Implementation notes: amd64, samba, crypto_core/mult3sntrup761

Computer: samba
Microarchitecture: amd64; Skylake (506e3)
Architecture: amd64
CPU ID: GenuineIntel-000506e3-bfebfbff
SUPERCOP version: 20240808
Operation: crypto_core
Primitive: mult3sntrup761

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
6476	45396 0 0	60389 804 992	`avx2unsigned`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
6872	35753 0 0	50963 844 1024	`avx2unsigned`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
6880	31065 0 0	45979 844 960	`avx2unsigned`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
7793	17676 0 0	30549 804 992	`avx2unsigned`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
8395	23207 0 0	34411 844 928	`avx2unsigned`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
8651	20931 0 0	33085 836 1024	`avx2unsigned`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
9639	12484 0 0	23904 780 960	`avx2unsigned`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
9687	17517 0 0	29988 796 992	`avx2unsigned`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
10567	15578 0 0	30803 844 960	`avx800`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
10637	18169 0 0	31035 844 960	`avx`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
11351	15081 0 0	25381 836 1024	`avx`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
11434	13132 0 0	25453 836 1024	`avx800`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
11473	19123 0 0	32291 844 1024	`avx`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
11722	16516 0 0	32043 844 1024	`avx800`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
12150	16334 0 0	25523 844 928	`avx`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
12201	13789 0 0	25339 844 928	`avx800`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
13355	13814 0 0	25852 796 992	`avx800`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
13715	14879 0 0	27260 796 992	`avx`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
15447	14513 0 0	29061 804 992	`avx800`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
15807	15482 0 0	30405 804 992	`avx`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
16303	14729 0 0	27509 804 992	`avx`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
16781	13760 0 0	26165 804 992	`avx800`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
17057	13461 0 0	24408 780 960	`avx800`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
17273	14270 0 0	25536 780 960	`avx`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
29960	11334 0 0	26963 844 1024	`round1`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
30304	9794 0 0	25139 844 960	`round1`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
31959	8770 0 0	20355 844 928	`round1`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
32427	8315 0 0	20749 836 1024	`round1`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
80851	1969 0 0	17267 844 960	`compact`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
83685	3873 0 0	19467 844 1024	`compact`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
88543	1790 0 0	16789 804 992	`compact`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
168016	1494 0 0	15451 844 928	`compact`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
180537	977 0 0	13813 804 992	`32`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
180912	1689 0 0	16987 844 960	`ref`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
188246	1094 0 0	13540 796 992	`32`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
189202	1689 0 0	17283 844 1024	`ref`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
201310	4345 0 0	19349 804 992	`ref`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
201353	913 0 0	12240 780 960	`32`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
208730	1728 0 0	17307 844 1024	`32`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
209284	1014 0 0	14947 844 928	`32`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
209949	1728 0 0	17011 844 960	`32`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
211283	998 0 0	13397 836 1024	`32`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
211640	820 0 0	12355 844 928	`32`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
236147	3677 0 0	18669 804 992	`32`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
417357	1134 0 0	15075 844 928	`ref`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
1187146	363 0 0	12749 836 1024	`compact`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
1196497	426 0 0	11963 844 928	`compact`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
1197181	471 0 0	12853 836 1024	`ref`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
1208063	504 0 0	12035 844 928	`ref`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
1379203	492 0 0	13333 804 992	`compact`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
1418999	627 0 0	13469 804 992	`ref`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
1571018	420 0 0	11752 780 960	`compact`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
2115124	682 0 0	13132 796 992	`ref`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
2474507	497 0 0	12948 796 992	`compact`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808
2484290	556 0 0	11888 780 960	`ref`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240808	20240808

Compiler output

mult768.c: mult768.c:209:7: error: always_inline function '_mm256_set1_epi16' requires target feature 'avx', but would be inlined into function 'crypto_core_mult3sntrup761_avx_constbranchindex' that is compiled without support for 'avx'
mult768.c:   x = const_x16(0);
mult768.c:       ^
mult768.c: mult768.c:11:19: note: expanded from macro 'const_x16'
mult768.c: #define const_x16 _mm256_set1_epi16
mult768.c:                   ^
mult768.c: mult768.c:209:7: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult768.c: mult768.c:11:19: note: expanded from macro 'const_x16'
mult768.c: #define const_x16 _mm256_set1_epi16
mult768.c:                   ^
mult768.c: mult768.c:210:35: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_mult3sntrup761_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:10:24: 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:210:35: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult768.c: mult768.c:10:24: 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:211:35: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_mult3sntrup761_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:10:24: 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 (Ubuntu_Clang_14.0.0)`

Compiler output

mult3_32x32.c: mult3_32x32.c:255:6: warning: unused function 'mult3_64x64_inplace_karatsuba_x2' [-Wunused-function]
mult3_32x32.c: void mult3_64x64_inplace_karatsuba_x2( __m256i * a0 , __m256i * a1) {
mult3_32x32.c:      ^
mult3_32x32.c: mult3_32x32.c:668:6: warning: unused function 'mult3_256x256_inplace_karatsuba' [-Wunused-function]
mult3_32x32.c: void mult3_256x256_inplace_karatsuba( __m256i * a ) {
mult3_32x32.c:      ^
mult3_32x32.c: mult3_32x32.c:765:9: warning: unused function 'right_shift_1' [-Wunused-function]
mult3_32x32.c: __m256i right_shift_1( __m256i a0 )
mult3_32x32.c:         ^
mult3_32x32.c: mult3_32x32.c:779:9: warning: unused function 'right_shift_2' [-Wunused-function]
mult3_32x32.c: __m256i right_shift_2( __m256i a0 )
mult3_32x32.c:         ^
mult3_32x32.c: mult3_32x32.c:793:9: warning: unused function 'left_shift_1' [-Wunused-function]
mult3_32x32.c: __m256i left_shift_1( __m256i a1 )
mult3_32x32.c:         ^
mult3_32x32.c: mult3_32x32.c:800:9: warning: unused function 'left_shift_2_high' [-Wunused-function]
mult3_32x32.c: __m256i left_shift_2_high( __m256i a1 , __m256i a0 )
mult3_32x32.c:         ^
mult3_32x32.c: mult3_32x32.c:807:9: warning: unused function 'left_shift_2' [-Wunused-function]
mult3_32x32.c: __m256i left_shift_2( __m256i a1 )
mult3_32x32.c:         ^
mult3_32x32.c: 7 warnings generated.

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

Implementation	Compiler
`avx2unsigned`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`avx2unsigned`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`avx2unsigned`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`avx2unsigned`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`

Compiler output

mult.c: mult.c:48:59: error: always_inline function '_mm256_load_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_mult3sntrup761_avx2unsigned_constbranchindex' that is compiled without support for 'avx'
mult.c:     _mm256_store_si256( (__m256i*)(a+i) , cvt_to_unsigned(_mm256_load_si256((__m256i*)(a+i))) );
mult.c:                                                           ^
mult.c: mult.c:48:59: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult.c: mult.c:48:43: warning: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI [-Wpsabi]
mult.c:     _mm256_store_si256( (__m256i*)(a+i) , cvt_to_unsigned(_mm256_load_si256((__m256i*)(a+i))) );
mult.c:                                           ^
mult.c: mult.c:48:5: error: always_inline function '_mm256_store_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_mult3sntrup761_avx2unsigned_constbranchindex' that is compiled without support for 'avx'
mult.c:     _mm256_store_si256( (__m256i*)(a+i) , cvt_to_unsigned(_mm256_load_si256((__m256i*)(a+i))) );
mult.c:     ^
mult.c: mult.c:48:5: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult.c: mult.c:51:59: error: always_inline function '_mm256_load_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_mult3sntrup761_avx2unsigned_constbranchindex' that is compiled without support for 'avx'
mult.c:     _mm256_store_si256( (__m256i*)(b+i) , cvt_to_unsigned(_mm256_load_si256((__m256i*)(b+i))) );
mult.c:                                                           ^
mult.c: mult.c:51:59: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult.c: mult.c:51:43: warning: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI [-Wpsabi]
mult.c:     _mm256_store_si256( (__m256i*)(b+i) , cvt_to_unsigned(_mm256_load_si256((__m256i*)(b+i))) );
mult.c:                                           ^
mult.c: mult.c:51:5: error: always_inline function '_mm256_store_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_mult3sntrup761_avx2unsigned_constbranchindex' that is compiled without support for 'avx'
mult.c:     _mm256_store_si256( (__m256i*)(b+i) , cvt_to_unsigned(_mm256_load_si256((__m256i*)(b+i))) );
mult.c:     ^
mult.c: mult.c:51:5: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult.c: mult.c:64:54: error: always_inline function '_mm256_load_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_mult3sntrup761_avx2unsigned_constbranchindex' that is compiled without support for 'avx'
mult.c:     _mm256_store_si256( (__m256i*)(c+i) , cvt_to_int(_mm256_load_si256((__m256i*)(c+i))) );
mult.c:                                                      ^
mult.c: ...

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

Implementation	Compiler
`avx2unsigned`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`

Compiler output

mult3_32x32.c: mult3_32x32.c:668:6: warning: 'mult3_256x256_inplace_karatsuba' defined but not used [-Wunused-function]
mult3_32x32.c:   668 | void mult3_256x256_inplace_karatsuba( __m256i * a ) {
mult3_32x32.c:       |      ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

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

Implementation	Compiler
`avx2unsigned`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`avx2unsigned`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`avx2unsigned`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`avx2unsigned`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`

Compiler output

mult768.c: mult768.c:209:7: error: always_inline function '_mm256_set1_epi16' requires target feature 'avx', but would be inlined into function 'crypto_core_mult3sntrup761_avx800_constbranchindex' that is compiled without support for 'avx'
mult768.c:   x = const_x16(0);
mult768.c:       ^
mult768.c: mult768.c:11:19: note: expanded from macro 'const_x16'
mult768.c: #define const_x16 _mm256_set1_epi16
mult768.c:                   ^
mult768.c: mult768.c:209:7: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult768.c: mult768.c:11:19: note: expanded from macro 'const_x16'
mult768.c: #define const_x16 _mm256_set1_epi16
mult768.c:                   ^
mult768.c: mult768.c:210:35: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_mult3sntrup761_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:10:24: 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:210:35: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult768.c: mult768.c:10:24: 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:211:35: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_mult3sntrup761_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:10:24: 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 (Ubuntu_Clang_14.0.0)`

Compiler output

mult.c: mult.c:147:22: error: invalid output size for constraint '=&x'
mult.c:   MULSTEP_fromzero(0,h0,h1,h2,h3,h4)
mult.c:                      ^
mult.c: mult.c:149:26: error: invalid output size for constraint '+x'
mult.c:     MULSTEP_noload(j + 1,h1,h2,h3,h4,h0)
mult.c:                          ^
mult.c: mult.c:150:26: error: invalid output size for constraint '+x'
mult.c:     MULSTEP_noload(j + 2,h2,h3,h4,h0,h1)
mult.c:                          ^
mult.c: mult.c:151:26: error: invalid output size for constraint '+x'
mult.c:     MULSTEP_noload(j + 3,h3,h4,h0,h1,h2)
mult.c:                          ^
mult.c: mult.c:152:26: error: invalid output size for constraint '+x'
mult.c:     MULSTEP_noload(j + 4,h4,h0,h1,h2,h3)
mult.c:                          ^
mult.c: mult.c:153:26: error: invalid output size for constraint '+x'
mult.c:     MULSTEP_noload(j + 5,h0,h1,h2,h3,h4)
mult.c:                          ^
mult.c: mult.c:155:24: error: invalid output size for constraint '+x'
mult.c:   MULSTEP_noload(j + 1,h1,h2,h3,h4,h0)
mult.c:                        ^
mult.c: mult.c:156:24: error: invalid output size for constraint '+x'
mult.c:   MULSTEP_noload(j + 2,h2,h3,h4,h0,h1)
mult.c:                        ^
mult.c: mult.c:157:24: error: invalid output size for constraint '+x'
mult.c: ...

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

Implementation	Compiler
`round1`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`

Compiler output

mult.c: In function 'mult768_mix2_m256i',
mult.c:     inlined from 'crypto_core_mult3sntrup761_round1_constbranchindex' at mult.c:752:3:
mult.c: mult.c:568:3: warning: 'mult96x16' accessing 6144 bytes in a region of size 512 [-Wstringop-overflow=]
mult.c:   568 |   mult96x16(hkara[12],fkara[6],(__m256i *) (1 + (__m128i *) gkara));
mult.c:       |   ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
mult.c: mult.c: In function 'crypto_core_mult3sntrup761_round1_constbranchindex':
mult.c: mult.c:568:3: note: referencing argument 1 of type '__m256i *'
mult.c: In function 'mult768_mix2_m256i',
mult.c:     inlined from 'crypto_core_mult3sntrup761_round1_constbranchindex' at mult.c:752:3:
mult.c: mult.c:568:3: warning: 'mult96x16' reading 3072 bytes from a region of size 512 [-Wstringop-overread]
mult.c: mult.c: In function 'crypto_core_mult3sntrup761_round1_constbranchindex':
mult.c: mult.c:568:3: note: referencing argument 2 of type 'const __m256i *'
mult.c: In function 'mult768_mix2_m256i',
mult.c:     inlined from 'crypto_core_mult3sntrup761_round1_constbranchindex' at mult.c:752:3:
mult.c: mult.c:568:3: warning: 'mult96x16' reading 3072 bytes from a region of size 3056 [-Wstringop-overread]
mult.c: mult.c: In function 'crypto_core_mult3sntrup761_round1_constbranchindex':
mult.c: mult.c:568:3: note: referencing argument 3 of type 'const __m256i *'
mult.c: mult.c:279:13: note: in a call to function 'mult96x16'
mult.c:   279 | static void mult96x16(__m256i h[192],const __m256i f[96],const __m256i g[96])
mult.c:       |             ^~~~~~~~~
mult.c: In function 'mult768_mix2_m256i',
mult.c:     inlined from 'crypto_core_mult3sntrup761_round1_constbranchindex' at mult.c:752:3:
mult.c: mult.c:569:3: warning: 'mult96x16' accessing 6144 bytes in a region of size 512 [-Wstringop-overflow=]
mult.c:   569 |   mult96x16(hkara[0],fkara[0],gkara[0]);
mult.c:       |   ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
mult.c: ...

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

Implementation	Compiler
`round1`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`round1`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`round1`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`round1`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`

Compiler output

ntt.c: ntt.c:444:35: 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:444:44: 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:444:41: 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:444:38: 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:741:44: 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:741:41: 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:741:38: 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:742:10: warning: unused variable 'origf' [-Wunused-variable]
ntt.c:   int16 *origf = f;
ntt.c:          ^
ntt.c: ntt.c:741:35: warning: unused variable 'h0' [-Wunused-variable]
ntt.c: ...

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

Implementation	Compiler
`round2`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`round2`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`

Compiler output

ntt.c: ntt.c:444:38: 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:444:41: 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:444:44: 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:444:35: 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:741:35: 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:742:10: warning: unused variable 'origf' [-Wunused-variable]
ntt.c:   int16 *origf = f;
ntt.c:          ^
ntt.c: ntt.c:741:44: 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:741:41: 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:741:38: warning: unused variable 'h1' [-Wunused-variable]
ntt.c: ...

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

Implementation	Compiler
`round2`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`

Compiler output

ntt.c: ntt.c:444:38: 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:444:35: 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:444:44: 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:444:41: 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:741:44: 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:741:41: 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:742:10: warning: unused variable 'origf' [-Wunused-variable]
ntt.c:   int16 *origf = f;
ntt.c:          ^
ntt.c: ntt.c:741:38: 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:741:35: warning: unused variable 'h0' [-Wunused-variable]
ntt.c: ...

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

Implementation	Compiler
`round2`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`

Compiler output

mult768.c: mult768.c:210:7: error: always_inline function '_mm256_set1_epi16' requires target feature 'avx', but would be inlined into function 'crypto_core_mult3sntrup761_round2_constbranchindex' that is compiled without support for 'avx'
mult768.c:   x = const_x16(0);
mult768.c:       ^
mult768.c: mult768.c:11:19: note: expanded from macro 'const_x16'
mult768.c: #define const_x16 _mm256_set1_epi16
mult768.c:                   ^
mult768.c: mult768.c:210:7: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult768.c: mult768.c:11:19: note: expanded from macro 'const_x16'
mult768.c: #define const_x16 _mm256_set1_epi16
mult768.c:                   ^
mult768.c: mult768.c:211:35: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_mult3sntrup761_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:10:24: 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:211:35: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult768.c: mult768.c:10:24: 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:212:35: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'crypto_core_mult3sntrup761_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:10:24: 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 (Ubuntu_Clang_14.0.0)`

Compiler output

ntt.c: ntt.c: In function 'ntt512':
ntt.c: ntt.c:444:44: warning: unused variable 'h3' [-Wunused-variable]
ntt.c:   444 |   __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c:       |                                            ^~
ntt.c: ntt.c:444:41: warning: unused variable 'h2' [-Wunused-variable]
ntt.c:   444 |   __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c:       |                                         ^~
ntt.c: ntt.c:444:38: warning: unused variable 'h1' [-Wunused-variable]
ntt.c:   444 |   __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c:       |                                      ^~
ntt.c: ntt.c:444:35: warning: unused variable 'h0' [-Wunused-variable]
ntt.c:   444 |   __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:742:10: warning: unused variable 'origf' [-Wunused-variable]
ntt.c:   742 |   int16 *origf = f;
ntt.c:       |          ^~~~~
ntt.c: ntt.c:741:44: warning: unused variable 'h3' [-Wunused-variable]
ntt.c:   741 |   __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c:       |                                            ^~
ntt.c: ntt.c:741:41: warning: unused variable 'h2' [-Wunused-variable]
ntt.c:   741 |   __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c:       |                                         ^~
ntt.c: ntt.c:741:38: warning: unused variable 'h1' [-Wunused-variable]
ntt.c:   741 |   __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 (11.4.0)`
`round2`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`round2`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`round2`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`

Passed TIMECOP

TIMECOP iterations: 1

Number of similar (implementation,compiler) pairs: 55, namely:

Implementation	Compiler
`32`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`32`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`32`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`32`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`32`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`32`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`32`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`32`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`32`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`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`	`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)`
`avx2unsigned`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`avx2unsigned`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`avx2unsigned`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`avx2unsigned`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`avx2unsigned`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`avx2unsigned`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`avx2unsigned`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`avx2unsigned`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`avx800`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`avx800`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`avx800`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`avx800`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`avx800`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`avx800`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`avx800`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`avx800`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`compact`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`compact`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`compact`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`compact`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`compact`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`compact`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`compact`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`compact`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`compact`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`ref`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`ref`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`ref`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`ref`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`ref`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`ref`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`ref`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`ref`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`ref`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`round1`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`round1`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`round1`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`round1`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`