Implementation notes: amd64, h6sandy, crypto_core/mult3sntrup761
Computer: h6sandy
Microarchitecture: amd64; Sandy Bridge (206a7)
Architecture: amd64
CPU ID: GenuineIntel-000206a7-bfebfbff
SUPERCOP version: 20240808
Operation: crypto_core
Primitive: mult3sntrup761
Time | Object size | Test size | Implementation | Compiler | Benchmark date | SUPERCOP version |
176120 | 1504 0 0 | 15533 804 992 | compact | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
191591 | 3294 0 0 | 17325 804 992 | 32 | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
203667 | 6892 0 0 | 22179 844 928 | compact | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
208551 | 980 0 0 | 13797 804 992 | 32 | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
214166 | 1816 0 0 | 15171 844 928 | compact | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
219302 | 1494 0 0 | 15451 844 928 | compact | clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
220472 | 1101 0 0 | 13588 796 992 | 32 | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
233921 | 1101 0 0 | 16403 844 928 | 32 | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
233936 | 1101 0 0 | 14459 844 928 | 32 | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
234724 | 863 0 0 | 12141 836 928 | 32 | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
235403 | 1014 0 0 | 14947 844 928 | 32 | clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
235870 | 820 0 0 | 12419 844 928 | 32 | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
236552 | 915 0 0 | 12224 780 960 | 32 | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
276909 | 1049 0 0 | 14411 844 928 | ref | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
280540 | 1049 0 0 | 16355 844 928 | ref | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
287434 | 3705 0 0 | 17749 804 992 | ref | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
378278 | 1134 0 0 | 15075 844 928 | ref | clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
1324445 | 504 0 0 | 12099 844 928 | ref | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
1334475 | 471 0 0 | 11741 836 928 | ref | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
1678891 | 638 0 0 | 13453 804 992 | ref | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
1762224 | 426 0 0 | 12027 844 928 | compact | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
1762666 | 363 0 0 | 11637 836 928 | compact | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
1770751 | 420 0 0 | 11736 780 960 | compact | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
1823507 | 497 0 0 | 13317 804 992 | compact | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
2395264 | 695 0 0 | 13180 796 992 | ref | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
2404088 | 503 0 0 | 12980 796 992 | compact | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
2437899 | 556 0 0 | 11872 780 960 | ref | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240809 | 20240808 |
Compiler output
mult768.c: mult768.c:231:21: 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:12:17: note: expanded from macro 'add_x16'
mult768.c: #define add_x16 _mm256_add_epi16
mult768.c: ^
mult768.c: mult768.c:231:9: 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:12:17: 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:
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) |
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
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:13:17: note: called from here
mult768.c: 13 | #define sub_x16 _mm256_sub_epi16
mult768.c: | ^
mult768.c: mult768.c:21:10: note: in expansion of macro 'sub_x16'
mult768.c: 21 | 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:13:17: note: called from here
mult768.c: 13 | #define sub_x16 _mm256_sub_epi16
mult768.c: | ^
mult768.c: mult768.c:21:10: note: in expansion of macro 'sub_x16'
mult768.c: 21 | 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: 8, 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 -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) |
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) |
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:
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
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:
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:231:21: 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:12:17: note: expanded from macro 'add_x16'
mult768.c: #define add_x16 _mm256_add_epi16
mult768.c: ^
mult768.c: mult768.c:231:9: 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:12:17: 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:
Implementation | Compiler |
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) |
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: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: g01 = _mm256_add_epi8(g0,g1); gkara[i][8] = g01;
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: g23 = _mm256_add_epi8(g2,g3); gkara[i][9] = g23;
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: g45 = _mm256_add_epi8(g4,g5); gkara[i][10] = g45;
mult.c: ^
mult.c: mult.c:526:11: 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: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: g02 = _mm256_add_epi8(g0,g2); gkara[i][16] = g02;
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: g04 = _mm256_add_epi8(g0,g4); gkara[i][22] = g04;
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: g46 = _mm256_add_epi8(g4,g6); gkara[i][19] = g46;
mult.c: ^
mult.c: mult.c:536:11: 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:543:11: 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:
Implementation | Compiler |
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) |
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 file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:99,
mult.c: from mult.c:3:
mult.c: mult.c: In function 'fastadd':
mult.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/fmaintrin.h:63:1: error: inlining failed in call to 'always_inline' '_mm256_fmadd_ps': target specific option mismatch
mult.c: 63 | _mm256_fmadd_ps (__m256 __A, __m256 __B, __m256 __C)
mult.c: | ^~~~~~~~~~~~~~~
mult.c: mult.c:88:10: note: called from here
mult.c: 88 | return _mm256_fmadd_ps(y,v1_float,x);
mult.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
mult.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:99,
mult.c: from mult.c:3:
mult.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/fmaintrin.h:63:1: error: inlining failed in call to 'always_inline' '_mm256_fmadd_ps': target specific option mismatch
mult.c: 63 | _mm256_fmadd_ps (__m256 __A, __m256 __B, __m256 __C)
mult.c: | ^~~~~~~~~~~~~~~
mult.c: mult.c:88:10: note: called from here
mult.c: 88 | return _mm256_fmadd_ps(y,v1_float,x);
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
mult768.c: mult768.c:232:21: 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:12:17: note: expanded from macro 'add_x16'
mult768.c: #define add_x16 _mm256_add_epi16
mult768.c: ^
mult768.c: mult768.c:232:9: 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:12:17: 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:
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) |
round2 | clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
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
mult768.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:47,
mult768.c: from mult768.c:3:
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:13:17: note: called from here
mult768.c: 13 | #define sub_x16 _mm256_sub_epi16
mult768.c: | ^
mult768.c: mult768.c:21:10: note: in expansion of macro 'sub_x16'
mult768.c: 21 | 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:3:
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:13:17: note: called from here
mult768.c: 13 | #define sub_x16 _mm256_sub_epi16
mult768.c: | ^
mult768.c: mult768.c:21:10: note: in expansion of macro 'sub_x16'
mult768.c: 21 | 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:3:
mult768.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: 27, 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) |
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) |