Implementation notes: amd64, samba, crypto_scalarmult/kummer

Computer: samba
Microarchitecture: amd64; Skylake (506e3)
Architecture: amd64
CPU ID: GenuineIntel-000506e3-bfebfbff
SUPERCOP version: 20240625
Operation: crypto_scalarmult
Primitive: kummer

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
212695	21269 0 0	46067 852 1824	`avx2int`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
213447	18821 0 0	43323 852 1792	`avx2int`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
229364	8493 0 0	30133 844 1824	`avx2int`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
229497	17423 0 0	38243 852 1760	`avx2int`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
249447	6525 0 0	26789 804 1792	`avx2int`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
253194	9170 0 0	30629 812 1824	`avx2int`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
262516	9150 0 0	33597 812 1824	`avx2`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
262685	9083 0 0	33795 852 1792	`avx2`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
263228	9000 0 0	30445 812 1824	`avx2`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
263268	8765 0 0	29021 804 1792	`avx2`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
263293	8449 0 0	30197 844 1824	`avx2`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
263498	8934 0 0	31245 812 1824	`avx2`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
264232	8891 0 0	32123 852 1760	`avx2`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
264416	9083 0 0	34075 852 1824	`avx2`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
264695	8587 0 0	29555 852 1760	`avx2`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
352427	9836 0 0	34269 812 1824	`avx`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
353079	9769 0 0	34747 852 1824	`avx`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
353713	9273 0 0	30227 852 1760	`avx`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
353845	9686 0 0	31117 812 1824	`avx`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
354057	9451 0 0	29693 804 1792	`avx`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
354290	9620 0 0	31917 812 1824	`avx`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
355115	9577 0 0	32763 852 1760	`avx`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
355375	9769 0 0	34467 852 1792	`avx`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
357576	9135 0 0	30869 844 1824	`avx`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
830116	13746 0 0	38651 852 1824	`ref5u`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
846333	12215 0 0	36827 852 1792	`ref5u`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
852282	4291 0 0	25957 844 1824	`ref5u`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
866162	13943 0 0	37051 852 1760	`ref5`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
871991	13716 0 0	38587 852 1824	`ref5`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
893186	4552 0 0	26773 812 1824	`ref5`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
896058	14185 0 0	37291 852 1760	`ref5u`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
896289	12045 0 0	36619 852 1792	`ref5`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
912760	12243 0 0	33075 852 1760	`ref5`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
927537	4341 0 0	26013 844 1824	`ref5`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
932198	6470 0 0	30821 812 1824	`ref5`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
946403	4857 0 0	27093 812 1824	`ref5u`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
968863	6826 0 0	31205 812 1824	`ref5u`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
976186	12477 0 0	33315 852 1760	`ref5u`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
997558	4448 0 0	24621 804 1792	`ref5`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
1040566	4734 0 0	24917 804 1792	`ref5u`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
1040858	4757 0 0	26117 812 1824	`ref5`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625
1107258	5076 0 0	26453 812 1824	`ref5u`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240626	20240625

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_mulprecomputed',
smult.c:     inlined from 'crypto_scalarmult_kummer_avx2int_constbranchindex' at smult.c:402:7:
smult.c: smult.c:162:6: warning: 'input' is used uninitialized [-Wuninitialized]
smult.c:   162 |   a0 = a->v[0];
smult.c:       |   ~~~^~~~~~~~~
smult.c: smult.c: In function 'crypto_scalarmult_kummer_avx2int_constbranchindex':
smult.c: smult.c:354:9: note: 'input' declared here
smult.c:   354 |   gfe4x input;
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:318:21: warning: 'xyzt3' 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:357:9: note: 'xyzt3' declared here
smult.c:   357 |   gfe4x xyzt3;
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: 42, 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 -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)`