Implementation notes: amd64, hydra5, crypto_aead/norx6441v1

Computer: hydra5
Architecture: amd64
CPU ID: AuthenticAMD-00300f10-178bfbff
SUPERCOP version: 20191221
Operation: crypto_aead
Primitive: norx6441v1
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
3624615029 0 031983 776 856xmmclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019122120191221
3624615029 0 033167 776 856xmmclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019122120191221
3624615029 0 033167 776 856xmmclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019122120191221
3646914434 0 029581 768 856xmmclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019122120191221
4042015029 0 031983 776 856xmmclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019122120191221
4173623601 8 043453 792 928refgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019122120191221
4202414904 0 032021 768 928xmmgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019122120191221
4252415106 0 034766 776 928xmmgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019122120191221
4326514048 8 030757 784 928refgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019122120191221
4643314484 8 031821 784 928refgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019122120191221
4674616451 0 033005 768 928xmmgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019122120191221
470753831 8 019170 760 896refgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019122120191221
513196138 8 023099 784 856refclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019122120191221
513416138 8 023099 784 856refclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019122120191221
514305866 8 024011 784 856refclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019122120191221
516743508 8 018785 776 856refclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019122120191221
573015850 8 024011 784 856refclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2019122120191221
5795112818 0 028041 752 896xmmgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2019122120191221

Compiler output

Implementation: ymm
Security model: unknown
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
norx.c: norx.c:350:24: error: always_inline function '_mm256_loadu_si256' requires target feature 'xsave', but would be inlined into function 'crypto_aead_norx6441v1_ymm_encrypt' that is compiled without support for 'xsave'
norx.c: const __m256i K = LOADU(k + 0);
norx.c: ^
norx.c: norx.c:47:19: note: expanded from macro 'LOADU'
norx.c: #define LOADU(in) _mm256_loadu_si256((__m256i*)(in))
norx.c: ^
norx.c: norx.c:355:5: error: always_inline function '_mm256_castsi128_si256' requires target feature 'xsave', but would be inlined into function 'crypto_aead_norx6441v1_ymm_encrypt' that is compiled without support for 'xsave'
norx.c: INITIALIZE(A, B, C, D, N, K);
norx.c: ^
norx.c: norx.c:270:9: note: expanded from macro 'INITIALIZE'
norx.c: A = _mm256_castsi128_si256(N); \
norx.c: ^
norx.c: norx.c:355:5: error: always_inline function '_mm256_castsi128_si256' requires target feature 'xsave', but would be inlined into function 'crypto_aead_norx6441v1_ymm_encrypt' that is compiled without support for 'xsave'
norx.c: norx.c:271:9: note: expanded from macro 'INITIALIZE'
norx.c: A = _mm256_inserti128_si256(A, _mm_set_epi64x(U1, U0), 1); \
norx.c: ^
norx.c: /usr/lib/llvm-6.0/lib/clang/6.0.0/include/avx2intrin.h:985:44: note: expanded from macro '_mm256_inserti128_si256'
norx.c: (__v4di)_mm256_castsi128_si256((__m128i)(V2)), \
norx.c: ^
norx.c: norx.c:355:5: error: always_inline function '_mm256_undefined_si256' requires target feature 'xsave', but would be inlined into function 'crypto_aead_norx6441v1_ymm_encrypt' that is compiled without support for 'xsave'
norx.c: norx.c:272:9: note: expanded from macro 'INITIALIZE'
norx.c: A = _mm256_permute4x64_epi64(A, _MM_SHUFFLE(3, 1, 0, 2)); \
norx.c: ^
norx.c: /usr/lib/llvm-6.0/lib/clang/6.0.0/include/avx2intrin.h:968:44: note: expanded from macro '_mm256_permute4x64_epi64'
norx.c: (__v4di)_mm256_undefined_si256(), \
norx.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:
CompilerImplementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE ymm
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE ymm
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE ymm
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE ymm

Compiler output

Implementation: ymm
Security model: unknown
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
norx.c: norx.c:350:24: error: always_inline function '_mm256_loadu_si256' requires target feature 'sse4.2', but would be inlined into function 'crypto_aead_norx6441v1_ymm_encrypt' that is compiled without support for 'sse4.2'
norx.c: const __m256i K = LOADU(k + 0);
norx.c: ^
norx.c: norx.c:47:19: note: expanded from macro 'LOADU'
norx.c: #define LOADU(in) _mm256_loadu_si256((__m256i*)(in))
norx.c: ^
norx.c: norx.c:355:5: error: always_inline function '_mm256_castsi128_si256' requires target feature 'sse4.2', but would be inlined into function 'crypto_aead_norx6441v1_ymm_encrypt' that is compiled without support for 'sse4.2'
norx.c: INITIALIZE(A, B, C, D, N, K);
norx.c: ^
norx.c: norx.c:270:9: note: expanded from macro 'INITIALIZE'
norx.c: A = _mm256_castsi128_si256(N); \
norx.c: ^
norx.c: norx.c:355:5: error: always_inline function '_mm256_castsi128_si256' requires target feature 'sse4.2', but would be inlined into function 'crypto_aead_norx6441v1_ymm_encrypt' that is compiled without support for 'sse4.2'
norx.c: norx.c:271:9: note: expanded from macro 'INITIALIZE'
norx.c: A = _mm256_inserti128_si256(A, _mm_set_epi64x(U1, U0), 1); \
norx.c: ^
norx.c: /usr/lib/llvm-6.0/lib/clang/6.0.0/include/avx2intrin.h:985:44: note: expanded from macro '_mm256_inserti128_si256'
norx.c: (__v4di)_mm256_castsi128_si256((__m128i)(V2)), \
norx.c: ^
norx.c: norx.c:355:5: error: always_inline function '_mm256_undefined_si256' requires target feature 'sse4.2', but would be inlined into function 'crypto_aead_norx6441v1_ymm_encrypt' that is compiled without support for 'sse4.2'
norx.c: norx.c:272:9: note: expanded from macro 'INITIALIZE'
norx.c: A = _mm256_permute4x64_epi64(A, _MM_SHUFFLE(3, 1, 0, 2)); \
norx.c: ^
norx.c: /usr/lib/llvm-6.0/lib/clang/6.0.0/include/avx2intrin.h:968:44: note: expanded from macro '_mm256_permute4x64_epi64'
norx.c: (__v4di)_mm256_undefined_si256(), \
norx.c: ...

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

Compiler output

Implementation: ymm
Security model: unknown
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE
norx.c: norx.c: In function 'crypto_aead_norx6441v1_ymm_encrypt':
norx.c: norx.c:350:19: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
norx.c: const __m256i K = LOADU(k + 0);
norx.c: ^
norx.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:41:0,
norx.c: from /usr/lib/gcc/x86_64-linux-gnu/7/include/x86intrin.h:48,
norx.c: from norx.c:26:
norx.c: norx.c: In function 'block_copy':
norx.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avxintrin.h:925:1: error: inlining failed in call to always_inline '_mm256_storeu_si256': target specific option mismatch
norx.c: _mm256_storeu_si256 (__m256i_u *__P, __m256i __A)
norx.c: ^~~~~~~~~~~~~~~~~~~
norx.c: norx.c:48:24: note: called from here
norx.c: #define STOREU(out, x) _mm256_storeu_si256((__m256i*)(out), (x))
norx.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
norx.c: norx.c:303:9: note: in expansion of macro 'STOREU'
norx.c: STOREU(out + 32, LOADU(in + 32));
norx.c: ^~~~~~
norx.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:41:0,
norx.c: from /usr/lib/gcc/x86_64-linux-gnu/7/include/x86intrin.h:48,
norx.c: from norx.c:26:
norx.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avxintrin.h:919:1: error: inlining failed in call to always_inline '_mm256_loadu_si256': target specific option mismatch
norx.c: _mm256_loadu_si256 (__m256i_u const *__P)
norx.c: ^~~~~~~~~~~~~~~~~~
norx.c: norx.c:48:24: note: called from here
norx.c: #define STOREU(out, x) _mm256_storeu_si256((__m256i*)(out), (x))
norx.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:
CompilerImplementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE ymm
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE ymm
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE ymm
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE ymm

Namespace violations

Implementation: ref
Security model: unknown
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
norx.o norx_aead_decrypt T
norx.o norx_aead_encrypt T
norx.o norx_decrypt_msg T
norx.o norx_encrypt_msg T
norx.o norx_init T
norx.o norx_output_tag T
norx.o norx_process_header T
norx.o norx_process_trailer T
norx.o norx_verify_tag T

Number of similar (compiler,implementation) pairs: 9, namely:
CompilerImplementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE ref
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE ref
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE ref
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE ref
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE ref
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE ref
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE ref
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE ref
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE ref