Implementation notes: amd64, rumba7, crypto_scalarmult/kummer

Computer: rumba7
Microarchitecture: amd64; Zen (800f11)
Architecture: amd64
CPU ID: AuthenticAMD-00800f11-178bfbff
SUPERCOP version: 20240808
Operation: crypto_scalarmult
Primitive: kummer

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
403078	21645 0 0	45651 852 1760	`avx2int`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
403156	19118 0 0	42779 852 1760	`avx2int`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
441579	9019 0 0	33243 852 1760	`avx2`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
441590	8891 0 0	31939 852 1728	`avx2`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
441591	9155 0 0	32757 812 1792	`avx2`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
442325	8587 0 0	29371 852 1728	`avx2`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
442491	8449 0 0	29973 844 1792	`avx2`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
442633	8859 0 0	31197 812 1792	`avx2`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
442905	8792 0 0	30045 812 1792	`avx2`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
443115	8763 0 0	28877 804 1760	`avx2`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
444765	9019 0 0	32867 852 1760	`avx2`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
466353	8619 0 0	29877 812 1792	`avx2int`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
468331	9705 0 0	33507 852 1760	`avx`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
468348	9577 0 0	32579 852 1728	`avx`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
468354	9705 0 0	33883 852 1760	`avx`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
469029	9273 0 0	30043 852 1728	`avx`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
469366	9135 0 0	30613 844 1792	`avx`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
469630	9545 0 0	31869 812 1792	`avx`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
469688	9478 0 0	30717 812 1792	`avx`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
469801	9449 0 0	29549 804 1760	`avx`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
471176	8967 0 0	31309 812 1792	`avx2int`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
473685	8598 0 0	30013 844 1792	`avx2int`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
485155	6527 0 0	26629 804 1760	`avx2int`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
487123	9841 0 0	33429 812 1792	`avx`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240716	20240716
490714	17503 0 0	38155 852 1728	`avx2int`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
956125	7174 0 0	30677 812 1792	`ref5u`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
973586	14059 0 0	38179 852 1760	`ref5u`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
987752	12463 0 0	36227 852 1760	`ref5u`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
992222	6809 0 0	30325 812 1792	`ref5`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
1015905	4369 0 0	25821 844 1792	`ref5u`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
1027831	4978 0 0	27277 812 1792	`ref5u`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
1031832	12085 0 0	35827 852 1760	`ref5`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
1034271	13884 0 0	38035 852 1760	`ref5`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
1050063	13943 0 0	36891 852 1728	`ref5`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
1055074	14185 0 0	37107 852 1728	`ref5u`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
1066122	12443 0 0	33083 852 1728	`ref5`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
1067403	4666 0 0	26949 812 1792	`ref5`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
1084693	4222 0 0	25645 844 1792	`ref5`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
1088956	12581 0 0	33251 852 1728	`ref5u`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
1144542	4775 0 0	25989 812 1792	`ref5`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
1198585	5085 0 0	26317 812 1792	`ref5u`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
1205376	4729 0 0	24749 804 1760	`ref5u`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
1249528	4441 0 0	24429 804 1760	`ref5`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808

Test failure

error 111
crypto_scalarmult not associative

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

Implementation	Compiler
`avx2int`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`

Compiler output

gfe.c: gfe.c:59:30: warning: argument 1 of type 'unsigned char *' declared as a pointer [-Warray-parameter=]
gfe.c:    59 | void gfe_pack(unsigned char *r, const gfe *x)
gfe.c:       |               ~~~~~~~~~~~~~~~^
gfe.c: In file included from gfe.c:1:
gfe.c: gfe.h:49:15: note: previously declared as an array 'unsigned char[16]'
gfe.c:    49 | void gfe_pack(unsigned char[16], const gfe *x);
gfe.c:       |               ^~~~~~~~~~~~~~~~~
gfe.c: gfe.c: In function 'fromdouble':
gfe.c: gfe.c:71:11: warning: dereferencing type-punned pointer will break strict-aliasing rules [-Wstrict-aliasing]
gfe.c:    71 |   return *(unsigned long long *) &d - 0x4338000000000000;
gfe.c:       |           ^~~~~~~~~~~~~~~~~~~~~~~~~
gfe.c: gfe.c: In function 'todouble':
gfe.c: gfe.c:77:11: warning: dereferencing type-punned pointer will break strict-aliasing rules [-Wstrict-aliasing]
gfe.c:    77 |   return *(double *) &l - 6755399441055744.0;
gfe.c:       |           ^~~~~~~~~~~~~
gfe.c: gfe.c: At top level:
gfe.c: gfe.c:80:28: warning: argument 1 of type 'gfe *' declared as a pointer [-Warray-parameter=]
gfe.c:    80 | void gfe4x3limb_split(gfe *r, const gfe4x *x)
gfe.c:       |                       ~~~~~^
gfe.c: In file included from gfe.c:1:
gfe.c: gfe.h:53:27: note: previously declared as an array 'gfe[4]'
gfe.c:    53 | void gfe4x3limb_split(gfe r[4], const gfe4x *a);
gfe.c:       |                       ~~~~^~~~

Number of similar (implementation,compiler) pairs: 6, namely:

Implementation	Compiler
`avx`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`avx`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`avx`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`avx2`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`avx2`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`avx2`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`

Compiler output

gfe.c: gfe.c:59:30: warning: argument 1 of type 'unsigned char *' declared as a pointer [-Warray-parameter=]
gfe.c:    59 | void gfe_pack(unsigned char *r, const gfe *x)
gfe.c:       |               ~~~~~~~~~~~~~~~^
gfe.c: In file included from gfe.c:1:
gfe.c: gfe.h:49:15: note: previously declared as an array 'unsigned char[16]'
gfe.c:    49 | void gfe_pack(unsigned char[16], const gfe *x);
gfe.c:       |               ^~~~~~~~~~~~~~~~~
gfe.c: gfe.c:80:28: warning: argument 1 of type 'gfe *' declared as a pointer [-Warray-parameter=]
gfe.c:    80 | void gfe4x3limb_split(gfe *r, const gfe4x *x)
gfe.c:       |                       ~~~~~^
gfe.c: In file included from gfe.c:1:
gfe.c: gfe.h:53:27: note: previously declared as an array 'gfe[4]'
gfe.c:    53 | void gfe4x3limb_split(gfe r[4], const gfe4x *a);
gfe.c:       |                       ~~~~^~~~

Number of similar (implementation,compiler) pairs: 2, namely:

Implementation	Compiler
`avx`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`avx2`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`

Compiler output

smult.c: smult.c:36:8: error: always_inline function '_mm256_mul_epi32' requires target feature 'avx2', but would be inlined into function 'crypto_scalarmult_kummer_avx2int_constbranchindex_gfe4x_mulconst' that is compiled without support for 'avx2'
smult.c:   t0 = _mm256_mul_epi32(a->v[0],*b);
smult.c:        ^
smult.c: smult.c:36:8: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
smult.c: smult.c:37:8: error: always_inline function '_mm256_mul_epi32' requires target feature 'avx2', but would be inlined into function 'crypto_scalarmult_kummer_avx2int_constbranchindex_gfe4x_mulconst' that is compiled without support for 'avx2'
smult.c:   t1 = _mm256_mul_epi32(a->v[1],*b);
smult.c:        ^
smult.c: smult.c:37:8: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
smult.c: smult.c:38:30: error: always_inline function '_mm256_srli_epi64' requires target feature 'avx2', but would be inlined into function 'crypto_scalarmult_kummer_avx2int_constbranchindex_gfe4x_mulconst' that is compiled without support for 'avx2'
smult.c:     t1 = _mm256_add_epi64(t1,_mm256_srli_epi64(t0,26)); t0 &= mask26;
smult.c:                              ^
smult.c: smult.c:38:30: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
smult.c: smult.c:38:10: error: always_inline function '_mm256_add_epi64' requires target feature 'avx2', but would be inlined into function 'crypto_scalarmult_kummer_avx2int_constbranchindex_gfe4x_mulconst' that is compiled without support for 'avx2'
smult.c:     t1 = _mm256_add_epi64(t1,_mm256_srli_epi64(t0,26)); t0 &= mask26;
smult.c:          ^
smult.c: smult.c:38:10: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
smult.c: smult.c:39:8: error: always_inline function '_mm256_mul_epi32' requires target feature 'avx2', but would be inlined into function 'crypto_scalarmult_kummer_avx2int_constbranchindex_gfe4x_mulconst' that is compiled without support for 'avx2'
smult.c:   t2 = _mm256_mul_epi32(a->v[2],*b);
smult.c:        ^
smult.c: smult.c:39:8: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
smult.c: smult.c:40:8: error: always_inline function '_mm256_mul_epi32' requires target feature 'avx2', but would be inlined into function 'crypto_scalarmult_kummer_avx2int_constbranchindex_gfe4x_mulconst' that is compiled without support for 'avx2'
smult.c:   t3 = _mm256_mul_epi32(a->v[3],*b);
smult.c:        ^
smult.c: smult.c:40:8: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
smult.c: smult.c:41:8: error: always_inline function '_mm256_mul_epi32' requires target feature 'avx2', but would be inlined into function 'crypto_scalarmult_kummer_avx2int_constbranchindex_gfe4x_mulconst' that is compiled without support for 'avx2'
smult.c: ...

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

Implementation	Compiler
`avx2int`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`

Compiler output

smult.c: smult.c: In function 'crypto_scalarmult_kummer_avx2int_constbranchindex_gfe4x_from_gfe':
smult.c: smult.c:14:6: warning: dereferencing type-punned pointer will break strict-aliasing rules [-Wstrict-aliasing]
smult.c:    14 |     0[(crypto_uint64 *) &y->v[i]] = x[0].v[i];
smult.c:       |      ^
smult.c: smult.c: In function 'crypto_scalarmult_kummer_avx2int_constbranchindex_gfe4x_to_gfe':
smult.c: smult.c:26:18: warning: dereferencing type-punned pointer will break strict-aliasing rules [-Wstrict-aliasing]
smult.c:    26 |     x[0].v[i] = 0[(crypto_uint64 *) &y->v[i]];
smult.c:       |                  ^
smult.c: In function 'crypto_scalarmult_kummer_avx2int_constbranchindex_gfe4x_hadamard',
smult.c:     inlined from 'crypto_scalarmult_kummer_avx2int_constbranchindex' at smult.c:390:7:
smult.c: smult.c:318:27: warning: 'xyzt2' is used uninitialized [-Wuninitialized]
smult.c:   318 |     vec z0123 = r->v[i] ^ _mm256_slli_epi64(s->v[i],32);
smult.c:       |                           ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
smult.c: smult.c: In function 'crypto_scalarmult_kummer_avx2int_constbranchindex':
smult.c: smult.c:356:9: note: 'xyzt2' declared here
smult.c:   356 |   gfe4x xyzt2;
smult.c:       |         ^~~~~

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

Implementation	Compiler
`avx2int`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`

Compiler output

smult.c: smult.c: In function 'crypto_scalarmult_kummer_avx2int_constbranchindex_gfe4x_from_gfe':
smult.c: smult.c:14:6: warning: dereferencing type-punned pointer will break strict-aliasing rules [-Wstrict-aliasing]
smult.c:    14 |     0[(crypto_uint64 *) &y->v[i]] = x[0].v[i];
smult.c:       |      ^
smult.c: smult.c: In function 'crypto_scalarmult_kummer_avx2int_constbranchindex_gfe4x_to_gfe':
smult.c: smult.c:26:18: warning: dereferencing type-punned pointer will break strict-aliasing rules [-Wstrict-aliasing]
smult.c:    26 |     x[0].v[i] = 0[(crypto_uint64 *) &y->v[i]];
smult.c:       |                  ^

Number of similar (implementation,compiler) pairs: 2, namely:

Implementation	Compiler
`avx2int`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`avx2int`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`

Passed TIMECOP

TIMECOP iterations: 10

Number of similar (implementation,compiler) pairs: 43, namely:

Implementation	Compiler
`avx`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`avx`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`avx`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`avx`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`avx`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`avx`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`avx`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`avx`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`avx`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`avx2`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`avx2`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`avx2`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`avx2`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`avx2`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`avx2`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`avx2`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`avx2`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`avx2`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`avx2int`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`avx2int`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`avx2int`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`avx2int`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`avx2int`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`avx2int`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`avx2int`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`ref5`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`ref5`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`ref5`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`ref5`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`ref5`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`ref5`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`ref5`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`ref5`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`ref5`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`ref5u`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`ref5u`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`ref5u`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`ref5u`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`ref5u`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`ref5u`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`ref5u`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`ref5u`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`ref5u`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`