-
Notifications
You must be signed in to change notification settings - Fork 31
SLOTHY for Neoverse-N1 #1088
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: main
Are you sure you want to change the base?
SLOTHY for Neoverse-N1 #1088
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Mac Mini (M1, 2020) benchmarks
Benchmark suite | Current: fde54f6 | Previous: a67a02e | Ratio |
---|---|---|---|
ML-KEM-512 keypair |
12281 cycles |
12300 cycles |
1.00 |
ML-KEM-512 encaps |
14887 cycles |
14893 cycles |
1.00 |
ML-KEM-512 decaps |
19221 cycles |
19239 cycles |
1.00 |
ML-KEM-768 keypair |
21330 cycles |
21358 cycles |
1.00 |
ML-KEM-768 encaps |
23538 cycles |
23566 cycles |
1.00 |
ML-KEM-768 decaps |
30098 cycles |
30140 cycles |
1.00 |
ML-KEM-1024 keypair |
30302 cycles |
30337 cycles |
1.00 |
ML-KEM-1024 encaps |
34642 cycles |
34662 cycles |
1.00 |
ML-KEM-1024 decaps |
44115 cycles |
44158 cycles |
1.00 |
This comment was automatically generated by workflow using github-action-benchmark.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Intel Xeon 4th gen (c7i)
Benchmark suite | Current: fde54f6 | Previous: a67a02e | Ratio |
---|---|---|---|
ML-KEM-512 keypair |
9544 cycles |
9520 cycles |
1.00 |
ML-KEM-512 encaps |
11027 cycles |
11000 cycles |
1.00 |
ML-KEM-512 decaps |
15146 cycles |
15103 cycles |
1.00 |
ML-KEM-768 keypair |
16292 cycles |
16324 cycles |
1.00 |
ML-KEM-768 encaps |
17673 cycles |
17733 cycles |
1.00 |
ML-KEM-768 decaps |
23372 cycles |
24255 cycles |
0.96 |
ML-KEM-1024 keypair |
21896 cycles |
21844 cycles |
1.00 |
ML-KEM-1024 encaps |
24041 cycles |
23989 cycles |
1.00 |
ML-KEM-1024 decaps |
31698 cycles |
31571 cycles |
1.00 |
This comment was automatically generated by workflow using github-action-benchmark.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Intel Xeon 4th gen (c7i) (no-opt)
Benchmark suite | Current: fde54f6 | Previous: a67a02e | Ratio |
---|---|---|---|
ML-KEM-512 keypair |
28714 cycles |
28754 cycles |
1.00 |
ML-KEM-512 encaps |
34672 cycles |
34632 cycles |
1.00 |
ML-KEM-512 decaps |
44413 cycles |
44387 cycles |
1.00 |
ML-KEM-768 keypair |
48014 cycles |
48039 cycles |
1.00 |
ML-KEM-768 encaps |
55782 cycles |
55837 cycles |
1.00 |
ML-KEM-768 decaps |
67332 cycles |
67417 cycles |
1.00 |
ML-KEM-1024 keypair |
73342 cycles |
73239 cycles |
1.00 |
ML-KEM-1024 encaps |
84839 cycles |
84962 cycles |
1.00 |
ML-KEM-1024 decaps |
99592 cycles |
99209 cycles |
1.00 |
This comment was automatically generated by workflow using github-action-benchmark.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
AMD EPYC 4th gen (c7a)
Benchmark suite | Current: fde54f6 | Previous: a67a02e | Ratio |
---|---|---|---|
ML-KEM-512 keypair |
11521 cycles |
11516 cycles |
1.00 |
ML-KEM-512 encaps |
13192 cycles |
13271 cycles |
0.99 |
ML-KEM-512 decaps |
18062 cycles |
18048 cycles |
1.00 |
ML-KEM-768 keypair |
20140 cycles |
20151 cycles |
1.00 |
ML-KEM-768 encaps |
21118 cycles |
21143 cycles |
1.00 |
ML-KEM-768 decaps |
29174 cycles |
28319 cycles |
1.03 |
ML-KEM-1024 keypair |
26937 cycles |
26894 cycles |
1.00 |
ML-KEM-1024 encaps |
29040 cycles |
28985 cycles |
1.00 |
ML-KEM-1024 decaps |
38527 cycles |
38488 cycles |
1.00 |
This comment was automatically generated by workflow using github-action-benchmark.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
AMD EPYC 3rd gen (c6a)
Benchmark suite | Current: fde54f6 | Previous: a67a02e | Ratio |
---|---|---|---|
ML-KEM-512 keypair |
17206 cycles |
17227 cycles |
1.00 |
ML-KEM-512 encaps |
18999 cycles |
19014 cycles |
1.00 |
ML-KEM-512 decaps |
24441 cycles |
24420 cycles |
1.00 |
ML-KEM-768 keypair |
29368 cycles |
29397 cycles |
1.00 |
ML-KEM-768 encaps |
30990 cycles |
30678 cycles |
1.01 |
ML-KEM-768 decaps |
38591 cycles |
38530 cycles |
1.00 |
ML-KEM-1024 keypair |
42799 cycles |
42816 cycles |
1.00 |
ML-KEM-1024 encaps |
45029 cycles |
45111 cycles |
1.00 |
ML-KEM-1024 decaps |
55429 cycles |
55480 cycles |
1.00 |
This comment was automatically generated by workflow using github-action-benchmark.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
AMD EPYC 4th gen (c7a) (no-opt)
Benchmark suite | Current: fde54f6 | Previous: a67a02e | Ratio |
---|---|---|---|
ML-KEM-512 keypair |
36173 cycles |
36185 cycles |
1.00 |
ML-KEM-512 encaps |
42788 cycles |
42830 cycles |
1.00 |
ML-KEM-512 decaps |
55845 cycles |
55843 cycles |
1.00 |
ML-KEM-768 keypair |
59892 cycles |
59926 cycles |
1.00 |
ML-KEM-768 encaps |
68191 cycles |
68182 cycles |
1.00 |
ML-KEM-768 decaps |
85686 cycles |
85665 cycles |
1.00 |
ML-KEM-1024 keypair |
87500 cycles |
87703 cycles |
1.00 |
ML-KEM-1024 encaps |
99566 cycles |
99667 cycles |
1.00 |
ML-KEM-1024 decaps |
121282 cycles |
121243 cycles |
1.00 |
This comment was automatically generated by workflow using github-action-benchmark.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Graviton4
Benchmark suite | Current: fde54f6 | Previous: a67a02e | Ratio |
---|---|---|---|
ML-KEM-512 keypair |
17656 cycles |
17923 cycles |
0.99 |
ML-KEM-512 encaps |
20814 cycles |
20985 cycles |
0.99 |
ML-KEM-512 decaps |
27335 cycles |
27613 cycles |
0.99 |
ML-KEM-768 keypair |
30509 cycles |
30898 cycles |
0.99 |
ML-KEM-768 encaps |
33308 cycles |
33573 cycles |
0.99 |
ML-KEM-768 decaps |
42624 cycles |
43173 cycles |
0.99 |
ML-KEM-1024 keypair |
44085 cycles |
44636 cycles |
0.99 |
ML-KEM-1024 encaps |
49248 cycles |
49586 cycles |
0.99 |
ML-KEM-1024 decaps |
62033 cycles |
62616 cycles |
0.99 |
This comment was automatically generated by workflow using github-action-benchmark.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Intel Xeon 3rd gen (c6i)
Benchmark suite | Current: fde54f6 | Previous: a67a02e | Ratio |
---|---|---|---|
ML-KEM-512 keypair |
16157 cycles |
16159 cycles |
1.00 |
ML-KEM-512 encaps |
18368 cycles |
18317 cycles |
1.00 |
ML-KEM-512 decaps |
24777 cycles |
24768 cycles |
1.00 |
ML-KEM-768 keypair |
27720 cycles |
27715 cycles |
1.00 |
ML-KEM-768 encaps |
29463 cycles |
29459 cycles |
1.00 |
ML-KEM-768 decaps |
39815 cycles |
39005 cycles |
1.02 |
ML-KEM-1024 keypair |
37578 cycles |
37547 cycles |
1.00 |
ML-KEM-1024 encaps |
40550 cycles |
40533 cycles |
1.00 |
ML-KEM-1024 decaps |
53079 cycles |
53061 cycles |
1.00 |
This comment was automatically generated by workflow using github-action-benchmark.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Graviton2
Benchmark suite | Current: fde54f6 | Previous: a67a02e | Ratio |
---|---|---|---|
ML-KEM-512 keypair |
28381 cycles |
28835 cycles |
0.98 |
ML-KEM-512 encaps |
33573 cycles |
34003 cycles |
0.99 |
ML-KEM-512 decaps |
43920 cycles |
44614 cycles |
0.98 |
ML-KEM-768 keypair |
48385 cycles |
49211 cycles |
0.98 |
ML-KEM-768 encaps |
53466 cycles |
54289 cycles |
0.98 |
ML-KEM-768 decaps |
67937 cycles |
69152 cycles |
0.98 |
ML-KEM-1024 keypair |
70537 cycles |
71496 cycles |
0.99 |
ML-KEM-1024 encaps |
78862 cycles |
79872 cycles |
0.99 |
ML-KEM-1024 decaps |
98497 cycles |
100020 cycles |
0.98 |
This comment was automatically generated by workflow using github-action-benchmark.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
AMD EPYC 3rd gen (c6a) (no-opt)
Benchmark suite | Current: fde54f6 | Previous: a67a02e | Ratio |
---|---|---|---|
ML-KEM-512 keypair |
38295 cycles |
38318 cycles |
1.00 |
ML-KEM-512 encaps |
46814 cycles |
46828 cycles |
1.00 |
ML-KEM-512 decaps |
60263 cycles |
60282 cycles |
1.00 |
ML-KEM-768 keypair |
63652 cycles |
63659 cycles |
1.00 |
ML-KEM-768 encaps |
74220 cycles |
74267 cycles |
1.00 |
ML-KEM-768 decaps |
92211 cycles |
92314 cycles |
1.00 |
ML-KEM-1024 keypair |
94381 cycles |
94104 cycles |
1.00 |
ML-KEM-1024 encaps |
108220 cycles |
107821 cycles |
1.00 |
ML-KEM-1024 decaps |
130405 cycles |
130392 cycles |
1.00 |
This comment was automatically generated by workflow using github-action-benchmark.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Graviton4 (no-opt)
Benchmark suite | Current: fde54f6 | Previous: a67a02e | Ratio |
---|---|---|---|
ML-KEM-512 keypair |
35785 cycles |
35801 cycles |
1.00 |
ML-KEM-512 encaps |
40683 cycles |
40660 cycles |
1.00 |
ML-KEM-512 decaps |
52115 cycles |
52073 cycles |
1.00 |
ML-KEM-768 keypair |
59533 cycles |
59557 cycles |
1.00 |
ML-KEM-768 encaps |
66465 cycles |
66613 cycles |
1.00 |
ML-KEM-768 decaps |
81524 cycles |
81054 cycles |
1.01 |
ML-KEM-1024 keypair |
88505 cycles |
88517 cycles |
1.00 |
ML-KEM-1024 encaps |
98504 cycles |
98569 cycles |
1.00 |
ML-KEM-1024 decaps |
117299 cycles |
117298 cycles |
1.00 |
This comment was automatically generated by workflow using github-action-benchmark.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Intel Xeon 3rd gen (c6i) (no-opt)
Benchmark suite | Current: fde54f6 | Previous: a67a02e | Ratio |
---|---|---|---|
ML-KEM-512 keypair |
46244 cycles |
46245 cycles |
1.00 |
ML-KEM-512 encaps |
54576 cycles |
54529 cycles |
1.00 |
ML-KEM-512 decaps |
70066 cycles |
69921 cycles |
1.00 |
ML-KEM-768 keypair |
75305 cycles |
75183 cycles |
1.00 |
ML-KEM-768 encaps |
86330 cycles |
86417 cycles |
1.00 |
ML-KEM-768 decaps |
106455 cycles |
106437 cycles |
1.00 |
ML-KEM-1024 keypair |
110867 cycles |
110874 cycles |
1.00 |
ML-KEM-1024 encaps |
124913 cycles |
124909 cycles |
1.00 |
ML-KEM-1024 decaps |
150401 cycles |
150390 cycles |
1.00 |
This comment was automatically generated by workflow using github-action-benchmark.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Graviton3
Benchmark suite | Current: fde54f6 | Previous: a67a02e | Ratio |
---|---|---|---|
ML-KEM-512 keypair |
18616 cycles |
19092 cycles |
0.98 |
ML-KEM-512 encaps |
21928 cycles |
22302 cycles |
0.98 |
ML-KEM-512 decaps |
28987 cycles |
29559 cycles |
0.98 |
ML-KEM-768 keypair |
31801 cycles |
32600 cycles |
0.98 |
ML-KEM-768 encaps |
35067 cycles |
35699 cycles |
0.98 |
ML-KEM-768 decaps |
45094 cycles |
46017 cycles |
0.98 |
ML-KEM-1024 keypair |
46166 cycles |
46884 cycles |
0.98 |
ML-KEM-1024 encaps |
51776 cycles |
52147 cycles |
0.99 |
ML-KEM-1024 decaps |
65242 cycles |
66035 cycles |
0.99 |
This comment was automatically generated by workflow using github-action-benchmark.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Graviton2 (no-opt)
Benchmark suite | Current: fde54f6 | Previous: a67a02e | Ratio |
---|---|---|---|
ML-KEM-512 keypair |
59381 cycles |
59284 cycles |
1.00 |
ML-KEM-512 encaps |
67988 cycles |
67872 cycles |
1.00 |
ML-KEM-512 decaps |
86687 cycles |
86571 cycles |
1.00 |
ML-KEM-768 keypair |
99904 cycles |
98761 cycles |
1.01 |
ML-KEM-768 encaps |
110154 cycles |
109955 cycles |
1.00 |
ML-KEM-768 decaps |
134600 cycles |
135045 cycles |
1.00 |
ML-KEM-1024 keypair |
148094 cycles |
148294 cycles |
1.00 |
ML-KEM-1024 encaps |
163411 cycles |
163704 cycles |
1.00 |
ML-KEM-1024 decaps |
194977 cycles |
195150 cycles |
1.00 |
This comment was automatically generated by workflow using github-action-benchmark.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Graviton3 (no-opt)
Benchmark suite | Current: fde54f6 | Previous: a67a02e | Ratio |
---|---|---|---|
ML-KEM-512 keypair |
38972 cycles |
38954 cycles |
1.00 |
ML-KEM-512 encaps |
44923 cycles |
44917 cycles |
1.00 |
ML-KEM-512 decaps |
56752 cycles |
56692 cycles |
1.00 |
ML-KEM-768 keypair |
64375 cycles |
64403 cycles |
1.00 |
ML-KEM-768 encaps |
71585 cycles |
71667 cycles |
1.00 |
ML-KEM-768 decaps |
87509 cycles |
88075 cycles |
0.99 |
ML-KEM-1024 keypair |
95557 cycles |
95498 cycles |
1.00 |
ML-KEM-1024 encaps |
106210 cycles |
106318 cycles |
1.00 |
ML-KEM-1024 decaps |
126894 cycles |
126824 cycles |
1.00 |
This comment was automatically generated by workflow using github-action-benchmark.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
SpacemiT K1 8 (Banana Pi F3) benchmarks
Benchmark suite | Current: fde54f6 | Previous: a67a02e | Ratio |
---|---|---|---|
ML-KEM-512 keypair |
224908 cycles |
224990 cycles |
1.00 |
ML-KEM-512 encaps |
270975 cycles |
271136 cycles |
1.00 |
ML-KEM-512 decaps |
345347 cycles |
345562 cycles |
1.00 |
ML-KEM-768 keypair |
373128 cycles |
373379 cycles |
1.00 |
ML-KEM-768 encaps |
432640 cycles |
433046 cycles |
1.00 |
ML-KEM-768 decaps |
530988 cycles |
531466 cycles |
1.00 |
ML-KEM-1024 keypair |
562876 cycles |
563353 cycles |
1.00 |
ML-KEM-1024 encaps |
640953 cycles |
641364 cycles |
1.00 |
ML-KEM-1024 decaps |
762736 cycles |
763282 cycles |
1.00 |
This comment was automatically generated by workflow using github-action-benchmark.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Arm Cortex-A76 (Raspberry Pi 5) benchmarks
Benchmark suite | Current: fde54f6 | Previous: a67a02e | Ratio |
---|---|---|---|
ML-KEM-512 keypair |
28334 cycles |
28850 cycles |
0.98 |
ML-KEM-512 encaps |
33609 cycles |
34094 cycles |
0.99 |
ML-KEM-512 decaps |
43966 cycles |
44556 cycles |
0.99 |
ML-KEM-768 keypair |
48369 cycles |
49187 cycles |
0.98 |
ML-KEM-768 encaps |
53391 cycles |
54242 cycles |
0.98 |
ML-KEM-768 decaps |
67918 cycles |
69158 cycles |
0.98 |
ML-KEM-1024 keypair |
70462 cycles |
71609 cycles |
0.98 |
ML-KEM-1024 encaps |
78979 cycles |
79849 cycles |
0.99 |
ML-KEM-1024 decaps |
98501 cycles |
99963 cycles |
0.99 |
This comment was automatically generated by workflow using github-action-benchmark.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Arm Cortex-A55 (Snapdragon 888) benchmarks
Benchmark suite | Current: fde54f6 | Previous: a67a02e | Ratio |
---|---|---|---|
ML-KEM-512 keypair |
59659 cycles |
59486 cycles |
1.00 |
ML-KEM-512 encaps |
67150 cycles |
66676 cycles |
1.01 |
ML-KEM-512 decaps |
86015 cycles |
85353 cycles |
1.01 |
ML-KEM-768 keypair |
101867 cycles |
101413 cycles |
1.00 |
ML-KEM-768 encaps |
113091 cycles |
112657 cycles |
1.00 |
ML-KEM-768 decaps |
140167 cycles |
139279 cycles |
1.01 |
ML-KEM-1024 keypair |
154633 cycles |
154035 cycles |
1.00 |
ML-KEM-1024 encaps |
172349 cycles |
172130 cycles |
1.00 |
ML-KEM-1024 decaps |
208073 cycles |
210202 cycles |
0.99 |
This comment was automatically generated by workflow using github-action-benchmark.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Arm Cortex-A72 (Raspberry Pi 4) benchmarks
Benchmark suite | Current: fde54f6 | Previous: a67a02e | Ratio |
---|---|---|---|
ML-KEM-512 keypair |
50975 cycles |
52215 cycles |
0.98 |
ML-KEM-512 encaps |
58609 cycles |
60959 cycles |
0.96 |
ML-KEM-512 decaps |
74800 cycles |
77353 cycles |
0.97 |
ML-KEM-768 keypair |
86530 cycles |
88656 cycles |
0.98 |
ML-KEM-768 encaps |
93943 cycles |
96003 cycles |
0.98 |
ML-KEM-768 decaps |
117641 cycles |
120459 cycles |
0.98 |
ML-KEM-1024 keypair |
131073 cycles |
132836 cycles |
0.99 |
ML-KEM-1024 encaps |
144047 cycles |
145404 cycles |
0.99 |
ML-KEM-1024 decaps |
174885 cycles |
177284 cycles |
0.99 |
This comment was automatically generated by workflow using github-action-benchmark.
8b37e2c
to
05d6058
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
⚠️ Performance Alert ⚠️
Possible performance regression was detected for benchmark 'Graviton4'.
Benchmark result of this commit is worse than the previous benchmark result exceeding threshold 1.03
.
Benchmark suite | Current: 04bfe78 | Previous: fa2c32b | Ratio |
---|---|---|---|
ML-KEM-512 keypair |
18480 cycles |
17914 cycles |
1.03 |
ML-KEM-512 encaps |
21751 cycles |
20987 cycles |
1.04 |
ML-KEM-512 decaps |
28937 cycles |
27635 cycles |
1.05 |
ML-KEM-768 keypair |
32047 cycles |
30909 cycles |
1.04 |
ML-KEM-768 encaps |
34817 cycles |
33570 cycles |
1.04 |
ML-KEM-768 decaps |
45192 cycles |
43156 cycles |
1.05 |
ML-KEM-1024 decaps |
64954 cycles |
62606 cycles |
1.04 |
This comment was automatically generated by workflow using github-action-benchmark.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
⚠️ Performance Alert ⚠️
Possible performance regression was detected for benchmark 'Graviton2'.
Benchmark result of this commit is worse than the previous benchmark result exceeding threshold 1.03
.
Benchmark suite | Current: 04bfe78 | Previous: fa2c32b | Ratio |
---|---|---|---|
ML-KEM-512 keypair |
30950 cycles |
28836 cycles |
1.07 |
ML-KEM-512 encaps |
36506 cycles |
34003 cycles |
1.07 |
ML-KEM-512 decaps |
49032 cycles |
44615 cycles |
1.10 |
ML-KEM-768 keypair |
53151 cycles |
49265 cycles |
1.08 |
ML-KEM-768 encaps |
58249 cycles |
54363 cycles |
1.07 |
ML-KEM-768 decaps |
76045 cycles |
69276 cycles |
1.10 |
ML-KEM-1024 keypair |
75260 cycles |
71496 cycles |
1.05 |
ML-KEM-1024 encaps |
84048 cycles |
79875 cycles |
1.05 |
ML-KEM-1024 decaps |
107971 cycles |
100019 cycles |
1.08 |
This comment was automatically generated by workflow using github-action-benchmark.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
⚠️ Performance Alert ⚠️
Possible performance regression was detected for benchmark 'Arm Cortex-A55 (Snapdragon 888) benchmarks'.
Benchmark result of this commit is worse than the previous benchmark result exceeding threshold 1.03
.
Benchmark suite | Current: 04bfe78 | Previous: fa2c32b | Ratio |
---|---|---|---|
ML-KEM-512 keypair |
94366 cycles |
59519 cycles |
1.59 |
ML-KEM-512 encaps |
100509 cycles |
66651 cycles |
1.51 |
ML-KEM-512 decaps |
127135 cycles |
85318 cycles |
1.49 |
ML-KEM-768 keypair |
159629 cycles |
101456 cycles |
1.57 |
ML-KEM-768 encaps |
170832 cycles |
112388 cycles |
1.52 |
ML-KEM-768 decaps |
209750 cycles |
139232 cycles |
1.51 |
ML-KEM-1024 keypair |
243347 cycles |
153658 cycles |
1.58 |
ML-KEM-1024 encaps |
263212 cycles |
171058 cycles |
1.54 |
ML-KEM-1024 decaps |
314629 cycles |
206463 cycles |
1.52 |
This comment was automatically generated by workflow using github-action-benchmark.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
⚠️ Performance Alert ⚠️
Possible performance regression was detected for benchmark 'Arm Cortex-A76 (Raspberry Pi 5) benchmarks'.
Benchmark result of this commit is worse than the previous benchmark result exceeding threshold 1.03
.
Benchmark suite | Current: 04bfe78 | Previous: fa2c32b | Ratio |
---|---|---|---|
ML-KEM-512 keypair |
30903 cycles |
28849 cycles |
1.07 |
ML-KEM-512 encaps |
36539 cycles |
34093 cycles |
1.07 |
ML-KEM-512 decaps |
49065 cycles |
44555 cycles |
1.10 |
ML-KEM-768 keypair |
53137 cycles |
49191 cycles |
1.08 |
ML-KEM-768 encaps |
58156 cycles |
54241 cycles |
1.07 |
ML-KEM-768 decaps |
75996 cycles |
69155 cycles |
1.10 |
ML-KEM-1024 keypair |
75274 cycles |
71614 cycles |
1.05 |
ML-KEM-1024 encaps |
84089 cycles |
79845 cycles |
1.05 |
ML-KEM-1024 decaps |
108056 cycles |
99964 cycles |
1.08 |
This comment was automatically generated by workflow using github-action-benchmark.
31bc1aa
to
577e1ed
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
⚠️ Performance Alert ⚠️
Possible performance regression was detected for benchmark 'AMD EPYC 4th gen (c7a)'.
Benchmark result of this commit is worse than the previous benchmark result exceeding threshold 1.03
.
Benchmark suite | Current: fde54f6 | Previous: a67a02e | Ratio |
---|---|---|---|
ML-KEM-768 decaps |
29174 cycles |
28319 cycles |
1.03 |
This comment was automatically generated by workflow using github-action-benchmark.
b6bb72b
to
099a06c
Compare
…onents on AArch64. For the FIPS202/Keccak back-end, we still use the Cortex-A55 model. Regenerate and update simplified assmebly code. Update HOL-Light proofs of the updated code. Signed-off-by: Rod Chapman <rodchap@amazon.com>
d209e9f
to
907b310
Compare
This PR experimentally applies SLOTHY to all AArch64 native units using the experimental Neoverse-N1 microarchitectural model.
At this point, this PR is only to assess performance impact of this change.