Implementation notes: amd64, kizomba, crypto_core/mult3sntrup761
Computer: kizomba
Microarchitecture: amd64; Kaby Lake (906e9)
Architecture: amd64
CPU ID: GenuineIntel-000906e9-1fc9cbf5
SUPERCOP version: 20240625
Operation: crypto_core
Primitive: mult3sntrup761
Time | Object size | Test size | Implementation | Compiler | Benchmark date | SUPERCOP version |
6420 | 45396 0 0 | 59902 776 832 | avx2unsigned | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
6634 | 15986 0 0 | 30772 816 776 | avx800 | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
6699 | 18577 0 0 | 31004 816 776 | avx | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
6710 | 17436 0 0 | 32524 816 856 | avx800 | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
6729 | 20043 0 0 | 32772 816 856 | avx | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
6804 | 35753 0 0 | 50524 816 856 | avx2unsigned | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
6861 | 31065 0 0 | 45540 816 776 | avx2unsigned | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
7569 | 16713 0 0 | 30814 776 832 | avx800 | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
7788 | 17676 0 0 | 30062 776 832 | avx2unsigned | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
7937 | 17682 0 0 | 32110 776 832 | avx | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
7978 | 23207 0 0 | 33972 816 760 | avx2unsigned | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
8546 | 20931 0 0 | 32646 808 856 | avx2unsigned | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
8865 | 17517 0 0 | 29501 768 832 | avx2unsigned | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
9024 | 12484 0 0 | 23417 752 800 | avx2unsigned | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
10646 | 16318 0 0 | 25068 816 760 | avx | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
10742 | 13773 0 0 | 24884 816 760 | avx800 | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
11461 | 13126 0 0 | 24998 808 856 | avx800 | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
12022 | 15075 0 0 | 24942 808 856 | avx | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
12657 | 13804 0 0 | 25413 768 832 | avx800 | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
13807 | 14869 0 0 | 26773 768 832 | avx | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
14330 | 14264 0 0 | 25033 752 800 | avx | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
14500 | 13760 0 0 | 25726 776 832 | avx800 | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
14621 | 13455 0 0 | 23969 752 800 | avx800 | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
14875 | 14729 0 0 | 27022 776 832 | avx | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
24902 | 12934 0 0 | 28100 816 856 | round1 | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
25216 | 11122 0 0 | 26004 816 776 | round1 | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
30605 | 8770 0 0 | 19916 816 760 | round1 | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
31175 | 8306 0 0 | 20294 808 856 | round1 | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
161581 | 5540 0 0 | 20046 776 832 | 32 | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
170781 | 3769 0 0 | 18644 816 776 | ref | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
174786 | 3769 0 0 | 18940 816 856 | ref | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
182174 | 993 0 0 | 13342 776 832 | 32 | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
187901 | 1096 0 0 | 13053 768 832 | 32 | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
195423 | 6220 0 0 | 20734 776 832 | ref | gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
202345 | 919 0 0 | 11753 752 800 | 32 | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
205572 | 3771 0 0 | 18636 816 776 | 32 | clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
205684 | 3771 0 0 | 18932 816 856 | 32 | clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
207687 | 1638 0 0 | 15148 816 760 | 32 | clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
209710 | 820 0 0 | 11916 816 760 | 32 | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
209947 | 993 0 0 | 12958 808 856 | 32 | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
405581 | 1742 0 0 | 15260 816 760 | ref | clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
1141546 | 471 0 0 | 12414 808 856 | ref | clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
1198448 | 504 0 0 | 11596 816 760 | ref | clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
1390085 | 643 0 0 | 12998 776 832 | ref | gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
2115867 | 692 0 0 | 12661 768 832 | ref | gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
2489796 | 556 0 0 | 11401 752 800 | ref | gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall | 20240626 | 20240625 |
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:
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: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:
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: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:
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:750:3:
mult.c: mult.c:567:3: warning: 'mult96x16' accessing 6144 bytes in a region of size 512 [-Wstringop-overflow=]
mult.c: 567 | 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:567:3: 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:750:3:
mult.c: mult.c:567:3: 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:567:3: 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:750:3:
mult.c: mult.c:567:3: 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:567:3: note: referencing argument 3 of type 'const __m256i *'
mult.c: mult.c:278:13: note: in a call to function 'mult96x16'
mult.c: 278 | 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:750:3:
mult.c: mult.c:568:3: warning: 'mult96x16' accessing 6144 bytes in a region of size 512 [-Wstringop-overflow=]
mult.c: 568 | mult96x16(hkara[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:444:38: 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:741:38: 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: __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:742:10: warning: unused variable 'origf' [-Wunused-variable]
ntt.c: int16 *origf = f;
ntt.c: ^
ntt.c: ntt.c:741:41: warning: unused variable 'h2' [-Wunused-variable]
ntt.c: ...
Number of similar (implementation,compiler) pairs: 1, namely:
Implementation | Compiler |
round2 | clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
Compiler output
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: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: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:741:35: 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:741:38: 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:741:41: warning: unused variable 'h2' [-Wunused-variable]
ntt.c: ...
Number of similar (implementation,compiler) pairs: 1, namely:
Implementation | Compiler |
round2 | clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0) |
Compiler output
ntt.c: ntt.c:444:35: 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: 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:444:35: 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:741:41: 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: __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: ...
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: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:
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: 46, 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) |
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) |