Implementation notes: amd64, samba, crypto_decode/256x2

Computer: samba
Architecture: amd64
CPU ID: GenuineIntel-000506e3-bfebfbff
SUPERCOP version: 20191221
Operation: crypto_decode
Primitive: 256x2
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
30410 0 013310 776 800avxgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019091020190910
34218 0 09917 768 800avxgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019091020190910
34216 0 09965 768 800avxgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019091020190910
35213 0 09129 752 768avxgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019091020190910
36480 0 012761 776 744avxclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019091020190910
37480 0 012761 776 744avxclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019091020190910
37480 0 013201 776 744avxclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019091020190910
43187 0 08903 768 728avxclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019091020190910
636209 0 012945 776 744refclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019091020190910
638209 0 012505 776 744refclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019091020190910
638209 0 012505 776 744refclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019091020190910
74490 0 08807 768 728refclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019091020190910
74497 0 09773 768 800refgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019091020190910
74497 0 013006 776 800refgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019091020190910
75090 0 08985 752 768refgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019091020190910
80694 0 09821 768 800refgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019091020190910
808130 0 012129 776 728refclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019101720191017

Compiler output

Implementation: crypto_decode/256x2/avx
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
decode.c: decode.c:16:17: error: always_inline function '_mm256_set1_epi32' requires target feature 'sse4.2', but would be inlined into function 'crypto_decode_256x2_avx' that is compiled without support for 'sse4.2'
decode.c: __m256i x = _mm256_set1_epi32(*(int32_t *) s);
decode.c: ^
decode.c: decode.c:18:9: error: always_inline function '_mm256_shuffle_epi8' requires target feature 'avx2', but would be inlined into function 'crypto_decode_256x2_avx' that is compiled without support for 'avx2'
decode.c: x = _mm256_shuffle_epi8(x,COPY);
decode.c: ^
decode.c: decode.c:18:31: error: always_inline function '_mm256_set_epi64x' requires target feature 'sse4.2', but would be inlined into function 'crypto_decode_256x2_avx' that is compiled without support for 'sse4.2'
decode.c: x = _mm256_shuffle_epi8(x,COPY);
decode.c: ^
decode.c: decode.c:5:14: note: expanded from macro 'COPY'
decode.c: #define COPY _mm256_set_epi64x(0x0303030303030303,0x0202020202020202,0x0101010101010101,0x0000000000000000)
decode.c: ^
decode.c: decode.c:20:9: error: always_inline function '_mm256_andnot_si256' requires target feature 'avx2', but would be inlined into function 'crypto_decode_256x2_avx' that is compiled without support for 'avx2'
decode.c: x = _mm256_andnot_si256(x,MASK);
decode.c: ^
decode.c: decode.c:20:31: error: always_inline function '_mm256_set1_epi64x' requires target feature 'sse4.2', but would be inlined into function 'crypto_decode_256x2_avx' that is compiled without support for 'sse4.2'
decode.c: x = _mm256_andnot_si256(x,MASK);
decode.c: ^
decode.c: decode.c:6:14: note: expanded from macro 'MASK'
decode.c: #define MASK _mm256_set1_epi64x(0x8040201008040201)
decode.c: ^
decode.c: decode.c:21:9: error: always_inline function '_mm256_cmpeq_epi8' requires target feature 'avx2', but would be inlined into function 'crypto_decode_256x2_avx' that is compiled without support for 'avx2'
decode.c: x = _mm256_cmpeq_epi8(x,_mm256_setzero_si256());
decode.c: ^
decode.c: decode.c:21:29: error: always_inline function '_mm256_setzero_si256' requires target feature 'sse4.2', but would be inlined into function 'crypto_decode_256x2_avx' that is compiled without support for 'sse4.2'
decode.c: ...

Number of similar (compiler,implementation) pairs: 1, namely:
CompilerImplementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE avx