Implementation notes: amd64, bolero, crypto_scalarmult/kummer

Computer: bolero
Microarchitecture: amd64; Broadwell+AES (406f1)
Architecture: amd64
CPU ID: GenuineIntel-000406f1-1fc9cbf5
SUPERCOP version: 20240808
Operation: crypto_scalarmult
Primitive: kummer

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
266204	8524 0 0	30830 816 1640	`avx2int`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
270388	21369 0 0	46924 824 1608	`avx2int`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
285040	17407 0 0	38972 824 1576	`avx2int`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
286124	18921 0 0	44164 824 1608	`avx2int`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
291456	6527 0 0	27550 776 1608	`avx2int`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
293124	9211 0 0	31422 784 1640	`avx2int`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
299184	9019 0 0	34788 824 1608	`avx2`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240717	20240716
300264	9102 0 0	34118 784 1640	`avx2`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240717	20240716
300664	8781 0 0	30966 784 1640	`avx2`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240717	20240716
300680	8854 0 0	31862 784 1640	`avx2`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240717	20240716
305188	9019 0 0	34476 824 1608	`avx2`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240717	20240716
305444	8891 0 0	32868 824 1576	`avx2`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240717	20240716
306200	8587 0 0	30300 824 1576	`avx2`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240717	20240716
306500	8449 0 0	30862 816 1640	`avx2`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240717	20240716
306620	8763 0 0	29766 776 1608	`avx2`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240717	20240716
368608	9705 0 0	35116 824 1608	`avx`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240717	20240716
369148	9788 0 0	34790 784 1640	`avx`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240717	20240716
369336	9577 0 0	33508 824 1576	`avx`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240717	20240716
369372	9449 0 0	30438 776 1608	`avx`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240717	20240716
370596	9135 0 0	31502 816 1640	`avx`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240717	20240716
371640	9273 0 0	30972 824 1576	`avx`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240717	20240716
375248	9705 0 0	35428 824 1608	`avx`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240717	20240716
375544	9467 0 0	31638 784 1640	`avx`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240717	20240716
376412	9540 0 0	32534 784 1640	`avx`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240717	20240716
903428	13524 0 0	39172 824 1608	`ref5`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
946984	11869 0 0	37204 824 1608	`ref5`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
951644	4567 0 0	27486 784 1640	`ref5`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
953452	4150 0 0	26502 816 1640	`ref5`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
957364	13943 0 0	37796 824 1576	`ref5`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
962132	12247 0 0	37604 824 1608	`ref5u`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
966388	14185 0 0	38036 824 1576	`ref5u`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
976812	13747 0 0	39412 824 1608	`ref5u`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
1006976	4292 0 0	26622 816 1640	`ref5u`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
1013832	12243 0 0	33820 824 1576	`ref5`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
1032116	4852 0 0	27790 784 1640	`ref5u`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
1033680	4441 0 0	25350 776 1608	`ref5`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
1034296	6465 0 0	31406 784 1640	`ref5`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
1056108	12477 0 0	34060 824 1576	`ref5u`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
1081820	4753 0 0	26862 784 1640	`ref5`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
1082288	4729 0 0	25662 776 1608	`ref5u`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
1094812	6815 0 0	31774 784 1640	`ref5u`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240809	20240808
1141392	5072 0 0	27198 784 1640	`ref5u`	`gcc_-march=native_-mtune=native_-O_-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_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)`