The way the KECCAK transform is currently coded involves many references
into the state array using indexes that are calculated at runtime using
simple but non-trivial arithmetic. This forces the compiler to treat the
state matrix as an array in memory rather than keep it in registers,
which results in poor performance.
So instead, let's rephrase the algorithm using fixed array indexes only.
This helps the compiler keep the state matrix in registers, resulting
in the following speedup (SHA3-256 performance in cycles per byte):
before after speedup
Intel Core i7 @ 2.0 GHz (2.9 turbo) 100.6 35.7 2.8x
Cortex-A57 @ 2.0 GHz (64-bit mode) 101.6 12.7 8.0x
Cortex-A53 @ 1.0 GHz 224.4 15.8 14.2x
Cortex-A57 @ 2.0 GHz (32-bit mode) 201.8 63.0 3.2x
Signed-off-by: Ard Biesheuvel <ard.biesheu...@linaro.org>
---
Raw tcrypt performance numbers after the patch.
crypto/sha3_generic.c | 134 ++++++++++++++------
1 file changed, 96 insertions(+), 38 deletions(-)
diff --git a/crypto/sha3_generic.c b/crypto/sha3_generic.c
index a68be626017c..5fecb609e3be 100644
--- a/crypto/sha3_generic.c
+++ b/crypto/sha3_generic.c
@@ -5,6 +5,7 @@
* http://nvlpubs.nist.gov/nistpubs/FIPS/NIST.FIPS.202.pdf
*
* SHA-3 code by Jeff Garzik <j...@garzik.org>
+ * Ard Biesheuvel <ard.biesheu...@linaro.org>
*
* 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
@@ -22,8 +23,6 @@
#define KECCAK_ROUNDS 24
-#define ROTL64(x, y) (((x) << (y)) | ((x) >> (64 - (y))))
-
static const u64 keccakf_rndc[24] = {
0x0000000000000001ULL, 0x0000000000008082ULL, 0x800000000000808aULL,
0x8000000080008000ULL, 0x000000000000808bULL, 0x0000000080000001ULL,
@@ -35,53 +34,112 @@ static const u64 keccakf_rndc[24] = {
0x8000000000008080ULL, 0x0000000080000001ULL, 0x8000000080008008ULL
};
-static const int keccakf_rotc[24] = {
- 1, 3, 6, 10, 15, 21, 28, 36, 45, 55, 2, 14,
- 27, 41, 56, 8, 25, 43, 62, 18, 39, 61, 20, 44
-};
-
-static const int keccakf_piln[24] = {
- 10, 7, 11, 17, 18, 3, 5, 16, 8, 21, 24, 4,
- 15, 23, 19, 13, 12, 2, 20, 14, 22, 9, 6, 1
-};
-
/* update the state with given number of rounds */
-static void keccakf(u64 st[25])
+static void __attribute__((__optimize__("O3"))) keccakf(u64 st[25])
{
- int i, j, round;
- u64 t, bc[5];
+ u64 t[5], tt, bc[5];
+ int round;
for (round = 0; round < KECCAK_ROUNDS; round++) {
/* Theta */
- for (i = 0; i < 5; i++)
- bc[i] = st[i] ^ st[i + 5] ^ st[i + 10] ^ st[i + 15]
- ^ st[i + 20];
-
- for (i = 0; i < 5; i++) {
- t = bc[(i + 4) % 5] ^ ROTL64(bc[(i + 1) % 5], 1);
- for (j = 0; j < 25; j += 5)
- st[j + i] ^= t;
- }
+ bc[0] = st[0] ^ st[5] ^ st[10] ^ st[15] ^ st[20];
+ bc[1] = st[1] ^ st[6] ^ st[11] ^ st[16] ^ st[21];
+ bc[2] = st[2] ^ st[7] ^ st[12] ^ st[17] ^ st[22];
+ bc[3] = st[3] ^ st[8] ^ st[13] ^ st[18] ^ st[23];
+ bc[4] = st[4] ^ st[9] ^ st[14] ^ st[19] ^ st[24];
+
+ t[0] = bc[4] ^ rol64(bc[1], 1);
+ t[1] = bc[0] ^ rol64(bc[2], 1);
+ t[2] = bc[1] ^ rol64(bc[3], 1);
+ t[3] = bc[2] ^ rol64(bc[4], 1);
+ t[4] = bc[3] ^ rol64(bc[0], 1);
+
+ st[0] ^= t[0];
/* Rho Pi */
- t = st[1];
- for (i = 0; i < 24; i++) {
- j = keccakf_piln[i];
- bc[0] = st[j];
- st[j] = ROTL64(t, keccakf_rotc[i]);
- t = bc[0];
- }
+ tt = st[1];
+ st[ 1] = rol64(st[ 6] ^ t[1], 44);
+ st[ 6] = rol64(st[ 9] ^ t[4], 20);
+ st[ 9] = rol64(st[22] ^ t[2], 61);
+ st[22] = rol64(st[14] ^ t[4], 39);
+ st[14] = rol64(st[20] ^ t[0], 18);
+ st[20] = rol64(st[ 2] ^ t[2], 62);
+ st[ 2] = rol64(st[12] ^ t[2], 43);
+ st[12] = rol64(st[13] ^ t[3], 25);
+ st[13] = rol64(st[19] ^ t[4], 8);
+ st[19] = rol64(st[23] ^ t[3], 56);
+ st[23] = rol64(st[15] ^ t[0], 41);
+ st[15] = rol64(st[ 4] ^ t[4], 27);
+ st[ 4] = rol64(st[24] ^ t[4], 14);
+ st[24] = rol64(st[21] ^ t[1], 2);
+ st[21] = rol64(st[ 8] ^ t[3], 55);
+ st[ 8] = rol64(st[16] ^ t[1], 45);
+ st[16] = rol64(st[ 5] ^ t[0], 36);
+ st[ 5] = rol64(st[ 3] ^ t[3], 28);
+ st[ 3] = rol64(st[18] ^ t[3], 21);
+ st[18] = rol64(st[17] ^ t[2], 15);
+ st[17] = rol64(st[11] ^ t[1], 10);
+ st[11] = rol64(st[ 7] ^ t[2], 6);
+ st[ 7] = rol64(st[10] ^ t[0], 3);
+ st[10] = rol64( tt ^ t[1], 1);
/* Chi */
- for (j = 0; j < 25; j += 5) {
- for (i = 0; i < 5; i++)
- bc[i] = st[j + i];
- for (i = 0; i < 5; i++)
- st[j + i] ^= (~bc[(i + 1) % 5]) &
- bc[(i + 2) % 5];
- }
+ bc[ 0] = ~st[ 1] & st[ 2];
+ bc[ 1] = ~st[ 2] & st[ 3];
+ bc[ 2] = ~st[ 3] & st[ 4];
+ bc[ 3] = ~st[ 4] & st[ 0];
+ bc[ 4] = ~st[ 0] & st[ 1];
+ st[ 0] ^= bc[ 0];
+ st[ 1] ^= bc[ 1];
+ st[ 2] ^= bc[ 2];
+ st[ 3] ^= bc[ 3];
+ st[ 4] ^= bc[ 4];
+
+ bc[ 0] = ~st[ 6] & st[ 7];
+ bc[ 1] = ~st[ 7] & st[ 8];
+ bc[ 2] = ~st[ 8] & st[ 9];
+ bc[ 3] = ~st[ 9] & st[ 5];
+ bc[ 4] = ~st[ 5] & st[ 6];
+ st[ 5] ^= bc[ 0];
+ st[ 6] ^= bc[ 1];
+ st[ 7] ^= bc[ 2];
+ st[ 8] ^= bc[ 3];
+ st[ 9] ^= bc[ 4];
+
+ bc[ 0] = ~st[11] & st[12];
+ bc[ 1] = ~st[12] & st[13];
+ bc[ 2] = ~st[13] & st[14];
+ bc[ 3] = ~st[14] & st[10];
+ bc[ 4] = ~st[10] & st[11];
+ st[10] ^= bc[ 0];
+ st[11] ^= bc[ 1];
+ st[12] ^= bc[ 2];
+ st[13] ^= bc[ 3];
+ st[14] ^= bc[ 4];
+
+ bc[ 0] = ~st[16] & st[17];
+ bc[ 1] = ~st[17] & st[18];
+ bc[ 2] = ~st[18] & st[19];
+ bc[ 3] = ~st[19] & st[15];
+ bc[ 4] = ~st[15] & st[16];
+ st[15] ^= bc[ 0];
+ st[16] ^= bc[ 1];
+ st[17] ^= bc[ 2];
+ st[18] ^= bc[ 3];
+ st[19] ^= bc[ 4];
+
+ bc[ 0] = ~st[21] & st[22];
+ bc[ 1] = ~st[22] & st[23];
+ bc[ 2] = ~st[23] & st[24];
+ bc[ 3] = ~st[24] & st[20];
+ bc[ 4] = ~st[20] & st[21];
+ st[20] ^= bc[ 0];
+ st[21] ^= bc[ 1];
+ st[22] ^= bc[ 2];
+ st[23] ^= bc[ 3];
+ st[24] ^= bc[ 4];
/* Iota */
st[0] ^= keccakf_rndc[round];
--
2.11.0
x86_64: Intel Core i7 @ 2.0 GHz (2.9 GHz turbo speed)
Before:
testing speed of async sha3-256 (sha3-256-generic)
tcrypt: test 0 ( 16 byte blocks, 16 bytes per update, 1 updates): 212552
opers/sec, 3400832 bytes/sec
tcrypt: test 1 ( 64 byte blocks, 16 bytes per update, 4 updates): 199875
opers/sec, 12792000 bytes/sec
tcrypt: test 2 ( 64 byte blocks, 64 bytes per update, 1 updates): 210336
opers/sec, 13461504 bytes/sec
tcrypt: test 3 ( 256 byte blocks, 16 bytes per update, 16 updates): 99741
opers/sec, 25533696 bytes/sec
tcrypt: test 4 ( 256 byte blocks, 64 bytes per update, 4 updates): 103238
opers/sec, 26428928 bytes/sec
tcrypt: test 5 ( 256 byte blocks, 256 bytes per update, 1 updates): 102563
opers/sec, 26256128 bytes/sec
tcrypt: test 6 ( 1024 byte blocks, 16 bytes per update, 64 updates): 24673
opers/sec, 25265152 bytes/sec
tcrypt: test 7 ( 1024 byte blocks, 256 bytes per update, 4 updates): 26060
opers/sec, 26685440 bytes/sec
tcrypt: test 8 ( 1024 byte blocks, 1024 bytes per update, 1 updates): 26006
opers/sec, 26630144 bytes/sec
tcrypt: test 9 ( 2048 byte blocks, 16 bytes per update, 128 updates): 12346
opers/sec, 25284608 bytes/sec
tcrypt: test 10 ( 2048 byte blocks, 256 bytes per update, 8 updates): 13463
opers/sec, 27572224 bytes/sec
tcrypt: test 11 ( 2048 byte blocks, 1024 bytes per update, 2 updates): 12921
opers/sec, 26462208 bytes/sec
tcrypt: test 12 ( 2048 byte blocks, 2048 bytes per update, 1 updates): 13493
opers/sec, 27633664 bytes/sec
tcrypt: test 13 ( 4096 byte blocks, 16 bytes per update, 256 updates): 6618
opers/sec, 27107328 bytes/sec
tcrypt: test 14 ( 4096 byte blocks, 256 bytes per update, 16 updates): 6806
opers/sec, 27877376 bytes/sec
tcrypt: test 15 ( 4096 byte blocks, 1024 bytes per update, 4 updates): 6884
opers/sec, 28196864 bytes/sec
tcrypt: test 16 ( 4096 byte blocks, 4096 bytes per update, 1 updates): 6737
opers/sec, 27594752 bytes/sec
tcrypt: test 17 ( 8192 byte blocks, 16 bytes per update, 512 updates): 3360
opers/sec, 27525120 bytes/sec
tcrypt: test 18 ( 8192 byte blocks, 256 bytes per update, 32 updates): 3530
opers/sec, 28917760 bytes/sec
tcrypt: test 19 ( 8192 byte blocks, 1024 bytes per update, 8 updates): 3550
opers/sec, 29081600 bytes/sec
tcrypt: test 20 ( 8192 byte blocks, 4096 bytes per update, 2 updates): 3550
opers/sec, 29081600 bytes/sec
tcrypt: test 21 ( 8192 byte blocks, 8192 bytes per update, 1 updates): 3519
opers/sec, 28827648 bytes/sec
After:
testing speed of async sha3-256 (sha3-256-generic)
tcrypt: test 0 ( 16 byte blocks, 16 bytes per update, 1 updates): 573076
opers/sec, 9169216 bytes/sec
tcrypt: test 1 ( 64 byte blocks, 16 bytes per update, 4 updates): 531555
opers/sec, 34019520 bytes/sec
tcrypt: test 2 ( 64 byte blocks, 64 bytes per update, 1 updates): 557783
opers/sec, 35698112 bytes/sec
tcrypt: test 3 ( 256 byte blocks, 16 bytes per update, 16 updates): 247385
opers/sec, 63330560 bytes/sec
tcrypt: test 4 ( 256 byte blocks, 64 bytes per update, 4 updates): 277352
opers/sec, 71002112 bytes/sec
tcrypt: test 5 ( 256 byte blocks, 256 bytes per update, 1 updates): 281026
opers/sec, 71942656 bytes/sec
tcrypt: test 6 ( 1024 byte blocks, 16 bytes per update, 64 updates): 59950
opers/sec, 61388800 bytes/sec
tcrypt: test 7 ( 1024 byte blocks, 256 bytes per update, 4 updates): 73643
opers/sec, 75410432 bytes/sec
tcrypt: test 8 ( 1024 byte blocks, 1024 bytes per update, 1 updates): 76192
opers/sec, 78020608 bytes/sec
tcrypt: test 9 ( 2048 byte blocks, 16 bytes per update, 128 updates): 32242
opers/sec, 66031616 bytes/sec
tcrypt: test 10 ( 2048 byte blocks, 256 bytes per update, 8 updates): 34339
opers/sec, 70326272 bytes/sec
tcrypt: test 11 ( 2048 byte blocks, 1024 bytes per update, 2 updates): 36767
opers/sec, 75298816 bytes/sec
tcrypt: test 12 ( 2048 byte blocks, 2048 bytes per update, 1 updates): 36617
opers/sec, 74991616 bytes/sec
tcrypt: test 13 ( 4096 byte blocks, 16 bytes per update, 256 updates): 15908
opers/sec, 65159168 bytes/sec
tcrypt: test 14 ( 4096 byte blocks, 256 bytes per update, 16 updates): 18932
opers/sec, 77545472 bytes/sec
tcrypt: test 15 ( 4096 byte blocks, 1024 bytes per update, 4 updates): 18032
opers/sec, 73859072 bytes/sec
tcrypt: test 16 ( 4096 byte blocks, 4096 bytes per update, 1 updates): 19103
opers/sec, 78245888 bytes/sec
tcrypt: test 17 ( 8192 byte blocks, 16 bytes per update, 512 updates): 7843
opers/sec, 64249856 bytes/sec
tcrypt: test 18 ( 8192 byte blocks, 256 bytes per update, 32 updates): 9161
opers/sec, 75046912 bytes/sec
tcrypt: test 19 ( 8192 byte blocks, 1024 bytes per update, 8 updates): 9679
opers/sec, 79290368 bytes/sec
tcrypt: test 20 ( 8192 byte blocks, 4096 bytes per update, 2 updates): 9878
opers/sec, 80920576 bytes/sec
tcrypt: test 21 ( 8192 byte blocks, 8192 bytes per update, 1 updates): 9907
opers/sec, 81158144 bytes/sec
arm64: Cortex-A57 @ 2 GHz
Before:
testing speed of async sha3-256 (sha3-256-generic)
tcrypt: test 0 ( 16 byte blocks, 16 bytes per update, 1 updates): 143072
opers/sec, 2289152 bytes/sec
tcrypt: test 1 ( 64 byte blocks, 16 bytes per update, 4 updates): 138358
opers/sec, 8854912 bytes/sec
tcrypt: test 2 ( 64 byte blocks, 64 bytes per update, 1 updates): 143392
opers/sec, 9177088 bytes/sec
tcrypt: test 3 ( 256 byte blocks, 16 bytes per update, 16 updates): 67063
opers/sec, 17168128 bytes/sec
tcrypt: test 4 ( 256 byte blocks, 64 bytes per update, 4 updates): 71026
opers/sec, 18182656 bytes/sec
tcrypt: test 5 ( 256 byte blocks, 256 bytes per update, 1 updates): 72294
opers/sec, 18507264 bytes/sec
tcrypt: test 6 ( 1024 byte blocks, 16 bytes per update, 64 updates): 16847
opers/sec, 17251328 bytes/sec
tcrypt: test 7 ( 1024 byte blocks, 256 bytes per update, 4 updates): 18163
opers/sec, 18598912 bytes/sec
tcrypt: test 8 ( 1024 byte blocks, 1024 bytes per update, 1 updates): 18290
opers/sec, 18728960 bytes/sec
tcrypt: test 9 ( 2048 byte blocks, 16 bytes per update, 128 updates): 8429
opers/sec, 17262592 bytes/sec
tcrypt: test 10 ( 2048 byte blocks, 256 bytes per update, 8 updates): 9090
opers/sec, 18616320 bytes/sec
tcrypt: test 11 ( 2048 byte blocks, 1024 bytes per update, 2 updates): 9144
opers/sec, 18726912 bytes/sec
tcrypt: test 12 ( 2048 byte blocks, 2048 bytes per update, 1 updates): 9160
opers/sec, 18759680 bytes/sec
tcrypt: test 13 ( 4096 byte blocks, 16 bytes per update, 256 updates): 4343
opers/sec, 17788928 bytes/sec
tcrypt: test 14 ( 4096 byte blocks, 256 bytes per update, 16 updates): 4684
opers/sec, 19185664 bytes/sec
tcrypt: test 15 ( 4096 byte blocks, 1024 bytes per update, 4 updates): 4721
opers/sec, 19337216 bytes/sec
tcrypt: test 16 ( 4096 byte blocks, 4096 bytes per update, 1 updates): 4719
opers/sec, 19329024 bytes/sec
tcrypt: test 17 ( 8192 byte blocks, 16 bytes per update, 512 updates): 2204
opers/sec, 18055168 bytes/sec
tcrypt: test 18 ( 8192 byte blocks, 256 bytes per update, 32 updates): 2382
opers/sec, 19513344 bytes/sec
tcrypt: test 19 ( 8192 byte blocks, 1024 bytes per update, 8 updates): 2398
opers/sec, 19644416 bytes/sec
tcrypt: test 20 ( 8192 byte blocks, 4096 bytes per update, 2 updates): 2402
opers/sec, 19677184 bytes/sec
tcrypt: test 21 ( 8192 byte blocks, 8192 bytes per update, 1 updates): 2403
opers/sec, 19685376 bytes/sec
After:
testing speed of async sha3-256 (sha3-256-generic)
tcrypt: test 0 ( 16 byte blocks, 16 bytes per update, 1 updates): 995408
opers/sec, 15926528 bytes/sec
tcrypt: test 1 ( 64 byte blocks, 16 bytes per update, 4 updates): 836897
opers/sec, 53561408 bytes/sec
tcrypt: test 2 ( 64 byte blocks, 64 bytes per update, 1 updates): 998895
opers/sec, 63929280 bytes/sec
tcrypt: test 3 ( 256 byte blocks, 16 bytes per update, 16 updates): 358970
opers/sec, 91896320 bytes/sec
tcrypt: test 4 ( 256 byte blocks, 64 bytes per update, 4 updates): 478617
opers/sec, 122525952 bytes/sec
tcrypt: test 5 ( 256 byte blocks, 256 bytes per update, 1 updates): 535961
opers/sec, 137206016 bytes/sec
tcrypt: test 6 ( 1024 byte blocks, 16 bytes per update, 64 updates): 92055
opers/sec, 94264320 bytes/sec
tcrypt: test 7 ( 1024 byte blocks, 256 bytes per update, 4 updates): 137677
opers/sec, 140981248 bytes/sec
tcrypt: test 8 ( 1024 byte blocks, 1024 bytes per update, 1 updates): 143914
opers/sec, 147367936 bytes/sec
tcrypt: test 9 ( 2048 byte blocks, 16 bytes per update, 128 updates): 46197
opers/sec, 94611456 bytes/sec
tcrypt: test 10 ( 2048 byte blocks, 256 bytes per update, 8 updates): 69153
opers/sec, 141625344 bytes/sec
tcrypt: test 11 ( 2048 byte blocks, 1024 bytes per update, 2 updates): 72247
opers/sec, 147961856 bytes/sec
tcrypt: test 12 ( 2048 byte blocks, 2048 bytes per update, 1 updates): 72836
opers/sec, 149168128 bytes/sec
tcrypt: test 13 ( 4096 byte blocks, 16 bytes per update, 256 updates): 23606
opers/sec, 96690176 bytes/sec
tcrypt: test 14 ( 4096 byte blocks, 256 bytes per update, 16 updates): 35578
opers/sec, 145727488 bytes/sec
tcrypt: test 15 ( 4096 byte blocks, 1024 bytes per update, 4 updates): 37365
opers/sec, 153047040 bytes/sec
tcrypt: test 16 ( 4096 byte blocks, 4096 bytes per update, 1 updates): 37776
opers/sec, 154730496 bytes/sec
tcrypt: test 17 ( 8192 byte blocks, 16 bytes per update, 512 updates): 11947
opers/sec, 97869824 bytes/sec
tcrypt: test 18 ( 8192 byte blocks, 256 bytes per update, 32 updates): 18095
opers/sec, 148234240 bytes/sec
tcrypt: test 19 ( 8192 byte blocks, 1024 bytes per update, 8 updates): 18981
opers/sec, 155492352 bytes/sec
tcrypt: test 20 ( 8192 byte blocks, 4096 bytes per update, 2 updates): 19243
opers/sec, 157638656 bytes/sec
tcrypt: test 21 ( 8192 byte blocks, 8192 bytes per update, 1 updates): 19231
opers/sec, 157540352 bytes/sec
ARM (32-bit): Cortex-A57 @ 2 GHz
Before:
testing speed of async sha3-256 (sha3-256-generic)
tcrypt: test 0 ( 16 byte blocks, 16 bytes per update, 1 updates): 73362
opers/sec, 1173792 bytes/sec
tcrypt: test 1 ( 64 byte blocks, 16 bytes per update, 4 updates): 71917
opers/sec, 4602688 bytes/sec
tcrypt: test 2 ( 64 byte blocks, 64 bytes per update, 1 updates): 73214
opers/sec, 4685696 bytes/sec
tcrypt: test 3 ( 256 byte blocks, 16 bytes per update, 16 updates): 35384
opers/sec, 9058304 bytes/sec
tcrypt: test 4 ( 256 byte blocks, 64 bytes per update, 4 updates): 36474
opers/sec, 9337344 bytes/sec
tcrypt: test 5 ( 256 byte blocks, 256 bytes per update, 1 updates): 36867
opers/sec, 9437952 bytes/sec
tcrypt: test 6 ( 1024 byte blocks, 16 bytes per update, 64 updates): 8862
opers/sec, 9074688 bytes/sec
tcrypt: test 7 ( 1024 byte blocks, 256 bytes per update, 4 updates): 9227
opers/sec, 9448448 bytes/sec
tcrypt: test 8 ( 1024 byte blocks, 1024 bytes per update, 1 updates): 9264
opers/sec, 9486336 bytes/sec
tcrypt: test 9 ( 2048 byte blocks, 16 bytes per update, 128 updates): 4434
opers/sec, 9080832 bytes/sec
tcrypt: test 10 ( 2048 byte blocks, 256 bytes per update, 8 updates): 4613
opers/sec, 9447424 bytes/sec
tcrypt: test 11 ( 2048 byte blocks, 1024 bytes per update, 2 updates): 4633
opers/sec, 9488384 bytes/sec
tcrypt: test 12 ( 2048 byte blocks, 2048 bytes per update, 1 updates): 4636
opers/sec, 9494528 bytes/sec
tcrypt: test 13 ( 4096 byte blocks, 16 bytes per update, 256 updates): 2286
opers/sec, 9363456 bytes/sec
tcrypt: test 14 ( 4096 byte blocks, 256 bytes per update, 16 updates): 2381
opers/sec, 9752576 bytes/sec
tcrypt: test 15 ( 4096 byte blocks, 1024 bytes per update, 4 updates): 2391
opers/sec, 9793536 bytes/sec
tcrypt: test 16 ( 4096 byte blocks, 4096 bytes per update, 1 updates): 2394
opers/sec, 9805824 bytes/sec
tcrypt: test 17 ( 8192 byte blocks, 16 bytes per update, 512 updates): 1161
opers/sec, 9510912 bytes/sec
tcrypt: test 18 ( 8192 byte blocks, 256 bytes per update, 32 updates): 1210
opers/sec, 9912320 bytes/sec
tcrypt: test 19 ( 8192 byte blocks, 1024 bytes per update, 8 updates): 1216
opers/sec, 9961472 bytes/sec
tcrypt: test 20 ( 8192 byte blocks, 4096 bytes per update, 2 updates): 1210
opers/sec, 9912320 bytes/sec
After:
testing speed of async sha3-256 (sha3-256-generic)
tcrypt: test 0 ( 16 byte blocks, 16 bytes per update, 1 updates): 227843
opers/sec, 3645488 bytes/sec
tcrypt: test 1 ( 64 byte blocks, 16 bytes per update, 4 updates): 215525
opers/sec, 13793600 bytes/sec
tcrypt: test 2 ( 64 byte blocks, 64 bytes per update, 1 updates): 227163
opers/sec, 14538432 bytes/sec
tcrypt: test 3 ( 256 byte blocks, 16 bytes per update, 16 updates): 102748
opers/sec, 26303488 bytes/sec
tcrypt: test 4 ( 256 byte blocks, 64 bytes per update, 4 updates): 112404
opers/sec, 28775424 bytes/sec
tcrypt: test 5 ( 256 byte blocks, 256 bytes per update, 1 updates): 115819
opers/sec, 29649664 bytes/sec
tcrypt: test 6 ( 1024 byte blocks, 16 bytes per update, 64 updates): 25852
opers/sec, 26472448 bytes/sec
tcrypt: test 7 ( 1024 byte blocks, 256 bytes per update, 4 updates): 29066
opers/sec, 29763584 bytes/sec
tcrypt: test 8 ( 1024 byte blocks, 1024 bytes per update, 1 updates): 29421
opers/sec, 30127104 bytes/sec
tcrypt: test 9 ( 2048 byte blocks, 16 bytes per update, 128 updates): 12941
opers/sec, 26503168 bytes/sec
tcrypt: test 10 ( 2048 byte blocks, 256 bytes per update, 8 updates): 14534
opers/sec, 29765632 bytes/sec
tcrypt: test 11 ( 2048 byte blocks, 1024 bytes per update, 2 updates): 14718
opers/sec, 30142464 bytes/sec
tcrypt: test 12 ( 2048 byte blocks, 2048 bytes per update, 1 updates): 14735
opers/sec, 30177280 bytes/sec
tcrypt: test 13 ( 4096 byte blocks, 16 bytes per update, 256 updates): 6651
opers/sec, 27242496 bytes/sec
tcrypt: test 14 ( 4096 byte blocks, 256 bytes per update, 16 updates): 7495
opers/sec, 30699520 bytes/sec
tcrypt: test 15 ( 4096 byte blocks, 1024 bytes per update, 4 updates): 7595
opers/sec, 31109120 bytes/sec
tcrypt: test 16 ( 4096 byte blocks, 4096 bytes per update, 1 updates): 7623
opers/sec, 31223808 bytes/sec
tcrypt: test 17 ( 8192 byte blocks, 16 bytes per update, 512 updates): 3375
opers/sec, 27648000 bytes/sec
tcrypt: test 18 ( 8192 byte blocks, 256 bytes per update, 32 updates): 3810
opers/sec, 31211520 bytes/sec
tcrypt: test 19 ( 8192 byte blocks, 1024 bytes per update, 8 updates): 3860
opers/sec, 31621120 bytes/sec
tcrypt: test 20 ( 8192 byte blocks, 4096 bytes per update, 2 updates): 3125
opers/sec, 25600000 bytes/sec
tcrypt: test 21 ( 8192 byte blocks, 8192 bytes per update, 1 updates): 3875
opers/sec, 31744000 bytes/sec
arm64: Cortex-A53 @ 1 GHz
Before:
testing speed of async sha3-256 (sha3-256-generic)
tcrypt: test 0 ( 16 byte blocks, 16 bytes per update, 1 updates): 32491
opers/sec, 519856 bytes/sec
tcrypt: test 1 ( 64 byte blocks, 16 bytes per update, 4 updates): 31554
opers/sec, 2019456 bytes/sec
tcrypt: test 2 ( 64 byte blocks, 64 bytes per update, 1 updates): 32510
opers/sec, 2080640 bytes/sec
tcrypt: test 3 ( 256 byte blocks, 16 bytes per update, 16 updates): 15363
opers/sec, 3932928 bytes/sec
tcrypt: test 4 ( 256 byte blocks, 64 bytes per update, 4 updates): 16164
opers/sec, 4137984 bytes/sec
tcrypt: test 5 ( 256 byte blocks, 256 bytes per update, 1 updates): 16440
opers/sec, 4208640 bytes/sec
tcrypt: test 6 ( 1024 byte blocks, 16 bytes per update, 64 updates): 3859
opers/sec, 3951616 bytes/sec
tcrypt: test 7 ( 1024 byte blocks, 256 bytes per update, 4 updates): 4124
opers/sec, 4222976 bytes/sec
tcrypt: test 8 ( 1024 byte blocks, 1024 bytes per update, 1 updates): 4144
opers/sec, 4243456 bytes/sec
tcrypt: test 9 ( 2048 byte blocks, 16 bytes per update, 128 updates): 1931
opers/sec, 3954688 bytes/sec
tcrypt: test 10 ( 2048 byte blocks, 256 bytes per update, 8 updates): 2064
opers/sec, 4227072 bytes/sec
tcrypt: test 11 ( 2048 byte blocks, 1024 bytes per update, 2 updates): 2072
opers/sec, 4243456 bytes/sec
tcrypt: test 12 ( 2048 byte blocks, 2048 bytes per update, 1 updates): 2073
opers/sec, 4245504 bytes/sec
tcrypt: test 13 ( 4096 byte blocks, 16 bytes per update, 256 updates): 995
opers/sec, 4075520 bytes/sec
tcrypt: test 14 ( 4096 byte blocks, 256 bytes per update, 16 updates): 1066
opers/sec, 4366336 bytes/sec
tcrypt: test 15 ( 4096 byte blocks, 1024 bytes per update, 4 updates): 1068
opers/sec, 4374528 bytes/sec
tcrypt: test 16 ( 4096 byte blocks, 4096 bytes per update, 1 updates): 1071
opers/sec, 4386816 bytes/sec
tcrypt: test 17 ( 8192 byte blocks, 16 bytes per update, 512 updates): 505
opers/sec, 4136960 bytes/sec
tcrypt: test 18 ( 8192 byte blocks, 256 bytes per update, 32 updates): 541
opers/sec, 4431872 bytes/sec
tcrypt: test 19 ( 8192 byte blocks, 1024 bytes per update, 8 updates): 544
opers/sec, 4456448 bytes/sec
tcrypt: test 20 ( 8192 byte blocks, 4096 bytes per update, 2 updates): 545
opers/sec, 4464640 bytes/sec
tcrypt: test 21 ( 8192 byte blocks, 8192 bytes per update, 1 updates): 544
opers/sec, 4456448 bytes/sec
After:
testing speed of async sha3-256 (sha3-256-generic)
tcrypt: test 0 ( 16 byte blocks, 16 bytes per update, 1 updates): 361457
opers/sec, 5783312 bytes/sec
tcrypt: test 1 ( 64 byte blocks, 16 bytes per update, 4 updates): 276617
opers/sec, 17703488 bytes/sec
tcrypt: test 2 ( 64 byte blocks, 64 bytes per update, 1 updates): 362401
opers/sec, 23193664 bytes/sec
tcrypt: test 3 ( 256 byte blocks, 16 bytes per update, 16 updates): 110172
opers/sec, 28204032 bytes/sec
tcrypt: test 4 ( 256 byte blocks, 64 bytes per update, 4 updates): 173328
opers/sec, 44371968 bytes/sec
tcrypt: test 5 ( 256 byte blocks, 256 bytes per update, 1 updates): 205239
opers/sec, 52541184 bytes/sec
tcrypt: test 6 ( 1024 byte blocks, 16 bytes per update, 64 updates): 28316
opers/sec, 28995584 bytes/sec
tcrypt: test 7 ( 1024 byte blocks, 256 bytes per update, 4 updates): 53766
opers/sec, 55056384 bytes/sec
tcrypt: test 8 ( 1024 byte blocks, 1024 bytes per update, 1 updates): 57094
opers/sec, 58464256 bytes/sec
tcrypt: test 9 ( 2048 byte blocks, 16 bytes per update, 128 updates): 14220
opers/sec, 29122560 bytes/sec
tcrypt: test 10 ( 2048 byte blocks, 256 bytes per update, 8 updates): 27074
opers/sec, 55447552 bytes/sec
tcrypt: test 11 ( 2048 byte blocks, 1024 bytes per update, 2 updates): 28814
opers/sec, 59011072 bytes/sec
tcrypt: test 12 ( 2048 byte blocks, 2048 bytes per update, 1 updates): 29113
opers/sec, 59623424 bytes/sec
tcrypt: test 13 ( 4096 byte blocks, 16 bytes per update, 256 updates): 7244
opers/sec, 29671424 bytes/sec
tcrypt: test 14 ( 4096 byte blocks, 256 bytes per update, 16 updates): 13987
opers/sec, 57290752 bytes/sec
tcrypt: test 15 ( 4096 byte blocks, 1024 bytes per update, 4 updates): 14925
opers/sec, 61132800 bytes/sec
tcrypt: test 16 ( 4096 byte blocks, 4096 bytes per update, 1 updates): 15140
opers/sec, 62013440 bytes/sec
tcrypt: test 17 ( 8192 byte blocks, 16 bytes per update, 512 updates): 3655
opers/sec, 29941760 bytes/sec
tcrypt: test 18 ( 8192 byte blocks, 256 bytes per update, 32 updates): 7116
opers/sec, 58294272 bytes/sec
tcrypt: test 19 ( 8192 byte blocks, 1024 bytes per update, 8 updates): 7590
opers/sec, 62177280 bytes/sec
tcrypt: test 20 ( 8192 byte blocks, 4096 bytes per update, 2 updates): 7720
opers/sec, 63242240 bytes/sec
tcrypt: test 21 ( 8192 byte blocks, 8192 bytes per update, 1 updates): 7718
opers/sec, 63225856 bytes/sec
