Implementation notes: amd64, panther, crypto_core/mult3sntrup761

Computer: panther
Microarchitecture: amd64; Tiger Lake (806c1)
Architecture: amd64
CPU ID: GenuineIntel-000806c1-00-bfebfbff
SUPERCOP version: 20240425
Operation: crypto_core
Primitive: mult3sntrup761
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
587444898 0 059176 780 984avx2unsignedgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024042620240425
615234065 0 048181 828 952avx2unsignedclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042620240425
619255957 0 070213 828 952avx2unsignedclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042620240425
620315551 0 029941 828 952avx800clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042620240425
622818138 0 032557 828 952avx800clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042620240425
630820421 0 032445 828 952avxclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042620240425
638016185 0 029237 828 952round2clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042620240425
641323024 0 035077 828 952avxclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042620240425
641318772 0 031853 828 952round2clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042620240425
661616562 0 030800 780 984avx800gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024042620240425
685713603 0 024827 820 920avx800clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042620240425
696417801 0 026979 820 920avxclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042620240425
703617121 0 029320 780 984avx2unsignedgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024042620240425
705918620 0 032808 780 984avxgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024042620240425
718711667 0 022347 820 920round2clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042620240425
732218097 0 032328 780 984round2gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024042620240425
741111210 0 021931 756 952avx2unsignedgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024042620240425
741221184 0 032267 820 920avx2unsignedclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042620240425
847917536 0 029231 772 984avx2unsignedgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024042620240425
1116213721 0 025131 820 920avx800clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042620240425
1275110956 0 022655 772 984round2gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024042620240425
1279013671 0 025343 772 984avx800gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024042620240425
1325116141 0 027751 772 984avxgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024042620240425
1491413645 0 025800 780 984avx800gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024042620240425
1516913317 0 023939 756 952avx800gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024042620240425
1535015703 0 027808 780 984avxgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024042620240425
1538917988 0 029739 820 920avx2unsignedclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042620240425
1585111399 0 022019 756 952round2gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024042620240425
1619215342 0 025899 756 952avxgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024042620240425
1628813148 0 025304 780 984round2gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024042620240425
2044615507 0 029712 780 984round1gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024042620240425
2166913864 0 028397 828 952round1clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042620240425
2220611004 0 025509 828 952round1clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042620240425
233498978 0 020323 820 920round1clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042620240425
2870715834 0 026939 820 920round2clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042620240425
2912626122 0 035411 820 920avxclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042620240425
298899097 0 021264 780 984round1gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024042620240425
306008943 0 020696 780 984round1gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024042620240425
378179380 0 020923 820 920round1clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042620240425
390178330 0 018955 756 952round1gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024042620240425
1683856336 0 020536 780 984refgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024042620240425
1700345596 0 019800 780 98432gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024042620240425
1819092841 0 017341 828 952refclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042620240425
1829502841 0 017325 828 952refclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042620240425
183396921 0 013048 780 98432gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024042620240425
1870431011 0 012663 772 98432gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024042620240425
2113383553 0 018037 828 95232clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042620240425
2131283553 0 018053 828 95232clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042620240425
2163731637 0 012955 820 92032clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042620240425
2166432850 0 016725 828 92032clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042620240425
218272856 0 011443 756 95232gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024042620240425
223872839 0 012331 820 92032clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042620240425
2709872718 0 016589 828 920refclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042620240425
4511551598 0 012923 820 920refclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042620240425
1199390559 0 012051 820 920refclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2024042620240425
1397710572 0 012696 780 984refgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024042620240425
2120863611 0 012263 772 984refgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024042620240425
2475913482 0 011075 756 952refgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2024042620240425

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: 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