Implementation notes: amd64, speed2supercop, crypto_core/multsntrup857

Computer: speed2supercop
Microarchitecture: amd64; Haswell+AES (306c3)
Architecture: amd64
CPU ID: GenuineIntel-000306c3-1fc9cbf5
SUPERCOP version: 20240625
Operation: crypto_core
Primitive: multsntrup857

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
24040	23942 0 0	39358 792 776	`avx`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
24044	24134 0 0	39758 792 776	`avx`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
24124	23902 0 0	39526 792 776	`avx800`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
24152	23726 0 0	39142 792 776	`avx800`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
25212	21030 0 0	36286 792 776	`round2`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
25264	21206 0 0	36638 792 776	`round2`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
25936	21607 0 0	33150 792 760	`avx`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
26064	20492 0 0	32983 784 856	`avx`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
26092	20412 0 0	32911 784 856	`avx800`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
26112	21687 0 0	33230 792 760	`avx800`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
26616	20964 0 0	35157 752 832	`avx800`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
27212	21508 0 0	35701 752 832	`avx`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
27268	18031 0 0	29382 792 760	`round2`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
27392	16096 0 0	28343 784 856	`round2`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
28268	18605 0 0	32349 752 832	`round2`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
29724	20008 0 0	30836 736 800	`avx800`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
30148	20562 0 0	32789 752 832	`avx800`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
30220	20576 0 0	31388 736 800	`avx`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
30712	21106 0 0	33333 752 832	`avx`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
31768	17172 0 0	28917 752 832	`round2`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
32956	16243 0 0	26828 736 800	`round2`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
32976	20576 0 0	32524 744 832	`avx800`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
33460	21157 0 0	33100 744 832	`avx`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
34468	17237 0 0	28740 744 832	`round2`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
234200	4313 0 0	18021 752 832	`ref`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
322712	3179 0 0	18630 792 776	`ref`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
327028	2507 0 0	17750 792 776	`ref`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
960448	1850 0 0	15854 792 760	`ref`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
1363804	986 0 0	12685 752 832	`ref`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
1385868	650 0 0	11990 792 760	`ref`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
1415708	641 0 0	12863 784 856	`ref`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
1462816	575 0 0	12028 744 832	`ref`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
1596864	463 0 0	10956 736 800	`ref`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625

Compiler output

mult1024.c: mult1024.c:307:7: error: always_inline function '_mm256_set1_epi16' requires target feature 'avx', but would be inlined into function 'crypto_core_multsntrup857_avx_constbranchindex' that is compiled without support for 'avx'
mult1024.c:   x = const_x16(0);
mult1024.c:       ^
mult1024.c: mult1024.c:10:19: note: expanded from macro 'const_x16'
mult1024.c: #define const_x16 _mm256_set1_epi16
mult1024.c:                   ^
mult1024.c: mult1024.c:307:7: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult1024.c: mult1024.c:10:19: note: expanded from macro 'const_x16'
mult1024.c: #define const_x16 _mm256_set1_epi16
mult1024.c:                   ^
mult1024.c: mult1024.c:308:36: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_multsntrup857_avx_constbranchindex' that is compiled without support for 'avx'
mult1024.c:   for (i = p&~15;i < 1024;i += 16) store_x16(&f[i],x);
mult1024.c:                                    ^
mult1024.c: mult1024.c:9:24: note: expanded from macro 'store_x16'
mult1024.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult1024.c:                        ^
mult1024.c: mult1024.c:308:36: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult1024.c: mult1024.c:9:24: note: expanded from macro 'store_x16'
mult1024.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult1024.c:                        ^
mult1024.c: mult1024.c:309:36: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_multsntrup857_avx_constbranchindex' that is compiled without support for 'avx'
mult1024.c:   for (i = p&~15;i < 1024;i += 16) store_x16(&g[i],x);
mult1024.c:                                    ^
mult1024.c: mult1024.c:9:24: note: expanded from macro 'store_x16'
mult1024.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult1024.c: ...

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

Implementation	Compiler
`avx`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`

Compiler output

mult1024.c: mult1024.c:307:7: error: always_inline function '_mm256_set1_epi16' requires target feature 'avx', but would be inlined into function 'crypto_core_multsntrup857_avx800_constbranchindex' that is compiled without support for 'avx'
mult1024.c:   x = const_x16(0);
mult1024.c:       ^
mult1024.c: mult1024.c:10:19: note: expanded from macro 'const_x16'
mult1024.c: #define const_x16 _mm256_set1_epi16
mult1024.c:                   ^
mult1024.c: mult1024.c:307:7: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult1024.c: mult1024.c:10:19: note: expanded from macro 'const_x16'
mult1024.c: #define const_x16 _mm256_set1_epi16
mult1024.c:                   ^
mult1024.c: mult1024.c:308:36: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_multsntrup857_avx800_constbranchindex' that is compiled without support for 'avx'
mult1024.c:   for (i = p&~15;i < 1024;i += 16) store_x16(&f[i],x);
mult1024.c:                                    ^
mult1024.c: mult1024.c:9:24: note: expanded from macro 'store_x16'
mult1024.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult1024.c:                        ^
mult1024.c: mult1024.c:308:36: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult1024.c: mult1024.c:9:24: note: expanded from macro 'store_x16'
mult1024.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult1024.c:                        ^
mult1024.c: mult1024.c:309:36: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_multsntrup857_avx800_constbranchindex' that is compiled without support for 'avx'
mult1024.c:   for (i = p&~15;i < 1024;i += 16) store_x16(&g[i],x);
mult1024.c:                                    ^
mult1024.c: mult1024.c:9:24: note: expanded from macro 'store_x16'
mult1024.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult1024.c: ...

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

Implementation	Compiler
`avx800`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`

Compiler output

ntt.c: ntt.c:562:35: warning: unused variable 'h0' [-Wunused-variable]
ntt.c:   __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c:                                   ^
ntt.c: ntt.c:562:38: warning: unused variable 'h1' [-Wunused-variable]
ntt.c:   __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c:                                      ^
ntt.c: ntt.c:562:41: warning: unused variable 'h2' [-Wunused-variable]
ntt.c:   __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c:                                         ^
ntt.c: ntt.c:562:44: warning: unused variable 'h3' [-Wunused-variable]
ntt.c:   __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c:                                            ^
ntt.c: ntt.c:864:35: warning: unused variable 'h0' [-Wunused-variable]
ntt.c:   __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c:                                   ^
ntt.c: ntt.c:864:38: warning: unused variable 'h1' [-Wunused-variable]
ntt.c:   __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c:                                      ^
ntt.c: ntt.c:864:41: warning: unused variable 'h2' [-Wunused-variable]
ntt.c:   __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c:                                         ^
ntt.c: ntt.c:864:44: warning: unused variable 'h3' [-Wunused-variable]
ntt.c:   __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c:                                            ^
ntt.c: ntt.c:865:10: warning: unused variable 'origf' [-Wunused-variable]
ntt.c: ...

Number of similar (implementation,compiler) pairs: 4, namely:

Implementation	Compiler
`round2`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`
`round2`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`
`round2`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`
`round2`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`

Compiler output

mult1024.c: mult1024.c:308:7: error: always_inline function '_mm256_set1_epi16' requires target feature 'avx', but would be inlined into function 'crypto_core_multsntrup857_round2_constbranchindex' that is compiled without support for 'avx'
mult1024.c:   x = const_x16(0);
mult1024.c:       ^
mult1024.c: mult1024.c:10:19: note: expanded from macro 'const_x16'
mult1024.c: #define const_x16 _mm256_set1_epi16
mult1024.c:                   ^
mult1024.c: mult1024.c:308:7: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult1024.c: mult1024.c:10:19: note: expanded from macro 'const_x16'
mult1024.c: #define const_x16 _mm256_set1_epi16
mult1024.c:                   ^
mult1024.c: mult1024.c:309:36: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_multsntrup857_round2_constbranchindex' that is compiled without support for 'avx'
mult1024.c:   for (i = p&~15;i < 1024;i += 16) store_x16(&f[i],x);
mult1024.c:                                    ^
mult1024.c: mult1024.c:9:24: note: expanded from macro 'store_x16'
mult1024.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult1024.c:                        ^
mult1024.c: mult1024.c:309:36: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult1024.c: mult1024.c:9:24: note: expanded from macro 'store_x16'
mult1024.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult1024.c:                        ^
mult1024.c: mult1024.c:310:36: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_multsntrup857_round2_constbranchindex' that is compiled without support for 'avx'
mult1024.c:   for (i = p&~15;i < 1024;i += 16) store_x16(&g[i],x);
mult1024.c:                                    ^
mult1024.c: mult1024.c:9:24: note: expanded from macro 'store_x16'
mult1024.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult1024.c: ...

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

Implementation	Compiler
`round2`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`

Compiler output

ntt.c: ntt.c: In function 'ntt512':
ntt.c: ntt.c:562:44: warning: unused variable 'h3' [-Wunused-variable]
ntt.c:   562 |   __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c:       |                                            ^~
ntt.c: ntt.c:562:41: warning: unused variable 'h2' [-Wunused-variable]
ntt.c:   562 |   __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c:       |                                         ^~
ntt.c: ntt.c:562:38: warning: unused variable 'h1' [-Wunused-variable]
ntt.c:   562 |   __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c:       |                                      ^~
ntt.c: ntt.c:562:35: warning: unused variable 'h0' [-Wunused-variable]
ntt.c:   562 |   __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c:       |                                   ^~
ntt.c: ntt.c: In function 'invntt512':
ntt.c: ntt.c:865:10: warning: unused variable 'origf' [-Wunused-variable]
ntt.c:   865 |   int16 *origf = f;
ntt.c:       |          ^~~~~
ntt.c: ntt.c:864:44: warning: unused variable 'h3' [-Wunused-variable]
ntt.c:   864 |   __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c:       |                                            ^~
ntt.c: ntt.c:864:41: warning: unused variable 'h2' [-Wunused-variable]
ntt.c:   864 |   __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c:       |                                         ^~
ntt.c: ntt.c:864:38: warning: unused variable 'h1' [-Wunused-variable]
ntt.c:   864 |   __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c: ...

Number of similar (implementation,compiler) pairs: 4, namely:

Implementation	Compiler
`round2`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`round2`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`round2`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`round2`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`

Passed TIMECOP

TIMECOP iterations: 1

Number of similar (implementation,compiler) pairs: 33, namely:

Implementation	Compiler
`avx`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`
`avx`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`
`avx`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`
`avx`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`
`avx`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`avx`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`avx`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`avx`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`avx800`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`
`avx800`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`
`avx800`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`
`avx800`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`
`avx800`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`avx800`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`avx800`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`avx800`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`ref`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`
`ref`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`
`ref`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`
`ref`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`
`ref`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`
`ref`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`ref`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`ref`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`ref`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`round2`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`
`round2`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`
`round2`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`
`round2`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))`
`round2`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`round2`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`round2`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`
`round2`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)`