Implementation notes: amd64, speed2supercop, crypto_core/mult3sntrup761

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: ...

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.

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: ...

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:       |      ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

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: ...

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: ...

Compiler output

mult.c: mult.c: In function 'mult768_mix2_m256i':
mult.c: mult.c:568:3: warning: 'mult96x16' accessing 6144 bytes in a region of size 512 [-Wstringop-overflow=]
mult.c:   568 |   mult96x16(hkara[12],fkara[6],(__m256i *) (1 + (__m128i *) gkara));
mult.c:       |   ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
mult.c: mult.c:568:3: note: referencing argument 1 of type '__m256i[192]'
mult.c: mult.c:568:3: warning: 'mult96x16' reading 3072 bytes from a region of size 512 [-Wstringop-overread]
mult.c: mult.c:568:3: note: referencing argument 2 of type 'const __m256i[96]'
mult.c: mult.c:568:3: warning: 'mult96x16' reading 3072 bytes from a region of size 3056 [-Wstringop-overread]
mult.c: mult.c:568:3: note: referencing argument 3 of type 'const __m256i[96]'
mult.c: mult.c:279:13: note: in a call to function 'mult96x16'
mult.c:   279 | static void mult96x16(__m256i h[192],const __m256i f[96],const __m256i g[96])
mult.c:       |             ^~~~~~~~~
mult.c: mult.c:569:3: warning: 'mult96x16' accessing 6144 bytes in a region of size 512 [-Wstringop-overflow=]
mult.c:   569 |   mult96x16(hkara[0],fkara[0],gkara[0]);
mult.c:       |   ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
mult.c: mult.c:569:3: note: referencing argument 1 of type '__m256i[192]'
mult.c: mult.c:569:3: warning: 'mult96x16' reading 3072 bytes from a region of size 512 [-Wstringop-overread]
mult.c: mult.c:569:3: note: referencing argument 2 of type 'const __m256i[96]'
mult.c: mult.c:569:3: warning: 'mult96x16' reading 3072 bytes from a region of size 1024 [-Wstringop-overread]
mult.c: mult.c:569:3: note: referencing argument 3 of type 'const __m256i[96]'
mult.c: mult.c:279:13: note: in a call to function 'mult96x16'
mult.c:   279 | static void mult96x16(__m256i h[192],const __m256i f[96],const __m256i g[96])
mult.c:       |             ^~~~~~~~~

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:444:38: warning: unused variable 'h1' [-Wunused-variable]
ntt.c:   __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c:                                      ^
ntt.c: ntt.c:444:41: warning: unused variable 'h2' [-Wunused-variable]
ntt.c:   __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c:                                         ^
ntt.c: ntt.c:444:44: warning: unused variable 'h3' [-Wunused-variable]
ntt.c:   __m256i f0,f1,f2,f3,g0,g1,g2,g3,h0,h1,h2,h3;
ntt.c:                                            ^
ntt.c: ntt.c: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:741:38: 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: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: ...

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: ...

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: ...

Passed TIMECOP

TIMECOP iterations: 1