Implementation notes: amd64, ghf51, crypto_kem/kyber768

Computer: ghf51
Architecture: amd64
CPU ID: AuthenticAMD-00810f81-178bfbff
SUPERCOP version: 20200702
Operation: crypto_kem
Primitive: kyber768

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
183820	140570 0 0	160354 784 1576	`avx2`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200717	20200702
249574	140570 0 0	160354 784 1576	`avx2`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200717	20200702
266370	158557 0 0	179444 792 1608	`avx2`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200717	20200702
280332	124229 0 0	141692 776 1576	`avx2`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200717	20200702
297492	126916 0 0	146260 792 1608	`avx2`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200717	20200702
303368	146669 0 0	166346 784 1576	`avx2`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200717	20200702
347828	125736 0 0	144828 792 1608	`avx2`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200717	20200702
391690	123713 0 0	141604 784 1576	`avx2`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200717	20200702
577876	34116 0 0	54490 784 1576	`ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200717	20200702
823212	51223 0 0	71234 784 1576	`ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200717	20200702
843986	37146 0 0	57298 784 1576	`ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200717	20200702
882388	11639 0 0	29492 776 1576	`ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200717	20200702
911638	37146 0 0	57298 784 1576	`ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200717	20200702
942968	46597 0 0	67269 784 1608	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200717	20200702
1011998	12830 0 0	31805 784 1608	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200717	20200702
1061398	13607 0 0	32813 784 1608	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200717	20200702
1064492	12183 0 0	29989 776 1576	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200717	20200702

Compiler output

Implementation: avx2
Security model: unknown
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 'avx', but would be inlined into function 'crypto_kem_kyber768_avx2_cbd' that is compiled without support for 'avx'
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 'avx', but would be inlined into function 'crypto_kem_kyber768_avx2_cbd' that is compiled without support for 'avx'
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 'avx', but would be inlined into function 'crypto_kem_kyber768_avx2_cbd' that is compiled without support for 'avx'
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 'avx', but would be inlined into function 'crypto_kem_kyber768_avx2_cbd' that is compiled without support for 'avx'
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 'avx2', but would be inlined into function 'crypto_kem_kyber768_avx2_cbd' that is compiled without support for 'avx2'
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 'avx2', but would be inlined into function 'crypto_kem_kyber768_avx2_cbd' that is compiled without support for 'avx2'
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 'avx2', but would be inlined into function 'crypto_kem_kyber768_avx2_cbd' that is compiled without support for 'avx2'
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 'avx2', but would be inlined into function 'crypto_kem_kyber768_avx2_cbd' that is compiled without support for 'avx2'
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 'avx2', but would be inlined into function 'crypto_kem_kyber768_avx2_cbd' that is compiled without support for 'avx2'
cbd.c: ...

Number of similar (compiler,implementation) pairs: 1, namely:

Compiler	Implementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx2