Implementation notes: amd64, saber214, crypto_core/mult3sntrup761

Computer: saber214
Microarchitecture: amd64; Bulldozer (600f20)
Architecture: amd64
CPU ID: AuthenticAMD-00600f20-1789c3f5
SUPERCOP version: 20240625
Operation: crypto_core
Primitive: mult3sntrup761
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
2748141638 0 015124 816 76032clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024062620240625
2878074324 0 016716 816 76032clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024062620240625
2878324324 0 019108 816 77632clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024062620240625
2937913593 0 017254 776 83232gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024062620240625
293837858 0 011598 808 76032clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024062620240625
295617820 0 011892 816 76032clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024062620240625
3117391045 0 013270 776 83232gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024062620240625
317755921 0 011729 752 80032gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024062620240625
3283871096 0 013101 768 83232gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024062620240625
3705404412 0 019204 816 776refclang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024062620240625
3714724412 0 016812 816 760refclang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024062620240625
4052553953 0 017622 776 832refgcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024062620240625
6306771742 0 015236 816 760refclang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024062620240625
2517657471 0 011182 808 760refclang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024062620240625
2537908671 0 012894 776 832refgcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024062620240625
2633935504 0 011572 816 760refclang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024062620240625
3007629692 0 012693 768 832refgcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024062620240625
3280970556 0 011361 752 800refgcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024062620240625

Compiler output


mult768.c: mult768.c:230:21: error: always_inline function '_mm256_add_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_core_mult3sntrup761_avx_constbranchindex' that is compiled without support for 'avx2'
mult768.c:     x = add_x16(fgi,add_x16(fgip,fgip1));
mult768.c:                     ^
mult768.c: mult768.c:11:17: note: expanded from macro 'add_x16'
mult768.c: #define add_x16 _mm256_add_epi16
mult768.c:                 ^
mult768.c: mult768.c:230:9: error: always_inline function '_mm256_add_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_core_mult3sntrup761_avx_constbranchindex' that is compiled without support for 'avx2'
mult768.c:     x = add_x16(fgi,add_x16(fgip,fgip1));
mult768.c:         ^
mult768.c: mult768.c:11:17: note: expanded from macro 'add_x16'
mult768.c: #define add_x16 _mm256_add_epi16
mult768.c:                 ^
mult768.c: 2 errors generated.

Number of similar (implementation,compiler) pairs: 4, namely:
ImplementationCompiler
avxclang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
avxclang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
avxclang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
avxclang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)

Compiler output


mult768.c: mult768.c:208:7: 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:10:19: note: expanded from macro 'const_x16'
mult768.c: #define const_x16 _mm256_set1_epi16
mult768.c:                   ^
mult768.c: mult768.c:208:7: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult768.c: mult768.c:10:19: note: expanded from macro 'const_x16'
mult768.c: #define const_x16 _mm256_set1_epi16
mult768.c:                   ^
mult768.c: mult768.c:209:35: 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:9:24: note: expanded from macro 'store_x16'
mult768.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult768.c:                        ^
mult768.c: mult768.c:209:35: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult768.c: mult768.c:9:24: note: expanded from macro 'store_x16'
mult768.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult768.c:                        ^
mult768.c: mult768.c: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(&g[i],x);
mult768.c:                                   ^
mult768.c: mult768.c:9:24: note: expanded from macro 'store_x16'
mult768.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult768.c: ...

Number of similar (implementation,compiler) pairs: 1, namely:
ImplementationCompiler
avxclang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)

Compiler output


mult768.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:47,
mult768.c:                  from mult768.c:2:
mult768.c: mult768.c: In function 'squeeze_3_x16':
mult768.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/avx2intrin.h:808:1: error: inlining failed in call to 'always_inline' '_mm256_sub_epi16': target specific option mismatch
mult768.c:   808 | _mm256_sub_epi16 (__m256i __A, __m256i __B)
mult768.c:       | ^~~~~~~~~~~~~~~~
mult768.c: mult768.c:12:17: note: called from here
mult768.c:    12 | #define sub_x16 _mm256_sub_epi16
mult768.c:       |                 ^
mult768.c: mult768.c:20:10: note: in expansion of macro 'sub_x16'
mult768.c:    20 |   return sub_x16(x,mullo_x16(mulhrs_x16(x,const_x16(10923)),const_x16(3)));
mult768.c:       |          ^~~~~~~
mult768.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:47,
mult768.c:                  from mult768.c:2:
mult768.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/avx2intrin.h:553:1: error: inlining failed in call to 'always_inline' '_mm256_mullo_epi16': target specific option mismatch
mult768.c:   553 | _mm256_mullo_epi16 (__m256i __A, __m256i __B)
mult768.c:       | ^~~~~~~~~~~~~~~~~~
mult768.c: mult768.c:12:17: note: called from here
mult768.c:    12 | #define sub_x16 _mm256_sub_epi16
mult768.c:       |                 ^
mult768.c: mult768.c:20:10: note: in expansion of macro 'sub_x16'
mult768.c:    20 |   return sub_x16(x,mullo_x16(mulhrs_x16(x,const_x16(10923)),const_x16(3)));
mult768.c:       |          ^~~~~~~
mult768.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:47,
mult768.c:                  from mult768.c:2:
mult768.c: ...

Number of similar (implementation,compiler) pairs: 12, namely:
ImplementationCompiler
avxgcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
avxgcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
avxgcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
avxgcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
avx800gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
avx800gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
avx800gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
avx800gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
round2gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
round2gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
round2gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
round2gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)

Compiler output


mult.c: In file included from mult.c:19:
mult.c: ./const_inline.h:38:61: error: always_inline function '_mm256_shuffle_epi8' requires target feature 'avx2', but would be inlined into function 'cvt_to_unsigned' that is compiled without support for 'avx2'
mult.c: static inline __m256i cvt_to_unsigned( __m256i a ) { return _mm256_shuffle_epi8(_cvt_to_unsigned,a&v_0x3); }
mult.c:                                                             ^
mult.c: ./const_inline.h:42:56: error: always_inline function '_mm256_shuffle_epi8' requires target feature 'avx2', but would be inlined into function 'cvt_to_int' that is compiled without support for 'avx2'
mult.c: static inline __m256i cvt_to_int( __m256i a ) { return _mm256_shuffle_epi8(_cvt_to_int,a); }
mult.c:                                                        ^
mult.c: 2 errors generated.

Number of similar (implementation,compiler) pairs: 4, namely:
ImplementationCompiler
avx2unsignedclang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
avx2unsignedclang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
avx2unsignedclang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
avx2unsignedclang -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:
ImplementationCompiler
avx2unsignedclang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)

Compiler output


mult.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:47,
mult.c:                  from mult.c:17:
mult.c: const_inline.h: In function 'cvt_to_unsigned':
mult.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/avx2intrin.h:588:1: error: inlining failed in call to 'always_inline' '_mm256_shuffle_epi8': target specific option mismatch
mult.c:   588 | _mm256_shuffle_epi8 (__m256i __X, __m256i __Y)
mult.c:       | ^~~~~~~~~~~~~~~~~~~
mult.c: In file included from mult.c:19:
mult.c: const_inline.h:38:61: note: called from here
mult.c:    38 | static inline __m256i cvt_to_unsigned( __m256i a ) { return _mm256_shuffle_epi8(_cvt_to_unsigned,a&v_0x3); }
mult.c:       |                                                             ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
mult.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:47,
mult.c:                  from mult.c:17:
mult.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/avx2intrin.h:588:1: error: inlining failed in call to 'always_inline' '_mm256_shuffle_epi8': target specific option mismatch
mult.c:   588 | _mm256_shuffle_epi8 (__m256i __X, __m256i __Y)
mult.c:       | ^~~~~~~~~~~~~~~~~~~
mult.c: In file included from mult.c:19:
mult.c: const_inline.h:38:61: note: called from here
mult.c:    38 | static inline __m256i cvt_to_unsigned( __m256i a ) { return _mm256_shuffle_epi8(_cvt_to_unsigned,a&v_0x3); }
mult.c:       |                                                             ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Number of similar (implementation,compiler) pairs: 4, namely:
ImplementationCompiler
avx2unsignedgcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
avx2unsignedgcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
avx2unsignedgcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
avx2unsignedgcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)

Compiler output


mult768.c: mult768.c:230:21: error: always_inline function '_mm256_add_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_core_mult3sntrup761_avx800_constbranchindex' that is compiled without support for 'avx2'
mult768.c:     x = add_x16(fgi,add_x16(fgip,fgip1));
mult768.c:                     ^
mult768.c: mult768.c:11:17: note: expanded from macro 'add_x16'
mult768.c: #define add_x16 _mm256_add_epi16
mult768.c:                 ^
mult768.c: mult768.c:230:9: error: always_inline function '_mm256_add_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_core_mult3sntrup761_avx800_constbranchindex' that is compiled without support for 'avx2'
mult768.c:     x = add_x16(fgi,add_x16(fgip,fgip1));
mult768.c:         ^
mult768.c: mult768.c:11:17: note: expanded from macro 'add_x16'
mult768.c: #define add_x16 _mm256_add_epi16
mult768.c:                 ^
mult768.c: 2 errors generated.

Number of similar (implementation,compiler) pairs: 4, namely:
ImplementationCompiler
avx800clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
avx800clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
avx800clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
avx800clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)

Compiler output


mult768.c: mult768.c:208:7: 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:10:19: note: expanded from macro 'const_x16'
mult768.c: #define const_x16 _mm256_set1_epi16
mult768.c:                   ^
mult768.c: mult768.c:208:7: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult768.c: mult768.c:10:19: note: expanded from macro 'const_x16'
mult768.c: #define const_x16 _mm256_set1_epi16
mult768.c:                   ^
mult768.c: mult768.c:209:35: 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:9:24: note: expanded from macro 'store_x16'
mult768.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult768.c:                        ^
mult768.c: mult768.c:209:35: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult768.c: mult768.c:9:24: note: expanded from macro 'store_x16'
mult768.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult768.c:                        ^
mult768.c: mult768.c: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(&g[i],x);
mult768.c:                                   ^
mult768.c: mult768.c:9:24: note: expanded from macro 'store_x16'
mult768.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult768.c: ...

Number of similar (implementation,compiler) pairs: 1, namely:
ImplementationCompiler
avx800clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)

Compiler output


mult.c: mult.c:522:11: error: always_inline function '_mm256_add_epi8' requires target feature 'avx2', but would be inlined into function 'mult768_mix2_m256i' that is compiled without support for 'avx2'
mult.c:     g01 = _mm256_add_epi8(g0,g1); gkara[i][8] = g01;
mult.c:           ^
mult.c: mult.c:523:11: error: always_inline function '_mm256_add_epi8' requires target feature 'avx2', but would be inlined into function 'mult768_mix2_m256i' that is compiled without support for 'avx2'
mult.c:     g23 = _mm256_add_epi8(g2,g3); gkara[i][9] = g23;
mult.c:           ^
mult.c: mult.c:524:11: error: always_inline function '_mm256_add_epi8' requires target feature 'avx2', but would be inlined into function 'mult768_mix2_m256i' that is compiled without support for 'avx2'
mult.c:     g45 = _mm256_add_epi8(g4,g5); gkara[i][10] = g45;
mult.c:           ^
mult.c: mult.c:525:11: error: always_inline function '_mm256_add_epi8' requires target feature 'avx2', but would be inlined into function 'mult768_mix2_m256i' that is compiled without support for 'avx2'
mult.c:     g67 = _mm256_add_epi8(g6,g7); gkara[i][11] = g67;
mult.c:           ^
mult.c: mult.c:532:11: error: always_inline function '_mm256_add_epi8' requires target feature 'avx2', but would be inlined into function 'mult768_mix2_m256i' that is compiled without support for 'avx2'
mult.c:     g02 = _mm256_add_epi8(g0,g2); gkara[i][16] = g02;
mult.c:           ^
mult.c: mult.c:533:11: error: always_inline function '_mm256_add_epi8' requires target feature 'avx2', but would be inlined into function 'mult768_mix2_m256i' that is compiled without support for 'avx2'
mult.c:     g04 = _mm256_add_epi8(g0,g4); gkara[i][22] = g04;
mult.c:           ^
mult.c: mult.c:534:11: error: always_inline function '_mm256_add_epi8' requires target feature 'avx2', but would be inlined into function 'mult768_mix2_m256i' that is compiled without support for 'avx2'
mult.c:     g46 = _mm256_add_epi8(g4,g6); gkara[i][19] = g46;
mult.c:           ^
mult.c: mult.c:535:11: error: always_inline function '_mm256_add_epi8' requires target feature 'avx2', but would be inlined into function 'mult768_mix2_m256i' that is compiled without support for 'avx2'
mult.c:     g26 = _mm256_add_epi8(g2,g6); gkara[i][24] = g26;
mult.c:           ^
mult.c: mult.c:542:11: error: always_inline function '_mm256_add_epi8' requires target feature 'avx2', but would be inlined into function 'mult768_mix2_m256i' that is compiled without support for 'avx2'
mult.c: ...

Number of similar (implementation,compiler) pairs: 4, namely:
ImplementationCompiler
round1clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
round1clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
round1clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
round1clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)

Compiler output


mult.c: mult.c:146:22: error: invalid output size for constraint '=&x'
mult.c:   MULSTEP_fromzero(0,h0,h1,h2,h3,h4)
mult.c:                      ^
mult.c: mult.c:148:26: error: invalid output size for constraint '+x'
mult.c:     MULSTEP_noload(j + 1,h1,h2,h3,h4,h0)
mult.c:                          ^
mult.c: mult.c:149:26: error: invalid output size for constraint '+x'
mult.c:     MULSTEP_noload(j + 2,h2,h3,h4,h0,h1)
mult.c:                          ^
mult.c: mult.c:150:26: error: invalid output size for constraint '+x'
mult.c:     MULSTEP_noload(j + 3,h3,h4,h0,h1,h2)
mult.c:                          ^
mult.c: mult.c:151:26: error: invalid output size for constraint '+x'
mult.c:     MULSTEP_noload(j + 4,h4,h0,h1,h2,h3)
mult.c:                          ^
mult.c: mult.c:152:26: error: invalid output size for constraint '+x'
mult.c:     MULSTEP_noload(j + 5,h0,h1,h2,h3,h4)
mult.c:                          ^
mult.c: mult.c:154:24: error: invalid output size for constraint '+x'
mult.c:   MULSTEP_noload(j + 1,h1,h2,h3,h4,h0)
mult.c:                        ^
mult.c: mult.c:155:24: error: invalid output size for constraint '+x'
mult.c:   MULSTEP_noload(j + 2,h2,h3,h4,h0,h1)
mult.c:                        ^
mult.c: mult.c:156:24: error: invalid output size for constraint '+x'
mult.c: ...

Number of similar (implementation,compiler) pairs: 1, namely:
ImplementationCompiler
round1clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)

Compiler output


mult.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:47,
mult.c:                  from mult.c:2:
mult.c: mult.c: In function 'squeeze':
mult.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/avx2intrin.h:808:1: error: inlining failed in call to 'always_inline' '_mm256_sub_epi16': target specific option mismatch
mult.c:   808 | _mm256_sub_epi16 (__m256i __A, __m256i __B)
mult.c:       | ^~~~~~~~~~~~~~~~
mult.c: mult.c:106:10: note: called from here
mult.c:   106 |   return _mm256_sub_epi16(x,q);
mult.c:       |          ^~~~~~~~~~~~~~~~~~~~~
mult.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:47,
mult.c:                  from mult.c:2:
mult.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/avx2intrin.h:553:1: error: inlining failed in call to 'always_inline' '_mm256_mullo_epi16': target specific option mismatch
mult.c:   553 | _mm256_mullo_epi16 (__m256i __A, __m256i __B)
mult.c:       | ^~~~~~~~~~~~~~~~~~
mult.c: mult.c:105:7: note: called from here
mult.c:   105 |   q = _mm256_mullo_epi16(q,v4591_16);
mult.c:       |       ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
mult.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:47,
mult.c:                  from mult.c:2:
mult.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/avx2intrin.h:531:1: error: inlining failed in call to 'always_inline' '_mm256_mulhrs_epi16': target specific option mismatch
mult.c:   531 | _mm256_mulhrs_epi16 (__m256i __X, __m256i __Y)
mult.c:       | ^~~~~~~~~~~~~~~~~~~
mult.c: mult.c:104:15: note: called from here
mult.c:   104 |   __m256i q = _mm256_mulhrs_epi16(x,v7);
mult.c:       |               ^~~~~~~~~~~~~~~~~~~~~~~~~
mult.c: ...

Number of similar (implementation,compiler) pairs: 4, namely:
ImplementationCompiler
round1gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
round1gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
round1gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
round1gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)

Compiler output


mult768.c: mult768.c:230:21: error: always_inline function '_mm256_add_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_core_mult3sntrup761_round2_constbranchindex' that is compiled without support for 'avx2'
mult768.c:     x = add_x16(fgi,add_x16(fgip,fgip1));
mult768.c:                     ^
mult768.c: mult768.c:11:17: note: expanded from macro 'add_x16'
mult768.c: #define add_x16 _mm256_add_epi16
mult768.c:                 ^
mult768.c: mult768.c:230:9: error: always_inline function '_mm256_add_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_core_mult3sntrup761_round2_constbranchindex' that is compiled without support for 'avx2'
mult768.c:     x = add_x16(fgi,add_x16(fgip,fgip1));
mult768.c:         ^
mult768.c: mult768.c:11:17: note: expanded from macro 'add_x16'
mult768.c: #define add_x16 _mm256_add_epi16
mult768.c:                 ^
mult768.c: 2 errors generated.

Number of similar (implementation,compiler) pairs: 4, namely:
ImplementationCompiler
round2clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
round2clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
round2clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
round2clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)

Compiler output


mult768.c: mult768.c:208:7: 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:10:19: note: expanded from macro 'const_x16'
mult768.c: #define const_x16 _mm256_set1_epi16
mult768.c:                   ^
mult768.c: mult768.c:208:7: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult768.c: mult768.c:10:19: note: expanded from macro 'const_x16'
mult768.c: #define const_x16 _mm256_set1_epi16
mult768.c:                   ^
mult768.c: mult768.c:209:35: 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:9:24: note: expanded from macro 'store_x16'
mult768.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult768.c:                        ^
mult768.c: mult768.c:209:35: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
mult768.c: mult768.c:9:24: note: expanded from macro 'store_x16'
mult768.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult768.c:                        ^
mult768.c: mult768.c:210:35: 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:9:24: note: expanded from macro 'store_x16'
mult768.c: #define store_x16(p,v) _mm256_storeu_si256((int16x16 *) (p),(v))
mult768.c: ...

Number of similar (implementation,compiler) pairs: 1, namely:
ImplementationCompiler
round2clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)

TIMECOP error (can be valgrind bug)


Process terminating with default action of signal 4 (SIGILL)
 Illegal opcode at address 0x10A1AD
   at 0x...: salsa20.part.0 (try-anything.c:102)
   by 0x...: salsa20 (try-anything.c:85)
   by 0x...: canary (try-anything.c:148)
   by 0x...: output_prepare (try-anything.c:178)
   by 0x...: test (try.c:99)
   by 0x...: main (try-anything.c:345)

Number of similar (implementation,compiler) pairs: 2, namely:
ImplementationCompiler
32gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
refgcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)

TIMECOP error (can be valgrind bug)


Process terminating with default action of signal 4 (SIGILL)
 Illegal opcode at address 0x109DFA
   at 0x...: core (try-anything.c:53)
   by 0x...: salsa20.part.0 (try-anything.c:89)
   by 0x...: salsa20 (try-anything.c:85)
   by 0x...: canary (try-anything.c:148)
   by 0x...: output_prepare (try-anything.c:178)
   by 0x...: test (try.c:99)
   by 0x...: main (try-anything.c:345)

Number of similar (implementation,compiler) pairs: 2, namely:
ImplementationCompiler
32gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
refgcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)

TIMECOP error (can be valgrind bug)


Process terminating with default action of signal 4 (SIGILL)
 Illegal opcode at address 0x109954
   at 0x...: memcpy (string_fortified.h:29)
   by 0x...: test (try.c:149)
   by 0x...: main (try-anything.c:345)

Number of similar (implementation,compiler) pairs: 2, namely:
ImplementationCompiler
32gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
refgcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)

TIMECOP error (can be valgrind bug)


Process terminating with default action of signal 4 (SIGILL)
 Illegal opcode at address 0x10B79D
   at 0x...: crypto_core_mult3sntrup761_ref_constbranchindex (mult.c:38)
   by 0x...: test (try.c:106)
   by 0x...: main (try-anything.c:345)

Number of similar (implementation,compiler) pairs: 1, namely:
ImplementationCompiler
refclang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)

TIMECOP error (can be valgrind bug)


Process terminating with default action of signal 4 (SIGILL)
 Illegal opcode at address 0x10B83D
   at 0x...: crypto_core_mult3sntrup761_ref_constbranchindex (mult.c:38)
   by 0x...: test (try.c:106)
   by 0x...: main (try-anything.c:345)

Number of similar (implementation,compiler) pairs: 1, namely:
ImplementationCompiler
refclang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)

Passed TIMECOP


TIMECOP iterations: 1

Number of similar (implementation,compiler) pairs: 10, namely:
ImplementationCompiler
32clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
32clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
32clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
32clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
32clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
32gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)
refclang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
refclang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
refclang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)
refgcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)