Implementation notes: amd64, speed2supercop, crypto_core/multsntrup653

Computer: speed2supercop
Microarchitecture: amd64; Haswell+AES (306c3)
Architecture: amd64
CPU ID: GenuineIntel-000306c3-1fc9cbf5
SUPERCOP version: 20240625
Operation: crypto_core
Primitive: multsntrup653

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
16268	20788 0 0	35774 792 776	`avx`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
16304	20572 0 0	35558 792 776	`avx800`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
16508	19788 0 0	34870 792 776	`avx800`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
16544	20020 0 0	35102 792 776	`avx`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
17180	18915 0 0	32373 752 832	`avx800`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
17336	17937 0 0	32894 792 776	`round2`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
17528	17116 0 0	32166 792 776	`round2`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
17704	19847 0 0	30942 792 760	`avx`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
17712	19459 0 0	32917 752 832	`avx`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
17940	19927 0 0	31022 792 760	`avx800`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
18428	17744 0 0	29639 784 856	`avx`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
18500	17664 0 0	29551 784 856	`avx800`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
18708	16469 0 0	29933 752 832	`round2`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
18780	18038 0 0	29493 752 832	`avx800`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
18972	16335 0 0	27398 792 760	`round2`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
18988	18106 0 0	29324 744 832	`avx800`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
19008	17707 0 0	27972 736 800	`avx800`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
19244	18582 0 0	30037 752 832	`avx`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
19312	18687 0 0	29900 744 832	`avx`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
19524	18275 0 0	28540 736 800	`avx`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
19608	13838 0 0	25703 784 856	`round2`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
20196	14758 0 0	25972 744 832	`round2`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
20428	14643 0 0	26101 752 832	`round2`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
21928	13839 0 0	24108 736 800	`round2`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
142408	5009 0 0	18437 752 832	`ref`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
211248	2635 0 0	17606 792 776	`ref`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
211380	3163 0 0	18310 792 776	`ref`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
558884	2074 0 0	15790 792 760	`ref`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
812744	1266 0 0	12677 752 832	`ref`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
817024	650 0 0	11702 792 760	`ref`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
839644	641 0 0	12575 784 856	`ref`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
861804	575 0 0	11740 744 832	`ref`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625
942312	463 0 0	10668 736 800	`ref`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240701	20240625

Compiler output

mult768.c: mult768.c:265:7: error: always_inline function '_mm256_set1_epi16' requires target feature 'avx', but would be inlined into function 'crypto_core_multsntrup653_avx_constbranchindex' that is compiled without support for 'avx'
mult768.c:   x = const_x16(0);
mult768.c:       ^
mult768.c: mult768.c:10:19: note: expanded from macro 'const_x16'
mult768.c: #define const_x16 _mm256_set1_epi16
mult768.c:                   ^
mult768.c: mult768.c:265:7: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult768.c: mult768.c:10:19: note: expanded from macro 'const_x16'
mult768.c: #define const_x16 _mm256_set1_epi16
mult768.c:                   ^
mult768.c: mult768.c:266:35: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_multsntrup653_avx_constbranchindex' that is compiled without support for 'avx'
mult768.c:   for (i = p&~15;i < 768;i += 16) store_x16(&f[i],x);
mult768.c:                                   ^
mult768.c: mult768.c:9:24: note: expanded from macro 'store_x16'
mult768.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult768.c:                        ^
mult768.c: mult768.c:266:35: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult768.c: mult768.c:9:24: note: expanded from macro 'store_x16'
mult768.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult768.c:                        ^
mult768.c: mult768.c:267:35: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_multsntrup653_avx_constbranchindex' that is compiled without support for 'avx'
mult768.c:   for (i = p&~15;i < 768;i += 16) store_x16(&g[i],x);
mult768.c:                                   ^
mult768.c: mult768.c:9:24: note: expanded from macro 'store_x16'
mult768.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult768.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

mult768.c: mult768.c:265:7: error: always_inline function '_mm256_set1_epi16' requires target feature 'avx', but would be inlined into function 'crypto_core_multsntrup653_avx800_constbranchindex' that is compiled without support for 'avx'
mult768.c:   x = const_x16(0);
mult768.c:       ^
mult768.c: mult768.c:10:19: note: expanded from macro 'const_x16'
mult768.c: #define const_x16 _mm256_set1_epi16
mult768.c:                   ^
mult768.c: mult768.c:265:7: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult768.c: mult768.c:10:19: note: expanded from macro 'const_x16'
mult768.c: #define const_x16 _mm256_set1_epi16
mult768.c:                   ^
mult768.c: mult768.c:266:35: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_multsntrup653_avx800_constbranchindex' that is compiled without support for 'avx'
mult768.c:   for (i = p&~15;i < 768;i += 16) store_x16(&f[i],x);
mult768.c:                                   ^
mult768.c: mult768.c:9:24: note: expanded from macro 'store_x16'
mult768.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult768.c:                        ^
mult768.c: mult768.c:266:35: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult768.c: mult768.c:9:24: note: expanded from macro 'store_x16'
mult768.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult768.c:                        ^
mult768.c: mult768.c:267:35: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_multsntrup653_avx800_constbranchindex' that is compiled without support for 'avx'
mult768.c:   for (i = p&~15;i < 768;i += 16) store_x16(&g[i],x);
mult768.c:                                   ^
mult768.c: mult768.c:9:24: note: expanded from macro 'store_x16'
mult768.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult768.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

mult768.c: mult768.c:266:7: error: always_inline function '_mm256_set1_epi16' requires target feature 'avx', but would be inlined into function 'crypto_core_multsntrup653_round2_constbranchindex' that is compiled without support for 'avx'
mult768.c:   x = const_x16(0);
mult768.c:       ^
mult768.c: mult768.c:10:19: note: expanded from macro 'const_x16'
mult768.c: #define const_x16 _mm256_set1_epi16
mult768.c:                   ^
mult768.c: mult768.c:266:7: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult768.c: mult768.c:10:19: note: expanded from macro 'const_x16'
mult768.c: #define const_x16 _mm256_set1_epi16
mult768.c:                   ^
mult768.c: mult768.c:267:35: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_multsntrup653_round2_constbranchindex' that is compiled without support for 'avx'
mult768.c:   for (i = p&~15;i < 768;i += 16) store_x16(&f[i],x);
mult768.c:                                   ^
mult768.c: mult768.c:9:24: note: expanded from macro 'store_x16'
mult768.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult768.c:                        ^
mult768.c: mult768.c:267:35: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult768.c: mult768.c:9:24: note: expanded from macro 'store_x16'
mult768.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult768.c:                        ^
mult768.c: mult768.c:268:35: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_multsntrup653_round2_constbranchindex' that is compiled without support for 'avx'
mult768.c:   for (i = p&~15;i < 768;i += 16) store_x16(&g[i],x);
mult768.c:                                   ^
mult768.c: mult768.c:9:24: note: expanded from macro 'store_x16'
mult768.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult768.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)`