Implementation notes: amd64, firefly, crypto_kem/kyber768

Computer: firefly
Architecture: amd64
CPU ID: AuthenticAMD-00800f12-178bfbff
SUPERCOP version: 20201130
Operation: crypto_kem
Primitive: kyber768
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
160655137861 0 0157479 800 1568T:avx2clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2020121320201130
164312137888 0 0158447 800 1568T:avx2clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2020121320201130
184207119592 0 0139014 824 1600T:avx2gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020121320201130
241155160779 0 0182430 824 1600T:avx2gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020121320201130
256036137861 0 0157479 800 1568T:avx2clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2020121320201130
260613120646 0 0140430 824 1600T:avx2gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020121320201130
284395119263 0 0137506 816 1568T:avx2gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020121320201130
293112128393 0 0146453 792 1568T:avx2clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2020121320201130
48380550427 0 071838 824 1600T:refgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020121320201130
50241216584 0 036455 808 1568T:refclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2020121320201130
61642310779 0 028874 816 1568T:refgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020121320201130
72778917032 0 037807 808 1568T:refclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2020121320201130
76297916584 0 036455 808 1568T:refclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2020121320201130
82199712092 0 031710 824 1600T:refgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020121320201130
82993210745 0 028997 800 1568T:refclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2020121320201130
83016216110 0 036359 808 1568T:refclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2020121320201130
89253811360 0 030638 824 1600T:refgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2020121320201130

Compiler output

Implementation: T:avx2
Security model: timingleaks
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
cbd.c: cbd.c:20:26: error: always_inline function '_mm256_set1_epi32' requires target feature 'sse4.2', but would be inlined into function 'crypto_kem_kyber768_avx2_timingleaks_cbd' that is compiled without support for 'sse4.2'
cbd.c: const __m256i mask55 = _mm256_set1_epi32(0x55555555);
cbd.c: ^
cbd.c: cbd.c:21:26: error: always_inline function '_mm256_set1_epi32' requires target feature 'sse4.2', but would be inlined into function 'crypto_kem_kyber768_avx2_timingleaks_cbd' that is compiled without support for 'sse4.2'
cbd.c: const __m256i mask33 = _mm256_set1_epi32(0x33333333);
cbd.c: ^
cbd.c: cbd.c:22:26: error: always_inline function '_mm256_set1_epi32' requires target feature 'sse4.2', but would be inlined into function 'crypto_kem_kyber768_avx2_timingleaks_cbd' that is compiled without support for 'sse4.2'
cbd.c: const __m256i mask03 = _mm256_set1_epi32(0x03030303);
cbd.c: ^
cbd.c: cbd.c:25:12: error: always_inline function '_mm256_loadu_si256' requires target feature 'sse4.2', but would be inlined into function 'crypto_kem_kyber768_avx2_timingleaks_cbd' that is compiled without support for 'sse4.2'
cbd.c: vec0 = _mm256_loadu_si256((__m256i *)&buf[32*i]);
cbd.c: ^
cbd.c: cbd.c:27:12: error: always_inline function '_mm256_srli_epi32' requires target feature 'sse4.2', but would be inlined into function 'crypto_kem_kyber768_avx2_timingleaks_cbd' that is compiled without support for 'sse4.2'
cbd.c: vec1 = _mm256_srli_epi32(vec0, 1);
cbd.c: ^
cbd.c: cbd.c:28:12: error: always_inline function '_mm256_and_si256' requires target feature 'sse4.2', but would be inlined into function 'crypto_kem_kyber768_avx2_timingleaks_cbd' that is compiled without support for 'sse4.2'
cbd.c: vec0 = _mm256_and_si256(mask55, vec0);
cbd.c: ^
cbd.c: cbd.c:29:12: error: always_inline function '_mm256_and_si256' requires target feature 'sse4.2', but would be inlined into function 'crypto_kem_kyber768_avx2_timingleaks_cbd' that is compiled without support for 'sse4.2'
cbd.c: vec1 = _mm256_and_si256(mask55, vec1);
cbd.c: ^
cbd.c: cbd.c:30:12: error: always_inline function '_mm256_add_epi32' requires target feature 'sse4.2', but would be inlined into function 'crypto_kem_kyber768_avx2_timingleaks_cbd' that is compiled without support for 'sse4.2'
cbd.c: vec0 = _mm256_add_epi32(vec0, vec1);
cbd.c: ^
cbd.c: cbd.c:32:12: error: always_inline function '_mm256_srli_epi32' requires target feature 'sse4.2', but would be inlined into function 'crypto_kem_kyber768_avx2_timingleaks_cbd' that is compiled without support for 'sse4.2'
cbd.c: ...
Number of similar (compiler,implementation) pairs: 1, namely:
CompilerImplementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:avx2