadd.i32	q2, q2, q10
+	veor		q2, q2, q6
+
+	// o3 = i3 ^ (x3 + s3)
+	vadd.i32	q3, q3, q11
+	veor		q3, q3, q7
+
+	add		ip, r1, #0x20
+	vst1.8		{q0-q1}, [r1]
+	vst1.8		{q2-q3}, [ip]
+
+	bx		lr
+ENDPROC(chacha20_ard_block_xor_neon)
+
+	.align		5
+ENTRY(chacha20_ard_4block_xor_neon)
+	push		{r4-r6, lr}
+	mov		ip, sp			// preserve the stack pointer
+	sub		r3, sp, #0x20		// allocate a 32 byte buffer
+	bic		r3, r3, #0x1f		// aligned to 32 bytes
+	mov		sp, r3
+
+	// r0: Input state matrix, s
+	// r1: 4 data blocks output, o
+	// r2: 4 data blocks input, i
+
+	//
+	// This function encrypts four consecutive ChaCha20 blocks by loading
+	// the state matrix in NEON registers four times. The algorithm performs
+	// each operation on the corresponding word of each state matrix, hence
+	// requires no word shuffling. For final XORing step we transpose the
+	// matrix by interleaving 32- and then 64-bit words, which allows us to
+	// do XOR in NEON registers.
+	//
+
+	// x0..15[0-3] = s0..3[0..3]
+	add		r3, r0, #0x20
+	vld1.32		{q0-q1}, [r0]
+	vld1.32		{q2-q3}, [r3]
+
+	adr		r3, CTRINC
+	vdup.32		q15, d7[1]
+	vdup.32		q14, d7[0]
+	vld1.32		{q11}, [r3, :128]
+	vdup.32		q13, d6[1]
+	vdup.32		q12, d6[0]
+	vadd.i32	q12, q12, q11		// x12 += counter values 0-3
+	vdup.32		q11, d5[1]
+	vdup.32		q10, d5[0]
+	vdup.32		q9, d4[1]
+	vdup.32		q8, d4[0]
+	vdup.32		q7, d3[1]
+	vdup.32		q6, d3[0]
+	vdup.32		q5, d2[1]
+	vdup.32		q4, d2[0]
+	vdup.32		q3, d1[1]
+	vdup.32		q2, d1[0]
+	vdup.32		q1, d0[1]
+	vdup.32		q0, d0[0]
+
+	mov		r3, #10
+
+.Ldoubleround4:
+	// x0 += x4, x12 = rotl32(x12 ^ x0, 16)
+	// x1 += x5, x13 = rotl32(x13 ^ x1, 16)
+	// x2 += x6, x14 = rotl32(x14 ^ x2, 16)
+	// x3 += x7, x15 = rotl32(x15 ^ x3, 16)
+	vadd.i32	q0, q0, q4
+	vadd.i32	q1, q1, q5
+	vadd.i32	q2, q2, q6
+	vadd.i32	q3, q3, q7
+
+	veor		q12, q12, q0
+	veor		q13, q13, q1
+	veor		q14, q14, q2
+	veor		q15, q15, q3
+
+	vrev32.16	q12, q12
+	vrev32.16	q13, q13
+	vrev32.16	q14, q14
+	vrev32.16	q15, q15
+
+	// x8 += x12, x4 = rotl32(x4 ^ x8, 12)
+	// x9 += x13, x5 = rotl32(x5 ^ x9, 12)
+	// x10 += x14, x6 = rotl32(x6 ^ x10, 12)
+	// x11 += x15, x7 = rotl32(x7 ^ x11, 12)
+	vadd.i32	q8, q8, q12
+	vadd.i32	q9, q9, q13
+	vadd.i32	q10, q10, q14
+	vadd.i32	q11, q11, q15
+
+	vst1.32		{q8-q9}, [sp, :256]
+
+	veor		q8, q4, q8
+	veor		q9, q5, q9
+	vshl.u32	q4, q8, #12
+	vshl.u32	q5, q9, #12
+	vsri.u32	q4, q8, #20
+	vsri.u32	q5, q9, #20
+
+	veor		q8, q6, q10
+	veor		q9, q7, q11
+	vshl.u32	q6, q8, #12
+	vshl.u32	q7, q9, #12
+	vsri.u32	q6, q8, #20
+	vsri.u32	q7, q9, #20
+
+	// x0 += x4, x12 = rotl32(x12 ^ x0, 8)
+	// x1 += x5, x13 = rotl32(x13 ^ x1, 8)
+	// x2 += x6, x14 = rotl32(x14 ^ x2, 8)
+	// x3 += x7, x15 = rotl32(x15 ^ x3, 8)
+	vadd.i32	q0, q0, q4
+	vadd.i32	q1, q1, q5
+	vadd.i32	q2, q2, q6
+	vadd.i32	q3, q3, q7
+
+	veor		q8, q12, q0
+	veor		q9, q13, q1
+	vshl.u32	q12, q8, #8
+	vshl.u32	q13, q9, #8
+	vsri.u32	q12, q8, #24
+	vsri.u32	q13, q9, #24
+
+	veor		q8, q14, q2
+	veor		q9, q15, q3
+	vshl.u32	q14, q8, #8
+	vshl.u32	q15, q9, #8
+	vsri.u32	q14, q8, #24
+	vsri.u32	q15, q9, #24
+
+	vld1.32		{q8-q9}, [sp, :256]
+
+	// x8 += x12, x4 = rotl32(x4 ^ x8, 7)
+	// x9 += x13, x5 = rotl32(x5 ^ x9, 7)
+	// x10 += x14, x6 = rotl32(x6 ^ x10, 7)
+	// x11 += x15, x7 = rotl32(x7 ^ x11, 7)
+	vadd.i32	q8, q8, q12
+	vadd.i32	q9, q9, q13
+	vadd.i32	q10, q10, q14
+	vadd.i32	q11, q11, q15
+
+	vst1.32		{q8-q9}, [sp, :256]
+
+	veor		q8, q4, q8
+	veor		q9, q5, q9
+	vshl.u32	q4, q8, #7
+	vshl.u32	q5, q9, #7
+	vsri.u32	q4, q8, #25
+	vsri.u32	q5, q9, #25
+
+	veor		q8, q6, q10
+	veor		q9, q7, q11
+	vshl.u32	q6, q8, #7
+	vshl.u32	q7, q9, #7
+	vsri.u32	q6, q8, #25
+	vsri.u32	q7, q9, #25
+
+	vld1.32		{q8-q9}, [sp, :256]
+
+	// x0 += x5, x15 = rotl32(x15 ^ x0, 16)
+	// x1 += x6, x12 = rotl32(x12 ^ x1, 16)
+	// x2 += x7, x13 = rotl32(x13 ^ x2, 16)
+	// x3 += x4, x14 = rotl32(x14 ^ x3, 16)
+	vadd.i32	q0, q0, q5
+	vadd.i32	q1, q1, q6
+	vadd.i32	q2, q2, q7
+	vadd.i32	q3, q3, q4
+
+	veor		q15, q15, q0
+	veor		q12, q12, q1
+	veor		q13, q13, q2
+	veor		q14, q14, q3
+
+	vrev32.16	q15, q15
+	vrev32.16	q12, q12
+	vrev32.16	q13, q13
+	vrev32.16	q14, q14
+
+	// x10 += x15, x5 = rotl32(x5 ^ x10, 12)
+	// x11 += x12, x6 = rotl32(x6 ^ x11, 12)
+	// x8 += x13, x7 = rotl32(x7 ^ x8, 12)
+	// x9 += x14, x4 = rotl32(x4 ^ x9, 12)
+	vadd.i32	q10, q10, q15
+	vadd.i32	q11, q11, q12
+	vadd.i32	q8, q8, q13
+	vadd.i32	q9, q9, q14
+
+	vst1.32		{q8-q9}, [sp, :256]
+
+	veor		q8, q7, q8
+	veor		q9, q4, q9
+	vshl.u32	q7, q8, #12
+	vshl.u32	q4, q9, #12
+	vsri.u32	q7, q8, #20
+	vsri.u32	q4, q9, #20
+
+	veor		q8, q5, q10
+	veor		q9, q6, q11
+	vshl.u32	q5, q8, #12
+	vshl.u32	q6, q9, #12
+	vsri.u32	q5, q8, #20
+	vsri.u32	q6, q9, #20
+
+	// x0 += x5, x15 = rotl32(x15 ^ x0, 8)
+	// x1 += x6, x12 = rotl32(x12 ^ x1, 8)
+	// x2 += x7, x13 = rotl32(x13 ^ x2, 8)
+	// x3 += x4, x14 = rotl32(x14 ^ x3, 8)
+	vadd.i32	q0, q0, q5
+	vadd.i32	q1, q1, q6
+	vadd.i32	q2, q2, q7
+	vadd.i32	q3, q3, q4
+
+	veor		q8, q15, q0
+	veor		q9, q12, q1
+	vshl.u32	q15, q8, #8
+	vshl.u32	q12, q9, #8
+	vsri.u32	q15, q8, #24
+	vsri.u32	q12, q9, #24
+
+	veor		q8, q13, q2
+	veor		q9, q14, q3
+	vshl.u32	q13, q8, #8
+	vshl.u32	q14, q9, #8
+	vsri.u32	q13, q8, #24
+	vsri.u32	q14, q9, #24
+
+	vld1.32		{q8-q9}, [sp, :256]
+
+	// x10 += x15, x5 = rotl32(x5 ^ x10, 7)
+	// x11 += x12, x6 = rotl32(x6 ^ x11, 7)
+	// x8 += x13, x7 = rotl32(x7 ^ x8, 7)
+	// x9 += x14, x4 = rotl32(x4 ^ x9, 7)
+	vadd.i32	q10, q10, q15
+	vadd.i32	q11, q11, q12
+	vadd.i32	q8, q8, q13
+	vadd.i32	q9, q9, q14
+
+	vst1.32		{q8-q9}, [sp, :256]
+
+	veor		q8, q7, q8
+	veor		q9, q4, q9
+	vshl.u32	q7, q8, #7
+	vshl.u32	q4, q9, #7
+	vsri.u32	q7, q8, #25
+	vsri.u32	q4, q9, #25
+
+	veor		q8, q5, q10
+	veor		q9, q6, q11
+	vshl.u32	q5, q8, #7
+	vshl.u32	q6, q9, #7
+	vsri.u32	q5, q8, #25
+	vsri.u32	q6, q9, #25
+
+	subs		r3, r3, #1
+	beq		0f
+
+	vld1.32		{q8-q9}, [sp, :256]
+	b		.Ldoubleround4
+
+	// x0[0-3] += s0[0]
+	// x1[0-3] += s0[1]
+	// x2[0-3] += s0[2]
+	// x3[0-3] += s0[3]
+0:	ldmia		r0!, {r3-r6}
+	vdup.32		q8, r3
+	vdup.32		q9, r4
+	vadd.i32	q0, q0, q8
+	vadd.i32	q1, q1, q9
+	vdup.32		q8, r5
+	vdup.32		q9, r6
+	vadd.i32	q2, q2, q8
+	vadd.i32	q3, q3, q9
+
+	// x4[0-3] += s1[0]
+	// x5[0-3] += s1[1]
+	// x6[0-3] += s1[2]
+	// x7[0-3] += s1[3]
+	ldmia		r0!, {r3-r6}
+	vdup.32		q8, r3
+	vdup.32		q9, r4
+	vadd.i32	q4, q4, q8
+	vadd.i32	q5, q5, q9
+	vdup.32		q8, r5
+	vdup.32		q9, r6
+	vadd.i32	q6, q6, q8
+	vadd.i32	q7, q7, q9
+
+	// interleave 32-bit words in state n, n+1
+	vzip.32		q0, q1
+	vzip.32		q2, q3
+	vzip.32		q4, q5
+	vzip.32		q6, q7
+
+	// interleave 64-bit words in state n, n+2
+	vswp		d1, d4
+	vswp		d3, d6
+	vswp		d9, d12
+	vswp		d11, d14
+
+	// xor with corresponding input, write to output
+	vld1.8		{q8-q9}, [r2]!
+	veor		q8, q8, q0
+	veor		q9, q9, q4
+	vst1.8		{q8-q9}, [r1]!
+
+	vld1.32		{q8-q9}, [sp, :256]
+
+	// x8[0-3] += s2[0]
+	// x9[0-3] += s2[1]
+	// x10[0-3] += s2[2]
+	// x11[0-3] += s2[3]
+	ldmia		r0!, {r3-r6}
+	vdup.32		q0, r3
+	vdup.32		q4, r4
+	vadd.i32	q8, q8, q0
+	vadd.i32	q9, q9, q4
+	vdup.32		q0, r5
+	vdup.32		q4, r6
+	vadd.i32	q10, q10, q0
+	vadd.i32	q11, q11, q4
+
+	// x12[0-3] += s3[0]
+	// x13[0-3] += s3[1]
+	// x14[0-3] += s3[2]
+	// x15[0-3] += s3[3]
+	ldmia		r0!, {r3-r6}
+	vdup.32		q0, r3
+	vdup.32		q4, r4
+	adr		r3, CTRINC
+	vadd.i32	q12, q12, q0
+	vld1.32		{q0}, [r3, :128]
+	vadd.i32	q13, q13, q4
+	vadd.i32	q12, q12, q0		// x12 += counter values 0-3
+
+	vdup.32		q0, r5
+	vdup.32		q4, r6
+	vadd.i32	q14, q14, q0
+	vadd.i32	q15, q15, q4
+
+	// interleave 32-bit words in state n, n+1
+	vzip.32		q8, q9
+	vzip.32		q10, q11
+	vzip.32		q12, q13
+	vzip.32		q14, q15
+
+	// interleave 64-bit words in state n, n+2
+	vswp		d17, d20
+	vswp		d19, d22
+	vswp		d25, d28
+	vswp		d27, d30
+
+	vmov		q4, q1
+
+	vld1.8		{q0-q1}, [r2]!
+	veor		q0, q0, q8
+	veor		q1, q1, q12
+	vst1.8		{q0-q1}, [r1]!
+
+	vld1.8		{q0-q1}, [r2]!
+	veor		q0, q0, q2
+	veor		q1, q1, q6
+	vst1.8		{q0-q1}, [r1]!
+
+	vld1.8		{q0-q1}, [r2]!
+	veor		q0, q0, q10
+	veor		q1, q1, q14
+	vst1.8		{q0-q1}, [r1]!
+
+	vld1.8		{q0-q1}, [r2]!
+	veor		q0, q0, q4
+	veor		q1, q1, q5
+	vst1.8		{q0-q1}, [r1]!
+
+	vld1.8		{q0-q1}, [r2]!
+	veor		q0, q0, q9
+	veor		q1, q1, q13
+	vst1.8		{q0-q1}, [r1]!
+
+	vld1.8		{q0-q1}, [r2]!
+	veor		q0, q0, q3
+	veor		q1, q1, q7
+	vst1.8		{q0-q1}, [r1]!
+
+	vld1.8		{q0-q1}, [r2]
+	veor		q0, q0, q11
+	veor		q1, q1, q15
+	vst1.8		{q0-q1}, [r1]
+
+	mov		sp, ip
+	pop		{r4-r6, pc}
+ENDPROC(chacha20_ard_4block_xor_neon)
+
+	.align		4
+CTRINC:	.word		0, 1, 2, 3
diff --git a/curve25519-donna32.c b/curve25519-donna32.c
deleted file mode 100644
index 4721864..0000000
--- a/curve25519-donna32.c
+++ /dev/null
@@ -1,861 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0
- *
- * Copyright (C) 2008 Google Inc. All Rights Reserved.
- * Copyright (C) 2015-2018 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
- *
- * Original author: Adam Langley <agl@imperialviolet.org>
- */
-
-#include <linux/kernel.h>
-#include <linux/string.h>
-
-enum { CURVE25519_POINT_SIZE = 32 };
-
-static __always_inline void normalize_secret(u8 secret[CURVE25519_POINT_SIZE])
-{
-	secret[0] &= 248;
-	secret[31] &= 127;
-	secret[31] |= 64;
-}
-
-typedef s64 limb;
-
-/* Field element representation:
- *
- * Field elements are written as an array of signed, 64-bit limbs, least
- * significant first. The value of the field element is:
- *   x[0] + 2^26·x[1] + x^51·x[2] + 2^102·x[3] + ...
- *
- * i.e. the limbs are 26, 25, 26, 25, ... bits wide.
- */
-
-/* Sum two numbers: output += in */
-static void fsum(limb *output, const limb *in)
-{
-	unsigned int i;
-
-	for (i = 0; i < 10; i += 2) {
-		output[0 + i] = output[0 + i] + in[0 + i];
-		output[1 + i] = output[1 + i] + in[1 + i];
-	}
-}
-
-/* Find the difference of two numbers: output = in - output
- * (note the order of the arguments!).
- */
-static void fdifference(limb *output, const limb *in)
-{
-	unsigned int i;
-
-	for (i = 0; i < 10; ++i)
-		output[i] = in[i] - output[i];
-}
-
-/* Multiply a number by a scalar: output = in * scalar */
-static void fscalar_product(limb *output, const limb *in, const limb scalar)
-{
-	unsigned int i;
-
-	for (i = 0; i < 10; ++i)
-		output[i] = in[i] * scalar;
-}
-
-/* Multiply two numbers: output = in2 * in
- *
- * output must be distinct to both inputs. The inputs are reduced coefficient
- * form, the output is not.
- *
- * output[x] <= 14 * the largest product of the input limbs.
- */
-static void fproduct(limb *output, const limb *in2, const limb *in)
-{
-	output[0] =       ((limb) ((s32) in2[0])) * ((s32) in[0]);
-	output[1] =       ((limb) ((s32) in2[0])) * ((s32) in[1]) +
-					    ((limb) ((s32) in2[1])) * ((s32) in[0]);
-	output[2] =  2 *  ((limb) ((s32) in2[1])) * ((s32) in[1]) +
-					    ((limb) ((s32) in2[0])) * ((s32) in[2]) +
-					    ((limb) ((s32) in2[2])) * ((s32) in[0]);
-	output[3] =       ((limb) ((s32) in2[1])) * ((s32) in[2]) +
-					    ((limb) ((s32) in2[2])) * ((s32) in[1]) +
-					    ((limb) ((s32) in2[0])) * ((s32) in[3]) +
-					    ((limb) ((s32) in2[3])) * ((s32) in[0]);
-	output[4] =       ((limb) ((s32) in2[2])) * ((s32) in[2]) +
-				       2 * (((limb) ((s32) in2[1])) * ((s32) in[3]) +
-					    ((limb) ((s32) in2[3])) * ((s32) in[1])) +
-					    ((limb) ((s32) in2[0])) * ((s32) in[4]) +
-					    ((limb) ((s32) in2[4])) * ((s32) in[0]);
-	output[5] =       ((limb) ((s32) in2[2])) * ((s32) in[3]) +
-					    ((limb) ((s32) in2[3])) * ((s32) in[2]) +
-					    ((limb) ((s32) in2[1])) * ((s32) in[4]) +
-					    ((limb) ((s32) in2[4])) * ((s32) in[1]) +
-					    ((limb) ((s32) in2[0])) * ((s32) in[5]) +
-					    ((limb) ((s32) in2[5])) * ((s32) in[0]);
-	output[6] =  2 * (((limb) ((s32) in2[3])) * ((s32) in[3]) +
-					    ((limb) ((s32) in2[1])) * ((s32) in[5]) +
-					    ((limb) ((s32) in2[5])) * ((s32) in[1])) +
-					    ((limb) ((s32) in2[2])) * ((s32) in[4]) +
-					    ((limb) ((s32) in2[4])) * ((s32) in[2]) +
-					    ((limb) ((s32) in2[0])) * ((s32) in[6]) +
-					    ((limb) ((s32) in2[6])) * ((s32) in[0]);
-	output[7] =       ((limb) ((s32) in2[3])) * ((s32) in[4]) +
-					    ((limb) ((s32) in2[4])) * ((s32) in[3]) +
-					    ((limb) ((s32) in2[2])) * ((s32) in[5]) +
-					    ((limb) ((s32) in2[5])) * ((s32) in[2]) +
-					    ((limb) ((s32) in2[1])) * ((s32) in[6]) +
-					    ((limb) ((s32) in2[6])) * ((s32) in[1]) +
-					    ((limb) ((s32) in2[0])) * ((s32) in[7]) +
-					    ((limb) ((s32) in2[7])) * ((s32) in[0]);
-	output[8] =       ((limb) ((s32) in2[4])) * ((s32) in[4]) +
-				       2 * (((limb) ((s32) in2[3])) * ((s32) in[5]) +
-					    ((limb) ((s32) in2[5])) * ((s32) in[3]) +
-					    ((limb) ((s32) in2[1])) * ((s32) in[7]) +
-					    ((limb) ((s32) in2[7])) * ((s32) in[1])) +
-					    ((limb) ((s32) in2[2])) * ((s32) in[6]) +
-					    ((limb) ((s32) in2[6])) * ((s32) in[2]) +
-					    ((limb) ((s32) in2[0])) * ((s32) in[8]) +
-					    ((limb) ((s32) in2[8])) * ((s32) in[0]);
-	output[9] =       ((limb) ((s32) in2[4])) * ((s32) in[5]) +
-					    ((limb) ((s32) in2[5])) * ((s32) in[4]) +
-					    ((limb) ((s32) in2[3])) * ((s32) in[6]) +
-					    ((limb) ((s32) in2[6])) * ((s32) in[3]) +
-					    ((limb) ((s32) in2[2])) * ((s32) in[7]) +
-					    ((limb) ((s32) in2[7])) * ((s32) in[2]) +
-					    ((limb) ((s32) in2[1])) * ((s32) in[8]) +
-					    ((limb) ((s32) in2[8])) * ((s32) in[1]) +
-					    ((limb) ((s32) in2[0])) * ((s32) in[9]) +
-					    ((limb) ((s32) in2[9])) * ((s32) in[0]);
-	output[10] = 2 * (((limb) ((s32) in2[5])) * ((s32) in[5]) +
-					    ((limb) ((s32) in2[3])) * ((s32) in[7]) +
-					    ((limb) ((s32) in2[7])) * ((s32) in[3]) +
-					    ((limb) ((s32) in2[1])) * ((s32) in[9]) +
-					    ((limb) ((s32) in2[9])) * ((s32) in[1])) +
-					    ((limb) ((s32) in2[4])) * ((s32) in[6]) +
-					    ((limb) ((s32) in2[6])) * ((s32) in[4]) +
-					    ((limb) ((s32) in2[2])) * ((s32) in[8]) +
-					    ((limb) ((s32) in2[8])) * ((s32) in[2]);
-	output[11] =      ((limb) ((s32) in2[5])) * ((s32) in[6]) +
-					    ((limb) ((s32) in2[6])) * ((s32) in[5]) +
-					    ((limb) ((s32) in2[4])) * ((s32) in[7]) +
-					    ((limb) ((s32) in2[7])) * ((s32) in[4]) +
-					    ((limb) ((s32) in2[3])) * ((s32) in[8]) +
-					    ((limb) ((s32) in2[8])) * ((s32) in[3]) +
-					    ((limb) ((s32) in2[2])) * ((s32) in[9]) +
-					    ((limb) ((s32) in2[9])) * ((s32) in[2]);
-	output[12] =      ((limb) ((s32) in2[6])) * ((s32) in[6]) +
-				       2 * (((limb) ((s32) in2[5])) * ((s32) in[7]) +
-					    ((limb) ((s32) in2[7])) * ((s32) in[5]) +
-					    ((limb) ((s32) in2[3])) * ((s32) in[9]) +
-					    ((limb) ((s32) in2[9])) * ((s32) in[3])) +
-					    ((limb) ((s32) in2[4])) * ((s32) in[8]) +
-					    ((limb) ((s32) in2[8])) * ((s32) in[4]);
-	output[13] =      ((limb) ((s32) in2[6])) * ((s32) in[7]) +
-					    ((limb) ((s32) in2[7])) * ((s32) in[6]) +
-					    ((limb) ((s32) in2[5])) * ((s32) in[8]) +
-					    ((limb) ((s32) in2[8])) * ((s32) in[5]) +
-					    ((limb) ((s32) in2[4])) * ((s32) in[9]) +
-					    ((limb) ((s32) in2[9])) * ((s32) in[4]);
-	output[14] = 2 * (((limb) ((s32) in2[7])) * ((s32) in[7]) +
-					    ((limb) ((s32) in2[5])) * ((s32) in[9]) +
-					    ((limb) ((s32) in2[9])) * ((s32) in[5])) +
-					    ((limb) ((s32) in2[6])) * ((s32) in[8]) +
-					    ((limb) ((s32) in2[8])) * ((s32) in[6]);
-	output[15] =      ((limb) ((s32) in2[7])) * ((s32) in[8]) +
-					    ((limb) ((s32) in2[8])) * ((s32) in[7]) +
-					    ((limb) ((s32) in2[6])) * ((s32) in[9]) +
-					    ((limb) ((s32) in2[9])) * ((s32) in[6]);
-	output[16] =      ((limb) ((s32) in2[8])) * ((s32) in[8]) +
-				       2 * (((limb) ((s32) in2[7])) * ((s32) in[9]) +
-					    ((limb) ((s32) in2[9])) * ((s32) in[7]));
-	output[17] =      ((limb) ((s32) in2[8])) * ((s32) in[9]) +
-					    ((limb) ((s32) in2[9])) * ((s32) in[8]);
-	output[18] = 2 *  ((limb) ((s32) in2[9])) * ((s32) in[9]);
-}
-
-/* Reduce a long form to a short form by taking the input mod 2^255 - 19.
- *
- * On entry: |output[i]| < 14*2^54
- * On exit: |output[0..8]| < 280*2^54
- */
-static void freduce_degree(limb *output)
-{
-	/* Each of these shifts and adds ends up multiplying the value by 19.
-	 *
-	 * For output[0..8], the absolute entry value is < 14*2^54 and we add, at
-	 * most, 19*14*2^54 thus, on exit, |output[0..8]| < 280*2^54.
-	 */
-	output[8] += output[18] << 4;
-	output[8] += output[18] << 1;
-	output[8] += output[18];
-	output[7] += output[17] << 4;
-	output[7] += output[17] << 1;
-	output[7] += output[17];
-	output[6] += output[16] << 4;
-	output[6] += output[16] << 1;
-	output[6] += output[16];
-	output[5] += output[15] << 4;
-	output[5] += output[15] << 1;
-	output[5] += output[15];
-	output[4] += output[14] << 4;
-	output[4] += output[14] << 1;
-	output[4] += output[14];
-	output[3] += output[13] << 4;
-	output[3] += output[13] << 1;
-	output[3] += output[13];
-	output[2] += output[12] << 4;
-	output[2] += output[12] << 1;
-	output[2] += output[12];
-	output[1] += output[11] << 4;
-	output[1] += output[11] << 1;
-	output[1] += output[11];
-	output[0] += output[10] << 4;
-	output[0] += output[10] << 1;
-	output[0] += output[10];
-}
-
-/* return v / 2^26, using only shifts and adds.
- *
- * On entry: v can take any value.
- */
-static inline limb div_by_2_26(const limb v)
-{
-	/* High word of v; no shift needed. */
-	const u32 highword = (u32) (((u64) v) >> 32);
-	/* Set to all 1s if v was negative; else set to 0s. */
-	const s32 sign = ((s32) highword) >> 31;
-	/* Set to 0x3ffffff if v was negative; else set to 0. */
-	const s32 roundoff = ((u32) sign) >> 6;
-	/* Should return v / (1<<26) */
-	return (v + roundoff) >> 26;
-}
-
-/* return v / (2^25), using only shifts and adds.
- *
- * On entry: v can take any value.
- */
-static inline limb div_by_2_25(const limb v)
-{
-	/* High word of v; no shift needed*/
-	const u32 highword = (u32) (((u64) v) >> 32);
-	/* Set to all 1s if v was negative; else set to 0s. */
-	const s32 sign = ((s32) highword) >> 31;
-	/* Set to 0x1ffffff if v was negative; else set to 0. */
-	const s32 roundoff = ((u32) sign) >> 7;
-	/* Should return v / (1<<25) */
-	return (v + roundoff) >> 25;
-}
-
-/* Reduce all coefficients of the short form input so that |x| < 2^26.
- *
- * On entry: |output[i]| < 280*2^54
- */
-static void freduce_coefficients(limb *output)
-{
-	unsigned int i;
-
-	output[10] = 0;
-
-	for (i = 0; i < 10; i += 2) {
-		limb over = div_by_2_26(output[i]);
-		/* The entry condition (that |output[i]| < 280*2^54) means that over is, at
-		 * most, 280*2^28 in the first iteration of this loop. This is added to the
-		 * next limb and we can approximate the resulting bound of that limb by
-		 * 281*2^54.
-		 */
-		output[i] -= over << 26;
-		output[i+1] += over;
-
-		/* For the first iteration, |output[i+1]| < 281*2^54, thus |over| <
-		 * 281*2^29. When this is added to the next limb, the resulting bound can
-		 * be approximated as 281*2^54.
-		 *
-		 * For subsequent iterations of the loop, 281*2^54 remains a conservative
-		 * bound and no overflow occurs.
-		 */
-		over = div_by_2_25(output[i+1]);
-		output[i+1] -= over << 25;
-		output[i+2] += over;
-	}
-	/* Now |output[10]| < 281*2^29 and all other coefficients are reduced. */
-	output[0] += output[10] << 4;
-	output[0] += output[10] << 1;
-	output[0] += output[10];
-
-	output[10] = 0;
-
-	/* Now output[1..9] are reduced, and |output[0]| < 2^26 + 19*281*2^29
-	 * So |over| will be no more than 2^16.
-	 */
-	{
-		limb over = div_by_2_26(output[0]);
-
-		output[0] -= over << 26;
-		output[1] += over;
-	}
-
-	/* Now output[0,2..9] are reduced, and |output[1]| < 2^25 + 2^16 < 2^26. The
-	 * bound on |output[1]| is sufficient to meet our needs.
-	 */
-}
-
-/* A helpful wrapper around fproduct: output = in * in2.
- *
- * On entry: |in[i]| < 2^27 and |in2[i]| < 2^27.
- *
- * output must be distinct to both inputs. The output is reduced degree
- * (indeed, one need only provide storage for 10 limbs) and |output[i]| < 2^26.
- */
-static void fmul(limb *output, const limb *in, const limb *in2)
-{
-	limb t[19];
-
-	fproduct(t, in, in2);
-	/* |t[i]| < 14*2^54 */
-	freduce_degree(t);
-	freduce_coefficients(t);
-	/* |t[i]| < 2^26 */
-	memcpy(output, t, sizeof(limb) * 10);
-}
-
-/* Square a number: output = in**2
- *
- * output must be distinct from the input. The inputs are reduced coefficient
- * form, the output is not.
- *
- * output[x] <= 14 * the largest product of the input limbs.
- */
-static void fsquare_inner(limb *output, const limb *in)
-{
-	output[0] =       ((limb) ((s32) in[0])) * ((s32) in[0]);
-	output[1] =  2 *  ((limb) ((s32) in[0])) * ((s32) in[1]);
-	output[2] =  2 * (((limb) ((s32) in[1])) * ((s32) in[1]) +
-					    ((limb) ((s32) in[0])) * ((s32) in[2]));
-	output[3] =  2 * (((limb) ((s32) in[1])) * ((s32) in[2]) +
-					    ((limb) ((s32) in[0])) * ((s32) in[3]));
-	output[4] =       ((limb) ((s32) in[2])) * ((s32) in[2]) +
-				       4 *  ((limb) ((s32) in[1])) * ((s32) in[3]) +
-				       2 *  ((limb) ((s32) in[0])) * ((s32) in[4]);
-	output[5] =  2 * (((limb) ((s32) in[2])) * ((s32) in[3]) +
-					    ((limb) ((s32) in[1])) * ((s32) in[4]) +
-					    ((limb) ((s32) in[0])) * ((s32) in[5]));
-	output[6] =  2 * (((limb) ((s32) in[3])) * ((s32) in[3]) +
-					    ((limb) ((s32) in[2])) * ((s32) in[4]) +
-					    ((limb) ((s32) in[0])) * ((s32) in[6]) +
-				       2 *  ((limb) ((s32) in[1])) * ((s32) in[5]));
-	output[7] =  2 * (((limb) ((s32) in[3])) * ((s32) in[4]) +
-					    ((limb) ((s32) in[2])) * ((s32) in[5]) +
-					    ((limb) ((s32) in[1])) * ((s32) in[6]) +
-					    ((limb) ((s32) in[0])) * ((s32) in[7]));
-	output[8] =       ((limb) ((s32) in[4])) * ((s32) in[4]) +
-				       2 * (((limb) ((s32) in[2])) * ((s32) in[6]) +
-					    ((limb) ((s32) in[0])) * ((s32) in[8]) +
-				       2 * (((limb) ((s32) in[1])) * ((s32) in[7]) +
-					    ((limb) ((s32) in[3])) * ((s32) in[5])));
-	output[9] =  2 * (((limb) ((s32) in[4])) * ((s32) in[5]) +
-					    ((limb) ((s32) in[3])) * ((s32) in[6]) +
-					    ((limb) ((s32) in[2])) * ((s32) in[7]) +
-					    ((limb) ((s32) in[1])) * ((s32) in[8]) +
-					    ((limb) ((s32) in[0])) * ((s32) in[9]));
-	output[10] = 2 * (((limb) ((s32) in[5])) * ((s32) in[5]) +
-					    ((limb) ((s32) in[4])) * ((s32) in[6]) +
-					    ((limb) ((s32) in[2])) * ((s32) in[8]) +
-				       2 * (((limb) ((s32) in[3])) * ((s32) in[7]) +
-					    ((limb) ((s32) in[1])) * ((s32) in[9])));
-	output[11] = 2 * (((limb) ((s32) in[5])) * ((s32) in[6]) +
-					    ((limb) ((s32) in[4])) * ((s32) in[7]) +
-					    ((limb) ((s32) in[3])) * ((s32) in[8]) +
-					    ((limb) ((s32) in[2])) * ((s32) in[9]));
-	output[12] =      ((limb) ((s32) in[6])) * ((s32) in[6]) +
-				       2 * (((limb) ((s32) in[4])) * ((s32) in[8]) +
-				       2 * (((limb) ((s32) in[5])) * ((s32) in[7]) +
-					    ((limb) ((s32) in[3])) * ((s32) in[9])));
-	output[13] = 2 * (((limb) ((s32) in[6])) * ((s32) in[7]) +
-					    ((limb) ((s32) in[5])) * ((s32) in[8]) +
-					    ((limb) ((s32) in[4])) * ((s32) in[9]));
-	output[14] = 2 * (((limb) ((s32) in[7])) * ((s32) in[7]) +
-					    ((limb) ((s32) in[6])) * ((s32) in[8]) +
-				       2 *  ((limb) ((s32) in[5])) * ((s32) in[9]));
-	output[15] = 2 * (((limb) ((s32) in[7])) * ((s32) in[8]) +
-					    ((limb) ((s32) in[6])) * ((s32) in[9]));
-	output[16] =      ((limb) ((s32) in[8])) * ((s32) in[8]) +
-				       4 *  ((limb) ((s32) in[7])) * ((s32) in[9]);
-	output[17] = 2 *  ((limb) ((s32) in[8])) * ((s32) in[9]);
-	output[18] = 2 *  ((limb) ((s32) in[9])) * ((s32) in[9]);
-}
-
-/* fsquare sets output = in^2.
- *
- * On entry: The |in| argument is in reduced coefficients form and |in[i]| <
- * 2^27.
- *
- * On exit: The |output| argument is in reduced coefficients form (indeed, one
- * need only provide storage for 10 limbs) and |out[i]| < 2^26.
- */
-static void fsquare(limb *output, const limb *in)
-{
-	limb t[19];
-
-	fsquare_inner(t, in);
-	/* |t[i]| < 14*2^54 because the largest product of two limbs will be <
-	 * 2^(27+27) and fsquare_inner adds together, at most, 14 of those
-	 * products.
-	 */
-	freduce_degree(t);
-	freduce_coefficients(t);
-	/* |t[i]| < 2^26 */
-	memcpy(output, t, sizeof(limb) * 10);
-}
-
-/* Take a little-endian, 32-byte number and expand it into polynomial form */
-static inline void fexpand(limb *output, const u8 *input)
-{
-#define F(n, start, shift, mask) \
-	output[n] = ((((limb) input[start + 0]) | \
-		      ((limb) input[start + 1]) << 8 | \
-		      ((limb) input[start + 2]) << 16 | \
-		      ((limb) input[start + 3]) << 24) >> shift) & mask;
-	F(0, 0, 0, 0x3ffffff);
-	F(1, 3, 2, 0x1ffffff);
-	F(2, 6, 3, 0x3ffffff);
-	F(3, 9, 5, 0x1ffffff);
-	F(4, 12, 6, 0x3ffffff);
-	F(5, 16, 0, 0x1ffffff);
-	F(6, 19, 1, 0x3ffffff);
-	F(7, 22, 3, 0x1ffffff);
-	F(8, 25, 4, 0x3ffffff);
-	F(9, 28, 6, 0x1ffffff);
-#undef F
-}
-
-/* s32_eq returns 0xffffffff iff a == b and zero otherwise. */
-static s32 s32_eq(s32 a, s32 b)
-{
-	a = ~(a ^ b);
-	a &= a << 16;
-	a &= a << 8;
-	a &= a << 4;
-	a &= a << 2;
-	a &= a << 1;
-	return a >> 31;
-}
-
-/* s32_gte returns 0xffffffff if a >= b and zero otherwise, where a and b are
- * both non-negative.
- */
-static s32 s32_gte(s32 a, s32 b)
-{
-	a -= b;
-	/* a >= 0 iff a >= b. */
-	return ~(a >> 31);
-}
-
-/* Take a fully reduced polynomial form number and contract it into a
- * little-endian, 32-byte array.
- *
- * On entry: |input_limbs[i]| < 2^26
- */
-static void fcontract(u8 *output, limb *input_limbs)
-{
-	int i;
-	int j;
-	s32 input[10];
-	s32 mask;
-
-	/* |input_limbs[i]| < 2^26, so it's valid to convert to an s32. */
-	for (i = 0; i < 10; i++) {
-		input[i] = input_limbs[i];
-	}
-
-	for (j = 0; j < 2; ++j) {
-		for (i = 0; i < 9; ++i) {
-			if ((i & 1) == 1) {
-				/* This calculation is a time-invariant way to make input[i]
-				 * non-negative by borrowing from the next-larger limb.
-				 */
-				const s32 mask = input[i] >> 31;
-				const s32 carry = -((input[i] & mask) >> 25);
-
-				input[i] = input[i] + (carry << 25);
-				input[i+1] = input[i+1] - carry;
-			} else {
-				const s32 mask = input[i] >> 31;
-				const s32 carry = -((input[i] & mask) >> 26);
-
-				input[i] = input[i] + (carry << 26);
-				input[i+1] = input[i+1] - carry;
-			}
-		}
-
-		/* There's no greater limb for input[9] to borrow from, but we can multiply
-		 * by 19 and borrow from input[0], which is valid mod 2^255-19.
-		 */
-		{
-			const s32 mask = input[9] >> 31;
-			const s32 carry = -((input[9] & mask) >> 25);
-
-			input[9] = input[9] + (carry << 25);
-			input[0] = input[0] - (carry * 19);
-		}
-
-		/* After the first iteration, input[1..9] are non-negative and fit within
-		 * 25 or 26 bits, depending on position. However, input[0] may be
-		 * negative.
-		 */
-	}
-
-	/* The first borrow-propagation pass above ended with every limb
-	   except (possibly) input[0] non-negative.
-	   If input[0] was negative after the first pass, then it was because of a
-	   carry from input[9]. On entry, input[9] < 2^26 so the carry was, at most,
-	   one, since (2**26-1) >> 25 = 1. Thus input[0] >= -19.
-	   In the second pass, each limb is decreased by at most one. Thus the second
-	   borrow-propagation pass could only have wrapped around to decrease
-	   input[0] again if the first pass left input[0] negative *and* input[1]
-	   through input[9] were all zero.  In that case, input[1] is now 2^25 - 1,
-	   and this last borrow-propagation step will leave input[1] non-negative. */
-	{
-		const s32 mask = input[0] >> 31;
-		const s32 carry = -((input[0] & mask) >> 26);
-
-		input[0] = input[0] + (carry << 26);
-		input[1] = input[1] - carry;
-	}
-
-	/* All input[i] are now non-negative. However, there might be values between
-	 * 2^25 and 2^26 in a limb which is, nominally, 25 bits wide.
-	 */
-	for (j = 0; j < 2; j++) {
-		for (i = 0; i < 9; i++) {
-			if ((i & 1) == 1) {
-				const s32 carry = input[i] >> 25;
-
-				input[i] &= 0x1ffffff;
-				input[i+1] += carry;
-			} else {
-				const s32 carry = input[i] >> 26;
-
-				input[i] &= 0x3ffffff;
-				input[i+1] += carry;
-			}
-		}
-
-		{
-			const s32 carry = input[9] >> 25;
-
-			input[9] &= 0x1ffffff;
-			input[0] += 19*carry;
-		}
-	}
-
-	/* If the first carry-chain pass, just above, ended up with a carry from
-	 * input[9], and that caused input[0] to be out-of-bounds, then input[0] was
-	 * < 2^26 + 2*19, because the carry was, at most, two.
-	 *
-	 * If the second pass carried from input[9] again then input[0] is < 2*19 and
-	 * the input[9] -> input[0] carry didn't push input[0] out of bounds.
-	 */
-
-	/* It still remains the case that input might be between 2^255-19 and 2^255.
-	 * In this case, input[1..9] must take their maximum value and input[0] must
-	 * be >= (2^255-19) & 0x3ffffff, which is 0x3ffffed.
-	 */
-	mask = s32_gte(input[0], 0x3ffffed);
-	for (i = 1; i < 10; i++) {
-		if ((i & 1) == 1) {
-			mask &= s32_eq(input[i], 0x1ffffff);
-		} else {
-			mask &= s32_eq(input[i], 0x3ffffff);
-		}
-	}
-
-	/* mask is either 0xffffffff (if input >= 2^255-19) and zero otherwise. Thus
-	 * this conditionally subtracts 2^255-19.
-	 */
-	input[0] -= mask & 0x3ffffed;
-
-	for (i = 1; i < 10; i++) {
-		if ((i & 1) == 1) {
-			input[i] -= mask & 0x1ffffff;
-		} else {
-			input[i] -= mask & 0x3ffffff;
-		}
-	}
-
-	input[1] <<= 2;
-	input[2] <<= 3;
-	input[3] <<= 5;
-	input[4] <<= 6;
-	input[6] <<= 1;
-	input[7] <<= 3;
-	input[8] <<= 4;
-	input[9] <<= 6;
-#define F(i, s) \
-	output[s+0] |=  input[i] & 0xff; \
-	output[s+1]  = (input[i] >> 8) & 0xff; \
-	output[s+2]  = (input[i] >> 16) & 0xff; \
-	output[s+3]  = (input[i] >> 24) & 0xff;
-	output[0] = 0;
-	output[16] = 0;
-	F(0, 0);
-	F(1, 3);
-	F(2, 6);
-	F(3, 9);
-	F(4, 12);
-	F(5, 16);
-	F(6, 19);
-	F(7, 22);
-	F(8, 25);
-	F(9, 28);
-#undef F
-}
-
-/* Conditionally swap two reduced-form limb arrays if 'iswap' is 1, but leave
- * them unchanged if 'iswap' is 0.  Runs in data-invariant time to avoid
- * side-channel attacks.
- *
- * NOTE that this function requires that 'iswap' be 1 or 0; other values give
- * wrong results.  Also, the two limb arrays must be in reduced-coefficient,
- * reduced-degree form: the values in a[10..19] or b[10..19] aren't swapped,
- * and all all values in a[0..9],b[0..9] must have magnitude less than
- * INT32_MAX.
- */
-static void swap_conditional(limb a[19], limb b[19], limb iswap)
-{
-	unsigned int i;
-	const s32 swap = (s32) -iswap;
-
-	for (i = 0; i < 10; ++i) {
-		const s32 x = swap & (((s32)a[i]) ^ ((s32)b[i]));
-
-		a[i] = ((s32)a[i]) ^ x;
-		b[i] = ((s32)b[i]) ^ x;
-	}
-}
-
-static void crecip(limb *out, const limb *z)
-{
-	limb z2[10];
-	limb z9[10];
-	limb z11[10];
-	limb z2_5_0[10];
-	limb z2_10_0[10];
-	limb z2_20_0[10];
-	limb z2_50_0[10];
-	limb z2_100_0[10];
-	limb t0[10];
-	limb t1[10];
-	int i;
-
-	/* 2 */ fsquare(z2, z);
-	/* 4 */ fsquare(t1, z2);
-	/* 8 */ fsquare(t0, t1);
-	/* 9 */ fmul(z9, t0, z);
-	/* 11 */ fmul(z11, z9, z2);
-	/* 22 */ fsquare(t0, z11);
-	/* 2^5 - 2^0 = 31 */ fmul(z2_5_0, t0, z9);
-
-	/* 2^6 - 2^1 */ fsquare(t0, z2_5_0);
-	/* 2^7 - 2^2 */ fsquare(t1, t0);
-	/* 2^8 - 2^3 */ fsquare(t0, t1);
-	/* 2^9 - 2^4 */ fsquare(t1, t0);
-	/* 2^10 - 2^5 */ fsquare(t0, t1);
-	/* 2^10 - 2^0 */ fmul(z2_10_0, t0, z2_5_0);
-
-	/* 2^11 - 2^1 */ fsquare(t0, z2_10_0);
-	/* 2^12 - 2^2 */ fsquare(t1, t0);
-	/* 2^20 - 2^10 */ for (i = 2; i < 10; i += 2) { fsquare(t0, t1); fsquare(t1, t0); }
-	/* 2^20 - 2^0 */ fmul(z2_20_0, t1, z2_10_0);
-
-	/* 2^21 - 2^1 */ fsquare(t0, z2_20_0);
-	/* 2^22 - 2^2 */ fsquare(t1, t0);
-	/* 2^40 - 2^20 */ for (i = 2; i < 20; i += 2) { fsquare(t0, t1); fsquare(t1, t0); }
-	/* 2^40 - 2^0 */ fmul(t0, t1, z2_20_0);
-
-	/* 2^41 - 2^1 */ fsquare(t1, t0);
-	/* 2^42 - 2^2 */ fsquare(t0, t1);
-	/* 2^50 - 2^10 */ for (i = 2; i < 10; i += 2) { fsquare(t1, t0); fsquare(t0, t1); }
-	/* 2^50 - 2^0 */ fmul(z2_50_0, t0, z2_10_0);
-
-	/* 2^51 - 2^1 */ fsquare(t0, z2_50_0);
-	/* 2^52 - 2^2 */ fsquare(t1, t0);
-	/* 2^100 - 2^50 */ for (i = 2; i < 50; i += 2) { fsquare(t0, t1); fsquare(t1, t0); }
-	/* 2^100 - 2^0 */ fmul(z2_100_0, t1, z2_50_0);
-
-	/* 2^101 - 2^1 */ fsquare(t1, z2_100_0);
-	/* 2^102 - 2^2 */ fsquare(t0, t1);
-	/* 2^200 - 2^100 */ for (i = 2; i < 100; i += 2) { fsquare(t1, t0); fsquare(t0, t1); }
-	/* 2^200 - 2^0 */ fmul(t1, t0, z2_100_0);
-
-	/* 2^201 - 2^1 */ fsquare(t0, t1);
-	/* 2^202 - 2^2 */ fsquare(t1, t0);
-	/* 2^250 - 2^50 */ for (i = 2; i < 50; i += 2) { fsquare(t0, t1); fsquare(t1, t0); }
-	/* 2^250 - 2^0 */ fmul(t0, t1, z2_50_0);
-
-	/* 2^251 - 2^1 */ fsquare(t1, t0);
-	/* 2^252 - 2^2 */ fsquare(t0, t1);
-	/* 2^253 - 2^3 */ fsquare(t1, t0);
-	/* 2^254 - 2^4 */ fsquare(t0, t1);
-	/* 2^255 - 2^5 */ fsquare(t1, t0);
-	/* 2^255 - 21 */ fmul(out, t1, z11);
-}
-
-
-/* Input: Q, Q', Q-Q'
- * Output: 2Q, Q+Q'
- *
- *   x2 z3: long form
- *   x3 z3: long form
- *   x z: short form, destroyed
- *   xprime zprime: short form, destroyed
- *   qmqp: short form, preserved
- *
- * On entry and exit, the absolute value of the limbs of all inputs and outputs
- * are < 2^26.
- */
-static void fmonty(limb *x2, limb *z2,  /* output 2Q */
-		   limb *x3, limb *z3,  /* output Q + Q' */
-		   limb *x, limb *z,    /* input Q */
-		   limb *xprime, limb *zprime,  /* input Q' */
-
-		   const limb *qmqp /* input Q - Q' */)
-{
-	limb origx[10], origxprime[10], zzz[19], xx[19], zz[19], xxprime[19],
-				zzprime[19], zzzprime[19], xxxprime[19];
-
-	memcpy(origx, x, 10 * sizeof(limb));
-	fsum(x, z);
-	/* |x[i]| < 2^27 */
-	fdifference(z, origx);  /* does x - z */
-	/* |z[i]| < 2^27 */
-
-	memcpy(origxprime, xprime, sizeof(limb) * 10);
-	fsum(xprime, zprime);
-	/* |xprime[i]| < 2^27 */
-	fdifference(zprime, origxprime);
-	/* |zprime[i]| < 2^27 */
-	fproduct(xxprime, xprime, z);
-	/* |xxprime[i]| < 14*2^54: the largest product of two limbs will be <
-	 * 2^(27+27) and fproduct adds together, at most, 14 of those products.
-	 * (Approximating that to 2^58 doesn't work out.)
-	 */
-	fproduct(zzprime, x, zprime);
-	/* |zzprime[i]| < 14*2^54 */
-	freduce_degree(xxprime);
-	freduce_coefficients(xxprime);
-	/* |xxprime[i]| < 2^26 */
-	freduce_degree(zzprime);
-	freduce_coefficients(zzprime);
-	/* |zzprime[i]| < 2^26 */
-	memcpy(origxprime, xxprime, sizeof(limb) * 10);
-	fsum(xxprime, zzprime);
-	/* |xxprime[i]| < 2^27 */
-	fdifference(zzprime, origxprime);
-	/* |zzprime[i]| < 2^27 */
-	fsquare(xxxprime, xxprime);
-	/* |xxxprime[i]| < 2^26 */
-	fsquare(zzzprime, zzprime);
-	/* |zzzprime[i]| < 2^26 */
-	fproduct(zzprime, zzzprime, qmqp);
-	/* |zzprime[i]| < 14*2^52 */
-	freduce_degree(zzprime);
-	freduce_coefficients(zzprime);
-	/* |zzprime[i]| < 2^26 */
-	memcpy(x3, xxxprime, sizeof(limb) * 10);
-	memcpy(z3, zzprime, sizeof(limb) * 10);
-
-	fsquare(xx, x);
-	/* |xx[i]| < 2^26 */
-	fsquare(zz, z);
-	/* |zz[i]| < 2^26 */
-	fproduct(x2, xx, zz);
-	/* |x2[i]| < 14*2^52 */
-	freduce_degree(x2);
-	freduce_coefficients(x2);
-	/* |x2[i]| < 2^26 */
-	fdifference(zz, xx);  // does zz = xx - zz
-	/* |zz[i]| < 2^27 */
-	memset(zzz + 10, 0, sizeof(limb) * 9);
-	fscalar_product(zzz, zz, 121665);
-	/* |zzz[i]| < 2^(27+17) */
-	/* No need to call freduce_degree here:
-		 fscalar_product doesn't increase the degree of its input. */
-	freduce_coefficients(zzz);
-	/* |zzz[i]| < 2^26 */
-	fsum(zzz, xx);
-	/* |zzz[i]| < 2^27 */
-	fproduct(z2, zz, zzz);
-	/* |z2[i]| < 14*2^(26+27) */
-	freduce_degree(z2);
-	freduce_coefficients(z2);
-	/* |z2|i| < 2^26 */
-}
-
-/* Calculates nQ where Q is the x-coordinate of a point on the curve
- *
- *   resultx/resultz: the x coordinate of the resulting curve point (short form)
- *   n: a little endian, 32-byte number
- *   q: a point of the curve (short form)
- */
-static void cmult(limb *resultx, limb *resultz, const u8 *n, const limb *q)
-{
-	limb a[19] = {0}, b[19] = {1}, c[19] = {1}, d[19] = {0};
-	limb *nqpqx = a, *nqpqz = b, *nqx = c, *nqz = d, *t;
-	limb e[19] = {0}, f[19] = {1}, g[19] = {0}, h[19] = {1};
-	limb *nqpqx2 = e, *nqpqz2 = f, *nqx2 = g, *nqz2 = h;
-
-	unsigned int i, j;
-
-	memcpy(nqpqx, q, sizeof(limb) * 10);
-
-	for (i = 0; i < 32; ++i) {
-		u8 byte = n[31 - i];
-
-		for (j = 0; j < 8; ++j) {
-			const limb bit = byte >> 7;
-
-			swap_conditional(nqx, nqpqx, bit);
-			swap_conditional(nqz, nqpqz, bit);
-			fmonty(nqx2, nqz2,
-			       nqpqx2, nqpqz2,
-			       nqx, nqz,
-			       nqpqx, nqpqz,
-			       q);
-			swap_conditional(nqx2, nqpqx2, bit);
-			swap_conditional(nqz2, nqpqz2, bit);
-
-			t = nqx;
-			nqx = nqx2;
-			nqx2 = t;
-			t = nqz;
-			nqz = nqz2;
-			nqz2 = t;
-			t = nqpqx;
-			nqpqx = nqpqx2;
-			nqpqx2 = t;
-			t = nqpqz;
-			nqpqz = nqpqz2;
-			nqpqz2 = t;
-
-			byte <<= 1;
-		}
-	}
-
-	memcpy(resultx, nqx, sizeof(limb) * 10);
-	memcpy(resultz, nqz, sizeof(limb) * 10);
-}
-
-bool curve25519_donna32(u8 mypublic[CURVE25519_POINT_SIZE], const u8 secret[CURVE25519_POINT_SIZE], const u8 basepoint[CURVE25519_POINT_SIZE])
-{
-	limb bp[10], x[10], z[11], zmone[10];
-	u8 e[32];
-
-	memcpy(e, secret, 32);
-	normalize_secret(e);
-
-	fexpand(bp, basepoint);
-	cmult(x, z, e, bp);
-	crecip(zmone, z);
-	fmul(z, x, zmone);
-	fcontract(mypublic, z);
-
-	return true;
-}
diff --git a/curve25519-fiat32.c b/curve25519-fiat32.c
deleted file mode 100644
index 5912097..0000000
--- a/curve25519-fiat32.c
+++ /dev/null
@@ -1,838 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0
- *
- * Copyright (C) 2015-2016 The fiat-crypto Authors.
- * Copyright (C) 2018 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
- *
- * This is a machine-generated formally verified implementation of curve25519 DH from:
- * https://github.com/mit-plv/fiat-crypto
- */
-
-#include <linux/kernel.h>
-#include <linux/string.h>
-
-enum { CURVE25519_POINT_SIZE = 32 };
-
-static __always_inline void normalize_secret(u8 secret[CURVE25519_POINT_SIZE])
-{
-	secret[0] &= 248;
-	secret[31] &= 127;
-	secret[31] |= 64;
-}
-
-/* fe means field element. Here the field is \Z/(2^255-19). An element t,
- * entries t[0]...t[9], represents the integer t[0]+2^26 t[1]+2^51 t[2]+2^77
- * t[3]+2^102 t[4]+...+2^230 t[9].
- * fe limbs are bounded by 1.125*2^26,1.125*2^25,1.125*2^26,1.125*2^25,etc.
- * Multiplication and carrying produce fe from fe_loose.
- */
-typedef struct fe { u32 v[10]; } fe;
-
-/* fe_loose limbs are bounded by 3.375*2^26,3.375*2^25,3.375*2^26,3.375*2^25,etc.
- * Addition and subtraction produce fe_loose from (fe, fe).
- */
-typedef struct fe_loose { u32 v[10]; } fe_loose;
-
-static __always_inline void fe_frombytes_impl(u32 h[10], const u8 *s)
-{
-	/* Ignores top bit of s. */
-	u32 a0 = le32_to_cpup((__force __le32 *)(s));
-	u32 a1 = le32_to_cpup((__force __le32 *)(s+4));
-	u32 a2 = le32_to_cpup((__force __le32 *)(s+8));
-	u32 a3 = le32_to_cpup((__force __le32 *)(s+12));
-	u32 a4 = le32_to_cpup((__force __le32 *)(s+16));
-	u32 a5 = le32_to_cpup((__force __le32 *)(s+20));
-	u32 a6 = le32_to_cpup((__force __le32 *)(s+24));
-	u32 a7 = le32_to_cpup((__force __le32 *)(s+28));
-	h[0] = a0&((1<<26)-1);                    /* 26 used, 32-26 left.   26 */
-	h[1] = (a0>>26) | ((a1&((1<<19)-1))<< 6); /* (32-26) + 19 =  6+19 = 25 */
-	h[2] = (a1>>19) | ((a2&((1<<13)-1))<<13); /* (32-19) + 13 = 13+13 = 26 */
-	h[3] = (a2>>13) | ((a3&((1<< 6)-1))<<19); /* (32-13) +  6 = 19+ 6 = 25 */
-	h[4] = (a3>> 6);                          /* (32- 6)              = 26 */
-	h[5] = a4&((1<<25)-1);                    /*                        25 */
-	h[6] = (a4>>25) | ((a5&((1<<19)-1))<< 7); /* (32-25) + 19 =  7+19 = 26 */
-	h[7] = (a5>>19) | ((a6&((1<<12)-1))<<13); /* (32-19) + 12 = 13+12 = 25 */
-	h[8] = (a6>>12) | ((a7&((1<< 6)-1))<<20); /* (32-12) +  6 = 20+ 6 = 26 */
-	h[9] = (a7>> 6)&((1<<25)-1); /*                                     25 */
-}
-
-static __always_inline void fe_frombytes(fe *h, const u8 *s)
-{
-	fe_frombytes_impl(h->v, s);
-}
-
-static __always_inline u8 /*bool*/ addcarryx_u25(u8 /*bool*/ c, u32 a, u32 b, u32 *low)
-{
-	/* This function extracts 25 bits of result and 1 bit of carry (26 total), so
-	 * a 32-bit intermediate is sufficient.
-	 */
-	u32 x = a + b + c;
-	*low = x & ((1 << 25) - 1);
-	return (x >> 25) & 1;
-}
-
-static __always_inline u8 /*bool*/ addcarryx_u26(u8 /*bool*/ c, u32 a, u32 b, u32 *low)
-{
-	/* This function extracts 26 bits of result and 1 bit of carry (27 total), so
-	 * a 32-bit intermediate is sufficient.
-	 */
-	u32 x = a + b + c;
-	*low = x & ((1 << 26) - 1);
-	return (x >> 26) & 1;
-}
-
-static __always_inline u8 /*bool*/ subborrow_u25(u8 /*bool*/ c, u32 a, u32 b, u32 *low)
-{
-	/* This function extracts 25 bits of result and 1 bit of borrow (26 total), so
-	 * a 32-bit intermediate is sufficient.
-	 */
-	u32 x = a - b - c;
-	*low = x & ((1 << 25) - 1);
-	return x >> 31;
-}
-
-static __always_inline u8 /*bool*/ subborrow_u26(u8 /*bool*/ c, u32 a, u32 b, u32 *low)
-{
-	/* This function extracts 26 bits of result and 1 bit of borrow (27 total), so
-	 * a 32-bit intermediate is sufficient.
-	 */
-	u32 x = a - b - c;
-	*low = x & ((1 << 26) - 1);
-	return x >> 31;
-}
-
-static __always_inline u32 cmovznz32(u32 t, u32 z, u32 nz)
-{
-	t = -!!t; /* all set if nonzero, 0 if 0 */
-	return (t&nz) | ((~t)&z);
-}
-
-static __always_inline void fe_freeze(u32 out[10], const u32 in1[10])
-{
-	{ const u32 x17 = in1[9];
-	{ const u32 x18 = in1[8];
-	{ const u32 x16 = in1[7];
-	{ const u32 x14 = in1[6];
-	{ const u32 x12 = in1[5];
-	{ const u32 x10 = in1[4];
-	{ const u32 x8 = in1[3];
-	{ const u32 x6 = in1[2];
-	{ const u32 x4 = in1[1];
-	{ const u32 x2 = in1[0];
-	{ u32 x20; u8/*bool*/ x21 = subborrow_u26(0x0, x2, 0x3ffffed, &x20);
-	{ u32 x23; u8/*bool*/ x24 = subborrow_u25(x21, x4, 0x1ffffff, &x23);
-	{ u32 x26; u8/*bool*/ x27 = subborrow_u26(x24, x6, 0x3ffffff, &x26);
-	{ u32 x29; u8/*bool*/ x30 = subborrow_u25(x27, x8, 0x1ffffff, &x29);
-	{ u32 x32; u8/*bool*/ x33 = subborrow_u26(x30, x10, 0x3ffffff, &x32);
-	{ u32 x35; u8/*bool*/ x36 = subborrow_u25(x33, x12, 0x1ffffff, &x35);
-	{ u32 x38; u8/*bool*/ x39 = subborrow_u26(x36, x14, 0x3ffffff, &x38);
-	{ u32 x41; u8/*bool*/ x42 = subborrow_u25(x39, x16, 0x1ffffff, &x41);
-	{ u32 x44; u8/*bool*/ x45 = subborrow_u26(x42, x18, 0x3ffffff, &x44);
-	{ u32 x47; u8/*bool*/ x48 = subborrow_u25(x45, x17, 0x1ffffff, &x47);
-	{ u32 x49 = cmovznz32(x48, 0x0, 0xffffffff);
-	{ u32 x50 = (x49 & 0x3ffffed);
-	{ u32 x52; u8/*bool*/ x53 = addcarryx_u26(0x0, x20, x50, &x52);
-	{ u32 x54 = (x49 & 0x1ffffff);
-	{ u32 x56; u8/*bool*/ x57 = addcarryx_u25(x53, x23, x54, &x56);
-	{ u32 x58 = (x49 & 0x3ffffff);
-	{ u32 x60; u8/*bool*/ x61 = addcarryx_u26(x57, x26, x58, &x60);
-	{ u32 x62 = (x49 & 0x1ffffff);
-	{ u32 x64; u8/*bool*/ x65 = addcarryx_u25(x61, x29, x62, &x64);
-	{ u32 x66 = (x49 & 0x3ffffff);
-	{ u32 x68; u8/*bool*/ x69 = addcarryx_u26(x65, x32, x66, &x68);
-	{ u32 x70 = (x49 & 0x1ffffff);
-	{ u32 x72; u8/*bool*/ x73 = addcarryx_u25(x69, x35, x70, &x72);
-	{ u32 x74 = (x49 & 0x3ffffff);
-	{ u32 x76; u8/*bool*/ x77 = addcarryx_u26(x73, x38, x74, &x76);
-	{ u32 x78 = (x49 & 0x1ffffff);
-	{ u32 x80; u8/*bool*/ x81 = addcarryx_u25(x77, x41, x78, &x80);
-	{ u32 x82 = (x49 & 0x3ffffff);
-	{ u32 x84; u8/*bool*/ x85 = addcarryx_u26(x81, x44, x82, &x84);
-	{ u32 x86 = (x49 & 0x1ffffff);
-	{ u32 x88; addcarryx_u25(x85, x47, x86, &x88);
-	out[0] = x52;
-	out[1] = x56;
-	out[2] = x60;
-	out[3] = x64;
-	out[4] = x68;
-	out[5] = x72;
-	out[6] = x76;
-	out[7] = x80;
-	out[8] = x84;
-	out[9] = x88;
-	}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}
-}
-
-static __always_inline void fe_tobytes(u8 s[32], const fe *f)
-{
-	u32 h[10];
-	fe_freeze(h, f->v);
-	s[0] = h[0] >> 0;
-	s[1] = h[0] >> 8;
-	s[2] = h[0] >> 16;
-	s[3] = (h[0] >> 24) | (h[1] << 2);
-	s[4] = h[1] >> 6;
-	s[5] = h[1] >> 14;
-	s[6] = (h[1] >> 22) | (h[2] << 3);
-	s[7] = h[2] >> 5;
-	s[8] = h[2] >> 13;
-	s[9] = (h[2] >> 21) | (h[3] << 5);
-	s[10] = h[3] >> 3;
-	s[11] = h[3] >> 11;
-	s[12] = (h[3] >> 19) | (h[4] << 6);
-	s[13] = h[4] >> 2;
-	s[14] = h[4] >> 10;
-	s[15] = h[4] >> 18;
-	s[16] = h[5] >> 0;
-	s[17] = h[5] >> 8;
-	s[18] = h[5] >> 16;
-	s[19] = (h[5] >> 24) | (h[6] << 1);
-	s[20] = h[6] >> 7;
-	s[21] = h[6] >> 15;
-	s[22] = (h[6] >> 23) | (h[7] << 3);
-	s[23] = h[7] >> 5;
-	s[24] = h[7] >> 13;
-	s[25] = (h[7] >> 21) | (h[8] << 4);
-	s[26] = h[8] >> 4;
-	s[27] = h[8] >> 12;
-	s[28] = (h[8] >> 20) | (h[9] << 6);
-	s[29] = h[9] >> 2;
-	s[30] = h[9] >> 10;
-	s[31] = h[9] >> 18;
-}
-
-/* h = f */
-static __always_inline void fe_copy(fe *h, const fe *f)
-{
-	memmove(h, f, sizeof(u32) * 10);
-}
-
-static __always_inline void fe_copy_lt(fe_loose *h, const fe *f)
-{
-	memmove(h, f, sizeof(u32) * 10);
-}
-
-/* h = 0 */
-static __always_inline void fe_0(fe *h)
-{
-	memset(h, 0, sizeof(u32) * 10);
-}
-
-/* h = 1 */
-static __always_inline void fe_1(fe *h)
-{
-	memset(h, 0, sizeof(u32) * 10);
-	h->v[0] = 1;
-}
-
-static void fe_add_impl(u32 out[10], const u32 in1[10], const u32 in2[10])
-{
-	{ const u32 x20 = in1[9];
-	{ const u32 x21 = in1[8];
-	{ const u32 x19 = in1[7];
-	{ const u32 x17 = in1[6];
-	{ const u32 x15 = in1[5];
-	{ const u32 x13 = in1[4];
-	{ const u32 x11 = in1[3];
-	{ const u32 x9 = in1[2];
-	{ const u32 x7 = in1[1];
-	{ const u32 x5 = in1[0];
-	{ const u32 x38 = in2[9];
-	{ const u32 x39 = in2[8];
-	{ const u32 x37 = in2[7];
-	{ const u32 x35 = in2[6];
-	{ const u32 x33 = in2[5];
-	{ const u32 x31 = in2[4];
-	{ const u32 x29 = in2[3];
-	{ const u32 x27 = in2[2];
-	{ const u32 x25 = in2[1];
-	{ const u32 x23 = in2[0];
-	out[0] = (x5 + x23);
-	out[1] = (x7 + x25);
-	out[2] = (x9 + x27);
-	out[3] = (x11 + x29);
-	out[4] = (x13 + x31);
-	out[5] = (x15 + x33);
-	out[6] = (x17 + x35);
-	out[7] = (x19 + x37);
-	out[8] = (x21 + x39);
-	out[9] = (x20 + x38);
-	}}}}}}}}}}}}}}}}}}}}
-}
-
-/* h = f + g
- * Can overlap h with f or g.
- */
-static __always_inline void fe_add(fe_loose *h, const fe *f, const fe *g)
-{
-	fe_add_impl(h->v, f->v, g->v);
-}
-
-static void fe_sub_impl(u32 out[10], const u32 in1[10], const u32 in2[10])
-{
-	{ const u32 x20 = in1[9];
-	{ const u32 x21 = in1[8];
-	{ const u32 x19 = in1[7];
-	{ const u32 x17 = in1[6];
-	{ const u32 x15 = in1[5];
-	{ const u32 x13 = in1[4];
-	{ const u32 x11 = in1[3];
-	{ const u32 x9 = in1[2];
-	{ const u32 x7 = in1[1];
-	{ const u32 x5 = in1[0];
-	{ const u32 x38 = in2[9];
-	{ const u32 x39 = in2[8];
-	{ const u32 x37 = in2[7];
-	{ const u32 x35 = in2[6];
-	{ const u32 x33 = in2[5];
-	{ const u32 x31 = in2[4];
-	{ const u32 x29 = in2[3];
-	{ const u32 x27 = in2[2];
-	{ const u32 x25 = in2[1];
-	{ const u32 x23 = in2[0];
-	out[0] = ((0x7ffffda + x5) - x23);
-	out[1] = ((0x3fffffe + x7) - x25);
-	out[2] = ((0x7fffffe + x9) - x27);
-	out[3] = ((0x3fffffe + x11) - x29);
-	out[4] = ((0x7fffffe + x13) - x31);
-	out[5] = ((0x3fffffe + x15) - x33);
-	out[6] = ((0x7fffffe + x17) - x35);
-	out[7] = ((0x3fffffe + x19) - x37);
-	out[8] = ((0x7fffffe + x21) - x39);
-	out[9] = ((0x3fffffe + x20) - x38);
-	}}}}}}}}}}}}}}}}}}}}
-}
-
-/* h = f - g
- * Can overlap h with f or g.
- */
-static __always_inline void fe_sub(fe_loose *h, const fe *f, const fe *g)
-{
-	fe_sub_impl(h->v, f->v, g->v);
-}
-
-static void fe_mul_impl(u32 out[10], const u32 in1[10], const u32 in2[10])
-{
-	{ const u32 x20 = in1[9];
-	{ const u32 x21 = in1[8];
-	{ const u32 x19 = in1[7];
-	{ const u32 x17 = in1[6];
-	{ const u32 x15 = in1[5];
-	{ const u32 x13 = in1[4];
-	{ const u32 x11 = in1[3];
-	{ const u32 x9 = in1[2];
-	{ const u32 x7 = in1[1];
-	{ const u32 x5 = in1[0];
-	{ const u32 x38 = in2[9];
-	{ const u32 x39 = in2[8];
-	{ const u32 x37 = in2[7];
-	{ const u32 x35 = in2[6];
-	{ const u32 x33 = in2[5];
-	{ const u32 x31 = in2[4];
-	{ const u32 x29 = in2[3];
-	{ const u32 x27 = in2[2];
-	{ const u32 x25 = in2[1];
-	{ const u32 x23 = in2[0];
-	{ u64 x40 = ((u64)x23 * x5);
-	{ u64 x41 = (((u64)x23 * x7) + ((u64)x25 * x5));
-	{ u64 x42 = ((((u64)(0x2 * x25) * x7) + ((u64)x23 * x9)) + ((u64)x27 * x5));
-	{ u64 x43 = (((((u64)x25 * x9) + ((u64)x27 * x7)) + ((u64)x23 * x11)) + ((u64)x29 * x5));
-	{ u64 x44 = (((((u64)x27 * x9) + (0x2 * (((u64)x25 * x11) + ((u64)x29 * x7)))) + ((u64)x23 * x13)) + ((u64)x31 * x5));
-	{ u64 x45 = (((((((u64)x27 * x11) + ((u64)x29 * x9)) + ((u64)x25 * x13)) + ((u64)x31 * x7)) + ((u64)x23 * x15)) + ((u64)x33 * x5));
-	{ u64 x46 = (((((0x2 * ((((u64)x29 * x11) + ((u64)x25 * x15)) + ((u64)x33 * x7))) + ((u64)x27 * x13)) + ((u64)x31 * x9)) + ((u64)x23 * x17)) + ((u64)x35 * x5));
-	{ u64 x47 = (((((((((u64)x29 * x13) + ((u64)x31 * x11)) + ((u64)x27 * x15)) + ((u64)x33 * x9)) + ((u64)x25 * x17)) + ((u64)x35 * x7)) + ((u64)x23 * x19)) + ((u64)x37 * x5));
-	{ u64 x48 = (((((((u64)x31 * x13) + (0x2 * (((((u64)x29 * x15) + ((u64)x33 * x11)) + ((u64)x25 * x19)) + ((u64)x37 * x7)))) + ((u64)x27 * x17)) + ((u64)x35 * x9)) + ((u64)x23 * x21)) + ((u64)x39 * x5));
-	{ u64 x49 = (((((((((((u64)x31 * x15) + ((u64)x33 * x13)) + ((u64)x29 * x17)) + ((u64)x35 * x11)) + ((u64)x27 * x19)) + ((u64)x37 * x9)) + ((u64)x25 * x21)) + ((u64)x39 * x7)) + ((u64)x23 * x20)) + ((u64)x38 * x5));
-	{ u64 x50 = (((((0x2 * ((((((u64)x33 * x15) + ((u64)x29 * x19)) + ((u64)x37 * x11)) + ((u64)x25 * x20)) + ((u64)x38 * x7))) + ((u64)x31 * x17)) + ((u64)x35 * x13)) + ((u64)x27 * x21)) + ((u64)x39 * x9));
-	{ u64 x51 = (((((((((u64)x33 * x17) + ((u64)x35 * x15)) + ((u64)x31 * x19)) + ((u64)x37 * x13)) + ((u64)x29 * x21)) + ((u64)x39 * x11)) + ((u64)x27 * x20)) + ((u64)x38 * x9));
-	{ u64 x52 = (((((u64)x35 * x17) + (0x2 * (((((u64)x33 * x19) + ((u64)x37 * x15)) + ((u64)x29 * x20)) + ((u64)x38 * x11)))) + ((u64)x31 * x21)) + ((u64)x39 * x13));
-	{ u64 x53 = (((((((u64)x35 * x19) + ((u64)x37 * x17)) + ((u64)x33 * x21)) + ((u64)x39 * x15)) + ((u64)x31 * x20)) + ((u64)x38 * x13));
-	{ u64 x54 = (((0x2 * ((((u64)x37 * x19) + ((u64)x33 * x20)) + ((u64)x38 * x15))) + ((u64)x35 * x21)) + ((u64)x39 * x17));
-	{ u64 x55 = (((((u64)x37 * x21) + ((u64)x39 * x19)) + ((u64)x35 * x20)) + ((u64)x38 * x17));
-	{ u64 x56 = (((u64)x39 * x21) + (0x2 * (((u64)x37 * x20) + ((u64)x38 * x19))));
-	{ u64 x57 = (((u64)x39 * x20) + ((u64)x38 * x21));
-	{ u64 x58 = ((u64)(0x2 * x38) * x20);
-	{ u64 x59 = (x48 + (x58 << 0x4));
-	{ u64 x60 = (x59 + (x58 << 0x1));
-	{ u64 x61 = (x60 + x58);
-	{ u64 x62 = (x47 + (x57 << 0x4));
-	{ u64 x63 = (x62 + (x57 << 0x1));
-	{ u64 x64 = (x63 + x57);
-	{ u64 x65 = (x46 + (x56 << 0x4));
-	{ u64 x66 = (x65 + (x56 << 0x1));
-	{ u64 x67 = (x66 + x56);
-	{ u64 x68 = (x45 + (x55 << 0x4));
-	{ u64 x69 = (x68 + (x55 << 0x1));
-	{ u64 x70 = (x69 + x55);
-	{ u64 x71 = (x44 + (x54 << 0x4));
-	{ u64 x72 = (x71 + (x54 << 0x1));
-	{ u64 x73 = (x72 + x54);
-	{ u64 x74 = (x43 + (x53 << 0x4));
-	{ u64 x75 = (x74 + (x53 << 0x1));
-	{ u64 x76 = (x75 + x53);
-	{ u64 x77 = (x42 + (x52 << 0x4));
-	{ u64 x78 = (x77 + (x52 << 0x1));
-	{ u64 x79 = (x78 + x52);
-	{ u64 x80 = (x41 + (x51 << 0x4));
-	{ u64 x81 = (x80 + (x51 << 0x1));
-	{ u64 x82 = (x81 + x51);
-	{ u64 x83 = (x40 + (x50 << 0x4));
-	{ u64 x84 = (x83 + (x50 << 0x1));
-	{ u64 x85 = (x84 + x50);
-	{ u64 x86 = (x85 >> 0x1a);
-	{ u32 x87 = ((u32)x85 & 0x3ffffff);
-	{ u64 x88 = (x86 + x82);
-	{ u64 x89 = (x88 >> 0x19);
-	{ u32 x90 = ((u32)x88 & 0x1ffffff);
-	{ u64 x91 = (x89 + x79);
-	{ u64 x92 = (x91 >> 0x1a);
-	{ u32 x93 = ((u32)x91 & 0x3ffffff);
-	{ u64 x94 = (x92 + x76);
-	{ u64 x95 = (x94 >> 0x19);
-	{ u32 x96 = ((u32)x94 & 0x1ffffff);
-	{ u64 x97 = (x95 + x73);
-	{ u64 x98 = (x97 >> 0x1a);
-	{ u32 x99 = ((u32)x97 & 0x3ffffff);
-	{ u64 x100 = (x98 + x70);
-	{ u64 x101 = (x100 >> 0x19);
-	{ u32 x102 = ((u32)x100 & 0x1ffffff);
-	{ u64 x103 = (x101 + x67);
-	{ u64 x104 = (x103 >> 0x1a);
-	{ u32 x105 = ((u32)x103 & 0x3ffffff);
-	{ u64 x106 = (x104 + x64);
-	{ u64 x107 = (x106 >> 0x19);
-	{ u32 x108 = ((u32)x106 & 0x1ffffff);
-	{ u64 x109 = (x107 + x61);
-	{ u64 x110 = (x109 >> 0x1a);
-	{ u32 x111 = ((u32)x109 & 0x3ffffff);
-	{ u64 x112 = (x110 + x49);
-	{ u64 x113 = (x112 >> 0x19);
-	{ u32 x114 = ((u32)x112 & 0x1ffffff);
-	{ u64 x115 = (x87 + (0x13 * x113));
-	{ u32 x116 = (u32) (x115 >> 0x1a);
-	{ u32 x117 = ((u32)x115 & 0x3ffffff);
-	{ u32 x118 = (x116 + x90);
-	{ u32 x119 = (x118 >> 0x19);
-	{ u32 x120 = (x118 & 0x1ffffff);
-	out[0] = x117;
-	out[1] = x120;
-	out[2] = (x119 + x93);
-	out[3] = x96;
-	out[4] = x99;
-	out[5] = x102;
-	out[6] = x105;
-	out[7] = x108;
-	out[8] = x111;
-	out[9] = x114;
-	}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}
-}
-
-static __always_inline void fe_mul_ttt(fe *h, const fe *f, const fe *g)
-{
-	fe_mul_impl(h->v, f->v, g->v);
-}
-
-static __always_inline void fe_mul_tlt(fe *h, const fe_loose *f, const fe *g)
-{
-	fe_mul_impl(h->v, f->v, g->v);
-}
-
-static __always_inline void fe_mul_tll(fe *h, const fe_loose *f, const fe_loose *g)
-{
-	fe_mul_impl(h->v, f->v, g->v);
-}
-
-static void fe_sqr_impl(u32 out[10], const u32 in1[10])
-{
-	{ const u32 x17 = in1[9];
-	{ const u32 x18 = in1[8];
-	{ const u32 x16 = in1[7];
-	{ const u32 x14 = in1[6];
-	{ const u32 x12 = in1[5];
-	{ const u32 x10 = in1[4];
-	{ const u32 x8 = in1[3];
-	{ const u32 x6 = in1[2];
-	{ const u32 x4 = in1[1];
-	{ const u32 x2 = in1[0];
-	{ u64 x19 = ((u64)x2 * x2);
-	{ u64 x20 = ((u64)(0x2 * x2) * x4);
-	{ u64 x21 = (0x2 * (((u64)x4 * x4) + ((u64)x2 * x6)));
-	{ u64 x22 = (0x2 * (((u64)x4 * x6) + ((u64)x2 * x8)));
-	{ u64 x23 = ((((u64)x6 * x6) + ((u64)(0x4 * x4) * x8)) + ((u64)(0x2 * x2) * x10));
-	{ u64 x24 = (0x2 * ((((u64)x6 * x8) + ((u64)x4 * x10)) + ((u64)x2 * x12)));
-	{ u64 x25 = (0x2 * (((((u64)x8 * x8) + ((u64)x6 * x10)) + ((u64)x2 * x14)) + ((u64)(0x2 * x4) * x12)));
-	{ u64 x26 = (0x2 * (((((u64)x8 * x10) + ((u64)x6 * x12)) + ((u64)x4 * x14)) + ((u64)x2 * x16)));
-	{ u64 x27 = (((u64)x10 * x10) + (0x2 * ((((u64)x6 * x14) + ((u64)x2 * x18)) + (0x2 * (((u64)x4 * x16) + ((u64)x8 * x12))))));
-	{ u64 x28 = (0x2 * ((((((u64)x10 * x12) + ((u64)x8 * x14)) + ((u64)x6 * x16)) + ((u64)x4 * x18)) + ((u64)x2 * x17)));
-	{ u64 x29 = (0x2 * (((((u64)x12 * x12) + ((u64)x10 * x14)) + ((u64)x6 * x18)) + (0x2 * (((u64)x8 * x16) + ((u64)x4 * x17)))));
-	{ u64 x30 = (0x2 * (((((u64)x12 * x14) + ((u64)x10 * x16)) + ((u64)x8 * x18)) + ((u64)x6 * x17)));
-	{ u64 x31 = (((u64)x14 * x14) + (0x2 * (((u64)x10 * x18) + (0x2 * (((u64)x12 * x16) + ((u64)x8 * x17))))));
-	{ u64 x32 = (0x2 * ((((u64)x14 * x16) + ((u64)x12 * x18)) + ((u64)x10 * x17)));
-	{ u64 x33 = (0x2 * ((((u64)x16 * x16) + ((u64)x14 * x18)) + ((u64)(0x2 * x12) * x17)));
-	{ u64 x34 = (0x2 * (((u64)x16 * x18) + ((u64)x14 * x17)));
-	{ u64 x35 = (((u64)x18 * x18) + ((u64)(0x4 * x16) * x17));
-	{ u64 x36 = ((u64)(0x2 * x18) * x17);
-	{ u64 x37 = ((u64)(0x2 * x17) * x17);
-	{ u64 x38 = (x27 + (x37 << 0x4));
-	{ u64 x39 = (x38 + (x37 << 0x1));
-	{ u64 x40 = (x39 + x37);
-	{ u64 x41 = (x26 + (x36 << 0x4));
-	{ u64 x42 = (x41 + (x36 << 0x1));
-	{ u64 x43 = (x42 + x36);
-	{ u64 x44 = (x25 + (x35 << 0x4));
-	{ u64 x45 = (x44 + (x35 << 0x1));
-	{ u64 x46 = (x45 + x35);
-	{ u64 x47 = (x24 + (x34 << 0x4));
-	{ u64 x48 = (x47 + (x34 << 0x1));
-	{ u64 x49 = (x48 + x34);
-	{ u64 x50 = (x23 + (x33 << 0x4));
-	{ u64 x51 = (x50 + (x33 << 0x1));
-	{ u64 x52 = (x51 + x33);
-	{ u64 x53 = (x22 + (x32 << 0x4));
-	{ u64 x54 = (x53 + (x32 << 0x1));
-	{ u64 x55 = (x54 + x32);
-	{ u64 x56 = (x21 + (x31 << 0x4));
-	{ u64 x57 = (x56 + (x31 << 0x1));
-	{ u64 x58 = (x57 + x31);
-	{ u64 x59 = (x20 + (x30 << 0x4));
-	{ u64 x60 = (x59 + (x30 << 0x1));
-	{ u64 x61 = (x60 + x30);
-	{ u64 x62 = (x19 + (x29 << 0x4));
-	{ u64 x63 = (x62 + (x29 << 0x1));
-	{ u64 x64 = (x63 + x29);
-	{ u64 x65 = (x64 >> 0x1a);
-	{ u32 x66 = ((u32)x64 & 0x3ffffff);
-	{ u64 x67 = (x65 + x61);
-	{ u64 x68 = (x67 >> 0x19);
-	{ u32 x69 = ((u32)x67 & 0x1ffffff);
-	{ u64 x70 = (x68 + x58);
-	{ u64 x71 = (x70 >> 0x1a);
-	{ u32 x72 = ((u32)x70 & 0x3ffffff);
-	{ u64 x73 = (x71 + x55);
-	{ u64 x74 = (x73 >> 0x19);
-	{ u32 x75 = ((u32)x73 & 0x1ffffff);
-	{ u64 x76 = (x74 + x52);
-	{ u64 x77 = (x76 >> 0x1a);
-	{ u32 x78 = ((u32)x76 & 0x3ffffff);
-	{ u64 x79 = (x77 + x49);
-	{ u64 x80 = (x79 >> 0x19);
-	{ u32 x81 = ((u32)x79 & 0x1ffffff);
-	{ u64 x82 = (x80 + x46);
-	{ u64 x83 = (x82 >> 0x1a);
-	{ u32 x84 = ((u32)x82 & 0x3ffffff);
-	{ u64 x85 = (x83 + x43);
-	{ u64 x86 = (x85 >> 0x19);
-	{ u32 x87 = ((u32)x85 & 0x1ffffff);
-	{ u64 x88 = (x86 + x40);
-	{ u64 x89 = (x88 >> 0x1a);
-	{ u32 x90 = ((u32)x88 & 0x3ffffff);
-	{ u64 x91 = (x89 + x28);
-	{ u64 x92 = (x91 >> 0x19);
-	{ u32 x93 = ((u32)x91 & 0x1ffffff);
-	{ u64 x94 = (x66 + (0x13 * x92));
-	{ u32 x95 = (u32) (x94 >> 0x1a);
-	{ u32 x96 = ((u32)x94 & 0x3ffffff);
-	{ u32 x97 = (x95 + x69);
-	{ u32 x98 = (x97 >> 0x19);
-	{ u32 x99 = (x97 & 0x1ffffff);
-	out[0] = x96;
-	out[1] = x99;
-	out[2] = (x98 + x72);
-	out[3] = x75;
-	out[4] = x78;
-	out[5] = x81;
-	out[6] = x84;
-	out[7] = x87;
-	out[8] = x90;
-	out[9] = x93;
-	}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}
-}
-
-static __always_inline void fe_sq_tl(fe *h, const fe_loose *f)
-{
-	fe_sqr_impl(h->v, f->v);
-}
-
-static __always_inline void fe_sq_tt(fe *h, const fe *f)
-{
-	fe_sqr_impl(h->v, f->v);
-}
-
-static __always_inline void fe_loose_invert(fe *out, const fe_loose *z)
-{
-	fe t0;
-	fe t1;
-	fe t2;
-	fe t3;
-	int i;
-
-	fe_sq_tl(&t0, z);
-	fe_sq_tt(&t1, &t0);
-	for (i = 1; i < 2; ++i)
-		fe_sq_tt(&t1, &t1);
-	fe_mul_tlt(&t1, z, &t1);
-	fe_mul_ttt(&t0, &t0, &t1);
-	fe_sq_tt(&t2, &t0);
-	fe_mul_ttt(&t1, &t1, &t2);
-	fe_sq_tt(&t2, &t1);
-	for (i = 1; i < 5; ++i)
-		fe_sq_tt(&t2, &t2);
-	fe_mul_ttt(&t1, &t2, &t1);
-	fe_sq_tt(&t2, &t1);
-	for (i = 1; i < 10; ++i)
-		fe_sq_tt(&t2, &t2);
-	fe_mul_ttt(&t2, &t2, &t1);
-	fe_sq_tt(&t3, &t2);
-	for (i = 1; i < 20; ++i)
-		fe_sq_tt(&t3, &t3);
-	fe_mul_ttt(&t2, &t3, &t2);
-	fe_sq_tt(&t2, &t2);
-	for (i = 1; i < 10; ++i)
-		fe_sq_tt(&t2, &t2);
-	fe_mul_ttt(&t1, &t2, &t1);
-	fe_sq_tt(&t2, &t1);
-	for (i = 1; i < 50; ++i)
-		fe_sq_tt(&t2, &t2);
-	fe_mul_ttt(&t2, &t2, &t1);
-	fe_sq_tt(&t3, &t2);
-	for (i = 1; i < 100; ++i)
-		fe_sq_tt(&t3, &t3);
-	fe_mul_ttt(&t2, &t3, &t2);
-	fe_sq_tt(&t2, &t2);
-	for (i = 1; i < 50; ++i)
-		fe_sq_tt(&t2, &t2);
-	fe_mul_ttt(&t1, &t2, &t1);
-	fe_sq_tt(&t1, &t1);
-	for (i = 1; i < 5; ++i)
-		fe_sq_tt(&t1, &t1);
-	fe_mul_ttt(out, &t1, &t0);
-}
-
-static __always_inline void fe_invert(fe *out, const fe *z)
-{
-	fe_loose l;
-	fe_copy_lt(&l, z);
-	fe_loose_invert(out, &l);
-}
-
-/* Replace (f,g) with (g,f) if b == 1;
- * replace (f,g) with (f,g) if b == 0.
- *
- * Preconditions: b in {0,1}
- */
-static __always_inline void fe_cswap(fe *f, fe *g, unsigned int b)
-{
-	unsigned i;
-	b = 0-b;
-	for (i = 0; i < 10; i++) {
-		u32 x = f->v[i] ^ g->v[i];
-		x &= b;
-		f->v[i] ^= x;
-		g->v[i] ^= x;
-	}
-}
-
-/* NOTE: based on fiat-crypto fe_mul, edited for in2=121666, 0, 0.*/
-static __always_inline void fe_mul_121666_impl(u32 out[10], const u32 in1[10])
-{
-	{ const u32 x20 = in1[9];
-	{ const u32 x21 = in1[8];
-	{ const u32 x19 = in1[7];
-	{ const u32 x17 = in1[6];
-	{ const u32 x15 = in1[5];
-	{ const u32 x13 = in1[4];
-	{ const u32 x11 = in1[3];
-	{ const u32 x9 = in1[2];
-	{ const u32 x7 = in1[1];
-	{ const u32 x5 = in1[0];
-	{ const u32 x38 = 0;
-	{ const u32 x39 = 0;
-	{ const u32 x37 = 0;
-	{ const u32 x35 = 0;
-	{ const u32 x33 = 0;
-	{ const u32 x31 = 0;
-	{ const u32 x29 = 0;
-	{ const u32 x27 = 0;
-	{ const u32 x25 = 0;
-	{ const u32 x23 = 121666;
-	{ u64 x40 = ((u64)x23 * x5);
-	{ u64 x41 = (((u64)x23 * x7) + ((u64)x25 * x5));
-	{ u64 x42 = ((((u64)(0x2 * x25) * x7) + ((u64)x23 * x9)) + ((u64)x27 * x5));
-	{ u64 x43 = (((((u64)x25 * x9) + ((u64)x27 * x7)) + ((u64)x23 * x11)) + ((u64)x29 * x5));
-	{ u64 x44 = (((((u64)x27 * x9) + (0x2 * (((u64)x25 * x11) + ((u64)x29 * x7)))) + ((u64)x23 * x13)) + ((u64)x31 * x5));
-	{ u64 x45 = (((((((u64)x27 * x11) + ((u64)x29 * x9)) + ((u64)x25 * x13)) + ((u64)x31 * x7)) + ((u64)x23 * x15)) + ((u64)x33 * x5));
-	{ u64 x46 = (((((0x2 * ((((u64)x29 * x11) + ((u64)x25 * x15)) + ((u64)x33 * x7))) + ((u64)x27 * x13)) + ((u64)x31 * x9)) + ((u64)x23 * x17)) + ((u64)x35 * x5));
-	{ u64 x47 = (((((((((u64)x29 * x13) + ((u64)x31 * x11)) + ((u64)x27 * x15)) + ((u64)x33 * x9)) + ((u64)x25 * x17)) + ((u64)x35 * x7)) + ((u64)x23 * x19)) + ((u64)x37 * x5));
-	{ u64 x48 = (((((((u64)x31 * x13) + (0x2 * (((((u64)x29 * x15) + ((u64)x33 * x11)) + ((u64)x25 * x19)) + ((u64)x37 * x7)))) + ((u64)x27 * x17)) + ((u64)x35 * x9)) + ((u64)x23 * x21)) + ((u64)x39 * x5));
-	{ u64 x49 = (((((((((((u64)x31 * x15) + ((u64)x33 * x13)) + ((u64)x29 * x17)) + ((u64)x35 * x11)) + ((u64)x27 * x19)) + ((u64)x37 * x9)) + ((u64)x25 * x21)) + ((u64)x39 * x7)) + ((u64)x23 * x20)) + ((u64)x38 * x5));
-	{ u64 x50 = (((((0x2 * ((((((u64)x33 * x15) + ((u64)x29 * x19)) + ((u64)x37 * x11)) + ((u64)x25 * x20)) + ((u64)x38 * x7))) + ((u64)x31 * x17)) + ((u64)x35 * x13)) + ((u64)x27 * x21)) + ((u64)x39 * x9));
-	{ u64 x51 = (((((((((u64)x33 * x17) + ((u64)x35 * x15)) + ((u64)x31 * x19)) + ((u64)x37 * x13)) + ((u64)x29 * x21)) + ((u64)x39 * x11)) + ((u64)x27 * x20)) + ((u64)x38 * x9));
-	{ u64 x52 = (((((u64)x35 * x17) + (0x2 * (((((u64)x33 * x19) + ((u64)x37 * x15)) + ((u64)x29 * x20)) + ((u64)x38 * x11)))) + ((u64)x31 * x21)) + ((u64)x39 * x13));
-	{ u64 x53 = (((((((u64)x35 * x19) + ((u64)x37 * x17)) + ((u64)x33 * x21)) + ((u64)x39 * x15)) + ((u64)x31 * x20)) + ((u64)x38 * x13));
-	{ u64 x54 = (((0x2 * ((((u64)x37 * x19) + ((u64)x33 * x20)) + ((u64)x38 * x15))) + ((u64)x35 * x21)) + ((u64)x39 * x17));
-	{ u64 x55 = (((((u64)x37 * x21) + ((u64)x39 * x19)) + ((u64)x35 * x20)) + ((u64)x38 * x17));
-	{ u64 x56 = (((u64)x39 * x21) + (0x2 * (((u64)x37 * x20) + ((u64)x38 * x19))));
-	{ u64 x57 = (((u64)x39 * x20) + ((u64)x38 * x21));
-	{ u64 x58 = ((u64)(0x2 * x38) * x20);
-	{ u64 x59 = (x48 + (x58 << 0x4));
-	{ u64 x60 = (x59 + (x58 << 0x1));
-	{ u64 x61 = (x60 + x58);
-	{ u64 x62 = (x47 + (x57 << 0x4));
-	{ u64 x63 = (x62 + (x57 << 0x1));
-	{ u64 x64 = (x63 + x57);
-	{ u64 x65 = (x46 + (x56 << 0x4));
-	{ u64 x66 = (x65 + (x56 << 0x1));
-	{ u64 x67 = (x66 + x56);
-	{ u64 x68 = (x45 + (x55 << 0x4));
-	{ u64 x69 = (x68 + (x55 << 0x1));
-	{ u64 x70 = (x69 + x55);
-	{ u64 x71 = (x44 + (x54 << 0x4));
-	{ u64 x72 = (x71 + (x54 << 0x1));
-	{ u64 x73 = (x72 + x54);
-	{ u64 x74 = (x43 + (x53 << 0x4));
-	{ u64 x75 = (x74 + (x53 << 0x1));
-	{ u64 x76 = (x75 + x53);
-	{ u64 x77 = (x42 + (x52 << 0x4));
-	{ u64 x78 = (x77 + (x52 << 0x1));
-	{ u64 x79 = (x78 + x52);
-	{ u64 x80 = (x41 + (x51 << 0x4));
-	{ u64 x81 = (x80 + (x51 << 0x1));
-	{ u64 x82 = (x81 + x51);
-	{ u64 x83 = (x40 + (x50 << 0x4));
-	{ u64 x84 = (x83 + (x50 << 0x1));
-	{ u64 x85 = (x84 + x50);
-	{ u64 x86 = (x85 >> 0x1a);
-	{ u32 x87 = ((u32)x85 & 0x3ffffff);
-	{ u64 x88 = (x86 + x82);
-	{ u64 x89 = (x88 >> 0x19);
-	{ u32 x90 = ((u32)x88 & 0x1ffffff);
-	{ u64 x91 = (x89 + x79);
-	{ u64 x92 = (x91 >> 0x1a);
-	{ u32 x93 = ((u32)x91 & 0x3ffffff);
-	{ u64 x94 = (x92 + x76);
-	{ u64 x95 = (x94 >> 0x19);
-	{ u32 x96 = ((u32)x94 & 0x1ffffff);
-	{ u64 x97 = (x95 + x73);
-	{ u64 x98 = (x97 >> 0x1a);
-	{ u32 x99 = ((u32)x97 & 0x3ffffff);
-	{ u64 x100 = (x98 + x70);
-	{ u64 x101 = (x100 >> 0x19);
-	{ u32 x102 = ((u32)x100 & 0x1ffffff);
-	{ u64 x103 = (x101 + x67);
-	{ u64 x104 = (x103 >> 0x1a);
-	{ u32 x105 = ((u32)x103 & 0x3ffffff);
-	{ u64 x106 = (x104 + x64);
-	{ u64 x107 = (x106 >> 0x19);
-	{ u32 x108 = ((u32)x106 & 0x1ffffff);
-	{ u64 x109 = (x107 + x61);
-	{ u64 x110 = (x109 >> 0x1a);
-	{ u32 x111 = ((u32)x109 & 0x3ffffff);
-	{ u64 x112 = (x110 + x49);
-	{ u64 x113 = (x112 >> 0x19);
-	{ u32 x114 = ((u32)x112 & 0x1ffffff);
-	{ u64 x115 = (x87 + (0x13 * x113));
-	{ u32 x116 = (u32) (x115 >> 0x1a);
-	{ u32 x117 = ((u32)x115 & 0x3ffffff);
-	{ u32 x118 = (x116 + x90);
-	{ u32 x119 = (x118 >> 0x19);
-	{ u32 x120 = (x118 & 0x1ffffff);
-	out[0] = x117;
-	out[1] = x120;
-	out[2] = (x119 + x93);
-	out[3] = x96;
-	out[4] = x99;
-	out[5] = x102;
-	out[6] = x105;
-	out[7] = x108;
-	out[8] = x111;
-	out[9] = x114;
-	}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}}
-}
-
-static __always_inline void fe_mul121666(fe *h, const fe_loose *f)
-{
-	fe_mul_121666_impl(h->v, f->v);
-}
-
-bool curve25519_fiat32(u8 out[CURVE25519_POINT_SIZE], const u8 scalar[CURVE25519_POINT_SIZE], const u8 point[CURVE25519_POINT_SIZE])
-{
-	fe x1, x2, z2, x3, z3, tmp0, tmp1;
-	fe_loose x2l, z2l, x3l, tmp0l, tmp1l;
-	unsigned swap = 0;
-	int pos;
-	u8 e[32];
-
-	memcpy(e, scalar, 32);
-	normalize_secret(e);
-
-	/* The following implementation was transcribed to Coq and proven to
-	 * correspond to unary scalar multiplication in affine coordinates given that
-	 * x1 != 0 is the x coordinate of some point on the curve. It was also checked
-	 * in Coq that doing a ladderstep with x1 = x3 = 0 gives z2' = z3' = 0, and z2
-	 * = z3 = 0 gives z2' = z3' = 0. The statement was quantified over the
-	 * underlying field, so it applies to Curve25519 itself and the quadratic
-	 * twist of Curve25519. It was not proven in Coq that prime-field arithmetic
-	 * correctly simulates extension-field arithmetic on prime-field values.
-	 * The decoding of the byte array representation of e was not considered.
-	 * Specification of Montgomery curves in affine coordinates:
-	 * <https://github.com/mit-plv/fiat-crypto/blob/2456d821825521f7e03e65882cc3521795b0320f/src/Spec/MontgomeryCurve.v#L27>
-	 * Proof that these form a group that is isomorphic to a Weierstrass curve:
-	 * <https://github.com/mit-plv/fiat-crypto/blob/2456d821825521f7e03e65882cc3521795b0320f/src/Curves/Montgomery/AffineProofs.v#L35>
-	 * Coq transcription and correctness proof of the loop (where scalarbits=255):
-	 * <https://github.com/mit-plv/fiat-crypto/blob/2456d821825521f7e03e65882cc3521795b0320f/src/Curves/Montgomery/XZ.v#L118>
-	 * <https://github.com/mit-plv/fiat-crypto/blob/2456d821825521f7e03e65882cc3521795b0320f/src/Curves/Montgomery/XZProofs.v#L278>
-	 * preconditions: 0 <= e < 2^255 (not necessarily e < order), fe_invert(0) = 0
-	 */
-	fe_frombytes(&x1, point);
-	fe_1(&x2);
-	fe_0(&z2);
-	fe_copy(&x3, &x1);
-	fe_1(&z3);
-
-	for (pos = 254; pos >= 0; --pos) {
-		/* loop invariant as of right before the test, for the case where x1 != 0:
-		 *   pos >= -1; if z2 = 0 then x2 is nonzero; if z3 = 0 then x3 is nonzero
-		 *   let r := e >> (pos+1) in the following equalities of projective points:
-		 *   to_xz (r*P)     === if swap then (x3, z3) else (x2, z2)
-		 *   to_xz ((r+1)*P) === if swap then (x2, z2) else (x3, z3)
-		 *   x1 is the nonzero x coordinate of the nonzero point (r*P-(r+1)*P)
-		 */
-		unsigned b = 1 & (e[pos / 8] >> (pos & 7));
-		swap ^= b;
-		fe_cswap(&x2, &x3, swap);
-		fe_cswap(&z2, &z3, swap);
-		swap = b;
-		/* Coq transcription of ladderstep formula (called from transcribed loop):
-		 * <https://github.com/mit-plv/fiat-crypto/blob/2456d821825521f7e03e65882cc3521795b0320f/src/Curves/Montgomery/XZ.v#L89>
-		 * <https://github.com/mit-plv/fiat-crypto/blob/2456d821825521f7e03e65882cc3521795b0320f/src/Curves/Montgomery/XZProofs.v#L131>
-		 * x1 != 0 <https://github.com/mit-plv/fiat-crypto/blob/2456d821825521f7e03e65882cc3521795b0320f/src/Curves/Montgomery/XZProofs.v#L217>
-		 * x1  = 0 <https://github.com/mit-plv/fiat-crypto/blob/2456d821825521f7e03e65882cc3521795b0320f/src/Curves/Montgomery/XZProofs.v#L147>
-		 */
-		fe_sub(&tmp0l, &x3, &z3);
-		fe_sub(&tmp1l, &x2, &z2);
-		fe_add(&x2l, &x2, &z2);
-		fe_add(&z2l, &x3, &z3);
-		fe_mul_tll(&z3, &tmp0l, &x2l);
-		fe_mul_tll(&z2, &z2l, &tmp1l);
-		fe_sq_tl(&tmp0, &tmp1l);
-		fe_sq_tl(&tmp1, &x2l);
-		fe_add(&x3l, &z3, &z2);
-		fe_sub(&z2l, &z3, &z2);
-		fe_mul_ttt(&x2, &tmp1, &tmp0);
-		fe_sub(&tmp1l, &tmp1, &tmp0);
-		fe_sq_tl(&z2, &z2l);
-		fe_mul121666(&z3, &tmp1l);
-		fe_sq_tl(&x3, &x3l);
-		fe_add(&tmp0l, &tmp0, &z3);
-		fe_mul_ttt(&z3, &x1, &z2);
-		fe_mul_tll(&z2, &tmp1l, &tmp0l);
-	}
-	/* here pos=-1, so r=e, so to_xz (e*P) === if swap then (x3, z3) else (x2, z2) */
-	fe_cswap(&x2, &x3, swap);
-	fe_cswap(&z2, &z3, swap);
-
-	fe_invert(&z2, &z2);
-	fe_mul_ttt(&x2, &x2, &z2);
-	fe_tobytes(out, &x2);
-
-	return true;
-}
diff --git a/curve25519-neon.S b/curve25519-neon.S
deleted file mode 100644
index b8e2c1d..0000000
--- a/curve25519-neon.S
+++ /dev/null
@@ -1,2110 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0
- *
- * Copyright (C) 2015-2018 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
- *
- * Based on algorithms from Daniel J. Bernstein and Peter Schwabe.
- */
-
-#if IS_ENABLED(CONFIG_KERNEL_MODE_NEON)
-
-#include <linux/linkage.h>
-
-	.text
-	.fpu		neon
-	.align		4
-
-ENTRY(curve25519_neon)
-	vpush {q4,q5,q6,q7}
-	mov r12,sp
-	sub r3,sp,#736
-	and r3,r3,#0xffffffe0
-	mov sp,r3
-	strd r4,[sp,#0]
-	strd r6,[sp,#8]
-	strd r8,[sp,#16]
-	strd r10,[sp,#24]
-	str r12,[sp,#480]
-	str r14,[sp,#484]
-	mov r0,r0
-	mov r1,r1
-	mov r2,r2
-	add r3,sp,#32
-	ldr r4,=0
-	ldr r5,=254
-	vmov.i32 q0,#1
-	vshr.u64 q1,q0,#7
-	vshr.u64 q0,q0,#8
-	vmov.i32 d4,#19
-	vmov.i32 d5,#38
-	add r6,sp,#512
-	vst1.8 {d2-d3},[r6,: 128]
-	add r6,sp,#528
-	vst1.8 {d0-d1},[r6,: 128]
-	add r6,sp,#544
-	vst1.8 {d4-d5},[r6,: 128]
-	add r6,r3,#0
-	vmov.i32 q2,#0
-	vst1.8 {d4-d5},[r6,: 128]!
-	vst1.8 {d4-d5},[r6,: 128]!
-	vst1.8 d4,[r6,: 64]
-	add r6,r3,#0
-	ldr r7,=960
-	sub r7,r7,#2
-	neg r7,r7
-	sub r7,r7,r7,LSL #7
-	str r7,[r6]
-	add r6,sp,#704
-	vld1.8 {d4-d5},[r1]!
-	vld1.8 {d6-d7},[r1]
-	vst1.8 {d4-d5},[r6,: 128]!
-	vst1.8 {d6-d7},[r6,: 128]
-	sub r1,r6,#16
-	ldrb r6,[r1]
-	and r6,r6,#248
-	strb r6,[r1]
-	ldrb r6,[r1,#31]
-	and r6,r6,#127
-	orr r6,r6,#64
-	strb r6,[r1,#31]
-	vmov.i64 q2,#0xffffffff
-	vshr.u64 q3,q2,#7
-	vshr.u64 q2,q2,#6
-	vld1.8 {d8},[r2]
-	vld1.8 {d10},[r2]
-	add r2,r2,#6
-	vld1.8 {d12},[r2]
-	vld1.8 {d14},[r2]
-	add r2,r2,#6
-	vld1.8 {d16},[r2]
-	add r2,r2,#4
-	vld1.8 {d18},[r2]
-	vld1.8 {d20},[r2]
-	add r2,r2,#6
-	vld1.8 {d22},[r2]
-	add r2,r2,#2
-	vld1.8 {d24},[r2]
-	vld1.8 {d26},[r2]
-	vshr.u64 q5,q5,#26
-	vshr.u64 q6,q6,#3
-	vshr.u64 q7,q7,#29
-	vshr.u64 q8,q8,#6
-	vshr.u64 q10,q10,#25
-	vshr.u64 q11,q11,#3
-	vshr.u64 q12,q12,#12
-	vshr.u64 q13,q13,#38
-	vand q4,q4,q2
-	vand q6,q6,q2
-	vand q8,q8,q2
-	vand q10,q10,q2
-	vand q2,q12,q2
-	vand q5,q5,q3
-	vand q7,q7,q3
-	vand q9,q9,q3
-	vand q11,q11,q3
-	vand q3,q13,q3
-	add r2,r3,#48
-	vadd.i64 q12,q4,q1
-	vadd.i64 q13,q10,q1
-	vshr.s64 q12,q12,#26
-	vshr.s64 q13,q13,#26
-	vadd.i64 q5,q5,q12
-	vshl.i64 q12,q12,#26
-	vadd.i64 q14,q5,q0
-	vadd.i64 q11,q11,q13
-	vshl.i64 q13,q13,#26
-	vadd.i64 q15,q11,q0
-	vsub.i64 q4,q4,q12
-	vshr.s64 q12,q14,#25
-	vsub.i64 q10,q10,q13
-	vshr.s64 q13,q15,#25
-	vadd.i64 q6,q6,q12
-	vshl.i64 q12,q12,#25
-	vadd.i64 q14,q6,q1
-	vadd.i64 q2,q2,q13
-	vsub.i64 q5,q5,q12
-	vshr.s64 q12,q14,#26
-	vshl.i64 q13,q13,#25
-	vadd.i64 q14,q2,q1
-	vadd.i64 q7,q7,q12
-	vshl.i64 q12,q12,#26
-	vadd.i64 q15,q7,q0
-	vsub.i64 q11,q11,q13
-	vshr.s64 q13,q14,#26
-	vsub.i64 q6,q6,q12
-	vshr.s64 q12,q15,#25
-	vadd.i64 q3,q3,q13
-	vshl.i64 q13,q13,#26
-	vadd.i64 q14,q3,q0
-	vadd.i64 q8,q8,q12
-	vshl.i64 q12,q12,#25
-	vadd.i64 q15,q8,q1
-	add r2,r2,#8
-	vsub.i64 q2,q2,q13
-	vshr.s64 q13,q14,#25
-	vsub.i64 q7,q7,q12
-	vshr.s64 q12,q15,#26
-	vadd.i64 q14,q13,q13
-	vadd.i64 q9,q9,q12
-	vtrn.32 d12,d14
-	vshl.i64 q12,q12,#26
-	vtrn.32 d13,d15
-	vadd.i64 q0,q9,q0
-	vadd.i64 q4,q4,q14
-	vst1.8 d12,[r2,: 64]!
-	vshl.i64 q6,q13,#4
-	vsub.i64 q7,q8,q12
-	vshr.s64 q0,q0,#25
-	vadd.i64 q4,q4,q6
-	vadd.i64 q6,q10,q0
-	vshl.i64 q0,q0,#25
-	vadd.i64 q8,q6,q1
-	vadd.i64 q4,q4,q13
-	vshl.i64 q10,q13,#25
-	vadd.i64 q1,q4,q1
-	vsub.i64 q0,q9,q0
-	vshr.s64 q8,q8,#26
-	vsub.i64 q3,q3,q10
-	vtrn.32 d14,d0
-	vshr.s64 q1,q1,#26
-	vtrn.32 d15,d1
-	vadd.i64 q0,q11,q8
-	vst1.8 d14,[r2,: 64]
-	vshl.i64 q7,q8,#26
-	vadd.i64 q5,q5,q1
-	vtrn.32 d4,d6
-	vshl.i64 q1,q1,#26
-	vtrn.32 d5,d7
-	vsub.i64 q3,q6,q7
-	add r2,r2,#16
-	vsub.i64 q1,q4,q1
-	vst1.8 d4,[r2,: 64]
-	vtrn.32 d6,d0
-	vtrn.32 d7,d1
-	sub r2,r2,#8
-	vtrn.32 d2,d10
-	vtrn.32 d3,d11
-	vst1.8 d6,[r2,: 64]
-	sub r2,r2,#24
-	vst1.8 d2,[r2,: 64]
-	add r2,r3,#96
-	vmov.i32 q0,#0
-	vmov.i64 d2,#0xff
-	vmov.i64 d3,#0
-	vshr.u32 q1,q1,#7
-	vst1.8 {d2-d3},[r2,: 128]!
-	vst1.8 {d0-d1},[r2,: 128]!
-	vst1.8 d0,[r2,: 64]
-	add r2,r3,#144
-	vmov.i32 q0,#0
-	vst1.8 {d0-d1},[r2,: 128]!
-	vst1.8 {d0-d1},[r2,: 128]!
-	vst1.8 d0,[r2,: 64]
-	add r2,r3,#240
-	vmov.i32 q0,#0
-	vmov.i64 d2,#0xff
-	vmov.i64 d3,#0
-	vshr.u32 q1,q1,#7
-	vst1.8 {d2-d3},[r2,: 128]!
-	vst1.8 {d0-d1},[r2,: 128]!
-	vst1.8 d0,[r2,: 64]
-	add r2,r3,#48
-	add r6,r3,#192
-	vld1.8 {d0-d1},[r2,: 128]!
-	vld1.8 {d2-d3},[r2,: 128]!
-	vld1.8 {d4},[r2,: 64]
-	vst1.8 {d0-d1},[r6,: 128]!
-	vst1.8 {d2-d3},[r6,: 128]!
-	vst1.8 d4,[r6,: 64]
-	.Lmainloop:
-	mov r2,r5,LSR #3
-	and r6,r5,#7
-	ldrb r2,[r1,r2]
-	mov r2,r2,LSR r6
-	and r2,r2,#1
-	str r5,[sp,#488]
-	eor r4,r4,r2
-	str r2,[sp,#492]
-	neg r2,r4
-	add r4,r3,#96
-	add r5,r3,#192
-	add r6,r3,#144
-	vld1.8 {d8-d9},[r4,: 128]!
-	add r7,r3,#240
-	vld1.8 {d10-d11},[r5,: 128]!
-	veor q6,q4,q5
-	vld1.8 {d14-d15},[r6,: 128]!
-	vdup.i32 q8,r2
-	vld1.8 {d18-d19},[r7,: 128]!
-	veor q10,q7,q9
-	vld1.8 {d22-d23},[r4,: 128]!
-	vand q6,q6,q8
-	vld1.8 {d24-d25},[r5,: 128]!
-	vand q10,q10,q8
-	vld1.8 {d26-d27},[r6,: 128]!
-	veor q4,q4,q6
-	vld1.8 {d28-d29},[r7,: 128]!
-	veor q5,q5,q6
-	vld1.8 {d0},[r4,: 64]
-	veor q6,q7,q10
-	vld1.8 {d2},[r5,: 64]
-	veor q7,q9,q10
-	vld1.8 {d4},[r6,: 64]
-	veor q9,q11,q12
-	vld1.8 {d6},[r7,: 64]
-	veor q10,q0,q1
-	sub r2,r4,#32
-	vand q9,q9,q8
-	sub r4,r5,#32
-	vand q10,q10,q8
-	sub r5,r6,#32
-	veor q11,q11,q9
-	sub r6,r7,#32
-	veor q0,q0,q10
-	veor q9,q12,q9
-	veor q1,q1,q10
-	veor q10,q13,q14
-	veor q12,q2,q3
-	vand q10,q10,q8
-	vand q8,q12,q8
-	veor q12,q13,q10
-	veor q2,q2,q8
-	veor q10,q14,q10
-	veor q3,q3,q8
-	vadd.i32 q8,q4,q6
-	vsub.i32 q4,q4,q6
-	vst1.8 {d16-d17},[r2,: 128]!
-	vadd.i32 q6,q11,q12
-	vst1.8 {d8-d9},[r5,: 128]!
-	vsub.i32 q4,q11,q12
-	vst1.8 {d12-d13},[r2,: 128]!
-	vadd.i32 q6,q0,q2
-	vst1.8 {d8-d9},[r5,: 128]!
-	vsub.i32 q0,q0,q2
-	vst1.8 d12,[r2,: 64]
-	vadd.i32 q2,q5,q7
-	vst1.8 d0,[r5,: 64]
-	vsub.i32 q0,q5,q7
-	vst1.8 {d4-d5},[r4,: 128]!
-	vadd.i32 q2,q9,q10
-	vst1.8 {d0-d1},[r6,: 128]!
-	vsub.i32 q0,q9,q10
-	vst1.8 {d4-d5},[r4,: 128]!
-	vadd.i32 q2,q1,q3
-	vst1.8 {d0-d1},[r6,: 128]!
-	vsub.i32 q0,q1,q3
-	vst1.8 d4,[r4,: 64]
-	vst1.8 d0,[r6,: 64]
-	add r2,sp,#544
-	add r4,r3,#96
-	add r5,r3,#144
-	vld1.8 {d0-d1},[r2,: 128]
-	vld1.8 {d2-d3},[r4,: 128]!
-	vld1.8 {d4-d5},[r5,: 128]!
-	vzip.i32 q1,q2
-	vld1.8 {d6-d7},[r4,: 128]!
-	vld1.8 {d8-d9},[r5,: 128]!
-	vshl.i32 q5,q1,#1
-	vzip.i32 q3,q4
-	vshl.i32 q6,q2,#1
-	vld1.8 {d14},[r4,: 64]
-	vshl.i32 q8,q3,#1
-	vld1.8 {d15},[r5,: 64]
-	vshl.i32 q9,q4,#1
-	vmul.i32 d21,d7,d1
-	vtrn.32 d14,d15
-	vmul.i32 q11,q4,q0
-	vmul.i32 q0,q7,q0
-	vmull.s32 q12,d2,d2
-	vmlal.s32 q12,d11,d1
-	vmlal.s32 q12,d12,d0
-	vmlal.s32 q12,d13,d23
-	vmlal.s32 q12,d16,d22
-	vmlal.s32 q12,d7,d21
-	vmull.s32 q10,d2,d11
-	vmlal.s32 q10,d4,d1
-	vmlal.s32 q10,d13,d0
-	vmlal.s32 q10,d6,d23
-	vmlal.s32 q10,d17,d22
-	vmull.s32 q13,d10,d4
-	vmlal.s32 q13,d11,d3
-	vmlal.s32 q13,d13,d1
-	vmlal.s32 q13,d16,d0
-	vmlal.s32 q13,d17,d23
-	vmlal.s32 q13,d8,d22
-	vmull.s32 q1,d10,d5
-	vmlal.s32 q1,d11,d4
-	vmlal.s32 q1,d6,d1
-	vmlal.s32 q1,d17,d0
-	vmlal.s32 q1,d8,d23
-	vmull.s32 q14,d10,d6
-	vmlal.s32 q14,d11,d13
-	vmlal.s32 q14,d4,d4
-	vmlal.s32 q14,d17,d1
-	vmlal.s32 q14,d18,d0
-	vmlal.s32 q14,d9,d23
-	vmull.s32 q11,d10,d7
-	vmlal.s32 q11,d11,d6
-	vmlal.s32 q11,d12,d5
-	vmlal.s32 q11,d8,d1
-	vmlal.s32 q11,d19,d0
-	vmull.s32 q15,d10,d8
-	vmlal.s32 q15,d11,d17
-	vmlal.s32 q15,d12,d6
-	vmlal.s32 q15,d13,d5
-	vmlal.s32 q15,d19,d1
-	vmlal.s32 q15,d14,d0
-	vmull.s32 q2,d10,d9
-	vmlal.s32 q2,d11,d8
-	vmlal.s32 q2,d12,d7
-	vmlal.s32 q2,d13,d6
-	vmlal.s32 q2,d14,d1
-	vmull.s32 q0,d15,d1
-	vmlal.s32 q0,d10,d14
-	vmlal.s32 q0,d11,d19
-	vmlal.s32 q0,d12,d8
-	vmlal.s32 q0,d13,d17
-	vmlal.s32 q0,d6,d6
-	add r2,sp,#512
-	vld1.8 {d18-d19},[r2,: 128]
-	vmull.s32 q3,d16,d7
-	vmlal.s32 q3,d10,d15
-	vmlal.s32 q3,d11,d14
-	vmlal.s32 q3,d12,d9
-	vmlal.s32 q3,d13,d8
-	add r2,sp,#528
-	vld1.8 {d8-d9},[r2,: 128]
-	vadd.i64 q5,q12,q9
-	vadd.i64 q6,q15,q9
-	vshr.s64 q5,q5,#26
-	vshr.s64 q6,q6,#26
-	vadd.i64 q7,q10,q5
-	vshl.i64 q5,q5,#26
-	vadd.i64 q8,q7,q4
-	vadd.i64 q2,q2,q6
-	vshl.i64 q6,q6,#26
-	vadd.i64 q10,q2,q4
-	vsub.i64 q5,q12,q5
-	vshr.s64 q8,q8,#25
-	vsub.i64 q6,q15,q6
-	vshr.s64 q10,q10,#25
-	vadd.i64 q12,q13,q8
-	vshl.i64 q8,q8,#25
-	vadd.i64 q13,q12,q9
-	vadd.i64 q0,q0,q10
-	vsub.i64 q7,q7,q8
-	vshr.s64 q8,q13,#26
-	vshl.i64 q10,q10,#25
-	vadd.i64 q13,q0,q9
-	vadd.i64 q1,q1,q8
-	vshl.i64 q8,q8,#26
-	vadd.i64 q15,q1,q4
-	vsub.i64 q2,q2,q10
-	vshr.s64 q10,q13,#26
-	vsub.i64 q8,q12,q8
-	vshr.s64 q12,q15,#25
-	vadd.i64 q3,q3,q10
-	vshl.i64 q10,q10,#26
-	vadd.i64 q13,q3,q4
-	vadd.i64 q14,q14,q12
-	add r2,r3,#288
-	vshl.i64 q12,q12,#25
-	add r4,r3,#336
-	vadd.i64 q15,q14,q9
-	add r2,r2,#8
-	vsub.i64 q0,q0,q10
-	add r4,r4,#8
-	vshr.s64 q10,q13,#25
-	vsub.i64 q1,q1,q12
-	vshr.s64 q12,q15,#26
-	vadd.i64 q13,q10,q10
-	vadd.i64 q11,q11,q12
-	vtrn.32 d16,d2
-	vshl.i64 q12,q12,#26
-	vtrn.32 d17,d3
-	vadd.i64 q1,q11,q4
-	vadd.i64 q4,q5,q13
-	vst1.8 d16,[r2,: 64]!
-	vshl.i64 q5,q10,#4
-	vst1.8 d17,[r4,: 64]!
-	vsub.i64 q8,q14,q12
-	vshr.s64 q1,q1,#25
-	vadd.i64 q4,q4,q5
-	vadd.i64 q5,q6,q1
-	vshl.i64 q1,q1,#25
-	vadd.i64 q6,q5,q9
-	vadd.i64 q4,q4,q10
-	vshl.i64 q10,q10,#25
-	vadd.i64 q9,q4,q9
-	vsub.i64 q1,q11,q1
-	vshr.s64 q6,q6,#26
-	vsub.i64 q3,q3,q10
-	vtrn.32 d16,d2
-	vshr.s64 q9,q9,#26
-	vtrn.32 d17,d3
-	vadd.i64 q1,q2,q6
-	vst1.8 d16,[r2,: 64]
-	vshl.i64 q2,q6,#26
-	vst1.8 d17,[r4,: 64]
-	vadd.i64 q6,q7,q9
-	vtrn.32 d0,d6
-	vshl.i64 q7,q9,#26
-	vtrn.32 d1,d7
-	vsub.i64 q2,q5,q2
-	add r2,r2,#16
-	vsub.i64 q3,q4,q7
-	vst1.8 d0,[r2,: 64]
-	add r4,r4,#16
-	vst1.8 d1,[r4,: 64]
-	vtrn.32 d4,d2
-	vtrn.32 d5,d3
-	sub r2,r2,#8
-	sub r4,r4,#8
-	vtrn.32 d6,d12
-	vtrn.32 d7,d13
-	vst1.8 d4,[r2,: 64]
-	vst1.8 d5,[r4,: 64]
-	sub r2,r2,#24
-	sub r4,r4,#24
-	vst1.8 d6,[r2,: 64]
-	vst1.8 d7,[r4,: 64]
-	add r2,r3,#240
-	add r4,r3,#96
-	vld1.8 {d0-d1},[r4,: 128]!
-	vld1.8 {d2-d3},[r4,: 128]!
-	vld1.8 {d4},[r4,: 64]
-	add r4,r3,#144
-	vld1.8 {d6-d7},[r4,: 128]!
-	vtrn.32 q0,q3
-	vld1.8 {d8-d9},[r4,: 128]!
-	vshl.i32 q5,q0,#4
-	vtrn.32 q1,q4
-	vshl.i32 q6,q3,#4
-	vadd.i32 q5,q5,q0
-	vadd.i32 q6,q6,q3
-	vshl.i32 q7,q1,#4
-	vld1.8 {d5},[r4,: 64]
-	vshl.i32 q8,q4,#4
-	vtrn.32 d4,d5
-	vadd.i32 q7,q7,q1
-	vadd.i32 q8,q8,q4
-	vld1.8 {d18-d19},[r2,: 128]!
-	vshl.i32 q10,q2,#4
-	vld1.8 {d22-d23},[r2,: 128]!
-	vadd.i32 q10,q10,q2
-	vld1.8 {d24},[r2,: 64]
-	vadd.i32 q5,q5,q0
-	add r2,r3,#192
-	vld1.8 {d26-d27},[r2,: 128]!
-	vadd.i32 q6,q6,q3
-	vld1.8 {d28-d29},[r2,: 128]!
-	vadd.i32 q8,q8,q4
-	vld1.8 {d25},[r2,: 64]
-	vadd.i32 q10,q10,q2
-	vtrn.32 q9,q13
-	vadd.i32 q7,q7,q1
-	vadd.i32 q5,q5,q0
-	vtrn.32 q11,q14
-	vadd.i32 q6,q6,q3
-	add r2,sp,#560
-	vadd.i32 q10,q10,q2
-	vtrn.32 d24,d25
-	vst1.8 {d12-d13},[r2,: 128]
-	vshl.i32 q6,q13,#1
-	add r2,sp,#576
-	vst1.8 {d20-d21},[r2,: 128]
-	vshl.i32 q10,q14,#1
-	add r2,sp,#592
-	vst1.8 {d12-d13},[r2,: 128]
-	vshl.i32 q15,q12,#1
-	vadd.i32 q8,q8,q4
-	vext.32 d10,d31,d30,#0
-	vadd.i32 q7,q7,q1
-	add r2,sp,#608
-	vst1.8 {d16-d17},[r2,: 128]
-	vmull.s32 q8,d18,d5
-	vmlal.s32 q8,d26,d4
-	vmlal.s32 q8,d19,d9
-	vmlal.s32 q8,d27,d3
-	vmlal.s32 q8,d22,d8
-	vmlal.s32 q8,d28,d2
-	vmlal.s32 q8,d23,d7
-	vmlal.s32 q8,d29,d1
-	vmlal.s32 q8,d24,d6
-	vmlal.s32 q8,d25,d0
-	add r2,sp,#624
-	vst1.8 {d14-d15},[r2,: 128]
-	vmull.s32 q2,d18,d4
-	vmlal.s32 q2,d12,d9
-	vmlal.s32 q2,d13,d8
-	vmlal.s32 q2,d19,d3
-	vmlal.s32 q2,d22,d2
-	vmlal.s32 q2,d23,d1
-	vmlal.s32 q2,d24,d0
-	add r2,sp,#640
-	vst1.8 {d20-d21},[r2,: 128]
-	vmull.s32 q7,d18,d9
-	vmlal.s32 q7,d26,d3
-	vmlal.s32 q7,d19,d8
-	vmlal.s32 q7,d27,d2
-	vmlal.s32 q7,d22,d7
-	vmlal.s32 q7,d28,d1
-	vmlal.s32 q7,d23,d6
-	vmlal.s32 q7,d29,d0
-	add r2,sp,#656
-	vst1.8 {d10-d11},[r2,: 128]
-	vmull.s32 q5,d18,d3
-	vmlal.s32 q5,d19,d2
-	vmlal.s32 q5,d22,d1
-	vmlal.s32 q5,d23,d0
-	vmlal.s32 q5,d12,d8
-	add r2,sp,#672
-	vst1.8 {d16-d17},[r2,: 128]
-	vmull.s32 q4,d18,d8
-	vmlal.s32 q4,d26,d2
-	vmlal.s32 q4,d19,d7
-	vmlal.s32 q4,d27,d1
-	vmlal.s32 q4,d22,d6
-	vmlal.s32 q4,d28,d0
-	vmull.s32 q8,d18,d7
-	vmlal.s32 q8,d26,d1
-	vmlal.s32 q8,d19,d6
-	vmlal.s32 q8,d27,d0
-	add r2,sp,#576
-	vld1.8 {d20-d21},[r2,: 128]
-	vmlal.s32 q7,d24,d21
-	vmlal.s32 q7,d25,d20
-	vmlal.s32 q4,d23,d21
-	vmlal.s32 q4,d29,d20
-	vmlal.s32 q8,d22,d21
-	vmlal.s32 q8,d28,d20
-	vmlal.s32 q5,d24,d20
-	add r2,sp,#576
-	vst1.8 {d14-d15},[r2,: 128]
-	vmull.s32 q7,d18,d6
-	vmlal.s32 q7,d26,d0
-	add r2,sp,#656
-	vld1.8 {d30-d31},[r2,: 128]
-	vmlal.s32 q2,d30,d21
-	vmlal.s32 q7,d19,d21
-	vmlal.s32 q7,d27,d20
-	add r2,sp,#624
-	vld1.8 {d26-d27},[r2,: 128]
-	vmlal.s32 q4,d25,d27
-	vmlal.s32 q8,d29,d27
-	vmlal.s32 q8,d25,d26
-	vmlal.s32 q7,d28,d27
-	vmlal.s32 q7,d29,d26
-	add r2,sp,#608
-	vld1.8 {d28-d29},[r2,: 128]
-	vmlal.s32 q4,d24,d29
-	vmlal.s32 q8,d23,d29
-	vmlal.s32 q8,d24,d28
-	vmlal.s32 q7,d22,d29
-	vmlal.s32 q7,d23,d28
-	add r2,sp,#608
-	vst1.8 {d8-d9},[r2,: 128]
-	add r2,sp,#560
-	vld1.8 {d8-d9},[r2,: 128]
-	vmlal.s32 q7,d24,d9
-	vmlal.s32 q7,d25,d31
-	vmull.s32 q1,d18,d2
-	vmlal.s32 q1,d19,d1
-	vmlal.s32 q1,d22,d0
-	vmlal.s32 q1,d24,d27
-	vmlal.s32 q1,d23,d20
-	vmlal.s32 q1,d12,d7
-	vmlal.s32 q1,d13,d6
-	vmull.s32 q6,d18,d1
-	vmlal.s32 q6,d19,d0
-	vmlal.s32 q6,d23,d27
-	vmlal.s32 q6,d22,d20
-	vmlal.s32 q6,d24,d26
-	vmull.s32 q0,d18,d0
-	vmlal.s32 q0,d22,d27
-	vmlal.s32 q0,d23,d26
-	vmlal.s32 q0,d24,d31
-	vmlal.s32 q0,d19,d20
-	add r2,sp,#640
-	vld1.8 {d18-d19},[r2,: 128]
-	vmlal.s32 q2,d18,d7
-	vmlal.s32 q2,d19,d6
-	vmlal.s32 q5,d18,d6
-	vmlal.s32 q5,d19,d21
-	vmlal.s32 q1,d18,d21
-	vmlal.s32 q1,d19,d29
-	vmlal.s32 q0,d18,d28
-	vmlal.s32 q0,d19,d9
-	vmlal.s32 q6,d18,d29
-	vmlal.s32 q6,d19,d28
-	add r2,sp,#592
-	vld1.8 {d18-d19},[r2,: 128]
-	add r2,sp,#512
-	vld1.8 {d22-d23},[r2,: 128]
-	vmlal.s32 q5,d19,d7
-	vmlal.s32 q0,d18,d21
-	vmlal.s32 q0,d19,d29
-	vmlal.s32 q6,d18,d6
-	add r2,sp,#528
-	vld1.8 {d6-d7},[r2,: 128]
-	vmlal.s32 q6,d19,d21
-	add r2,sp,#576
-	vld1.8 {d18-d19},[r2,: 128]
-	vmlal.s32 q0,d30,d8
-	add r2,sp,#672
-	vld1.8 {d20-d21},[r2,: 128]
-	vmlal.s32 q5,d30,d29
-	add r2,sp,#608
-	vld1.8 {d24-d25},[r2,: 128]
-	vmlal.s32 q1,d30,d28
-	vadd.i64 q13,q0,q11
-	vadd.i64 q14,q5,q11
-	vmlal.s32 q6,d30,d9
-	vshr.s64 q4,q13,#26
-	vshr.s64 q13,q14,#26
-	vadd.i64 q7,q7,q4
-	vshl.i64 q4,q4,#26
-	vadd.i64 q14,q7,q3
-	vadd.i64 q9,q9,q13
-	vshl.i64 q13,q13,#26
-	vadd.i64 q15,q9,q3
-	vsub.i64 q0,q0,q4
-	vshr.s64 q4,q14,#25
-	vsub.i64 q5,q5,q13
-	vshr.s64 q13,q15,#25
-	vadd.i64 q6,q6,q4
-	vshl.i64 q4,q4,#25
-	vadd.i64 q14,q6,q11
-	vadd.i64 q2,q2,q13
-	vsub.i64 q4,q7,q4
-	vshr.s64 q7,q14,#26
-	vshl.i64 q13,q13,#25
-	vadd.i64 q14,q2,q11
-	vadd.i64 q8,q8,q7
-	vshl.i64 q7,q7,#26
-	vadd.i64 q15,q8,q3
-	vsub.i64 q9,q9,q13
-	vshr.s64 q13,q14,#26
-	vsub.i64 q6,q6,q7
-	vshr.s64 q7,q15,#25
-	vadd.i64 q10,q10,q13
-	vshl.i64 q13,q13,#26
-	vadd.i64 q14,q10,q3
-	vadd.i64 q1,q1,q7
-	add r2,r3,#144
-	vshl.i64 q7,q7,#25
-	add r4,r3,#96
-	vadd.i64 q15,q1,q11
-	add r2,r2,#8
-	vsub.i64 q2,q2,q13
-	add r4,r4,#8
-	vshr.s64 q13,q14,#25
-	vsub.i64 q7,q8,q7
-	vshr.s64 q8,q15,#26
-	vadd.i64 q14,q13,q13
-	vadd.i64 q12,q12,q8
-	vtrn.32 d12,d14
-	vshl.i64 q8,q8,#26
-	vtrn.32 d13,d15
-	vadd.i64 q3,q12,q3
-	vadd.i64 q0,q0,q14
-	vst1.8 d12,[r2,: 64]!
-	vshl.i64 q7,q13,#4
-	vst1.8 d13,[r4,: 64]!
-	vsub.i64 q1,q1,q8
-	vshr.s64 q3,q3,#25
-	vadd.i64 q0,q0,q7
-	vadd.i64 q5,q5,q3
-	vshl.i64 q3,q3,#25
-	vadd.i64 q6,q5,q11
-	vadd.i64 q0,q0,q13
-	vshl.i64 q7,q13,#25
-	vadd.i64 q8,q0,q11
-	vsub.i64 q3,q12,q3
-	vshr.s64 q6,q6,#26
-	vsub.i64 q7,q10,q7
-	vtrn.32 d2,d6
-	vshr.s64 q8,q8,#26
-	vtrn.32 d3,d7
-	vadd.i64 q3,q9,q6
-	vst1.8 d2,[r2,: 64]
-	vshl.i64 q6,q6,#26
-	vst1.8 d3,[r4,: 64]
-	vadd.i64 q1,q4,q8
-	vtrn.32 d4,d14
-	vshl.i64 q4,q8,#26
-	vtrn.32 d5,d15
-	vsub.i64 q5,q5,q6
-	add r2,r2,#16
-	vsub.i64 q0,q0,q4
-	vst1.8 d4,[r2,: 64]
-	add r4,r4,#16
-	vst1.8 d5,[r4,: 64]
-	vtrn.32 d10,d6
-	vtrn.32 d11,d7
-	sub r2,r2,#8
-	sub r4,r4,#8
-	vtrn.32 d0,d2
-	vtrn.32 d1,d3
-	vst1.8 d10,[r2,: 64]
-	vst1.8 d11,[r4,: 64]
-	sub r2,r2,#24
-	sub r4,r4,#24
-	vst1.8 d0,[r2,: 64]
-	vst1.8 d1,[r4,: 64]
-	add r2,r3,#288
-	add r4,r3,#336
-	vld1.8 {d0-d1},[r2,: 128]!
-	vld1.8 {d2-d3},[r4,: 128]!
-	vsub.i32 q0,q0,q1
-	vld1.8 {d2-d3},[r2,: 128]!
-	vld1.8 {d4-d5},[r4,: 128]!
-	vsub.i32 q1,q1,q2
-	add r5,r3,#240
-	vld1.8 {d4},[r2,: 64]
-	vld1.8 {d6},[r4,: 64]
-	vsub.i32 q2,q2,q3
-	vst1.8 {d0-d1},[r5,: 128]!
-	vst1.8 {d2-d3},[r5,: 128]!
-	vst1.8 d4,[r5,: 64]
-	add r2,r3,#144
-	add r4,r3,#96
-	add r5,r3,#144
-	add r6,r3,#192
-	vld1.8 {d0-d1},[r2,: 128]!
-	vld1.8 {d2-d3},[r4,: 128]!
-	vsub.i32 q2,q0,q1
-	vadd.i32 q0,q0,q1
-	vld1.8 {d2-d3},[r2,: 128]!
-	vld1.8 {d6-d7},[r4,: 128]!
-	vsub.i32 q4,q1,q3
-	vadd.i32 q1,q1,q3
-	vld1.8 {d6},[r2,: 64]
-	vld1.8 {d10},[r4,: 64]
-	vsub.i32 q6,q3,q5
-	vadd.i32 q3,q3,q5
-	vst1.8 {d4-d5},[r5,: 128]!
-	vst1.8 {d0-d1},[r6,: 128]!
-	vst1.8 {d8-d9},[r5,: 128]!
-	vst1.8 {d2-d3},[r6,: 128]!
-	vst1.8 d12,[r5,: 64]
-	vst1.8 d6,[r6,: 64]
-	add r2,r3,#0
-	add r4,r3,#240
-	vld1.8 {d0-d1},[r4,: 128]!
-	vld1.8 {d2-d3},[r4,: 128]!
-	vld1.8 {d4},[r4,: 64]
-	add r4,r3,#336
-	vld1.8 {d6-d7},[r4,: 128]!
-	vtrn.32 q0,q3
-	vld1.8 {d8-d9},[r4,: 128]!
-	vshl.i32 q5,q0,#4
-	vtrn.32 q1,q4
-	vshl.i32 q6,q3,#4
-	vadd.i32 q5,q5,q0
-	vadd.i32 q6,q6,q3
-	vshl.i32 q7,q1,#4
-	vld1.8 {d5},[r4,: 64]
-	vshl.i32 q8,q4,#4
-	vtrn.32 d4,d5
-	vadd.i32 q7,q7,q1
-	vadd.i32 q8,q8,q4
-	vld1.8 {d18-d19},[r2,: 128]!
-	vshl.i32 q10,q2,#4
-	vld1.8 {d22-d23},[r2,: 128]!
-	vadd.i32 q10,q10,q2
-	vld1.8 {d24},[r2,: 64]
-	vadd.i32 q5,q5,q0
-	add r2,r3,#288
-	vld1.8 {d26-d27},[r2,: 128]!
-	vadd.i32 q6,q6,q3
-	vld1.8 {d28-d29},[r2,: 128]!
-	vadd.i32 q8,q8,q4
-	vld1.8 {d25},[r2,: 64]
-	vadd.i32 q10,q10,q2
-	vtrn.32 q9,q13
-	vadd.i32 q7,q7,q1
-	vadd.i32 q5,q5,q0
-	vtrn.32 q11,q14
-	vadd.i32 q6,q6,q3
-	add r2,sp,#560
-	vadd.i32 q10,q10,q2
-	vtrn.32 d24,d25
-	vst1.8 {d12-d13},[r2,: 128]
-	vshl.i32 q6,q13,#1
-	add r2,sp,#576
-	vst1.8 {d20-d21},[r2,: 128]
-	vshl.i32 q10,q14,#1
-	add r2,sp,#592
-	vst1.8 {d12-d13},[r2,: 128]
-	vshl.i32 q15,q12,#1
-	vadd.i32 q8,q8,q4
-	vext.32 d10,d31,d30,#0
-	vadd.i32 q7,q7,q1
-	add r2,sp,#608
-	vst1.8 {d16-d17},[r2,: 128]
-	vmull.s32 q8,d18,d5
-	vmlal.s32 q8,d26,d4
-	vmlal.s32 q8,d19,d9
-	vmlal.s32 q8,d27,d3
-	vmlal.s32 q8,d22,d8
-	vmlal.s32 q8,d28,d2
-	vmlal.s32 q8,d23,d7
-	vmlal.s32 q8,d29,d1
-	vmlal.s32 q8,d24,d6
-	vmlal.s32 q8,d25,d0
-	add r2,sp,#624
-	vst1.8 {d14-d15},[r2,: 128]
-	vmull.s32 q2,d18,d4
-	vmlal.s32 q2,d12,d9
-	vmlal.s32 q2,d13,d8
-	vmlal.s32 q2,d19,d3
-	vmlal.s32 q2,d22,d2
-	vmlal.s32 q2,d23,d1
-	vmlal.s32 q2,d24,d0
-	add r2,sp,#640
-	vst1.8 {d20-d21},[r2,: 128]
-	vmull.s32 q7,d18,d9
-	vmlal.s32 q7,d26,d3
-	vmlal.s32 q7,d19,d8
-	vmlal.s32 q7,d27,d2
-	vmlal.s32 q7,d22,d7
-	vmlal.s32 q7,d28,d1
-	vmlal.s32 q7,d23,d6
-	vmlal.s32 q7,d29,d0
-	add r2,sp,#656
-	vst1.8 {d10-d11},[r2,: 128]
-	vmull.s32 q5,d18,d3
-	vmlal.s32 q5,d19,d2
-	vmlal.s32 q5,d22,d1
-	vmlal.s32 q5,d23,d0
-	vmlal.s32 q5,d12,d8
-	add r2,sp,#672
-	vst1.8 {d16-d17},[r2,: 128]
-	vmull.s32 q4,d18,d8
-	vmlal.s32 q4,d26,d2
-	vmlal.s32 q4,d19,d7
-	vmlal.s32 q4,d27,d1
-	vmlal.s32 q4,d22,d6
-	vmlal.s32 q4,d28,d0
-	vmull.s32 q8,d18,d7
-	vmlal.s32 q8,d26,d1
-	vmlal.s32 q8,d19,d6
-	vmlal.s32 q8,d27,d0
-	add r2,sp,#576
-	vld1.8 {d20-d21},[r2,: 128]
-	vmlal.s32 q7,d24,d21
-	vmlal.s32 q7,d25,d20
-	vmlal.s32 q4,d23,d21
-	vmlal.s32 q4,d29,d20
-	vmlal.s32 q8,d22,d21
-	vmlal.s32 q8,d28,d20
-	vmlal.s32 q5,d24,d20
-	add r2,sp,#576
-	vst1.8 {d14-d15},[r2,: 128]
-	vmull.s32 q7,d18,d6
-	vmlal.s32 q7,d26,d0
-	add r2,sp,#656
-	vld1.8 {d30-d31},[r2,: 128]
-	vmlal.s32 q2,d30,d21
-	vmlal.s32 q7,d19,d21
-	vmlal.s32 q7,d27,d20
-	add r2,sp,#624
-	vld1.8 {d26-d27},[r2,: 128]
-	vmlal.s32 q4,d25,d27
-	vmlal.s32 q8,d29,d27
-	vmlal.s32 q8,d25,d26
-	vmlal.s32 q7,d28,d27
-	vmlal.s32 q7,d29,d26
-	add r2,sp,#608
-	vld1.8 {d28-d29},[r2,: 128]
-	vmlal.s32 q4,d24,d29
-	vmlal.s32 q8,d23,d29
-	vmlal.s32 q8,d24,d28
-	vmlal.s32 q7,d22,d29
-	vmlal.s32 q7,d23,d28
-	add r2,sp,#608
-	vst1.8 {d8-d9},[r2,: 128]
-	add r2,sp,#560
-	vld1.8 {d8-d9},[r2,: 128]
-	vmlal.s32 q7,d24,d9
-	vmlal.s32 q7,d25,d31
-	vmull.s32 q1,d18,d2
-	vmlal.s32 q1,d19,d1
-	vmlal.s32 q1,d22,d0
-	vmlal.s32 q1,d24,d27
-	vmlal.s32 q1,d23,d20
-	vmlal.s32 q1,d12,d7
-	vmlal.s32 q1,d13,d6
-	vmull.s32 q6,d18,d1
-	vmlal.s32 q6,d19,d0
-	vmlal.s32 q6,d23,d27
-	vmlal.s32 q6,d22,d20
-	vmlal.s32 q6,d24,d26
-	vmull.s32 q0,d18,d0
-	vmlal.s32 q0,d22,d27
-	vmlal.s32 q0,d23,d26
-	vmlal.s32 q0,d24,d31
-	vmlal.s32 q0,d19,d20
-	add r2,sp,#640
-	vld1.8 {d18-d19},[r2,: 128]
-	vmlal.s32 q2,d18,d7
-	vmlal.s32 q2,d19,d6
-	vmlal.s32 q5,d18,d6
-	vmlal.s32 q5,d19,d21
-	vmlal.s32 q1,d18,d21
-	vmlal.s32 q1,d19,d29
-	vmlal.s32 q0,d18,d28
-	vmlal.s32 q0,d19,d9
-	vmlal.s32 q6,d18,d29
-	vmlal.s32 q6,d19,d28
-	add r2,sp,#592
-	vld1.8 {d18-d19},[r2,: 128]
-	add r2,sp,#512
-	vld1.8 {d22-d23},[r2,: 128]
-	vmlal.s32 q5,d19,d7
-	vmlal.s32 q0,d18,d21
-	vmlal.s32 q0,d19,d29
-	vmlal.s32 q6,d18,d6
-	add r2,sp,#528
-	vld1.8 {d6-d7},[r2,: 128]
-	vmlal.s32 q6,d19,d21
-	add r2,sp,#576
-	vld1.8 {d18-d19},[r2,: 128]
-	vmlal.s32 q0,d30,d8
-	add r2,sp,#672
-	vld1.8 {d20-d21},[r2,: 128]
-	vmlal.s32 q5,d30,d29
-	add r2,sp,#608
-	vld1.8 {d24-d25},[r2,: 128]
-	vmlal.s32 q1,d30,d28
-	vadd.i64 q13,q0,q11
-	vadd.i64 q14,q5,q11
-	vmlal.s32 q6,d30,d9
-	vshr.s64 q4,q13,#26
-	vshr.s64 q13,q14,#26
-	vadd.i64 q7,q7,q4
-	vshl.i64 q4,q4,#26
-	vadd.i64 q14,q7,q3
-	vadd.i64 q9,q9,q13
-	vshl.i64 q13,q13,#26
-	vadd.i64 q15,q9,q3
-	vsub.i64 q0,q0,q4
-	vshr.s64 q4,q14,#25
-	vsub.i64 q5,q5,q13
-	vshr.s64 q13,q15,#25
-	vadd.i64 q6,q6,q4
-	vshl.i64 q4,q4,#25
-	vadd.i64 q14,q6,q11
-	vadd.i64 q2,q2,q13
-	vsub.i64 q4,q7,q4
-	vshr.s64 q7,q14,#26
-	vshl.i64 q13,q13,#25
-	vadd.i64 q14,q2,q11
-	vadd.i64 q8,q8,q7
-	vshl.i64 q7,q7,#26
-	vadd.i64 q15,q8,q3
-	vsub.i64 q9,q9,q13
-	vshr.s64 q13,q14,#26
-	vsub.i64 q6,q6,q7
-	vshr.s64 q7,q15,#25
-	vadd.i64 q10,q10,q13
-	vshl.i64 q13,q13,#26
-	vadd.i64 q14,q10,q3
-	vadd.i64 q1,q1,q7
-	add r2,r3,#288
-	vshl.i64 q7,q7,#25
-	add r4,r3,#96
-	vadd.i64 q15,q1,q11
-	add r2,r2,#8
-	vsub.i64 q2,q2,q13
-	add r4,r4,#8
-	vshr.s64 q13,q14,#25
-	vsub.i64 q7,q8,q7
-	vshr.s64 q8,q15,#26
-	vadd.i64 q14,q13,q13
-	vadd.i64 q12,q12,q8
-	vtrn.32 d12,d14
-	vshl.i64 q8,q8,#26
-	vtrn.32 d13,d15
-	vadd.i64 q3,q12,q3
-	vadd.i64 q0,q0,q14
-	vst1.8 d12,[r2,: 64]!
-	vshl.i64 q7,q13,#4
-	vst1.8 d13,[r4,: 64]!
-	vsub.i64 q1,q1,q8
-	vshr.s64 q3,q3,#25
-	vadd.i64 q0,q0,q7
-	vadd.i64 q5,q5,q3
-	vshl.i64 q3,q3,#25
-	vadd.i64 q6,q5,q11
-	vadd.i64 q0,q0,q13
-	vshl.i64 q7,q13,#25
-	vadd.i64 q8,q0,q11
-	vsub.i64 q3,q12,q3
-	vshr.s64 q6,q6,#26
-	vsub.i64 q7,q10,q7
-	vtrn.32 d2,d6
-	vshr.s64 q8,q8,#26
-	vtrn.32 d3,d7
-	vadd.i64 q3,q9,q6
-	vst1.8 d2,[r2,: 64]
-	vshl.i64 q6,q6,#26
-	vst1.8 d3,[r4,: 64]
-	vadd.i64 q1,q4,q8
-	vtrn.32 d4,d14
-	vshl.i64 q4,q8,#26
-	vtrn.32 d5,d15
-	vsub.i64 q5,q5,q6
-	add r2,r2,#16
-	vsub.i64 q0,q0,q4
-	vst1.8 d4,[r2,: 64]
-	add r4,r4,#16
-	vst1.8 d5,[r4,: 64]
-	vtrn.32 d10,d6
-	vtrn.32 d11,d7
-	sub r2,r2,#8
-	sub r4,r4,#8
-	vtrn.32 d0,d2
-	vtrn.32 d1,d3
-	vst1.8 d10,[r2,: 64]
-	vst1.8 d11,[r4,: 64]
-	sub r2,r2,#24
-	sub r4,r4,#24
-	vst1.8 d0,[r2,: 64]
-	vst1.8 d1,[r4,: 64]
-	add r2,sp,#544
-	add r4,r3,#144
-	add r5,r3,#192
-	vld1.8 {d0-d1},[r2,: 128]
-	vld1.8 {d2-d3},[r4,: 128]!
-	vld1.8 {d4-d5},[r5,: 128]!
-	vzip.i32 q1,q2
-	vld1.8 {d6-d7},[r4,: 128]!
-	vld1.8 {d8-d9},[r5,: 128]!
-	vshl.i32 q5,q1,#1
-	vzip.i32 q3,q4
-	vshl.i32 q6,q2,#1
-	vld1.8 {d14},[r4,: 64]
-	vshl.i32 q8,q3,#1
-	vld1.8 {d15},[r5,: 64]
-	vshl.i32 q9,q4,#1
-	vmul.i32 d21,d7,d1
-	vtrn.32 d14,d15
-	vmul.i32 q11,q4,q0
-	vmul.i32 q0,q7,q0
-	vmull.s32 q12,d2,d2
-	vmlal.s32 q12,d11,d1
-	vmlal.s32 q12,d12,d0
-	vmlal.s32 q12,d13,d23
-	vmlal.s32 q12,d16,d22
-	vmlal.s32 q12,d7,d21
-	vmull.s32 q10,d2,d11
-	vmlal.s32 q10,d4,d1
-	vmlal.s32 q10,d13,d0
-	vmlal.s32 q10,d6,d23
-	vmlal.s32 q10,d17,d22
-	vmull.s32 q13,d10,d4
-	vmlal.s32 q13,d11,d3
-	vmlal.s32 q13,d13,d1
-	vmlal.s32 q13,d16,d0
-	vmlal.s32 q13,d17,d23
-	vmlal.s32 q13,d8,d22
-	vmull.s32 q1,d10,d5
-	vmlal.s32 q1,d11,d4
-	vmlal.s32 q1,d6,d1
-	vmlal.s32 q1,d17,d0
-	vmlal.s32 q1,d8,d23
-	vmull.s32 q14,d10,d6
-	vmlal.s32 q14,d11,d13
-	vmlal.s32 q14,d4,d4
-	vmlal.s32 q14,d17,d1
-	vmlal.s32 q14,d18,d0
-	vmlal.s32 q14,d9,d23
-	vmull.s32 q11,d10,d7
-	vmlal.s32 q11,d11,d6
-	vmlal.s32 q11,d12,d5
-	vmlal.s32 q11,d8,d1
-	vmlal.s32 q11,d19,d0
-	vmull.s32 q15,d10,d8
-	vmlal.s32 q15,d11,d17
-	vmlal.s32 q15,d12,d6
-	vmlal.s32 q15,d13,d5
-	vmlal.s32 q15,d19,d1
-	vmlal.s32 q15,d14,d0
-	vmull.s32 q2,d10,d9
-	vmlal.s32 q2,d11,d8
-	vmlal.s32 q2,d12,d7
-	vmlal.s32 q2,d13,d6
-	vmlal.s32 q2,d14,d1
-	vmull.s32 q0,d15,d1
-	vmlal.s32 q0,d10,d14
-	vmlal.s32 q0,d11,d19
-	vmlal.s32 q0,d12,d8
-	vmlal.s32 q0,d13,d17
-	vmlal.s32 q0,d6,d6
-	add r2,sp,#512
-	vld1.8 {d18-d19},[r2,: 128]
-	vmull.s32 q3,d16,d7
-	vmlal.s32 q3,d10,d15
-	vmlal.s32 q3,d11,d14
-	vmlal.s32 q3,d12,d9
-	vmlal.s32 q3,d13,d8
-	add r2,sp,#528
-	vld1.8 {d8-d9},[r2,: 128]
-	vadd.i64 q5,q12,q9
-	vadd.i64 q6,q15,q9
-	vshr.s64 q5,q5,#26
-	vshr.s64 q6,q6,#26
-	vadd.i64 q7,q10,q5
-	vshl.i64 q5,q5,#26
-	vadd.i64 q8,q7,q4
-	vadd.i64 q2,q2,q6
-	vshl.i64 q6,q6,#26
-	vadd.i64 q10,q2,q4
-	vsub.i64 q5,q12,q5
-	vshr.s64 q8,q8,#25
-	vsub.i64 q6,q15,q6
-	vshr.s64 q10,q10,#25
-	vadd.i64 q12,q13,q8
-	vshl.i64 q8,q8,#25
-	vadd.i64 q13,q12,q9
-	vadd.i64 q0,q0,q10
-	vsub.i64 q7,q7,q8
-	vshr.s64 q8,q13,#26
-	vshl.i64 q10,q10,#25
-	vadd.i64 q13,q0,q9
-	vadd.i64 q1,q1,q8
-	vshl.i64 q8,q8,#26
-	vadd.i64 q15,q1,q4
-	vsub.i64 q2,q2,q10
-	vshr.s64 q10,q13,#26
-	vsub.i64 q8,q12,q8
-	vshr.s64 q12,q15,#25
-	vadd.i64 q3,q3,q10
-	vshl.i64 q10,q10,#26
-	vadd.i64 q13,q3,q4
-	vadd.i64 q14,q14,q12
-	add r2,r3,#144
-	vshl.i64 q12,q12,#25
-	add r4,r3,#192
-	vadd.i64 q15,q14,q9
-	add r2,r2,#8
-	vsub.i64 q0,q0,q10
-	add r4,r4,#8
-	vshr.s64 q10,q13,#25
-	vsub.i64 q1,q1,q12
-	vshr.s64 q12,q15,#26
-	vadd.i64 q13,q10,q10
-	vadd.i64 q11,q11,q12
-	vtrn.32 d16,d2
-	vshl.i64 q12,q12,#26
-	vtrn.32 d17,d3
-	vadd.i64 q1,q11,q4
-	vadd.i64 q4,q5,q13
-	vst1.8 d16,[r2,: 64]!
-	vshl.i64 q5,q10,#4
-	vst1.8 d17,[r4,: 64]!
-	vsub.i64 q8,q14,q12
-	vshr.s64 q1,q1,#25
-	vadd.i64 q4,q4,q5
-	vadd.i64 q5,q6,q1
-	vshl.i64 q1,q1,#25
-	vadd.i64 q6,q5,q9
-	vadd.i64 q4,q4,q10
-	vshl.i64 q10,q10,#25
-	vadd.i64 q9,q4,q9
-	vsub.i64 q1,q11,q1
-	vshr.s64 q6,q6,#26
-	vsub.i64 q3,q3,q10
-	vtrn.32 d16,d2
-	vshr.s64 q9,q9,#26
-	vtrn.32 d17,d3
-	vadd.i64 q1,q2,q6
-	vst1.8 d16,[r2,: 64]
-	vshl.i64 q2,q6,#26
-	vst1.8 d17,[r4,: 64]
-	vadd.i64 q6,q7,q9
-	vtrn.32 d0,d6
-	vshl.i64 q7,q9,#26
-	vtrn.32 d1,d7
-	vsub.i64 q2,q5,q2
-	add r2,r2,#16
-	vsub.i64 q3,q4,q7
-	vst1.8 d0,[r2,: 64]
-	add r4,r4,#16
-	vst1.8 d1,[r4,: 64]
-	vtrn.32 d4,d2
-	vtrn.32 d5,d3
-	sub r2,r2,#8
-	sub r4,r4,#8
-	vtrn.32 d6,d12
-	vtrn.32 d7,d13
-	vst1.8 d4,[r2,: 64]
-	vst1.8 d5,[r4,: 64]
-	sub r2,r2,#24
-	sub r4,r4,#24
-	vst1.8 d6,[r2,: 64]
-	vst1.8 d7,[r4,: 64]
-	add r2,r3,#336
-	add r4,r3,#288
-	vld1.8 {d0-d1},[r2,: 128]!
-	vld1.8 {d2-d3},[r4,: 128]!
-	vadd.i32 q0,q0,q1
-	vld1.8 {d2-d3},[r2,: 128]!
-	vld1.8 {d4-d5},[r4,: 128]!
-	vadd.i32 q1,q1,q2
-	add r5,r3,#288
-	vld1.8 {d4},[r2,: 64]
-	vld1.8 {d6},[r4,: 64]
-	vadd.i32 q2,q2,q3
-	vst1.8 {d0-d1},[r5,: 128]!
-	vst1.8 {d2-d3},[r5,: 128]!
-	vst1.8 d4,[r5,: 64]
-	add r2,r3,#48
-	add r4,r3,#144
-	vld1.8 {d0-d1},[r4,: 128]!
-	vld1.8 {d2-d3},[r4,: 128]!
-	vld1.8 {d4},[r4,: 64]
-	add r4,r3,#288
-	vld1.8 {d6-d7},[r4,: 128]!
-	vtrn.32 q0,q3
-	vld1.8 {d8-d9},[r4,: 128]!
-	vshl.i32 q5,q0,#4
-	vtrn.32 q1,q4
-	vshl.i32 q6,q3,#4
-	vadd.i32 q5,q5,q0
-	vadd.i32 q6,q6,q3
-	vshl.i32 q7,q1,#4
-	vld1.8 {d5},[r4,: 64]
-	vshl.i32 q8,q4,#4
-	vtrn.32 d4,d5
-	vadd.i32 q7,q7,q1
-	vadd.i32 q8,q8,q4
-	vld1.8 {d18-d19},[r2,: 128]!
-	vshl.i32 q10,q2,#4
-	vld1.8 {d22-d23},[r2,: 128]!
-	vadd.i32 q10,q10,q2
-	vld1.8 {d24},[r2,: 64]
-	vadd.i32 q5,q5,q0
-	add r2,r3,#240
-	vld1.8 {d26-d27},[r2,: 128]!
-	vadd.i32 q6,q6,q3
-	vld1.8 {d28-d29},[r2,: 128]!
-	vadd.i32 q8,q8,q4
-	vld1.8 {d25},[r2,: 64]
-	vadd.i32 q10,q10,q2
-	vtrn.32 q9,q13
-	vadd.i32 q7,q7,q1
-	vadd.i32 q5,q5,q0
-	vtrn.32 q11,q14
-	vadd.i32 q6,q6,q3
-	add r2,sp,#560
-	vadd.i32 q10,q10,q2
-	vtrn.32 d24,d25
-	vst1.8 {d12-d13},[r2,: 128]
-	vshl.i32 q6,q13,#1
-	add r2,sp,#576
-	vst1.8 {d20-d21},[r2,: 128]
-	vshl.i32 q10,q14,#1
-	add r2,sp,#592
-	vst1.8 {d12-d13},[r2,: 128]
-	vshl.i32 q15,q12,#1
-	vadd.i32 q8,q8,q4
-	vext.32 d10,d31,d30,#0
-	vadd.i32 q7,q7,q1
-	add r2,sp,#608
-	vst1.8 {d16-d17},[r2,: 128]
-	vmull.s32 q8,d18,d5
-	vmlal.s32 q8,d26,d4
-	vmlal.s32 q8,d19,d9
-	vmlal.s32 q8,d27,d3
-	vmlal.s32 q8,d22,d8
-	vmlal.s32 q8,d28,d2
-	vmlal.s32 q8,d23,d7
-	vmlal.s32 q8,d29,d1
-	vmlal.s32 q8,d24,d6
-	vmlal.s32 q8,d25,d0
-	add r2,sp,#624
-	vst1.8 {d14-d15},[r2,: 128]
-	vmull.s32 q2,d18,d4
-	vmlal.s32 q2,d12,d9
-	vmlal.s32 q2,d13,d8
-	vmlal.s32 q2,d19,d3
-	vmlal.s32 q2,d22,d2
-	vmlal.s32 q2,d23,d1
-	vmlal.s32 q2,d24,d0
-	add r2,sp,#640
-	vst1.8 {d20-d21},[r2,: 128]
-	vmull.s32 q7,d18,d9
-	vmlal.s32 q7,d26,d3
-	vmlal.s32 q7,d19,d8
-	vmlal.s32 q7,d27,d2
-	vmlal.s32 q7,d22,d7
-	vmlal.s32 q7,d28,d1
-	vmlal.s32 q7,d23,d6
-	vmlal.s32 q7,d29,d0
-	add r2,sp,#656
-	vst1.8 {d10-d11},[r2,: 128]
-	vmull.s32 q5,d18,d3
-	vmlal.s32 q5,d19,d2
-	vmlal.s32 q5,d22,d1
-	vmlal.s32 q5,d23,d0
-	vmlal.s32 q5,d12,d8
-	add r2,sp,#672
-	vst1.8 {d16-d17},[r2,: 128]
-	vmull.s32 q4,d18,d8
-	vmlal.s32 q4,d26,d2
-	vmlal.s32 q4,d19,d7
-	vmlal.s32 q4,d27,d1
-	vmlal.s32 q4,d22,d6
-	vmlal.s32 q4,d28,d0
-	vmull.s32 q8,d18,d7
-	vmlal.s32 q8,d26,d1
-	vmlal.s32 q8,d19,d6
-	vmlal.s32 q8,d27,d0
-	add r2,sp,#576
-	vld1.8 {d20-d21},[r2,: 128]
-	vmlal.s32 q7,d24,d21
-	vmlal.s32 q7,d25,d20
-	vmlal.s32 q4,d23,d21
-	vmlal.s32 q4,d29,d20
-	vmlal.s32 q8,d22,d21
-	vmlal.s32 q8,d28,d20
-	vmlal.s32 q5,d24,d20
-	add r2,sp,#576
-	vst1.8 {d14-d15},[r2,: 128]
-	vmull.s32 q7,d18,d6
-	vmlal.s32 q7,d26,d0
-	add r2,sp,#656
-	vld1.8 {d30-d31},[r2,: 128]
-	vmlal.s32 q2,d30,d21
-	vmlal.s32 q7,d19,d21
-	vmlal.s32 q7,d27,d20
-	add r2,sp,#624
-	vld1.8 {d26-d27},[r2,: 128]
-	vmlal.s32 q4,d25,d27
-	vmlal.s32 q8,d29,d27
-	vmlal.s32 q8,d25,d26
-	vmlal.s32 q7,d28,d27
-	vmlal.s32 q7,d29,d26
-	add r2,sp,#608
-	vld1.8 {d28-d29},[r2,: 128]
-	vmlal.s32 q4,d24,d29
-	vmlal.s32 q8,d23,d29
-	vmlal.s32 q8,d24,d28
-	vmlal.s32 q7,d22,d29
-	vmlal.s32 q7,d23,d28
-	add r2,sp,#608
-	vst1.8 {d8-d9},[r2,: 128]
-	add r2,sp,#560
-	vld1.8 {d8-d9},[r2,: 128]
-	vmlal.s32 q7,d24,d9
-	vmlal.s32 q7,d25,d31
-	vmull.s32 q1,d18,d2
-	vmlal.s32 q1,d19,d1
-	vmlal.s32 q1,d22,d0
-	vmlal.s32 q1,d24,d27
-	vmlal.s32 q1,d23,d20
-	vmlal.s32 q1,d12,d7
-	vmlal.s32 q1,d13,d6
-	vmull.s32 q6,d18,d1
-	vmlal.s32 q6,d19,d0
-	vmlal.s32 q6,d23,d27
-	vmlal.s32 q6,d22,d20
-	vmlal.s32 q6,d24,d26
-	vmull.s32 q0,d18,d0
-	vmlal.s32 q0,d22,d27
-	vmlal.s32 q0,d23,d26
-	vmlal.s32 q0,d24,d31
-	vmlal.s32 q0,d19,d20
-	add r2,sp,#640
-	vld1.8 {d18-d19},[r2,: 128]
-	vmlal.s32 q2,d18,d7
-	vmlal.s32 q2,d19,d6
-	vmlal.s32 q5,d18,d6
-	vmlal.s32 q5,d19,d21
-	vmlal.s32 q1,d18,d21
-	vmlal.s32 q1,d19,d29
-	vmlal.s32 q0,d18,d28
-	vmlal.s32 q0,d19,d9
-	vmlal.s32 q6,d18,d29
-	vmlal.s32 q6,d19,d28
-	add r2,sp,#592
-	vld1.8 {d18-d19},[r2,: 128]
-	add r2,sp,#512
-	vld1.8 {d22-d23},[r2,: 128]
-	vmlal.s32 q5,d19,d7
-	vmlal.s32 q0,d18,d21
-	vmlal.s32 q0,d19,d29
-	vmlal.s32 q6,d18,d6
-	add r2,sp,#528
-	vld1.8 {d6-d7},[r2,: 128]
-	vmlal.s32 q6,d19,d21
-	add r2,sp,#576
-	vld1.8 {d18-d19},[r2,: 128]
-	vmlal.s32 q0,d30,d8
-	add r2,sp,#672
-	vld1.8 {d20-d21},[r2,: 128]
-	vmlal.s32 q5,d30,d29
-	add r2,sp,#608
-	vld1.8 {d24-d25},[r2,: 128]
-	vmlal.s32 q1,d30,d28
-	vadd.i64 q13,q0,q11
-	vadd.i64 q14,q5,q11
-	vmlal.s32 q6,d30,d9
-	vshr.s64 q4,q13,#26
-	vshr.s64 q13,q14,#26
-	vadd.i64 q7,q7,q4
-	vshl.i64 q4,q4,#26
-	vadd.i64 q14,q7,q3
-	vadd.i64 q9,q9,q13
-	vshl.i64 q13,q13,#26
-	vadd.i64 q15,q9,q3
-	vsub.i64 q0,q0,q4
-	vshr.s64 q4,q14,#25
-	vsub.i64 q5,q5,q13
-	vshr.s64 q13,q15,#25
-	vadd.i64 q6,q6,q4
-	vshl.i64 q4,q4,#25
-	vadd.i64 q14,q6,q11
-	vadd.i64 q2,q2,q13
-	vsub.i64 q4,q7,q4
-	vshr.s64 q7,q14,#26
-	vshl.i64 q13,q13,#25
-	vadd.i64 q14,q2,q11
-	vadd.i64 q8,q8,q7
-	vshl.i64 q7,q7,#26
-	vadd.i64 q15,q8,q3
-	vsub.i64 q9,q9,q13
-	vshr.s64 q13,q14,#26
-	vsub.i64 q6,q6,q7
-	vshr.s64 q7,q15,#25
-	vadd.i64 q10,q10,q13
-	vshl.i64 q13,q13,#26
-	vadd.i64 q14,q10,q3
-	vadd.i64 q1,q1,q7
-	add r2,r3,#240
-	vshl.i64 q7,q7,#25
-	add r4,r3,#144
-	vadd.i64 q15,q1,q11
-	add r2,r2,#8
-	vsub.i64 q2,q2,q13
-	add r4,r4,#8
-	vshr.s64 q13,q14,#25
-	vsub.i64 q7,q8,q7
-	vshr.s64 q8,q15,#26
-	vadd.i64 q14,q13,q13
-	vadd.i64 q12,q12,q8
-	vtrn.32 d12,d14
-	vshl.i64 q8,q8,#26
-	vtrn.32 d13,d15
-	vadd.i64 q3,q12,q3
-	vadd.i64 q0,q0,q14
-	vst1.8 d12,[r2,: 64]!
-	vshl.i64 q7,q13,#4
-	vst1.8 d13,[r4,: 64]!
-	vsub.i64 q1,q1,q8
-	vshr.s64 q3,q3,#25
-	vadd.i64 q0,q0,q7
-	vadd.i64 q5,q5,q3
-	vshl.i64 q3,q3,#25
-	vadd.i64 q6,q5,q11
-	vadd.i64 q0,q0,q13
-	vshl.i64 q7,q13,#25
-	vadd.i64 q8,q0,q11
-	vsub.i64 q3,q12,q3
-	vshr.s64 q6,q6,#26
-	vsub.i64 q7,q10,q7
-	vtrn.32 d2,d6
-	vshr.s64 q8,q8,#26
-	vtrn.32 d3,d7
-	vadd.i64 q3,q9,q6
-	vst1.8 d2,[r2,: 64]
-	vshl.i64 q6,q6,#26
-	vst1.8 d3,[r4,: 64]
-	vadd.i64 q1,q4,q8
-	vtrn.32 d4,d14
-	vshl.i64 q4,q8,#26
-	vtrn.32 d5,d15
-	vsub.i64 q5,q5,q6
-	add r2,r2,#16
-	vsub.i64 q0,q0,q4
-	vst1.8 d4,[r2,: 64]
-	add r4,r4,#16
-	vst1.8 d5,[r4,: 64]
-	vtrn.32 d10,d6
-	vtrn.32 d11,d7
-	sub r2,r2,#8
-	sub r4,r4,#8
-	vtrn.32 d0,d2
-	vtrn.32 d1,d3
-	vst1.8 d10,[r2,: 64]
-	vst1.8 d11,[r4,: 64]
-	sub r2,r2,#24
-	sub r4,r4,#24
-	vst1.8 d0,[r2,: 64]
-	vst1.8 d1,[r4,: 64]
-	ldr r2,[sp,#488]
-	ldr r4,[sp,#492]
-	subs r5,r2,#1
-	bge .Lmainloop
-	add r1,r3,#144
-	add r2,r3,#336
-	vld1.8 {d0-d1},[r1,: 128]!
-	vld1.8 {d2-d3},[r1,: 128]!
-	vld1.8 {d4},[r1,: 64]
-	vst1.8 {d0-d1},[r2,: 128]!
-	vst1.8 {d2-d3},[r2,: 128]!
-	vst1.8 d4,[r2,: 64]
-	ldr r1,=0
-	.Linvertloop:
-	add r2,r3,#144
-	ldr r4,=0
-	ldr r5,=2
-	cmp r1,#1
-	ldreq r5,=1
-	addeq r2,r3,#336
-	addeq r4,r3,#48
-	cmp r1,#2
-	ldreq r5,=1
-	addeq r2,r3,#48
-	cmp r1,#3
-	ldreq r5,=5
-	addeq r4,r3,#336
-	cmp r1,#4
-	ldreq r5,=10
-	cmp r1,#5
-	ldreq r5,=20
-	cmp r1,#6
-	ldreq r5,=10
-	addeq r2,r3,#336
-	addeq r4,r3,#336
-	cmp r1,#7
-	ldreq r5,=50
-	cmp r1,#8
-	ldreq r5,=100
-	cmp r1,#9
-	ldreq r5,=50
-	addeq r2,r3,#336
-	cmp r1,#10
-	ldreq r5,=5
-	addeq r2,r3,#48
-	cmp r1,#11
-	ldreq r5,=0
-	addeq r2,r3,#96
-	add r6,r3,#144
-	add r7,r3,#288
-	vld1.8 {d0-d1},[r6,: 128]!
-	vld1.8 {d2-d3},[r6,: 128]!
-	vld1.8 {d4},[r6,: 64]
-	vst1.8 {d0-d1},[r7,: 128]!
-	vst1.8 {d2-d3},[r7,: 128]!
-	vst1.8 d4,[r7,: 64]
-	cmp r5,#0
-	beq .Lskipsquaringloop
-	.Lsquaringloop:
-	add r6,r3,#288
-	add r7,r3,#288
-	add r8,r3,#288
-	vmov.i32 q0,#19
-	vmov.i32 q1,#0
-	vmov.i32 q2,#1
-	vzip.i32 q1,q2
-	vld1.8 {d4-d5},[r7,: 128]!
-	vld1.8 {d6-d7},[r7,: 128]!
-	vld1.8 {d9},[r7,: 64]
-	vld1.8 {d10-d11},[r6,: 128]!
-	add r7,sp,#416
-	vld1.8 {d12-d13},[r6,: 128]!
-	vmul.i32 q7,q2,q0
-	vld1.8 {d8},[r6,: 64]
-	vext.32 d17,d11,d10,#1
-	vmul.i32 q9,q3,q0
-	vext.32 d16,d10,d8,#1
-	vshl.u32 q10,q5,q1
-	vext.32 d22,d14,d4,#1
-	vext.32 d24,d18,d6,#1
-	vshl.u32 q13,q6,q1
-	vshl.u32 d28,d8,d2
-	vrev64.i32 d22,d22
-	vmul.i32 d1,d9,d1
-	vrev64.i32 d24,d24
-	vext.32 d29,d8,d13,#1
-	vext.32 d0,d1,d9,#1
-	vrev64.i32 d0,d0
-	vext.32 d2,d9,d1,#1
-	vext.32 d23,d15,d5,#1
-	vmull.s32 q4,d20,d4
-	vrev64.i32 d23,d23
-	vmlal.s32 q4,d21,d1
-	vrev64.i32 d2,d2
-	vmlal.s32 q4,d26,d19
-	vext.32 d3,d5,d15,#1
-	vmlal.s32 q4,d27,d18
-	vrev64.i32 d3,d3
-	vmlal.s32 q4,d28,d15
-	vext.32 d14,d12,d11,#1
-	vmull.s32 q5,d16,d23
-	vext.32 d15,d13,d12,#1
-	vmlal.s32 q5,d17,d4
-	vst1.8 d8,[r7,: 64]!
-	vmlal.s32 q5,d14,d1
-	vext.32 d12,d9,d8,#0
-	vmlal.s32 q5,d15,d19
-	vmov.i64 d13,#0
-	vmlal.s32 q5,d29,d18
-	vext.32 d25,d19,d7,#1
-	vmlal.s32 q6,d20,d5
-	vrev64.i32 d25,d25
-	vmlal.s32 q6,d21,d4
-	vst1.8 d11,[r7,: 64]!
-	vmlal.s32 q6,d26,d1
-	vext.32 d9,d10,d10,#0
-	vmlal.s32 q6,d27,d19
-	vmov.i64 d8,#0
-	vmlal.s32 q6,d28,d18
-	vmlal.s32 q4,d16,d24
-	vmlal.s32 q4,d17,d5
-	vmlal.s32 q4,d14,d4
-	vst1.8 d12,[r7,: 64]!
-	vmlal.s32 q4,d15,d1
-	vext.32 d10,d13,d12,#0
-	vmlal.s32 q4,d29,d19
-	vmov.i64 d11,#0
-	vmlal.s32 q5,d20,d6
-	vmlal.s32 q5,d21,d5
-	vmlal.s32 q5,d26,d4
-	vext.32 d13,d8,d8,#0
-	vmlal.s32 q5,d27,d1
-	vmov.i64 d12,#0
-	vmlal.s32 q5,d28,d19
-	vst1.8 d9,[r7,: 64]!
-	vmlal.s32 q6,d16,d25
-	vmlal.s32 q6,d17,d6
-	vst1.8 d10,[r7,: 64]
-	vmlal.s32 q6,d14,d5
-	vext.32 d8,d11,d10,#0
-	vmlal.s32 q6,d15,d4
-	vmov.i64 d9,#0
-	vmlal.s32 q6,d29,d1
-	vmlal.s32 q4,d20,d7
-	vmlal.s32 q4,d21,d6
-	vmlal.s32 q4,d26,d5
-	vext.32 d11,d12,d12,#0
-	vmlal.s32 q4,d27,d4
-	vmov.i64 d10,#0
-	vmlal.s32 q4,d28,d1
-	vmlal.s32 q5,d16,d0
-	sub r6,r7,#32
-	vmlal.s32 q5,d17,d7
-	vmlal.s32 q5,d14,d6
-	vext.32 d30,d9,d8,#0
-	vmlal.s32 q5,d15,d5
-	vld1.8 {d31},[r6,: 64]!
-	vmlal.s32 q5,d29,d4
-	vmlal.s32 q15,d20,d0
-	vext.32 d0,d6,d18,#1
-	vmlal.s32 q15,d21,d25
-	vrev64.i32 d0,d0
-	vmlal.s32 q15,d26,d24
-	vext.32 d1,d7,d19,#1
-	vext.32 d7,d10,d10,#0
-	vmlal.s32 q15,d27,d23
-	vrev64.i32 d1,d1
-	vld1.8 {d6},[r6,: 64]
-	vmlal.s32 q15,d28,d22
-	vmlal.s32 q3,d16,d4
-	add r6,r6,#24
-	vmlal.s32 q3,d17,d2
-	vext.32 d4,d31,d30,#0
-	vmov d17,d11
-	vmlal.s32 q3,d14,d1
-	vext.32 d11,d13,d13,#0
-	vext.32 d13,d30,d30,#0
-	vmlal.s32 q3,d15,d0
-	vext.32 d1,d8,d8,#0
-	vmlal.s32 q3,d29,d3
-	vld1.8 {d5},[r6,: 64]
-	sub r6,r6,#16
-	vext.32 d10,d6,d6,#0
-	vmov.i32 q1,#0xffffffff
-	vshl.i64 q4,q1,#25
-	add r7,sp,#512
-	vld1.8 {d14-d15},[r7,: 128]
-	vadd.i64 q9,q2,q7
-	vshl.i64 q1,q1,#26
-	vshr.s64 q10,q9,#26
-	vld1.8 {d0},[r6,: 64]!
-	vadd.i64 q5,q5,q10
-	vand q9,q9,q1
-	vld1.8 {d16},[r6,: 64]!
-	add r6,sp,#528
-	vld1.8 {d20-d21},[r6,: 128]
-	vadd.i64 q11,q5,q10
-	vsub.i64 q2,q2,q9
-	vshr.s64 q9,q11,#25
-	vext.32 d12,d5,d4,#0
-	vand q11,q11,q4
-	vadd.i64 q0,q0,q9
-	vmov d19,d7
-	vadd.i64 q3,q0,q7
-	vsub.i64 q5,q5,q11
-	vshr.s64 q11,q3,#26
-	vext.32 d18,d11,d10,#0
-	vand q3,q3,q1
-	vadd.i64 q8,q8,q11
-	vadd.i64 q11,q8,q10
-	vsub.i64 q0,q0,q3
-	vshr.s64 q3,q11,#25
-	vand q11,q11,q4
-	vadd.i64 q3,q6,q3
-	vadd.i64 q6,q3,q7
-	vsub.i64 q8,q8,q11
-	vshr.s64 q11,q6,#26
-	vand q6,q6,q1
-	vadd.i64 q9,q9,q11
-	vadd.i64 d25,d19,d21
-	vsub.i64 q3,q3,q6
-	vshr.s64 d23,d25,#25
-	vand q4,q12,q4
-	vadd.i64 d21,d23,d23
-	vshl.i64 d25,d23,#4
-	vadd.i64 d21,d21,d23
-	vadd.i64 d25,d25,d21
-	vadd.i64 d4,d4,d25
-	vzip.i32 q0,q8
-	vadd.i64 d12,d4,d14
-	add r6,r8,#8
-	vst1.8 d0,[r6,: 64]
-	vsub.i64 d19,d19,d9
-	add r6,r6,#16
-	vst1.8 d16,[r6,: 64]
-	vshr.s64 d22,d12,#26
-	vand q0,q6,q1
-	vadd.i64 d10,d10,d22
-	vzip.i32 q3,q9
-	vsub.i64 d4,d4,d0
-	sub r6,r6,#8
-	vst1.8 d6,[r6,: 64]
-	add r6,r6,#16
-	vst1.8 d18,[r6,: 64]
-	vzip.i32 q2,q5
-	sub r6,r6,#32
-	vst1.8 d4,[r6,: 64]
-	subs r5,r5,#1
-	bhi .Lsquaringloop
-	.Lskipsquaringloop:
-	mov r2,r2
-	add r5,r3,#288
-	add r6,r3,#144
-	vmov.i32 q0,#19
-	vmov.i32 q1,#0
-	vmov.i32 q2,#1
-	vzip.i32 q1,q2
-	vld1.8 {d4-d5},[r5,: 128]!
-	vld1.8 {d6-d7},[r5,: 128]!
-	vld1.8 {d9},[r5,: 64]
-	vld1.8 {d10-d11},[r2,: 128]!
-	add r5,sp,#416
-	vld1.8 {d12-d13},[r2,: 128]!
-	vmul.i32 q7,q2,q0
-	vld1.8 {d8},[r2,: 64]
-	vext.32 d17,d11,d10,#1
-	vmul.i32 q9,q3,q0
-	vext.32 d16,d10,d8,#1
-	vshl.u32 q10,q5,q1
-	vext.32 d22,d14,d4,#1
-	vext.32 d24,d18,d6,#1
-	vshl.u32 q13,q6,q1
-	vshl.u32 d28,d8,d2
-	vrev64.i32 d22,d22
-	vmul.i32 d1,d9,d1
-	vrev64.i32 d24,d24
-	vext.32 d29,d8,d13,#1
-	vext.32 d0,d1,d9,#1
-	vrev64.i32 d0,d0
-	vext.32 d2,d9,d1,#1
-	vext.32 d23,d15,d5,#1
-	vmull.s32 q4,d20,d4
-	vrev64.i32 d23,d23
-	vmlal.s32 q4,d21,d1
-	vrev64.i32 d2,d2
-	vmlal.s32 q4,d26,d19
-	vext.32 d3,d5,d15,#1
-	vmlal.s32 q4,d27,d18
-	vrev64.i32 d3,d3
-	vmlal.s32 q4,d28,d15
-	vext.32 d14,d12,d11,#1
-	vmull.s32 q5,d16,d23
-	vext.32 d15,d13,d12,#1
-	vmlal.s32 q5,d17,d4
-	vst1.8 d8,[r5,: 64]!
-	vmlal.s32 q5,d14,d1
-	vext.32 d12,d9,d8,#0
-	vmlal.s32 q5,d15,d19
-	vmov.i64 d13,#0
-	vmlal.s32 q5,d29,d18
-	vext.32 d25,d19,d7,#1
-	vmlal.s32 q6,d20,d5
-	vrev64.i32 d25,d25
-	vmlal.s32 q6,d21,d4
-	vst1.8 d11,[r5,: 64]!
-	vmlal.s32 q6,d26,d1
-	vext.32 d9,d10,d10,#0
-	vmlal.s32 q6,d27,d19
-	vmov.i64 d8,#0
-	vmlal.s32 q6,d28,d18
-	vmlal.s32 q4,d16,d24
-	vmlal.s32 q4,d17,d5
-	vmlal.s32 q4,d14,d4
-	vst1.8 d12,[r5,: 64]!
-	vmlal.s32 q4,d15,d1
-	vext.32 d10,d13,d12,#0
-	vmlal.s32 q4,d29,d19
-	vmov.i64 d11,#0
-	vmlal.s32 q5,d20,d6
-	vmlal.s32 q5,d21,d5
-	vmlal.s32 q5,d26,d4
-	vext.32 d13,d8,d8,#0
-	vmlal.s32 q5,d27,d1
-	vmov.i64 d12,#0
-	vmlal.s32 q5,d28,d19
-	vst1.8 d9,[r5,: 64]!
-	vmlal.s32 q6,d16,d25
-	vmlal.s32 q6,d17,d6
-	vst1.8 d10,[r5,: 64]
-	vmlal.s32 q6,d14,d5
-	vext.32 d8,d11,d10,#0
-	vmlal.s32 q6,d15,d4
-	vmov.i64 d9,#0
-	vmlal.s32 q6,d29,d1
-	vmlal.s32 q4,d20,d7
-	vmlal.s32 q4,d21,d6
-	vmlal.s32 q4,d26,d5
-	vext.32 d11,d12,d12,#0
-	vmlal.s32 q4,d27,d4
-	vmov.i64 d10,#0
-	vmlal.s32 q4,d28,d1
-	vmlal.s32 q5,d16,d0
-	sub r2,r5,#32
-	vmlal.s32 q5,d17,d7
-	vmlal.s32 q5,d14,d6
-	vext.32 d30,d9,d8,#0
-	vmlal.s32 q5,d15,d5
-	vld1.8 {d31},[r2,: 64]!
-	vmlal.s32 q5,d29,d4
-	vmlal.s32 q15,d20,d0
-	vext.32 d0,d6,d18,#1
-	vmlal.s32 q15,d21,d25
-	vrev64.i32 d0,d0
-	vmlal.s32 q15,d26,d24
-	vext.32 d1,d7,d19,#1
-	vext.32 d7,d10,d10,#0
-	vmlal.s32 q15,d27,d23
-	vrev64.i32 d1,d1
-	vld1.8 {d6},[r2,: 64]
-	vmlal.s32 q15,d28,d22
-	vmlal.s32 q3,d16,d4
-	add r2,r2,#24
-	vmlal.s32 q3,d17,d2
-	vext.32 d4,d31,d30,#0
-	vmov d17,d11
-	vmlal.s32 q3,d14,d1
-	vext.32 d11,d13,d13,#0
-	vext.32 d13,d30,d30,#0
-	vmlal.s32 q3,d15,d0
-	vext.32 d1,d8,d8,#0
-	vmlal.s32 q3,d29,d3
-	vld1.8 {d5},[r2,: 64]
-	sub r2,r2,#16
-	vext.32 d10,d6,d6,#0
-	vmov.i32 q1,#0xffffffff
-	vshl.i64 q4,q1,#25
-	add r5,sp,#512
-	vld1.8 {d14-d15},[r5,: 128]
-	vadd.i64 q9,q2,q7
-	vshl.i64 q1,q1,#26
-	vshr.s64 q10,q9,#26
-	vld1.8 {d0},[r2,: 64]!
-	vadd.i64 q5,q5,q10
-	vand q9,q9,q1
-	vld1.8 {d16},[r2,: 64]!
-	add r2,sp,#528
-	vld1.8 {d20-d21},[r2,: 128]
-	vadd.i64 q11,q5,q10
-	vsub.i64 q2,q2,q9
-	vshr.s64 q9,q11,#25
-	vext.32 d12,d5,d4,#0
-	vand q11,q11,q4
-	vadd.i64 q0,q0,q9
-	vmov d19,d7
-	vadd.i64 q3,q0,q7
-	vsub.i64 q5,q5,q11
-	vshr.s64 q11,q3,#26
-	vext.32 d18,d11,d10,#0
-	vand q3,q3,q1
-	vadd.i64 q8,q8,q11
-	vadd.i64 q11,q8,q10
-	vsub.i64 q0,q0,q3
-	vshr.s64 q3,q11,#25
-	vand q11,q11,q4
-	vadd.i64 q3,q6,q3
-	vadd.i64 q6,q3,q7
-	vsub.i64 q8,q8,q11
-	vshr.s64 q11,q6,#26
-	vand q6,q6,q1
-	vadd.i64 q9,q9,q11
-	vadd.i64 d25,d19,d21
-	vsub.i64 q3,q3,q6
-	vshr.s64 d23,d25,#25
-	vand q4,q12,q4
-	vadd.i64 d21,d23,d23
-	vshl.i64 d25,d23,#4
-	vadd.i64 d21,d21,d23
-	vadd.i64 d25,d25,d21
-	vadd.i64 d4,d4,d25
-	vzip.i32 q0,q8
-	vadd.i64 d12,d4,d14
-	add r2,r6,#8
-	vst1.8 d0,[r2,: 64]
-	vsub.i64 d19,d19,d9
-	add r2,r2,#16
-	vst1.8 d16,[r2,: 64]
-	vshr.s64 d22,d12,#26
-	vand q0,q6,q1
-	vadd.i64 d10,d10,d22
-	vzip.i32 q3,q9
-	vsub.i64 d4,d4,d0
-	sub r2,r2,#8
-	vst1.8 d6,[r2,: 64]
-	add r2,r2,#16
-	vst1.8 d18,[r2,: 64]
-	vzip.i32 q2,q5
-	sub r2,r2,#32
-	vst1.8 d4,[r2,: 64]
-	cmp r4,#0
-	beq .Lskippostcopy
-	add r2,r3,#144
-	mov r4,r4
-	vld1.8 {d0-d1},[r2,: 128]!
-	vld1.8 {d2-d3},[r2,: 128]!
-	vld1.8 {d4},[r2,: 64]
-	vst1.8 {d0-d1},[r4,: 128]!
-	vst1.8 {d2-d3},[r4,: 128]!
-	vst1.8 d4,[r4,: 64]
-	.Lskippostcopy:
-	cmp r1,#1
-	bne .Lskipfinalcopy
-	add r2,r3,#288
-	add r4,r3,#144
-	vld1.8 {d0-d1},[r2,: 128]!
-	vld1.8 {d2-d3},[r2,: 128]!
-	vld1.8 {d4},[r2,: 64]
-	vst1.8 {d0-d1},[r4,: 128]!
-	vst1.8 {d2-d3},[r4,: 128]!
-	vst1.8 d4,[r4,: 64]
-	.Lskipfinalcopy:
-	add r1,r1,#1
-	cmp r1,#12
-	blo .Linvertloop
-	add r1,r3,#144
-	ldr r2,[r1],#4
-	ldr r3,[r1],#4
-	ldr r4,[r1],#4
-	ldr r5,[r1],#4
-	ldr r6,[r1],#4
-	ldr r7,[r1],#4
-	ldr r8,[r1],#4
-	ldr r9,[r1],#4
-	ldr r10,[r1],#4
-	ldr r1,[r1]
-	add r11,r1,r1,LSL #4
-	add r11,r11,r1,LSL #1
-	add r11,r11,#16777216
-	mov r11,r11,ASR #25
-	add r11,r11,r2
-	mov r11,r11,ASR #26
-	add r11,r11,r3
-	mov r11,r11,ASR #25
-	add r11,r11,r4
-	mov r11,r11,ASR #26
-	add r11,r11,r5
-	mov r11,r11,ASR #25
-	add r11,r11,r6
-	mov r11,r11,ASR #26
-	add r11,r11,r7
-	mov r11,r11,ASR #25
-	add r11,r11,r8
-	mov r11,r11,ASR #26
-	add r11,r11,r9
-	mov r11,r11,ASR #25
-	add r11,r11,r10
-	mov r11,r11,ASR #26
-	add r11,r11,r1
-	mov r11,r11,ASR #25
-	add r2,r2,r11
-	add r2,r2,r11,LSL #1
-	add r2,r2,r11,LSL #4
-	mov r11,r2,ASR #26
-	add r3,r3,r11
-	sub r2,r2,r11,LSL #26
-	mov r11,r3,ASR #25
-	add r4,r4,r11
-	sub r3,r3,r11,LSL #25
-	mov r11,r4,ASR #26
-	add r5,r5,r11
-	sub r4,r4,r11,LSL #26
-	mov r11,r5,ASR #25
-	add r6,r6,r11
-	sub r5,r5,r11,LSL #25
-	mov r11,r6,ASR #26
-	add r7,r7,r11
-	sub r6,r6,r11,LSL #26
-	mov r11,r7,ASR #25
-	add r8,r8,r11
-	sub r7,r7,r11,LSL #25
-	mov r11,r8,ASR #26
-	add r9,r9,r11
-	sub r8,r8,r11,LSL #26
-	mov r11,r9,ASR #25
-	add r10,r10,r11
-	sub r9,r9,r11,LSL #25
-	mov r11,r10,ASR #26
-	add r1,r1,r11
-	sub r10,r10,r11,LSL #26
-	mov r11,r1,ASR #25
-	sub r1,r1,r11,LSL #25
-	add r2,r2,r3,LSL #26
-	mov r3,r3,LSR #6
-	add r3,r3,r4,LSL #19
-	mov r4,r4,LSR #13
-	add r4,r4,r5,LSL #13
-	mov r5,r5,LSR #19
-	add r5,r5,r6,LSL #6
-	add r6,r7,r8,LSL #25
-	mov r7,r8,LSR #7
-	add r7,r7,r9,LSL #19
-	mov r8,r9,LSR #13
-	add r8,r8,r10,LSL #12
-	mov r9,r10,LSR #20
-	add r1,r9,r1,LSL #6
-	str r2,[r0],#4
-	str r3,[r0],#4
-	str r4,[r0],#4
-	str r5,[r0],#4
-	str r6,[r0],#4
-	str r7,[r0],#4
-	str r8,[r0],#4
-	str r1,[r0]
-	ldrd r4,[sp,#0]
-	ldrd r6,[sp,#8]
-	ldrd r8,[sp,#16]
-	ldrd r10,[sp,#24]
-	ldr r12,[sp,#480]
-	ldr r14,[sp,#484]
-	ldr r0,=0
-	mov sp,r12
-	vpop {q4,q5,q6,q7}
-	bx lr
-ENDPROC(curve25519_neon)
-#endif
diff --git a/generic.c b/generic.c
new file mode 100644
index 0000000..4e311df
--- /dev/null
+++ b/generic.c
@@ -0,0 +1,96 @@
+/* SPDX-License-Identifier: MIT
+ *
+ * Copyright (C) 2015-2018 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ */
+
+#include <linux/kernel.h>
+#include <crypto/algapi.h>
+
+enum {
+	CHACHA20_IV_SIZE = 16,
+	CHACHA20_KEY_SIZE = 32,
+	CHACHA20_BLOCK_SIZE = 64,
+	CHACHA20_BLOCK_WORDS = CHACHA20_BLOCK_SIZE / sizeof(u32)
+};
+
+#define EXPAND_32_BYTE_K 0x61707865U, 0x3320646eU, 0x79622d32U, 0x6b206574U
+
+#define QUARTER_ROUND(x, a, b, c, d) ( \
+	x[a] += x[b], \
+	x[d] = rol32((x[d] ^ x[a]), 16), \
+	x[c] += x[d], \
+	x[b] = rol32((x[b] ^ x[c]), 12), \
+	x[a] += x[b], \
+	x[d] = rol32((x[d] ^ x[a]), 8), \
+	x[c] += x[d], \
+	x[b] = rol32((x[b] ^ x[c]), 7) \
+)
+
+#define C(i, j) (i * 4 + j)
+
+#define DOUBLE_ROUND(x) ( \
+	/* Column Round */ \
+	QUARTER_ROUND(x, C(0, 0), C(1, 0), C(2, 0), C(3, 0)), \
+	QUARTER_ROUND(x, C(0, 1), C(1, 1), C(2, 1), C(3, 1)), \
+	QUARTER_ROUND(x, C(0, 2), C(1, 2), C(2, 2), C(3, 2)), \
+	QUARTER_ROUND(x, C(0, 3), C(1, 3), C(2, 3), C(3, 3)), \
+	/* Diagonal Round */ \
+	QUARTER_ROUND(x, C(0, 0), C(1, 1), C(2, 2), C(3, 3)), \
+	QUARTER_ROUND(x, C(0, 1), C(1, 2), C(2, 3), C(3, 0)), \
+	QUARTER_ROUND(x, C(0, 2), C(1, 3), C(2, 0), C(3, 1)), \
+	QUARTER_ROUND(x, C(0, 3), C(1, 0), C(2, 1), C(3, 2)) \
+)
+
+#define TWENTY_ROUNDS(x) ( \
+	DOUBLE_ROUND(x), \
+	DOUBLE_ROUND(x), \
+	DOUBLE_ROUND(x), \
+	DOUBLE_ROUND(x), \
+	DOUBLE_ROUND(x), \
+	DOUBLE_ROUND(x), \
+	DOUBLE_ROUND(x), \
+	DOUBLE_ROUND(x), \
+	DOUBLE_ROUND(x), \
+	DOUBLE_ROUND(x) \
+)
+
+static void chacha20_block_generic(__le32 *stream, u32 *state)
+{
+	u32 x[CHACHA20_BLOCK_WORDS];
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(x); ++i)
+		x[i] = state[i];
+
+	TWENTY_ROUNDS(x);
+
+	for (i = 0; i < ARRAY_SIZE(x); ++i)
+		stream[i] = cpu_to_le32(x[i] + state[i]);
+
+	++state[12];
+}
+
+void chacha20_generic(u8 *out, const u8 *in, u32 len, const u32 key[8], const u32 counter[4])
+{
+	__le32 buf[CHACHA20_BLOCK_WORDS];
+	u32 x[] = {
+		EXPAND_32_BYTE_K,
+		key[0], key[1], key[2], key[3],
+		key[4], key[5], key[6], key[7],
+		counter[0], counter[1], counter[2], counter[3]
+	};
+
+	if (out != in)
+		memmove(out, in, len);
+
+	while (len >= CHACHA20_BLOCK_SIZE) {
+		chacha20_block_generic(buf, x);
+		crypto_xor(out, (u8 *)buf, CHACHA20_BLOCK_SIZE);
+		len -= CHACHA20_BLOCK_SIZE;
+		out += CHACHA20_BLOCK_SIZE;
+	}
+	if (len) {
+		chacha20_block_generic(buf, x);
+		crypto_xor(out, (u8 *)buf, len);
+	}
+}
diff --git a/main.c b/main.c
index ce5f496..7c4a776 100644
--- a/main.c
+++ b/main.c
@@ -6,98 +6,88 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/delay.h>
+#include <linux/slab.h>
+#include <linux/sort.h>
 #include <asm/neon.h>
 
 static unsigned long stamp = 0;
 module_param(stamp, ulong, 0);
-int dummy;
 
+#define declare_it(name) void chacha20_ ## name(u8 *dst, const u8 *src, u32 len, const u32 key[8], const u32 counter[4]);
 
-enum { CURVE25519_POINT_SIZE = 32 };
-u8 dummy_out[CURVE25519_POINT_SIZE];
-#include "test_vectors.h"
-
-#define declare_it(name) \
-bool curve25519_ ## name(u8 mypublic[CURVE25519_POINT_SIZE], const u8 secret[CURVE25519_POINT_SIZE], const u8 basepoint[CURVE25519_POINT_SIZE]); \
-static __always_inline int name(void) \
-{ \
-	return curve25519_ ## name(dummy_out, curve25519_test_vectors[0].private, curve25519_test_vectors[0].public); \
+static int compare_cycles(const void *a, const void *b)
+{
+	return *((cycles_t *)a) - *((cycles_t *)b);
 }
 
-#define do_it(name) do { \
-	for (i = 0; i < WARMUP; ++i) \
-		ret |= name(); \
-	start_ ## name = get_cycles(); \
-	for (i = 0; i < TRIALS; ++i) \
-		ret |= name(); \
-	end_ ## name = get_cycles(); \
-} while (0)
-
-#define test_it(name, before, after) do { \
-	memset(out, __LINE__, CURVE25519_POINT_SIZE); \
+#define do_it(name, len, before, after) ({ \
 	before; \
-	ret = curve25519_ ## name(out, curve25519_test_vectors[i].private, curve25519_test_vectors[i].public); \
-	after; \
-	if (memcmp(out, curve25519_test_vectors[i].result, CURVE25519_POINT_SIZE)) { \
-		pr_err(#name " self-test %zu: FAIL\n", i + 1); \
-		return false; \
+	for (j = 0; j < WARMUP; ++j) \
+		chacha20_ ## name(output, input, len, key, counter); \
+	for (j = 0; j <= TRIALS; ++j) { \
+		trial_times[j] = get_cycles(); \
+		chacha20_ ## name(output, input, len, key, counter); \
 	} \
-} while (0)
-
-#define report_it(name) do { \
-	pr_err("%lu: %7s: %lu cycles per call\n", stamp, #name, (end_ ## name - start_ ## name) / TRIALS); \
-} while (0)
-
-
-declare_it(neon)
-declare_it(fiat32)
-declare_it(donna32)
+	after; \
+	for (j = 0; j < TRIALS; ++j) \
+		trial_times[j] = trial_times[j + 1] - trial_times[j]; \
+	sort(trial_times, TRIALS + 1, sizeof(cycles_t), compare_cycles, NULL); \
+	trial_times[TRIALS / 2]; \
+})
 
-static bool verify(void)
-{
-	int ret;
-	size_t i = 0;
-	u8 out[CURVE25519_POINT_SIZE];
-
-	for (i = 0; i < ARRAY_SIZE(curve25519_test_vectors); ++i) {
-		test_it(neon, { kernel_neon_begin(); }, { kernel_neon_end(); });
-		test_it(fiat32, {}, {});
-		test_it(donna32, {}, {});
-	}
-	return true;
-}
+declare_it(generic)
+declare_it(ossl_scalar)
+declare_it(ossl_neon)
+declare_it(ard_neon)
 
 static int __init mod_init(void)
 {
-	enum { WARMUP = 5000, TRIALS = 10000, IDLE = 1 * 1000 };
-	int ret = 0, i;
-	cycles_t start_neon, end_neon;
-	cycles_t start_fiat32, end_fiat32;
-	cycles_t start_donna32, end_donna32;
+	enum { WARMUP = 500, TRIALS = 5000, IDLE = 1 * 1000, STEP = 32, STEPS = 128 };
+	u32 key[8] = { 1, 2, 3, 4, 5, 6, 7, 8 };
+	u32 counter[4] = { 1, 2, 3, 4 };
+	u8 *input = NULL, *output = NULL;
+	cycles_t *trial_times = NULL;
+	cycles_t median_generic[STEPS], median_ossl_scalar[STEPS], median_ossl_neon[STEPS], median_ard_neon[STEPS];
+	size_t i, j;
 	unsigned long flags;
 	DEFINE_SPINLOCK(lock);
 
-	if (!verify())
-		return -EBFONT;
+	trial_times = kcalloc(TRIALS + 1, sizeof(cycles_t), GFP_KERNEL);
+	if (!trial_times)
+		goto out;
+	input = kcalloc(STEP, STEPS, GFP_KERNEL);
+	if (!input)
+		goto out;
+	output = kcalloc(STEP, STEPS, GFP_KERNEL);
+	if (!output)
+		goto out;
+
+	for (i = 0; i < (STEP * STEPS); ++i)
+		input[i] = i;
 	
 	msleep(IDLE);
 
 	spin_lock_irqsave(&lock, flags);
 
-	kernel_neon_begin();
-	do_it(neon);
-	kernel_neon_end();
-	do_it(fiat32);
-	do_it(donna32);
+	for (i = 0; i < STEPS; ++i) {
+		median_generic[i] = do_it(generic, i * STEP, {}, {});
+		median_ossl_scalar[i] = do_it(ossl_scalar, i * STEP, {}, {});
+		median_ossl_neon[i] = do_it(ossl_neon, i * STEP, { kernel_neon_begin(); }, { kernel_neon_end(); });
+		median_ard_neon[i] = do_it(ard_neon, i * STEP, { kernel_neon_begin(); }, { kernel_neon_end(); });
+	}
 
 	spin_unlock_irqrestore(&lock, flags);
-	
-	report_it(neon);
-	report_it(fiat32);
-	report_it(donna32);
 
-	/* Don't let compiler be too clever. */
-	dummy = ret;
+	pr_err("%lu: %12s %12s %12s %12s %12s\n", stamp, "length", "generic", "ossl scalar", "ossl neon", "ard neon");
+
+	for (i = 0; i < STEPS; ++i)
+		pr_err("%lu: %12u %12lu %12lu %12lu %12lu ", stamp, i * STEP,
+		       median_generic[i], median_ossl_scalar[i], median_ossl_neon[i], median_ard_neon[i]);
+
+out:
+	kfree(trial_times);
+	kfree(input);
+	kfree(output);
 	
 	/* We should never actually agree to insert the module. Choosing
 	 * -0x1000 here is an amazing hack. It causes the kernel to not
diff --git a/openssl.S b/openssl.S
new file mode 100644
index 0000000..d3c3f82
--- /dev/null
+++ b/openssl.S
@@ -0,0 +1,1471 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ *
+ * Copyright (C) 2015-2018 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ * Copyright (C) 2006-2017 CRYPTOGAMS by <appro@openssl.org>. All Rights Reserved.
+ */
+
+#include <linux/linkage.h>
+
+.text
+#if defined(__thumb2__) || defined(__clang__)
+.syntax	unified
+#endif
+#if defined(__thumb2__)
+.thumb
+#else
+.code	32
+#endif
+
+#if defined(__thumb2__) || defined(__clang__)
+#define ldrhsb	ldrbhs
+#endif
+
+.align	5
+.Lsigma:
+.long	0x61707865,0x3320646e,0x79622d32,0x6b206574	@ endian-neutral
+.Lone:
+.long	1,0,0,0
+.word -1
+
+.align	5
+ENTRY(chacha20_ossl_scalar)
+	ldr	r12,[sp,#0]		@ pull pointer to counter and nonce
+	stmdb	sp!,{r0-r2,r4-r11,lr}
+	cmp	r2,#0			@ len==0?
+#ifdef	__thumb2__
+	itt	eq
+#endif
+	addeq	sp,sp,#4*3
+	beq	.Lno_data_arm
+.Lshort:
+	ldmia	r12,{r4-r7}		@ load counter and nonce
+	sub	sp,sp,#4*(16)		@ off-load area
+#if __LINUX_ARM_ARCH__ < 7 && !defined(__thumb2__)
+	sub	r14,pc,#100		@ .Lsigma
+#else
+	adr	r14,.Lsigma		@ .Lsigma
+#endif
+	stmdb	sp!,{r4-r7}		@ copy counter and nonce
+	ldmia	r3,{r4-r11}		@ load key
+	ldmia	r14,{r0-r3}		@ load sigma
+	stmdb	sp!,{r4-r11}		@ copy key
+	stmdb	sp!,{r0-r3}		@ copy sigma
+	str	r10,[sp,#4*(16+10)]	@ off-load "rx"
+	str	r11,[sp,#4*(16+11)]	@ off-load "rx"
+	b	.Loop_outer_enter
+
+.align	4
+.Loop_outer:
+	ldmia	sp,{r0-r9}		@ load key material
+	str	r11,[sp,#4*(32+2)]	@ save len
+	str	r12,  [sp,#4*(32+1)]	@ save inp
+	str	r14,  [sp,#4*(32+0)]	@ save out
+.Loop_outer_enter:
+	ldr	r11, [sp,#4*(15)]
+	ldr	r12,[sp,#4*(12)]	@ modulo-scheduled load
+	ldr	r10, [sp,#4*(13)]
+	ldr	r14,[sp,#4*(14)]
+	str	r11, [sp,#4*(16+15)]
+	mov	r11,#10
+	b	.Loop
+
+.align	4
+.Loop:
+	subs	r11,r11,#1
+	add	r0,r0,r4
+	mov	r12,r12,ror#16
+	add	r1,r1,r5
+	mov	r10,r10,ror#16
+	eor	r12,r12,r0,ror#16
+	eor	r10,r10,r1,ror#16
+	add	r8,r8,r12
+	mov	r4,r4,ror#20
+	add	r9,r9,r10
+	mov	r5,r5,ror#20
+	eor	r4,r4,r8,ror#20
+	eor	r5,r5,r9,ror#20
+	add	r0,r0,r4
+	mov	r12,r12,ror#24
+	add	r1,r1,r5
+	mov	r10,r10,ror#24
+	eor	r12,r12,r0,ror#24
+	eor	r10,r10,r1,ror#24
+	add	r8,r8,r12
+	mov	r4,r4,ror#25
+	add	r9,r9,r10
+	mov	r5,r5,ror#25
+	str	r10,[sp,#4*(16+13)]
+	ldr	r10,[sp,#4*(16+15)]
+	eor	r4,r4,r8,ror#25
+	eor	r5,r5,r9,ror#25
+	str	r8,[sp,#4*(16+8)]
+	ldr	r8,[sp,#4*(16+10)]
+	add	r2,r2,r6
+	mov	r14,r14,ror#16
+	str	r9,[sp,#4*(16+9)]
+	ldr	r9,[sp,#4*(16+11)]
+	add	r3,r3,r7
+	mov	r10,r10,ror#16
+	eor	r14,r14,r2,ror#16
+	eor	r10,r10,r3,ror#16
+	add	r8,r8,r14
+	mov	r6,r6,ror#20
+	add	r9,r9,r10
+	mov	r7,r7,ror#20
+	eor	r6,r6,r8,ror#20
+	eor	r7,r7,r9,ror#20
+	add	r2,r2,r6
+	mov	r14,r14,ror#24
+	add	r3,r3,r7
+	mov	r10,r10,ror#24
+	eor	r14,r14,r2,ror#24
+	eor	r10,r10,r3,ror#24
+	add	r8,r8,r14
+	mov	r6,r6,ror#25
+	add	r9,r9,r10
+	mov	r7,r7,ror#25
+	eor	r6,r6,r8,ror#25
+	eor	r7,r7,r9,ror#25
+	add	r0,r0,r5
+	mov	r10,r10,ror#16
+	add	r1,r1,r6
+	mov	r12,r12,ror#16
+	eor	r10,r10,r0,ror#16
+	eor	r12,r12,r1,ror#16
+	add	r8,r8,r10
+	mov	r5,r5,ror#20
+	add	r9,r9,r12
+	mov	r6,r6,ror#20
+	eor	r5,r5,r8,ror#20
+	eor	r6,r6,r9,ror#20
+	add	r0,r0,r5
+	mov	r10,r10,ror#24
+	add	r1,r1,r6
+	mov	r12,r12,ror#24
+	eor	r10,r10,r0,ror#24
+	eor	r12,r12,r1,ror#24
+	add	r8,r8,r10
+	mov	r5,r5,ror#25
+	str	r10,[sp,#4*(16+15)]
+	ldr	r10,[sp,#4*(16+13)]
+	add	r9,r9,r12
+	mov	r6,r6,ror#25
+	eor	r5,r5,r8,ror#25
+	eor	r6,r6,r9,ror#25
+	str	r8,[sp,#4*(16+10)]
+	ldr	r8,[sp,#4*(16+8)]
+	add	r2,r2,r7
+	mov	r10,r10,ror#16
+	str	r9,[sp,#4*(16+11)]
+	ldr	r9,[sp,#4*(16+9)]
+	add	r3,r3,r4
+	mov	r14,r14,ror#16
+	eor	r10,r10,r2,ror#16
+	eor	r14,r14,r3,ror#16
+	add	r8,r8,r10
+	mov	r7,r7,ror#20
+	add	r9,r9,r14
+	mov	r4,r4,ror#20
+	eor	r7,r7,r8,ror#20
+	eor	r4,r4,r9,ror#20
+	add	r2,r2,r7
+	mov	r10,r10,ror#24
+	add	r3,r3,r4
+	mov	r14,r14,ror#24
+	eor	r10,r10,r2,ror#24
+	eor	r14,r14,r3,ror#24
+	add	r8,r8,r10
+	mov	r7,r7,ror#25
+	add	r9,r9,r14
+	mov	r4,r4,ror#25
+	eor	r7,r7,r8,ror#25
+	eor	r4,r4,r9,ror#25
+	bne	.Loop
+
+	ldr	r11,[sp,#4*(32+2)]	@ load len
+
+	str	r8, [sp,#4*(16+8)]	@ modulo-scheduled store
+	str	r9, [sp,#4*(16+9)]
+	str	r12,[sp,#4*(16+12)]
+	str	r10, [sp,#4*(16+13)]
+	str	r14,[sp,#4*(16+14)]
+
+	@ at this point we have first half of 512-bit result in
+	@ rx and second half at sp+4*(16+8)
+
+	cmp	r11,#64		@ done yet?
+#ifdef	__thumb2__
+	itete	lo
+#endif
+	addlo	r12,sp,#4*(0)		@ shortcut or ...
+	ldrhs	r12,[sp,#4*(32+1)]	@ ... load inp
+	addlo	r14,sp,#4*(0)		@ shortcut or ...
+	ldrhs	r14,[sp,#4*(32+0)]	@ ... load out
+
+	ldr	r8,[sp,#4*(0)]	@ load key material
+	ldr	r9,[sp,#4*(1)]
+
+#if __LINUX_ARM_ARCH__ >= 6 || !defined(__ARMEB__)
+#if __LINUX_ARM_ARCH__ < 7
+	orr	r10,r12,r14
+	tst	r10,#3		@ are input and output aligned?
+	ldr	r10,[sp,#4*(2)]
+	bne	.Lunaligned
+	cmp	r11,#64		@ restore flags
+#else
+	ldr	r10,[sp,#4*(2)]
+#endif
+	ldr	r11,[sp,#4*(3)]
+
+	add	r0,r0,r8	@ accumulate key material
+	add	r1,r1,r9
+#ifdef	__thumb2__
+	itt	hs
+#endif
+	ldrhs	r8,[r12],#16		@ load input
+	ldrhs	r9,[r12,#-12]
+
+	add	r2,r2,r10
+	add	r3,r3,r11
+#ifdef	__thumb2__
+	itt	hs
+#endif
+	ldrhs	r10,[r12,#-8]
+	ldrhs	r11,[r12,#-4]
+#if __LINUX_ARM_ARCH__ >= 6 && defined(__ARMEB__)
+	rev	r0,r0
+	rev	r1,r1
+	rev	r2,r2
+	rev	r3,r3
+#endif
+#ifdef	__thumb2__
+	itt	hs
+#endif
+	eorhs	r0,r0,r8	@ xor with input
+	eorhs	r1,r1,r9
+	 add	r8,sp,#4*(4)
+	str	r0,[r14],#16		@ store output
+#ifdef	__thumb2__
+	itt	hs
+#endif
+	eorhs	r2,r2,r10
+	eorhs	r3,r3,r11
+	 ldmia	r8,{r8-r11}	@ load key material
+	str	r1,[r14,#-12]
+	str	r2,[r14,#-8]
+	str	r3,[r14,#-4]
+
+	add	r4,r4,r8	@ accumulate key material
+	add	r5,r5,r9
+#ifdef	__thumb2__
+	itt	hs
+#endif
+	ldrhs	r8,[r12],#16		@ load input
+	ldrhs	r9,[r12,#-12]
+	add	r6,r6,r10
+	add	r7,r7,r11
+#ifdef	__thumb2__
+	itt	hs
+#endif
+	ldrhs	r10,[r12,#-8]
+	ldrhs	r11,[r12,#-4]
+#if __LINUX_ARM_ARCH__ >= 6 && defined(__ARMEB__)
+	rev	r4,r4
+	rev	r5,r5
+	rev	r6,r6
+	rev	r7,r7
+#endif
+#ifdef	__thumb2__
+	itt	hs
+#endif
+	eorhs	r4,r4,r8
+	eorhs	r5,r5,r9
+	 add	r8,sp,#4*(8)
+	str	r4,[r14],#16		@ store output
+#ifdef	__thumb2__
+	itt	hs
+#endif
+	eorhs	r6,r6,r10
+	eorhs	r7,r7,r11
+	str	r5,[r14,#-12]
+	 ldmia	r8,{r8-r11}	@ load key material
+	str	r6,[r14,#-8]
+	 add	r0,sp,#4*(16+8)
+	str	r7,[r14,#-4]
+
+	ldmia	r0,{r0-r7}	@ load second half
+
+	add	r0,r0,r8	@ accumulate key material
+	add	r1,r1,r9
+#ifdef	__thumb2__
+	itt	hs
+#endif
+	ldrhs	r8,[r12],#16		@ load input
+	ldrhs	r9,[r12,#-12]
+#ifdef	__thumb2__
+	itt	hi
+#endif
+	 strhi	r10,[sp,#4*(16+10)]	@ copy "rx" while at it
+	 strhi	r11,[sp,#4*(16+11)]	@ copy "rx" while at it
+	add	r2,r2,r10
+	add	r3,r3,r11
+#ifdef	__thumb2__
+	itt	hs
+#endif
+	ldrhs	r10,[r12,#-8]
+	ldrhs	r11,[r12,#-4]
+#if __LINUX_ARM_ARCH__ >= 6 && defined(__ARMEB__)
+	rev	r0,r0
+	rev	r1,r1
+	rev	r2,r2
+	rev	r3,r3
+#endif
+#ifdef	__thumb2__
+	itt	hs
+#endif
+	eorhs	r0,r0,r8
+	eorhs	r1,r1,r9
+	 add	r8,sp,#4*(12)
+	str	r0,[r14],#16		@ store output
+#ifdef	__thumb2__
+	itt	hs
+#endif
+	eorhs	r2,r2,r10
+	eorhs	r3,r3,r11
+	str	r1,[r14,#-12]
+	 ldmia	r8,{r8-r11}	@ load key material
+	str	r2,[r14,#-8]
+	str	r3,[r14,#-4]
+
+	add	r4,r4,r8	@ accumulate key material
+	add	r5,r5,r9
+#ifdef	__thumb2__
+	itt	hi
+#endif
+	 addhi	r8,r8,#1		@ next counter value
+	 strhi	r8,[sp,#4*(12)]	@ save next counter value
+#ifdef	__thumb2__
+	itt	hs
+#endif
+	ldrhs	r8,[r12],#16		@ load input
+	ldrhs	r9,[r12,#-12]
+	add	r6,r6,r10
+	add	r7,r7,r11
+#ifdef	__thumb2__
+	itt	hs
+#endif
+	ldrhs	r10,[r12,#-8]
+	ldrhs	r11,[r12,#-4]
+#if __LINUX_ARM_ARCH__ >= 6 && defined(__ARMEB__)
+	rev	r4,r4
+	rev	r5,r5
+	rev	r6,r6
+	rev	r7,r7
+#endif
+#ifdef	__thumb2__
+	itt	hs
+#endif
+	eorhs	r4,r4,r8
+	eorhs	r5,r5,r9
+#ifdef	__thumb2__
+	 it	ne
+#endif
+	 ldrne	r8,[sp,#4*(32+2)]	@ re-load len
+#ifdef	__thumb2__
+	itt	hs
+#endif
+	eorhs	r6,r6,r10
+	eorhs	r7,r7,r11
+	str	r4,[r14],#16		@ store output
+	str	r5,[r14,#-12]
+#ifdef	__thumb2__
+	it	hs
+#endif
+	 subhs	r11,r8,#64		@ len-=64
+	str	r6,[r14,#-8]
+	str	r7,[r14,#-4]
+	bhi	.Loop_outer
+
+	beq	.Ldone
+#if __LINUX_ARM_ARCH__ < 7
+	b	.Ltail
+
+.align	4
+.Lunaligned:				@ unaligned endian-neutral path
+	cmp	r11,#64		@ restore flags
+#endif
+#endif
+#if __LINUX_ARM_ARCH__ < 7
+	ldr	r11,[sp,#4*(3)]
+	add	r0,r0,r8		@ accumulate key material
+	add	r1,r1,r9
+	add	r2,r2,r10
+#ifdef	__thumb2__
+	itete	lo
+#endif
+	eorlo	r8,r8,r8		@ zero or ...
+	ldrhsb	r8,[r12],#16			@ ... load input
+	eorlo	r9,r9,r9
+	ldrhsb	r9,[r12,#-12]
+
+	add	r3,r3,r11
+#ifdef	__thumb2__
+	itete	lo
+#endif
+	eorlo	r10,r10,r10
+	ldrhsb	r10,[r12,#-8]
+	eorlo	r11,r11,r11
+	ldrhsb	r11,[r12,#-4]
+
+	eor	r0,r8,r0		@ xor with input (or zero)
+	eor	r1,r9,r1
+#ifdef	__thumb2__
+	itt	hs
+#endif
+	ldrhsb	r8,[r12,#-15]		@ load more input
+	ldrhsb	r9,[r12,#-11]
+	eor	r2,r10,r2
+	 strb	r0,[r14],#16		@ store output
+	eor	r3,r11,r3
+#ifdef	__thumb2__
+	itt	hs
+#endif
+	ldrhsb	r10,[r12,#-7]
+	ldrhsb	r11,[r12,#-3]
+	 strb	r1,[r14,#-12]
+	eor	r0,r8,r0,lsr#8
+	 strb	r2,[r14,#-8]
+	eor	r1,r9,r1,lsr#8
+#ifdef	__thumb2__
+	itt	hs
+#endif
+	ldrhsb	r8,[r12,#-14]		@ load more input
+	ldrhsb	r9,[r12,#-10]
+	 strb	r3,[r14,#-4]
+	eor	r2,r10,r2,lsr#8
+	 strb	r0,[r14,#-15]
+	eor	r3,r11,r3,lsr#8
+#ifdef	__thumb2__
+	itt	hs
+#endif
+	ldrhsb	r10,[r12,#-6]
+	ldrhsb	r11,[r12,#-2]
+	 strb	r1,[r14,#-11]
+	eor	r0,r8,r0,lsr#8
+	 strb	r2,[r14,#-7]
+	eor	r1,r9,r1,lsr#8
+#ifdef	__thumb2__
+	itt	hs
+#endif
+	ldrhsb	r8,[r12,#-13]		@ load more input
+	ldrhsb	r9,[r12,#-9]
+	 strb	r3,[r14,#-3]
+	eor	r2,r10,r2,lsr#8
+	 strb	r0,[r14,#-14]
+	eor	r3,r11,r3,lsr#8
+#ifdef	__thumb2__
+	itt	hs
+#endif
+	ldrhsb	r10,[r12,#-5]
+	ldrhsb	r11,[r12,#-1]
+	 strb	r1,[r14,#-10]
+	 strb	r2,[r14,#-6]
+	eor	r0,r8,r0,lsr#8
+	 strb	r3,[r14,#-2]
+	eor	r1,r9,r1,lsr#8
+	 strb	r0,[r14,#-13]
+	eor	r2,r10,r2,lsr#8
+	 strb	r1,[r14,#-9]
+	eor	r3,r11,r3,lsr#8
+	 strb	r2,[r14,#-5]
+	 strb	r3,[r14,#-1]
+	add	r8,sp,#4*(4+0)
+	ldmia	r8,{r8-r11}		@ load key material
+	add	r0,sp,#4*(16+8)
+	add	r4,r4,r8		@ accumulate key material
+	add	r5,r5,r9
+	add	r6,r6,r10
+#ifdef	__thumb2__
+	itete	lo
+#endif
+	eorlo	r8,r8,r8		@ zero or ...
+	ldrhsb	r8,[r12],#16			@ ... load input
+	eorlo	r9,r9,r9
+	ldrhsb	r9,[r12,#-12]
+
+	add	r7,r7,r11
+#ifdef	__thumb2__
+	itete	lo
+#endif
+	eorlo	r10,r10,r10
+	ldrhsb	r10,[r12,#-8]
+	eorlo	r11,r11,r11
+	ldrhsb	r11,[r12,#-4]
+
+	eor	r4,r8,r4		@ xor with input (or zero)
+	eor	r5,r9,r5
+#ifdef	__thumb2__
+	itt	hs
+#endif
+	ldrhsb	r8,[r12,#-15]		@ load more input
+	ldrhsb	r9,[r12,#-11]
+	eor	r6,r10,r6
+	 strb	r4,[r14],#16		@ store output
+	eor	r7,r11,r7
+#ifdef	__thumb2__
+	itt	hs
+#endif
+	ldrhsb	r10,[r12,#-7]
+	ldrhsb	r11,[r12,#-3]
+	 strb	r5,[r14,#-12]
+	eor	r4,r8,r4,lsr#8
+	 strb	r6,[r14,#-8]
+	eor	r5,r9,r5,lsr#8
+#ifdef	__thumb2__
+	itt	hs
+#endif
+	ldrhsb	r8,[r12,#-14]		@ load more input
+	ldrhsb	r9,[r12,#-10]
+	 strb	r7,[r14,#-4]
+	eor	r6,r10,r6,lsr#8
+	 strb	r4,[r14,#-15]
+	eor	r7,r11,r7,lsr#8
+#ifdef	__thumb2__
+	itt	hs
+#endif
+	ldrhsb	r10,[r12,#-6]
+	ldrhsb	r11,[r12,#-2]
+	 strb	r5,[r14,#-11]
+	eor	r4,r8,r4,lsr#8
+	 strb	r6,[r14,#-7]
+	eor	r5,r9,r5,lsr#8
+#ifdef	__thumb2__
+	itt	hs
+#endif
+	ldrhsb	r8,[r12,#-13]		@ load more input
+	ldrhsb	r9,[r12,#-9]
+	 strb	r7,[r14,#-3]
+	eor	r6,r10,r6,lsr#8
+	 strb	r4,[r14,#-14]
+	eor	r7,r11,r7,lsr#8
+#ifdef	__thumb2__
+	itt	hs
+#endif
+	ldrhsb	r10,[r12,#-5]
+	ldrhsb	r11,[r12,#-1]
+	 strb	r5,[r14,#-10]
+	 strb	r6,[r14,#-6]
+	eor	r4,r8,r4,lsr#8
+	 strb	r7,[r14,#-2]
+	eor	r5,r9,r5,lsr#8
+	 strb	r4,[r14,#-13]
+	eor	r6,r10,r6,lsr#8
+	 strb	r5,[r14,#-9]
+	eor	r7,r11,r7,lsr#8
+	 strb	r6,[r14,#-5]
+	 strb	r7,[r14,#-1]
+	add	r8,sp,#4*(4+4)
+	ldmia	r8,{r8-r11}		@ load key material
+	ldmia	r0,{r0-r7}		@ load second half
+#ifdef	__thumb2__
+	itt	hi
+#endif
+	strhi	r10,[sp,#4*(16+10)]		@ copy "rx"
+	strhi	r11,[sp,#4*(16+11)]		@ copy "rx"
+	add	r0,r0,r8		@ accumulate key material
+	add	r1,r1,r9
+	add	r2,r2,r10
+#ifdef	__thumb2__
+	itete	lo
+#endif
+	eorlo	r8,r8,r8		@ zero or ...
+	ldrhsb	r8,[r12],#16			@ ... load input
+	eorlo	r9,r9,r9
+	ldrhsb	r9,[r12,#-12]
+
+	add	r3,r3,r11
+#ifdef	__thumb2__
+	itete	lo
+#endif
+	eorlo	r10,r10,r10
+	ldrhsb	r10,[r12,#-8]
+	eorlo	r11,r11,r11
+	ldrhsb	r11,[r12,#-4]
+
+	eor	r0,r8,r0		@ xor with input (or zero)
+	eor	r1,r9,r1
+#ifdef	__thumb2__
+	itt	hs
+#endif
+	ldrhsb	r8,[r12,#-15]		@ load more input
+	ldrhsb	r9,[r12,#-11]
+	eor	r2,r10,r2
+	 strb	r0,[r14],#16		@ store output
+	eor	r3,r11,r3
+#ifdef	__thumb2__
+	itt	hs
+#endif
+	ldrhsb	r10,[r12,#-7]
+	ldrhsb	r11,[r12,#-3]
+	 strb	r1,[r14,#-12]
+	eor	r0,r8,r0,lsr#8
+	 strb	r2,[r14,#-8]
+	eor	r1,r9,r1,lsr#8
+#ifdef	__thumb2__
+	itt	hs
+#endif
+	ldrhsb	r8,[r12,#-14]		@ load more input
+	ldrhsb	r9,[r12,#-10]
+	 strb	r3,[r14,#-4]
+	eor	r2,r10,r2,lsr#8
+	 strb	r0,[r14,#-15]
+	eor	r3,r11,r3,lsr#8
+#ifdef	__thumb2__
+	itt	hs
+#endif
+	ldrhsb	r10,[r12,#-6]
+	ldrhsb	r11,[r12,#-2]
+	 strb	r1,[r14,#-11]
+	eor	r0,r8,r0,lsr#8
+	 strb	r2,[r14,#-7]
+	eor	r1,r9,r1,lsr#8
+#ifdef	__thumb2__
+	itt	hs
+#endif
+	ldrhsb	r8,[r12,#-13]		@ load more input
+	ldrhsb	r9,[r12,#-9]
+	 strb	r3,[r14,#-3]
+	eor	r2,r10,r2,lsr#8
+	 strb	r0,[r14,#-14]
+	eor	r3,r11,r3,lsr#8
+#ifdef	__thumb2__
+	itt	hs
+#endif
+	ldrhsb	r10,[r12,#-5]
+	ldrhsb	r11,[r12,#-1]
+	 strb	r1,[r14,#-10]
+	 strb	r2,[r14,#-6]
+	eor	r0,r8,r0,lsr#8
+	 strb	r3,[r14,#-2]
+	eor	r1,r9,r1,lsr#8
+	 strb	r0,[r14,#-13]
+	eor	r2,r10,r2,lsr#8
+	 strb	r1,[r14,#-9]
+	eor	r3,r11,r3,lsr#8
+	 strb	r2,[r14,#-5]
+	 strb	r3,[r14,#-1]
+	add	r8,sp,#4*(4+8)
+	ldmia	r8,{r8-r11}		@ load key material
+	add	r4,r4,r8		@ accumulate key material
+#ifdef	__thumb2__
+	itt	hi
+#endif
+	addhi	r8,r8,#1			@ next counter value
+	strhi	r8,[sp,#4*(12)]		@ save next counter value
+	add	r5,r5,r9
+	add	r6,r6,r10
+#ifdef	__thumb2__
+	itete	lo
+#endif
+	eorlo	r8,r8,r8		@ zero or ...
+	ldrhsb	r8,[r12],#16			@ ... load input
+	eorlo	r9,r9,r9
+	ldrhsb	r9,[r12,#-12]
+
+	add	r7,r7,r11
+#ifdef	__thumb2__
+	itete	lo
+#endif
+	eorlo	r10,r10,r10
+	ldrhsb	r10,[r12,#-8]
+	eorlo	r11,r11,r11
+	ldrhsb	r11,[r12,#-4]
+
+	eor	r4,r8,r4		@ xor with input (or zero)
+	eor	r5,r9,r5
+#ifdef	__thumb2__
+	itt	hs
+#endif
+	ldrhsb	r8,[r12,#-15]		@ load more input
+	ldrhsb	r9,[r12,#-11]
+	eor	r6,r10,r6
+	 strb	r4,[r14],#16		@ store output
+	eor	r7,r11,r7
+#ifdef	__thumb2__
+	itt	hs
+#endif
+	ldrhsb	r10,[r12,#-7]
+	ldrhsb	r11,[r12,#-3]
+	 strb	r5,[r14,#-12]
+	eor	r4,r8,r4,lsr#8
+	 strb	r6,[r14,#-8]
+	eor	r5,r9,r5,lsr#8
+#ifdef	__thumb2__
+	itt	hs
+#endif
+	ldrhsb	r8,[r12,#-14]		@ load more input
+	ldrhsb	r9,[r12,#-10]
+	 strb	r7,[r14,#-4]
+	eor	r6,r10,r6,lsr#8
+	 strb	r4,[r14,#-15]
+	eor	r7,r11,r7,lsr#8
+#ifdef	__thumb2__
+	itt	hs
+#endif
+	ldrhsb	r10,[r12,#-6]
+	ldrhsb	r11,[r12,#-2]
+	 strb	r5,[r14,#-11]
+	eor	r4,r8,r4,lsr#8
+	 strb	r6,[r14,#-7]
+	eor	r5,r9,r5,lsr#8
+#ifdef	__thumb2__
+	itt	hs
+#endif
+	ldrhsb	r8,[r12,#-13]		@ load more input
+	ldrhsb	r9,[r12,#-9]
+	 strb	r7,[r14,#-3]
+	eor	r6,r10,r6,lsr#8
+	 strb	r4,[r14,#-14]
+	eor	r7,r11,r7,lsr#8
+#ifdef	__thumb2__
+	itt	hs
+#endif
+	ldrhsb	r10,[r12,#-5]
+	ldrhsb	r11,[r12,#-1]
+	 strb	r5,[r14,#-10]
+	 strb	r6,[r14,#-6]
+	eor	r4,r8,r4,lsr#8
+	 strb	r7,[r14,#-2]
+	eor	r5,r9,r5,lsr#8
+	 strb	r4,[r14,#-13]
+	eor	r6,r10,r6,lsr#8
+	 strb	r5,[r14,#-9]
+	eor	r7,r11,r7,lsr#8
+	 strb	r6,[r14,#-5]
+	 strb	r7,[r14,#-1]
+#ifdef	__thumb2__
+	it	ne
+#endif
+	ldrne	r8,[sp,#4*(32+2)]		@ re-load len
+#ifdef	__thumb2__
+	it	hs
+#endif
+	subhs	r11,r8,#64			@ len-=64
+	bhi	.Loop_outer
+
+	beq	.Ldone
+#endif
+
+.Ltail:
+	ldr	r12,[sp,#4*(32+1)]	@ load inp
+	add	r9,sp,#4*(0)
+	ldr	r14,[sp,#4*(32+0)]	@ load out
+
+.Loop_tail:
+	ldrb	r10,[r9],#1	@ read buffer on stack
+	ldrb	r11,[r12],#1		@ read input
+	subs	r8,r8,#1
+	eor	r11,r11,r10
+	strb	r11,[r14],#1		@ store output
+	bne	.Loop_tail
+
+.Ldone:
+	add	sp,sp,#4*(32+3)
+.Lno_data_arm:
+	ldmia	sp!,{r4-r11,pc}
+ENDPROC(chacha20_ossl_scalar)
+
+#if __LINUX_ARM_ARCH__ >= 7 && IS_ENABLED(CONFIG_KERNEL_MODE_NEON)
+.align	5
+.Lsigma2:
+.long	0x61707865,0x3320646e,0x79622d32,0x6b206574	@ endian-neutral
+.Lone2:
+.long	1,0,0,0
+.word -1
+
+.arch	armv7-a
+.fpu	neon
+
+.align	5
+ENTRY(chacha20_ossl_neon)
+	ldr		r12,[sp,#0]		@ pull pointer to counter and nonce
+	stmdb		sp!,{r0-r2,r4-r11,lr}
+	cmp		r2,#0			@ len==0?
+#ifdef	__thumb2__
+	itt		eq
+#endif
+	addeq		sp,sp,#4*3
+	beq		.Lno_data_neon
+	cmp		r2,#192			@ test len
+	bls		.Lshort
+.Lchacha20_ossl_neon_begin:
+	adr		r14,.Lsigma2
+	vstmdb		sp!,{d8-d15}		@ ABI spec says so
+	stmdb		sp!,{r0-r3}
+
+	vld1.32		{q1-q2},[r3]		@ load key
+	ldmia		r3,{r4-r11}		@ load key
+
+	sub		sp,sp,#4*(16+16)
+	vld1.32		{q3},[r12]		@ load counter and nonce
+	add		r12,sp,#4*8
+	ldmia		r14,{r0-r3}		@ load sigma
+	vld1.32		{q0},[r14]!		@ load sigma
+	vld1.32		{q12},[r14]		@ one
+	vst1.32		{q2-q3},[r12]		@ copy 1/2key|counter|nonce
+	vst1.32		{q0-q1},[sp]		@ copy sigma|1/2key
+
+	str		r10,[sp,#4*(16+10)]	@ off-load "rx"
+	str		r11,[sp,#4*(16+11)]	@ off-load "rx"
+	vshl.i32	d26,d24,#1	@ two
+	vstr		d24,[sp,#4*(16+0)]
+	vshl.i32	d28,d24,#2	@ four
+	vstr		d26,[sp,#4*(16+2)]
+	vmov		q4,q0
+	vstr		d28,[sp,#4*(16+4)]
+	vmov		q8,q0
+	vmov		q5,q1
+	vmov		q9,q1
+	b		.Loop_neon_enter
+
+.align	4
+.Loop_neon_outer:
+	ldmia		sp,{r0-r9}		@ load key material
+	cmp		r11,#64*2		@ if len<=64*2
+	bls		.Lbreak_neon		@ switch to integer-only
+	vmov		q4,q0
+	str		r11,[sp,#4*(32+2)]	@ save len
+	vmov		q8,q0
+	str		r12,  [sp,#4*(32+1)]	@ save inp
+	vmov		q5,q1
+	str		r14,  [sp,#4*(32+0)]	@ save out
+	vmov		q9,q1
+.Loop_neon_enter:
+	ldr		r11, [sp,#4*(15)]
+	vadd.i32	q7,q3,q12		@ counter+1
+	ldr		r12,[sp,#4*(12)]	@ modulo-scheduled load
+	vmov		q6,q2
+	ldr		r10, [sp,#4*(13)]
+	vmov		q10,q2
+	ldr		r14,[sp,#4*(14)]
+	vadd.i32	q11,q7,q12		@ counter+2
+	str		r11, [sp,#4*(16+15)]
+	mov		r11,#10
+	add		r12,r12,#3	@ counter+3
+	b		.Loop_neon
+
+.align	4
+.Loop_neon:
+	subs		r11,r11,#1
+	vadd.i32	q0,q0,q1
+	add	r0,r0,r4
+	vadd.i32	q4,q4,q5
+	mov	r12,r12,ror#16
+	vadd.i32	q8,q8,q9
+	add	r1,r1,r5
+	veor	q3,q3,q0
+	mov	r10,r10,ror#16
+	veor	q7,q7,q4
+	eor	r12,r12,r0,ror#16
+	veor	q11,q11,q8
+	eor	r10,r10,r1,ror#16
+	vrev32.16	q3,q3
+	add	r8,r8,r12
+	vrev32.16	q7,q7
+	mov	r4,r4,ror#20
+	vrev32.16	q11,q11
+	add	r9,r9,r10
+	vadd.i32	q2,q2,q3
+	mov	r5,r5,ror#20
+	vadd.i32	q6,q6,q7
+	eor	r4,r4,r8,ror#20
+	vadd.i32	q10,q10,q11
+	eor	r5,r5,r9,ror#20
+	veor	q12,q1,q2
+	add	r0,r0,r4
+	veor	q13,q5,q6
+	mov	r12,r12,ror#24
+	veor	q14,q9,q10
+	add	r1,r1,r5
+	vshr.u32	q1,q12,#20
+	mov	r10,r10,ror#24
+	vshr.u32	q5,q13,#20
+	eor	r12,r12,r0,ror#24
+	vshr.u32	q9,q14,#20
+	eor	r10,r10,r1,ror#24
+	vsli.32	q1,q12,#12
+	add	r8,r8,r12
+	vsli.32	q5,q13,#12
+	mov	r4,r4,ror#25
+	vsli.32	q9,q14,#12
+	add	r9,r9,r10
+	vadd.i32	q0,q0,q1
+	mov	r5,r5,ror#25
+	vadd.i32	q4,q4,q5
+	str	r10,[sp,#4*(16+13)]
+	vadd.i32	q8,q8,q9
+	ldr	r10,[sp,#4*(16+15)]
+	veor	q12,q3,q0
+	eor	r4,r4,r8,ror#25
+	veor	q13,q7,q4
+	eor	r5,r5,r9,ror#25
+	veor	q14,q11,q8
+	str	r8,[sp,#4*(16+8)]
+	vshr.u32	q3,q12,#24
+	ldr	r8,[sp,#4*(16+10)]
+	vshr.u32	q7,q13,#24
+	add	r2,r2,r6
+	vshr.u32	q11,q14,#24
+	mov	r14,r14,ror#16
+	vsli.32	q3,q12,#8
+	str	r9,[sp,#4*(16+9)]
+	vsli.32	q7,q13,#8
+	ldr	r9,[sp,#4*(16+11)]
+	vsli.32	q11,q14,#8
+	add	r3,r3,r7
+	vadd.i32	q2,q2,q3
+	mov	r10,r10,ror#16
+	vadd.i32	q6,q6,q7
+	eor	r14,r14,r2,ror#16
+	vadd.i32	q10,q10,q11
+	eor	r10,r10,r3,ror#16
+	veor	q12,q1,q2
+	add	r8,r8,r14
+	veor	q13,q5,q6
+	mov	r6,r6,ror#20
+	veor	q14,q9,q10
+	add	r9,r9,r10
+	vshr.u32	q1,q12,#25
+	mov	r7,r7,ror#20
+	vshr.u32	q5,q13,#25
+	eor	r6,r6,r8,ror#20
+	vshr.u32	q9,q14,#25
+	eor	r7,r7,r9,ror#20
+	vsli.32	q1,q12,#7
+	add	r2,r2,r6
+	vsli.32	q5,q13,#7
+	mov	r14,r14,ror#24
+	vsli.32	q9,q14,#7
+	add	r3,r3,r7
+	vext.8	q2,q2,q2,#8
+	mov	r10,r10,ror#24
+	vext.8	q6,q6,q6,#8
+	eor	r14,r14,r2,ror#24
+	vext.8	q10,q10,q10,#8
+	eor	r10,r10,r3,ror#24
+	vext.8	q1,q1,q1,#4
+	add	r8,r8,r14
+	vext.8	q5,q5,q5,#4
+	mov	r6,r6,ror#25
+	vext.8	q9,q9,q9,#4
+	add	r9,r9,r10
+	vext.8	q3,q3,q3,#12
+	mov	r7,r7,ror#25
+	vext.8	q7,q7,q7,#12
+	eor	r6,r6,r8,ror#25
+	vext.8	q11,q11,q11,#12
+	eor	r7,r7,r9,ror#25
+	vadd.i32	q0,q0,q1
+	add	r0,r0,r5
+	vadd.i32	q4,q4,q5
+	mov	r10,r10,ror#16
+	vadd.i32	q8,q8,q9
+	add	r1,r1,r6
+	veor	q3,q3,q0
+	mov	r12,r12,ror#16
+	veor	q7,q7,q4
+	eor	r10,r10,r0,ror#16
+	veor	q11,q11,q8
+	eor	r12,r12,r1,ror#16
+	vrev32.16	q3,q3
+	add	r8,r8,r10
+	vrev32.16	q7,q7
+	mov	r5,r5,ror#20
+	vrev32.16	q11,q11
+	add	r9,r9,r12
+	vadd.i32	q2,q2,q3
+	mov	r6,r6,ror#20
+	vadd.i32	q6,q6,q7
+	eor	r5,r5,r8,ror#20
+	vadd.i32	q10,q10,q11
+	eor	r6,r6,r9,ror#20
+	veor	q12,q1,q2
+	add	r0,r0,r5
+	veor	q13,q5,q6
+	mov	r10,r10,ror#24
+	veor	q14,q9,q10
+	add	r1,r1,r6
+	vshr.u32	q1,q12,#20
+	mov	r12,r12,ror#24
+	vshr.u32	q5,q13,#20
+	eor	r10,r10,r0,ror#24
+	vshr.u32	q9,q14,#20
+	eor	r12,r12,r1,ror#24
+	vsli.32	q1,q12,#12
+	add	r8,r8,r10
+	vsli.32	q5,q13,#12
+	mov	r5,r5,ror#25
+	vsli.32	q9,q14,#12
+	str	r10,[sp,#4*(16+15)]
+	vadd.i32	q0,q0,q1
+	ldr	r10,[sp,#4*(16+13)]
+	vadd.i32	q4,q4,q5
+	add	r9,r9,r12
+	vadd.i32	q8,q8,q9
+	mov	r6,r6,ror#25
+	veor	q12,q3,q0
+	eor	r5,r5,r8,ror#25
+	veor	q13,q7,q4
+	eor	r6,r6,r9,ror#25
+	veor	q14,q11,q8
+	str	r8,[sp,#4*(16+10)]
+	vshr.u32	q3,q12,#24
+	ldr	r8,[sp,#4*(16+8)]
+	vshr.u32	q7,q13,#24
+	add	r2,r2,r7
+	vshr.u32	q11,q14,#24
+	mov	r10,r10,ror#16
+	vsli.32	q3,q12,#8
+	str	r9,[sp,#4*(16+11)]
+	vsli.32	q7,q13,#8
+	ldr	r9,[sp,#4*(16+9)]
+	vsli.32	q11,q14,#8
+	add	r3,r3,r4
+	vadd.i32	q2,q2,q3
+	mov	r14,r14,ror#16
+	vadd.i32	q6,q6,q7
+	eor	r10,r10,r2,ror#16
+	vadd.i32	q10,q10,q11
+	eor	r14,r14,r3,ror#16
+	veor	q12,q1,q2
+	add	r8,r8,r10
+	veor	q13,q5,q6
+	mov	r7,r7,ror#20
+	veor	q14,q9,q10
+	add	r9,r9,r14
+	vshr.u32	q1,q12,#25
+	mov	r4,r4,ror#20
+	vshr.u32	q5,q13,#25
+	eor	r7,r7,r8,ror#20
+	vshr.u32	q9,q14,#25
+	eor	r4,r4,r9,ror#20
+	vsli.32	q1,q12,#7
+	add	r2,r2,r7
+	vsli.32	q5,q13,#7
+	mov	r10,r10,ror#24
+	vsli.32	q9,q14,#7
+	add	r3,r3,r4
+	vext.8	q2,q2,q2,#8
+	mov	r14,r14,ror#24
+	vext.8	q6,q6,q6,#8
+	eor	r10,r10,r2,ror#24
+	vext.8	q10,q10,q10,#8
+	eor	r14,r14,r3,ror#24
+	vext.8	q1,q1,q1,#12
+	add	r8,r8,r10
+	vext.8	q5,q5,q5,#12
+	mov	r7,r7,ror#25
+	vext.8	q9,q9,q9,#12
+	add	r9,r9,r14
+	vext.8	q3,q3,q3,#4
+	mov	r4,r4,ror#25
+	vext.8	q7,q7,q7,#4
+	eor	r7,r7,r8,ror#25
+	vext.8	q11,q11,q11,#4
+	eor	r4,r4,r9,ror#25
+	bne		.Loop_neon
+
+	add		r11,sp,#32
+	vld1.32		{q12-q13},[sp]		@ load key material
+	vld1.32		{q14-q15},[r11]
+
+	ldr		r11,[sp,#4*(32+2)]	@ load len
+
+	str		r8, [sp,#4*(16+8)]	@ modulo-scheduled store
+	str		r9, [sp,#4*(16+9)]
+	str		r12,[sp,#4*(16+12)]
+	str		r10, [sp,#4*(16+13)]
+	str		r14,[sp,#4*(16+14)]
+
+	@ at this point we have first half of 512-bit result in
+	@ rx and second half at sp+4*(16+8)
+
+	ldr		r12,[sp,#4*(32+1)]	@ load inp
+	ldr		r14,[sp,#4*(32+0)]	@ load out
+
+	vadd.i32	q0,q0,q12		@ accumulate key material
+	vadd.i32	q4,q4,q12
+	vadd.i32	q8,q8,q12
+	vldr		d24,[sp,#4*(16+0)]	@ one
+
+	vadd.i32	q1,q1,q13
+	vadd.i32	q5,q5,q13
+	vadd.i32	q9,q9,q13
+	vldr		d26,[sp,#4*(16+2)]	@ two
+
+	vadd.i32	q2,q2,q14
+	vadd.i32	q6,q6,q14
+	vadd.i32	q10,q10,q14
+	vadd.i32	d14,d14,d24	@ counter+1
+	vadd.i32	d22,d22,d26	@ counter+2
+
+	vadd.i32	q3,q3,q15
+	vadd.i32	q7,q7,q15
+	vadd.i32	q11,q11,q15
+
+	cmp		r11,#64*4
+	blo		.Ltail_neon
+
+	vld1.8		{q12-q13},[r12]!	@ load input
+	 mov		r11,sp
+	vld1.8		{q14-q15},[r12]!
+	veor		q0,q0,q12		@ xor with input
+	veor		q1,q1,q13
+	vld1.8		{q12-q13},[r12]!
+	veor		q2,q2,q14
+	veor		q3,q3,q15
+	vld1.8		{q14-q15},[r12]!
+
+	veor		q4,q4,q12
+	 vst1.8		{q0-q1},[r14]!	@ store output
+	veor		q5,q5,q13
+	vld1.8		{q12-q13},[r12]!
+	veor		q6,q6,q14
+	 vst1.8		{q2-q3},[r14]!
+	veor		q7,q7,q15
+	vld1.8		{q14-q15},[r12]!
+
+	veor		q8,q8,q12
+	 vld1.32	{q0-q1},[r11]!	@ load for next iteration
+	 veor		d25,d25,d25
+	 vldr		d24,[sp,#4*(16+4)]	@ four
+	veor		q9,q9,q13
+	 vld1.32	{q2-q3},[r11]
+	veor		q10,q10,q14
+	 vst1.8		{q4-q5},[r14]!
+	veor		q11,q11,q15
+	 vst1.8		{q6-q7},[r14]!
+
+	vadd.i32	d6,d6,d24	@ next counter value
+	vldr		d24,[sp,#4*(16+0)]	@ one
+
+	ldmia		sp,{r8-r11}	@ load key material
+	add		r0,r0,r8	@ accumulate key material
+	ldr		r8,[r12],#16		@ load input
+	 vst1.8		{q8-q9},[r14]!
+	add		r1,r1,r9
+	ldr		r9,[r12,#-12]
+	 vst1.8		{q10-q11},[r14]!
+	add		r2,r2,r10
+	ldr		r10,[r12,#-8]
+	add		r3,r3,r11
+	ldr		r11,[r12,#-4]
+#ifdef	__ARMEB__
+	rev		r0,r0
+	rev		r1,r1
+	rev		r2,r2
+	rev		r3,r3
+#endif
+	eor		r0,r0,r8	@ xor with input
+	 add		r8,sp,#4*(4)
+	eor		r1,r1,r9
+	str		r0,[r14],#16		@ store output
+	eor		r2,r2,r10
+	str		r1,[r14,#-12]
+	eor		r3,r3,r11
+	 ldmia		r8,{r8-r11}	@ load key material
+	str		r2,[r14,#-8]
+	str		r3,[r14,#-4]
+
+	add		r4,r4,r8	@ accumulate key material
+	ldr		r8,[r12],#16		@ load input
+	add		r5,r5,r9
+	ldr		r9,[r12,#-12]
+	add		r6,r6,r10
+	ldr		r10,[r12,#-8]
+	add		r7,r7,r11
+	ldr		r11,[r12,#-4]
+#ifdef	__ARMEB__
+	rev		r4,r4
+	rev		r5,r5
+	rev		r6,r6
+	rev		r7,r7
+#endif
+	eor		r4,r4,r8
+	 add		r8,sp,#4*(8)
+	eor		r5,r5,r9
+	str		r4,[r14],#16		@ store output
+	eor		r6,r6,r10
+	str		r5,[r14,#-12]
+	eor		r7,r7,r11
+	 ldmia		r8,{r8-r11}	@ load key material
+	str		r6,[r14,#-8]
+	 add		r0,sp,#4*(16+8)
+	str		r7,[r14,#-4]
+
+	ldmia		r0,{r0-r7}	@ load second half
+
+	add		r0,r0,r8	@ accumulate key material
+	ldr		r8,[r12],#16		@ load input
+	add		r1,r1,r9
+	ldr		r9,[r12,#-12]
+#ifdef	__thumb2__
+	it	hi
+#endif
+	 strhi		r10,[sp,#4*(16+10)]	@ copy "rx" while at it
+	add		r2,r2,r10
+	ldr		r10,[r12,#-8]
+#ifdef	__thumb2__
+	it	hi
+#endif
+	 strhi		r11,[sp,#4*(16+11)]	@ copy "rx" while at it
+	add		r3,r3,r11
+	ldr		r11,[r12,#-4]
+#ifdef	__ARMEB__
+	rev		r0,r0
+	rev		r1,r1
+	rev		r2,r2
+	rev		r3,r3
+#endif
+	eor		r0,r0,r8
+	 add		r8,sp,#4*(12)
+	eor		r1,r1,r9
+	str		r0,[r14],#16		@ store output
+	eor		r2,r2,r10
+	str		r1,[r14,#-12]
+	eor		r3,r3,r11
+	 ldmia		r8,{r8-r11}	@ load key material
+	str		r2,[r14,#-8]
+	str		r3,[r14,#-4]
+
+	add		r4,r4,r8	@ accumulate key material
+	 add		r8,r8,#4		@ next counter value
+	add		r5,r5,r9
+	 str		r8,[sp,#4*(12)]	@ save next counter value
+	ldr		r8,[r12],#16		@ load input
+	add		r6,r6,r10
+	 add		r4,r4,#3		@ counter+3
+	ldr		r9,[r12,#-12]
+	add		r7,r7,r11
+	ldr		r10,[r12,#-8]
+	ldr		r11,[r12,#-4]
+#ifdef	__ARMEB__
+	rev		r4,r4
+	rev		r5,r5
+	rev		r6,r6
+	rev		r7,r7
+#endif
+	eor		r4,r4,r8
+#ifdef	__thumb2__
+	it	hi
+#endif
+	 ldrhi		r8,[sp,#4*(32+2)]	@ re-load len
+	eor		r5,r5,r9
+	eor		r6,r6,r10
+	str		r4,[r14],#16		@ store output
+	eor		r7,r7,r11
+	str		r5,[r14,#-12]
+	 sub		r11,r8,#64*4	@ len-=64*4
+	str		r6,[r14,#-8]
+	str		r7,[r14,#-4]
+	bhi		.Loop_neon_outer
+
+	b		.Ldone_neon
+
+.align	4
+.Lbreak_neon:
+	@ harmonize NEON and integer-only stack frames: load data
+	@ from NEON frame, but save to integer-only one; distance
+	@ between the two is 4*(32+4+16-32)=4*(20).
+
+	str		r11, [sp,#4*(20+32+2)]	@ save len
+	 add		r11,sp,#4*(32+4)
+	str		r12,   [sp,#4*(20+32+1)]	@ save inp
+	str		r14,   [sp,#4*(20+32+0)]	@ save out
+
+	ldr		r12,[sp,#4*(16+10)]
+	ldr		r14,[sp,#4*(16+11)]
+	 vldmia		r11,{d8-d15}			@ fulfill ABI requirement
+	str		r12,[sp,#4*(20+16+10)]	@ copy "rx"
+	str		r14,[sp,#4*(20+16+11)]	@ copy "rx"
+
+	ldr		r11, [sp,#4*(15)]
+	ldr		r12,[sp,#4*(12)]		@ modulo-scheduled load
+	ldr		r10, [sp,#4*(13)]
+	ldr		r14,[sp,#4*(14)]
+	str		r11, [sp,#4*(20+16+15)]
+	add		r11,sp,#4*(20)
+	vst1.32		{q0-q1},[r11]!		@ copy key
+	add		sp,sp,#4*(20)			@ switch frame
+	vst1.32		{q2-q3},[r11]
+	mov		r11,#10
+	b		.Loop				@ go integer-only
+
+.align	4
+.Ltail_neon:
+	cmp		r11,#64*3
+	bhs		.L192_or_more_neon
+	cmp		r11,#64*2
+	bhs		.L128_or_more_neon
+	cmp		r11,#64*1
+	bhs		.L64_or_more_neon
+
+	add		r8,sp,#4*(8)
+	vst1.8		{q0-q1},[sp]
+	add		r10,sp,#4*(0)
+	vst1.8		{q2-q3},[r8]
+	b		.Loop_tail_neon
+
+.align	4
+.L64_or_more_neon:
+	vld1.8		{q12-q13},[r12]!
+	vld1.8		{q14-q15},[r12]!
+	veor		q0,q0,q12
+	veor		q1,q1,q13
+	veor		q2,q2,q14
+	veor		q3,q3,q15
+	vst1.8		{q0-q1},[r14]!
+	vst1.8		{q2-q3},[r14]!
+
+	beq		.Ldone_neon
+
+	add		r8,sp,#4*(8)
+	vst1.8		{q4-q5},[sp]
+	add		r10,sp,#4*(0)
+	vst1.8		{q6-q7},[r8]
+	sub		r11,r11,#64*1	@ len-=64*1
+	b		.Loop_tail_neon
+
+.align	4
+.L128_or_more_neon:
+	vld1.8		{q12-q13},[r12]!
+	vld1.8		{q14-q15},[r12]!
+	veor		q0,q0,q12
+	veor		q1,q1,q13
+	vld1.8		{q12-q13},[r12]!
+	veor		q2,q2,q14
+	veor		q3,q3,q15
+	vld1.8		{q14-q15},[r12]!
+
+	veor		q4,q4,q12
+	veor		q5,q5,q13
+	 vst1.8		{q0-q1},[r14]!
+	veor		q6,q6,q14
+	 vst1.8		{q2-q3},[r14]!
+	veor		q7,q7,q15
+	vst1.8		{q4-q5},[r14]!
+	vst1.8		{q6-q7},[r14]!
+
+	beq		.Ldone_neon
+
+	add		r8,sp,#4*(8)
+	vst1.8		{q8-q9},[sp]
+	add		r10,sp,#4*(0)
+	vst1.8		{q10-q11},[r8]
+	sub		r11,r11,#64*2	@ len-=64*2
+	b		.Loop_tail_neon
+
+.align	4
+.L192_or_more_neon:
+	vld1.8		{q12-q13},[r12]!
+	vld1.8		{q14-q15},[r12]!
+	veor		q0,q0,q12
+	veor		q1,q1,q13
+	vld1.8		{q12-q13},[r12]!
+	veor		q2,q2,q14
+	veor		q3,q3,q15
+	vld1.8		{q14-q15},[r12]!
+
+	veor		q4,q4,q12
+	veor		q5,q5,q13
+	vld1.8		{q12-q13},[r12]!
+	veor		q6,q6,q14
+	 vst1.8		{q0-q1},[r14]!
+	veor		q7,q7,q15
+	vld1.8		{q14-q15},[r12]!
+
+	veor		q8,q8,q12
+	 vst1.8		{q2-q3},[r14]!
+	veor		q9,q9,q13
+	 vst1.8		{q4-q5},[r14]!
+	veor		q10,q10,q14
+	 vst1.8		{q6-q7},[r14]!
+	veor		q11,q11,q15
+	vst1.8		{q8-q9},[r14]!
+	vst1.8		{q10-q11},[r14]!
+
+	beq		.Ldone_neon
+
+	ldmia		sp,{r8-r11}	@ load key material
+	add		r0,r0,r8	@ accumulate key material
+	 add		r8,sp,#4*(4)
+	add		r1,r1,r9
+	add		r2,r2,r10
+	add		r3,r3,r11
+	 ldmia		r8,{r8-r11}	@ load key material
+
+	add		r4,r4,r8	@ accumulate key material
+	 add		r8,sp,#4*(8)
+	add		r5,r5,r9
+	add		r6,r6,r10
+	add		r7,r7,r11
+	 ldmia		r8,{r8-r11}	@ load key material
+#ifdef	__ARMEB__
+	rev		r0,r0
+	rev		r1,r1
+	rev		r2,r2
+	rev		r3,r3
+	rev		r4,r4
+	rev		r5,r5
+	rev		r6,r6
+	rev		r7,r7
+#endif
+	stmia		sp,{r0-r7}
+	 add		r0,sp,#4*(16+8)
+
+	ldmia		r0,{r0-r7}	@ load second half
+
+	add		r0,r0,r8	@ accumulate key material
+	 add		r8,sp,#4*(12)
+	add		r1,r1,r9
+	add		r2,r2,r10
+	add		r3,r3,r11
+	 ldmia		r8,{r8-r11}	@ load key material
+
+	add		r4,r4,r8	@ accumulate key material
+	 add		r8,sp,#4*(8)
+	add		r5,r5,r9
+	 add		r4,r4,#3		@ counter+3
+	add		r6,r6,r10
+	add		r7,r7,r11
+	 ldr		r11,[sp,#4*(32+2)]	@ re-load len
+#ifdef	__ARMEB__
+	rev		r0,r0
+	rev		r1,r1
+	rev		r2,r2
+	rev		r3,r3
+	rev		r4,r4
+	rev		r5,r5
+	rev		r6,r6
+	rev		r7,r7
+#endif
+	stmia		r8,{r0-r7}
+	 add		r10,sp,#4*(0)
+	 sub		r11,r11,#64*3	@ len-=64*3
+
+.Loop_tail_neon:
+	ldrb		r8,[r10],#1	@ read buffer on stack
+	ldrb		r9,[r12],#1		@ read input
+	subs		r11,r11,#1
+	eor		r8,r8,r9
+	strb		r8,[r14],#1		@ store output
+	bne		.Loop_tail_neon
+
+.Ldone_neon:
+	add		sp,sp,#4*(32+4)
+	vldmia		sp,{d8-d15}
+	add		sp,sp,#4*(16+3)
+.Lno_data_neon:
+	ldmia		sp!,{r4-r11,pc}
+ENDPROC(chacha20_ossl_neon)
+#endif
diff --git a/test_vectors.h b/test_vectors.h
deleted file mode 100644
index 91b24ee..0000000
--- a/test_vectors.h
+++ /dev/null
@@ -1,48 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0
- *
- * Copyright (C) 2018 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
- */
-
-struct curve25519_test_vector {
-	u8 private[CURVE25519_POINT_SIZE];
-	u8 public[CURVE25519_POINT_SIZE];
-	u8 result[CURVE25519_POINT_SIZE];
-};
-
-static const struct curve25519_test_vector curve25519_test_vectors[] __initconst = {
-	{
-		.private = { 0x77, 0x07, 0x6d, 0x0a, 0x73, 0x18, 0xa5, 0x7d, 0x3c, 0x16, 0xc1, 0x72, 0x51, 0xb2, 0x66, 0x45, 0xdf, 0x4c, 0x2f, 0x87, 0xeb, 0xc0, 0x99, 0x2a, 0xb1, 0x77, 0xfb, 0xa5, 0x1d, 0xb9, 0x2c, 0x2a },
-		.public = { 0xde, 0x9e, 0xdb, 0x7d, 0x7b, 0x7d, 0xc1, 0xb4, 0xd3, 0x5b, 0x61, 0xc2, 0xec, 0xe4, 0x35, 0x37, 0x3f, 0x83, 0x43, 0xc8, 0x5b, 0x78, 0x67, 0x4d, 0xad, 0xfc, 0x7e, 0x14, 0x6f, 0x88, 0x2b, 0x4f },
-		.result = { 0x4a, 0x5d, 0x9d, 0x5b, 0xa4, 0xce, 0x2d, 0xe1, 0x72, 0x8e, 0x3b, 0xf4, 0x80, 0x35, 0x0f, 0x25, 0xe0, 0x7e, 0x21, 0xc9, 0x47, 0xd1, 0x9e, 0x33, 0x76, 0xf0, 0x9b, 0x3c, 0x1e, 0x16, 0x17, 0x42 }
-	},
-	{
-		.private = { 0x5d, 0xab, 0x08, 0x7e, 0x62, 0x4a, 0x8a, 0x4b, 0x79, 0xe1, 0x7f, 0x8b, 0x83, 0x80, 0x0e, 0xe6, 0x6f, 0x3b, 0xb1, 0x29, 0x26, 0x18, 0xb6, 0xfd, 0x1c, 0x2f, 0x8b, 0x27, 0xff, 0x88, 0xe0, 0xeb },
-		.public = { 0x85, 0x20, 0xf0, 0x09, 0x89, 0x30, 0xa7, 0x54, 0x74, 0x8b, 0x7d, 0xdc, 0xb4, 0x3e, 0xf7, 0x5a, 0x0d, 0xbf, 0x3a, 0x0d, 0x26, 0x38, 0x1a, 0xf4, 0xeb, 0xa4, 0xa9, 0x8e, 0xaa, 0x9b, 0x4e, 0x6a },
-		.result = { 0x4a, 0x5d, 0x9d, 0x5b, 0xa4, 0xce, 0x2d, 0xe1, 0x72, 0x8e, 0x3b, 0xf4, 0x80, 0x35, 0x0f, 0x25, 0xe0, 0x7e, 0x21, 0xc9, 0x47, 0xd1, 0x9e, 0x33, 0x76, 0xf0, 0x9b, 0x3c, 0x1e, 0x16, 0x17, 0x42 }
-	},
-	{
-		.private = { 1 },
-		.public = { 0x25, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 },
-		.result = { 0x3c, 0x77, 0x77, 0xca, 0xf9, 0x97, 0xb2, 0x64, 0x41, 0x60, 0x77, 0x66, 0x5b, 0x4e, 0x22, 0x9d, 0xb, 0x95, 0x48, 0xdc, 0xc, 0xd8, 0x19, 0x98, 0xdd, 0xcd, 0xc5, 0xc8, 0x53, 0x3c, 0x79, 0x7f }
-	},
-	{
-		.private = { 1 },
-		.public = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff },
-		.result = { 0xb3, 0x2d, 0x13, 0x62, 0xc2, 0x48, 0xd6, 0x2f, 0xe6, 0x26, 0x19, 0xcf, 0xf0, 0x4d, 0xd4, 0x3d, 0xb7, 0x3f, 0xfc, 0x1b, 0x63, 0x8, 0xed, 0xe3, 0xb, 0x78, 0xd8, 0x73, 0x80, 0xf1, 0xe8, 0x34 }
-	},
-	{
-		.private = { 0xa5, 0x46, 0xe3, 0x6b, 0xf0, 0x52, 0x7c, 0x9d, 0x3b, 0x16, 0x15, 0x4b, 0x82, 0x46, 0x5e, 0xdd, 0x62, 0x14, 0x4c, 0x0a, 0xc1, 0xfc, 0x5a, 0x18, 0x50, 0x6a, 0x22, 0x44, 0xba, 0x44, 0x9a, 0xc4 },
-		.public = { 0xe6, 0xdb, 0x68, 0x67, 0x58, 0x30, 0x30, 0xdb, 0x35, 0x94, 0xc1, 0xa4, 0x24, 0xb1, 0x5f, 0x7c, 0x72, 0x66, 0x24, 0xec, 0x26, 0xb3, 0x35, 0x3b, 0x10, 0xa9, 0x03, 0xa6, 0xd0, 0xab, 0x1c, 0x4c },
-		.result = { 0xc3, 0xda, 0x55, 0x37, 0x9d, 0xe9, 0xc6, 0x90, 0x8e, 0x94, 0xea, 0x4d, 0xf2, 0x8d, 0x08, 0x4f, 0x32, 0xec, 0xcf, 0x03, 0x49, 0x1c, 0x71, 0xf7, 0x54, 0xb4, 0x07, 0x55, 0x77, 0xa2, 0x85, 0x52 }
-	},
-	{
-		.private = { 1, 2, 3, 4 },
-		.public = { 0 },
-		.result = { 0 }
-	},
-	{
-		.private = { 2, 4, 6, 8 },
-		.public = { 0xe0, 0xeb, 0x7a, 0x7c, 0x3b, 0x41, 0xb8, 0xae, 0x16, 0x56, 0xe3, 0xfa, 0xf1, 0x9f, 0xc4, 0x6a, 0xda, 0x09, 0x8d, 0xeb, 0x9c, 0x32, 0xb1, 0xfd, 0x86, 0x62, 0x05, 0x16, 0x5f, 0x49, 0xb8 },
-		.result = { 0 }
-	}
-};