Implementation notes: amd64, speed2supercop, crypto_kem/titaniumccasuper

Computer: speed2supercop
Microarchitecture: amd64; Haswell+AES (306c3)
Architecture: amd64
CPU ID: GenuineIntel-000306c3-1fc9cbf5
SUPERCOP version: 20240625
Operation: crypto_kem
Primitive: titaniumccasuper
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
4689076155382 0 64316461 760 1664T:avx2gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024071320240625
4715068156546 0 36318429 800 1600T:avx2clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024071320240625
4749304151320 0 64310533 760 1664T:avx2gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024071320240625
4845084145415 0 36304599 792 1696T:avx2clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024071320240625
4855624157141 0 36319253 800 1600T:avx2clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024071320240625
4858788149440 0 36307493 800 1600T:avx2clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024071320240625
4912640145874 0 64304773 760 1664T:avx2gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024071320240625
6690432142440 0 36304093 800 1600T:optclang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024071320240625
6726888115825 0 36277565 800 1600T:optclang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024071320240625
7243764110879 0 64271957 760 1664T:optgcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024071320240625
7306712101267 0 36262038 800 1600T:optclang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024071320240625
746851688997 0 64248269 760 1664T:optgcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024071320240625
759826482929 0 36241598 800 1600T:optclang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024071320240625
779022483895 0 36243415 792 1696T:optclang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024071320240625
837205281496 0 64240461 760 1664T:optgcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024071320240625
1108084340100479 0 36262990 800 1600T:refclang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024071320240625
110812091271824 0 36234126 800 1600T:refclang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024071320240625
113445290473473 0 36234638 800 1600T:refclang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024071320240625
113468839271819 0 64232957 760 1664T:refgcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024071320240625
113479850856640 0 36216007 792 1696T:refclang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024071320240625
114925930455654 0 64214789 760 1664T:refgcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024071320240625
117326640855583 0 36214206 800 1600T:refclang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall2024071320240625
145089264854918 0 64213717 760 1664T:refgcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024071320240625
460873660453827 0 64211573 752 1632T:refgcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall2024071320240625

Compiler output


encrypt.c: encrypt.c:63:8: error: always_inline function '_mm256_loadu_si256' requires target feature 'avx', but would be inlined into function 'crypto_encrypt_keypair' that is compiled without support for 'avx'
encrypt.c:                         u = _mm256_loadu_si256((__m256i *)(a[i] + j));
encrypt.c:                             ^
encrypt.c: encrypt.c:63:8: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
encrypt.c: encrypt.c:64:8: error: always_inline function '_mm256_loadu_si256' requires target feature 'avx', but would be inlined into function 'crypto_encrypt_keypair' that is compiled without support for 'avx'
encrypt.c:                         v = _mm256_loadu_si256((__m256i *)(s + j));
encrypt.c:                             ^
encrypt.c: encrypt.c:64:8: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
encrypt.c: encrypt.c:65:8: error: always_inline function '_mm256_mul_epu32' requires target feature 'avx2', but would be inlined into function 'crypto_encrypt_keypair' that is compiled without support for 'avx2'
encrypt.c:                         t = _mm256_mul_epu32(u, v);
encrypt.c:                             ^
encrypt.c: encrypt.c:65:8: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
encrypt.c: encrypt.c:66:4: error: always_inline function '_mm256_storeu_si256' requires target feature 'avx', but would be inlined into function 'crypto_encrypt_keypair' that is compiled without support for 'avx'
encrypt.c:                         _mm256_storeu_si256((__m256i *)(a[i] + j), t);
encrypt.c:                         ^
encrypt.c: encrypt.c:66:4: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
encrypt.c: encrypt.c:78:8: error: always_inline function '_mm256_loadu_si256' requires target feature 'avx', but would be inlined into function 'crypto_encrypt_keypair' that is compiled without support for 'avx'
encrypt.c:                         u = _mm256_loadu_si256((__m256i *)(a[i] + j));
encrypt.c:                             ^
encrypt.c: encrypt.c:78:8: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
encrypt.c: encrypt.c:79:8: error: always_inline function '_mm256_loadu_si256' requires target feature 'avx', but would be inlined into function 'crypto_encrypt_keypair' that is compiled without support for 'avx'
encrypt.c:                         v = _mm256_loadu_si256((__m256i *)(e[i] + j));
encrypt.c:                             ^
encrypt.c: encrypt.c:79:8: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
encrypt.c: encrypt.c:80:8: error: always_inline function '_mm256_add_epi64' requires target feature 'avx2', but would be inlined into function 'crypto_encrypt_keypair' that is compiled without support for 'avx2'
encrypt.c: ...

Number of similar (implementation,compiler) pairs: 1, namely:
ImplementationCompiler
T:avx2clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_16.0.6_(27+b1))

Compiler output


try.c: /usr/bin/ld: libcrypto_kem_titaniumccasuper.a(sampler.o): in function `sampler_zq':
try.c: .../supercop-data/speed2supercop/amd64/try/c/gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall/timingleaks/crypto_kem/titaniumccasuper/avx2/work/sampler.c:160:(.text+0x...): undefined reference to `barrett_zq'
try.c: collect2: error: ld returned 1 exit status

Number of similar (implementation,compiler) pairs: 1, namely:
ImplementationCompiler
T:avx2gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)

Compiler output


try.c: /usr/bin/ld: libcrypto_kem_titaniumccasuper.a(encrypt.o): in function `crypto_encrypt_keypair':
try.c: .../supercop-data/speed2supercop/amd64/try/c/gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall/timingleaks/crypto_kem/titaniumccasuper/opt/work/encrypt.c:63:(.text+0x...): undefined reference to `barrett_4q'
try.c: /usr/bin/ld: libcrypto_kem_titaniumccasuper.a(ntt.o): in function `ntt_2':
try.c: .../supercop-data/speed2supercop/amd64/try/c/gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall/timingleaks/crypto_kem/titaniumccasuper/opt/work/ntt.c:725:(.text+0x...): undefined reference to `barrett_4q'
try.c: /usr/bin/ld: .../supercop-data/speed2supercop/amd64/try/c/gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall/timingleaks/crypto_kem/titaniumccasuper/opt/work/ntt.c:726:(.text+0x...): undefined reference to `barrett_4q'
try.c: /usr/bin/ld: .../supercop-data/speed2supercop/amd64/try/c/gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall/timingleaks/crypto_kem/titaniumccasuper/opt/work/ntt.c:737:(.text+0x...): undefined reference to `barrett_4q'
try.c: /usr/bin/ld: .../supercop-data/speed2supercop/amd64/try/c/gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall/timingleaks/crypto_kem/titaniumccasuper/opt/work/ntt.c:738:(.text+0x...): undefined reference to `montgomery'
try.c: /usr/bin/ld: .../supercop-data/speed2supercop/amd64/try/c/gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall/timingleaks/crypto_kem/titaniumccasuper/opt/work/ntt.c:756:(.text+0x...): undefined reference to `barrett_4q'
try.c: /usr/bin/ld: .../supercop-data/speed2supercop/amd64/try/c/gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall/timingleaks/crypto_kem/titaniumccasuper/opt/work/ntt.c:757:(.text+0x...): undefined reference to `barrett_4q'
try.c: /usr/bin/ld: .../supercop-data/speed2supercop/amd64/try/c/gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall/timingleaks/crypto_kem/titaniumccasuper/opt/work/ntt.c:762:(.text+0x...): undefined reference to `barrett_4q'
try.c: /usr/bin/ld: .../supercop-data/speed2supercop/amd64/try/c/gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall/timingleaks/crypto_kem/titaniumccasuper/opt/work/ntt.c:763:(.text+0x...): undefined reference to `montgomery'
try.c: /usr/bin/ld: .../supercop-data/speed2supercop/amd64/try/c/gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall/timingleaks/crypto_kem/titaniumccasuper/opt/work/ntt.c:773:(.text+0x...): undefined reference to `barrett_4q'
try.c: /usr/bin/ld: .../supercop-data/speed2supercop/amd64/try/c/gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall/timingleaks/crypto_kem/titaniumccasuper/opt/work/ntt.c:774:(.text+0x...): undefined reference to `barrett_4q'
try.c: /usr/bin/ld: libcrypto_kem_titaniumccasuper.a(ntt.o): in function `ntt_core':
try.c: .../supercop-data/speed2supercop/amd64/try/c/gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall/timingleaks/crypto_kem/titaniumccasuper/opt/work/ntt.c:802:(.text+0x...): undefined reference to `montgomery'
try.c: /usr/bin/ld: libcrypto_kem_titaniumccasuper.a(ntt.o): in function `intt_core':
try.c: .../supercop-data/speed2supercop/amd64/try/c/gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall/timingleaks/crypto_kem/titaniumccasuper/opt/work/ntt.c:830:(.text+0x...): undefined reference to `montgomery'
try.c: /usr/bin/ld: .../supercop-data/speed2supercop/amd64/try/c/gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall/timingleaks/crypto_kem/titaniumccasuper/opt/work/ntt.c:842:(.text+0x...): undefined reference to `montgomery'
try.c: /usr/bin/ld: libcrypto_kem_titaniumccasuper.a(ntt.o): in function `ntt_butterfly_2048_3328':
try.c: .../supercop-data/speed2supercop/amd64/try/c/gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall/timingleaks/crypto_kem/titaniumccasuper/opt/work/ntt.c:860:(.text+0x...): undefined reference to `barrett_16q'
try.c: /usr/bin/ld: libcrypto_kem_titaniumccasuper.a(ntt.o): in function `ntt_butterfly_3328_1280':
try.c: .../supercop-data/speed2supercop/amd64/try/c/gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall/timingleaks/crypto_kem/titaniumccasuper/opt/work/ntt.c:894:(.text+0x...): undefined reference to `barrett_32q'
try.c: /usr/bin/ld: libcrypto_kem_titaniumccasuper.a(ntt.o): in function `ntt_butterfly_2048_3072':
try.c: .../supercop-data/speed2supercop/amd64/try/c/gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall/timingleaks/crypto_kem/titaniumccasuper/opt/work/ntt.c:916:(.text+0x...): undefined reference to `barrett_4q'
try.c: /usr/bin/ld: libcrypto_kem_titaniumccasuper.a(ntt.o): in function `ntt_butterfly_3072_3072_inv':
try.c: ...

Number of similar (implementation,compiler) pairs: 1, namely:
ImplementationCompiler
T:optgcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (13.3.0)