Implementation notes: amd64, rumba7, crypto_core/mult3sntrup761

Computer: rumba7
Microarchitecture: amd64; Zen (800f11)
Architecture: amd64
CPU ID: AuthenticAMD-00800f11-178bfbff
SUPERCOP version: 20240107
Operation: crypto_core
Primitive: mult3sntrup761
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
1137741468 0 055733 804 992avx2unsignedgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121220231212
1176835667 0 050323 844 960avx2unsignedclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121220231212
1192330419 0 044699 844 960avx2unsignedclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121220231212
1230323159 0 034379 844 928avx2unsignedclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121220231212
1233215460 0 028485 804 992avx2unsignedgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121220231212
1259620910 0 032965 836 1024avx2unsignedclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121220231212
1418214491 0 026988 796 992avx2unsignedgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121220231212
1484319803 0 032411 844 960avxclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121220231212
1496315458 0 030043 844 960avx800clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121220231212
1496917164 0 032131 844 960avx800clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121220231212
1504818081 0 030307 844 960avxclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121220231212
1506111904 0 023344 780 960avx2unsignedgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121220231212
1527914593 0 028397 804 992avx800gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121220231212
1578216186 0 030365 804 992avxgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121220231212
1698017415 0 031043 844 960round2clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121220231212
1714915709 0 028955 844 960round2clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121220231212
1817416068 0 030285 804 992round2gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121220231212
1907315041 0 025269 836 1024avxclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121220231212
1929516318 0 025523 844 928avxclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121220231212
1930313128 0 025381 836 1024avx800clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121220231212
1930413773 0 025339 844 928avx800clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121220231212
2029013803 0 025868 796 992avx800gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121220231212
2084415436 0 027836 796 992avxgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121220231212
2169910902 0 022613 836 1024round2clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121220231212
2190112168 0 022875 844 928round2clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121220231212
2251413600 0 026165 804 992avx800gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121220231212
2294914253 0 025536 780 960avxgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121220231212
2296813464 0 024424 780 960avx800gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121220231212
2334111559 0 024044 796 992round2gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121220231212
2358015193 0 028133 804 992avxgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121220231212
2537511345 0 022688 780 960round2gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121220231212
2542713051 0 026045 804 992round2gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121220231212
4430712902 0 027947 844 960round1clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121220231212
4709910946 0 025627 844 960round1clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121220231212
507058351 0 020709 836 1024round1clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121220231212
508188818 0 020419 844 928round1clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121220231212
1737153439 0 017653 804 99232gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121220231212
1945791034 0 014037 804 99232gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121220231212
1973731098 0 013572 796 99232gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121220231212
1977243172 0 018211 844 96032clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121220231212
1978043172 0 017835 844 96032clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121220231212
2001483875 0 018093 804 992refgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121220231212
201343994 0 013325 836 102432clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121220231212
2077881638 0 015603 844 92832clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121220231212
208765820 0 012371 844 92832clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121220231212
210199921 0 012256 780 96032gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121220231212
2217163680 0 018347 844 960refclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121220231212
2218523680 0 018723 844 960refclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121220231212
3240281742 0 015715 844 928refclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121220231212
1329484660 0 013661 804 992refgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121220231212
1389032471 0 012781 836 1024refclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121220231212
1453145504 0 012051 844 928refclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121220231212
2155154692 0 013164 796 992refgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121220231212
2763065556 0 011904 780 960refgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121220231212

Compiler output

Implementation: avx
Security model: constbranchindex
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
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 (compiler,implementation) pairs: 1, namely:
CompilerImplementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE avx

Compiler output

Implementation: avx2unsigned
Security model: constbranchindex
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
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 (compiler,implementation) pairs: 1, namely:
CompilerImplementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE avx2unsigned

Compiler output

Implementation: avx800
Security model: constbranchindex
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
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 (compiler,implementation) pairs: 1, namely:
CompilerImplementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE avx800

Compiler output

Implementation: round1
Security model: constbranchindex
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
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 (compiler,implementation) pairs: 1, namely:
CompilerImplementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE round1

Compiler output

Implementation: round1
Security model: constbranchindex
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE
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 (compiler,implementation) pairs: 4, namely:
CompilerImplementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE round1
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE round1
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE round1
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE round1

Compiler output

Implementation: round2
Security model: constbranchindex
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
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 (compiler,implementation) pairs: 1, namely:
CompilerImplementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE round2