Test results for amd64, h8bobcat, crypto_xof/bitwrite16

[Page version: 20241109 15:20:14]

Measurements for amd64, h8bobcat, crypto_xof Test results for amd64, h8bobcat, crypto_xof Test results for crypto_xof/bitwrite16

Computer: h8bobcat
Microarchitecture: amd64; Bobcat (500f10)
Architecture: amd64
CPU ID: AuthenticAMD-00500f20-178bfbff
SUPERCOP version: 20241022
Operation: crypto_xof
Primitive: bitwrite16

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
840522	1229 0 0	13406 776 800	`64`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
984305	716 0 0	11037 768 800	`128`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
1061331	762 0 0	11446 776 800	`128`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
1464933	1562 0 0	13742 776 800	`128`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
1839566	571 0 0	9881 752 768	`128`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
2364227	627 0 0	9694 808 744	`128`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
2435278	1263 0 0	13252 816 744	`64x4`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
2435306	1214 0 0	12988 816 744	`64x4`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
2435325	1155 0 0	10214 808 744	`64x4`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
2436161	1314 0 0	11998 776 800	`64x4`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
2436204	1230 0 0	10908 816 744	`64x4`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
2789333	722 0 0	11406 776 800	`64`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
2871204	1587 0 0	13588 816 744	`64x4x2`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
2922005	1561 0 0	10630 808 744	`64x4x2`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
2965126	1522 0 0	12164 816 744	`64x4x2`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
2970152	1602 0 0	11292 816 744	`64x4x2`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
2971799	514 0 0	9817 752 768	`64`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
2972845	1522 0 0	13308 816 744	`64x4x2`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
3645497	764 0 0	10436 816 744	`128`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
3650442	763 0 0	11388 816 744	`128`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
3653301	1172 0 0	13156 816 744	`128`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
3794125	939 0 0	12708 816 744	`128`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
3912010	1214 0 0	11844 816 744	`64x4`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
4279180	817 0 0	12820 816 744	`64`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
4279313	784 0 0	12556 816 744	`64`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
4939463	1101 0 0	10417 752 768	`64x4x2`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
4971018	1658 0 0	12342 776 800	`64x4x2`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
5111807	774 0 0	11093 768 800	`64`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
5231926	6683 0 0	18862 776 800	`64x4x2`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
5385897	1968 0 0	12285 768 800	`64x4x2`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
6127077	831 0 0	10161 752 768	`64x4`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
6700663	671 0 0	9734 808 744	`64`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
6703614	688 0 0	11316 816 744	`64`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
6710657	752 0 0	10428 816 744	`64`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
7481839	5488 0 0	17662 776 800	`64x4`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
7563838	1647 0 0	11973 768 800	`64x4`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
8145433	256 0 0	12430 776 800	`ref`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
8147732	274 0 0	12260 816 744	`ref`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
8149077	258 0 0	12028 816 744	`ref`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
8150506	255 0 0	9932 816 744	`ref`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
8152088	255 0 0	10884 816 744	`ref`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
8152991	235 0 0	9286 808 744	`ref`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
8153071	254 0 0	10565 768 800	`ref`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
13046474	253 0 0	10934 776 800	`ref`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011
14235194	230 0 0	9529 752 768	`ref`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20241019	20241011

Compiler output

write.c: write.c:36:19: error: always_inline function '_mm256_set1_epi64x' requires target feature 'avx', but would be inlined into function 'atmost8192' that is compiled without support for 'avx'
write.c:   __m256i hlast = _mm256_set1_epi64x(0);
write.c:                   ^
write.c: write.c:36:19: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
write.c: write.c:42:23: warning: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI [-Wpsabi]
write.c:     __m256i word256 = vec256_1shlmod(pos);
write.c:                       ^
write.c: write.c:44:20: error: always_inline function '_mm256_loadu_si256' requires target feature 'avx', but would be inlined into function 'atmost8192' that is compiled without support for 'avx'
write.c:       __m256i hi = _mm256_loadu_si256((__m256i *) (h+32*i));
write.c:                    ^
write.c: write.c:44:20: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
write.c: write.c:45:23: warning: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI [-Wpsabi]
write.c:       hi |= word256 & vec256_equal_mask(i,pos>>8);
write.c:                       ^
write.c: write.c:46:7: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'atmost8192' that is compiled without support for 'avx'
write.c:       _mm256_storeu_si256((__m256i *) (h+32*i),hi);
write.c:       ^
write.c: write.c:46:7: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
write.c: write.c:48:24: warning: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI [-Wpsabi]
write.c:     hlast |= word256 & vec256_equal_mask(words,pos>>8);
write.c:                        ^
write.c: write.c:25:21: error: always_inline function '_mm256_set_m128i' requires target feature 'avx', but would be inlined into function 'vec256_1shlmod' that is compiled without support for 'avx'
write.c:   __m256i word256 = _mm256_set_m128i(word128&mask7,word128&~mask7);
write.c:                     ^
write.c: write.c:25:21: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
write.c: ...

Number of similar (implementation,compiler) pairs: 5, namely:

Implementation	Compiler
`256`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`256`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`256`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`256`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`256`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`

Compiler output

write.c: write.c: In function 'vec256_equal_mask':
write.c: write.c:12:1: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
write.c:    12 | {
write.c:       | ^
write.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:43,
write.c:                  from write.c:5:
write.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/avxintrin.h:1349:1: error: inlining failed in call to 'always_inline' '_mm256_set1_epi64x': target specific option mismatch
write.c:  1349 | _mm256_set1_epi64x (long long __A)
write.c:       | ^~~~~~~~~~~~~~~~~~
write.c: write.c:16:10: note: called from here
write.c:    16 |   return _mm256_set1_epi64x(mask);
write.c:       |          ^~~~~~~~~~~~~~~~~~~~~~~~

Number of similar (implementation,compiler) pairs: 12, namely:

Implementation	Compiler
`256`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`256`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`256`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`256`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`256x4`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`256x4`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`256x4`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`256x4`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`256x4x2`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`256x4x2`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`256x4x2`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`256x4x2`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`

Compiler output

write.c: write.c:36:19: error: always_inline function '_mm256_set1_epi64x' requires target feature 'avx', but would be inlined into function 'atmost8192' that is compiled without support for 'avx'
write.c:   __m256i hlast = _mm256_set1_epi64x(0);
write.c:                   ^
write.c: write.c:36:19: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
write.c: write.c:42:23: warning: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI [-Wpsabi]
write.c:     __m256i word256 = vec256_1shlmod(pos);
write.c:                       ^
write.c: write.c:44:21: error: always_inline function '_mm256_loadu_si256' requires target feature 'avx', but would be inlined into function 'atmost8192' that is compiled without support for 'avx'
write.c:       __m256i hi0 = _mm256_loadu_si256((__m256i *) (h+32*i));
write.c:                     ^
write.c: write.c:44:21: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
write.c: write.c:45:21: error: always_inline function '_mm256_loadu_si256' requires target feature 'avx', but would be inlined into function 'atmost8192' that is compiled without support for 'avx'
write.c:       __m256i hi1 = _mm256_loadu_si256((__m256i *) (h+32*i+32));
write.c:                     ^
write.c: write.c:45:21: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
write.c: write.c:46:21: error: always_inline function '_mm256_loadu_si256' requires target feature 'avx', but would be inlined into function 'atmost8192' that is compiled without support for 'avx'
write.c:       __m256i hi2 = _mm256_loadu_si256((__m256i *) (h+32*i+64));
write.c:                     ^
write.c: write.c:46:21: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
write.c: write.c:47:21: error: always_inline function '_mm256_loadu_si256' requires target feature 'avx', but would be inlined into function 'atmost8192' that is compiled without support for 'avx'
write.c:       __m256i hi3 = _mm256_loadu_si256((__m256i *) (h+32*i+96));
write.c:                     ^
write.c: write.c:47:21: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
write.c: write.c:48:32: warning: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI [-Wpsabi]
write.c:       __m256i base = word256 & vec256_equal_mask(i>>2,pos>>10);
write.c: ...

Number of similar (implementation,compiler) pairs: 5, namely:

Implementation	Compiler
`256x4`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`256x4`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`256x4`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`256x4`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`256x4`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`

Compiler output

write.c: write.c:36:19: error: always_inline function '_mm256_set1_epi64x' requires target feature 'avx', but would be inlined into function 'atmost8192' that is compiled without support for 'avx'
write.c:   __m256i hlast = _mm256_set1_epi64x(0);
write.c:                   ^
write.c: write.c:36:19: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
write.c: write.c:44:17: warning: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI [-Wpsabi]
write.c:     word256_0 = vec256_1shlmod(pos_0);
write.c:                 ^
write.c: write.c:47:19: warning: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI [-Wpsabi]
write.c:       word256_1 = vec256_1shlmod(pos_1);
write.c:                   ^
write.c: write.c:50:19: error: always_inline function '_mm256_set1_epi64x' requires target feature 'avx', but would be inlined into function 'atmost8192' that is compiled without support for 'avx'
write.c:       word256_1 = _mm256_set1_epi64x(0);
write.c:                   ^
write.c: write.c:50:19: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
write.c: write.c:53:21: error: always_inline function '_mm256_loadu_si256' requires target feature 'avx', but would be inlined into function 'atmost8192' that is compiled without support for 'avx'
write.c:       __m256i hi0 = _mm256_loadu_si256((__m256i *) (h+32*i));
write.c:                     ^
write.c: write.c:53:21: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
write.c: write.c:54:21: error: always_inline function '_mm256_loadu_si256' requires target feature 'avx', but would be inlined into function 'atmost8192' that is compiled without support for 'avx'
write.c:       __m256i hi1 = _mm256_loadu_si256((__m256i *) (h+32*i+32));
write.c:                     ^
write.c: write.c:54:21: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
write.c: write.c:55:21: error: always_inline function '_mm256_loadu_si256' requires target feature 'avx', but would be inlined into function 'atmost8192' that is compiled without support for 'avx'
write.c:       __m256i hi2 = _mm256_loadu_si256((__m256i *) (h+32*i+64));
write.c:                     ^
write.c: ...

Number of similar (implementation,compiler) pairs: 5, namely:

Implementation	Compiler
`256x4x2`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`256x4x2`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`256x4x2`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`256x4x2`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`256x4x2`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`

Compiler output

write.c: write.c: In function 'crypto_xof_bitwrite16_64x4_constbranchindex':
write.c: write.c:51:46: warning: iteration 2305843009213693952 invokes undefined behavior [-Waggressive-loop-optimizations]
write.c:    51 |       crypto_uint64 hi = crypto_uint64_load(h+8*i);
write.c:       |                                             ~^~~~
write.c: write.c:50:13: note: within this loop
write.c:    50 |     for (;i < words;++i) {
write.c:       |           ~~^~~~~~~

Number of similar (implementation,compiler) pairs: 1, namely:

Implementation	Compiler
`64x4`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`

Compiler output

write.c: write.c: In function 'crypto_xof_bitwrite16_64x4x2_constbranchindex':
write.c: write.c:69:46: warning: iteration 2305843009213693952 invokes undefined behavior [-Waggressive-loop-optimizations]
write.c:    69 |       crypto_uint64 hi = crypto_uint64_load(h+8*i);
write.c:       |                                             ~^~~~
write.c: write.c:68:13: note: within this loop
write.c:    68 |     for (;i < words;++i) {
write.c:       |           ~~^~~~~~~

Number of similar (implementation,compiler) pairs: 1, namely:

Implementation	Compiler
`64x4x2`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`

Passed TIMECOP

TIMECOP iterations: 10

Number of similar (implementation,compiler) pairs: 45, namely:

Implementation	Compiler
`128`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`128`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`128`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`128`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`128`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`128`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`128`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`128`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`128`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`64`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`64`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`64`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`64`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`64`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`64`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`64`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`64`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`64`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`64x4`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`64x4`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`64x4`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`64x4`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`64x4`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`64x4`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`64x4`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`64x4`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`64x4`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`64x4x2`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`64x4x2`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`64x4x2`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`64x4x2`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`64x4x2`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`64x4x2`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`64x4x2`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`64x4x2`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`64x4x2`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`ref`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`ref`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`ref`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`ref`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`ref`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`ref`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`ref`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`ref`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`ref`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`