Implementation notes: amd64, cannon, crypto_aead/aes256gcmv1

Computer: cannon
Architecture: amd64
CPU ID: GenuineIntel-00060663-bfebfbff
SUPERCOP version: 20190910
Operation: crypto_aead
Primitive: aes256gcmv1

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
7470	12486 0 0	29100 800 928	`dolbeau/aesenc-int`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190910	20190910
7528	18789 0 0	38245 808 928	`dolbeau/aesenc-int`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190910	20190910
7676	12685 0 0	29180 800 928	`dolbeau/aesenc-int`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190910	20190910
7856	17192 0 0	36627 832 904	`dolbeau/aesenc-int`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190910	20190910
7858	17192 0 0	36627 832 904	`dolbeau/aesenc-int`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190910	20190910
7862	17208 0 0	36963 832 904	`dolbeau/aesenc-int`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190910	20190910
8476	6095 0 0	21292 784 896	`dolbeau/aesenc-int`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190910	20190910
18270	34554 3040 0	1725496 148023 10904	`cryptopp`	`g++_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190910	20190910
18346	19777 3040 0	1723733 148079 10840	`cryptopp`	`clang++_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190910	20190910
18396	36221 3040 0	1730791 148015 10904	`cryptopp`	`g++_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190910	20190910
18414	19777 3040 0	1723733 148079 10840	`cryptopp`	`clang++_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190910	20190910
18506	15449 2456 0	1721449 148071 10840	`cryptopp`	`clang++_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190910	20190910
18772	14491 3264 0	1693139 148055 10872	`cryptopp`	`g++_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190910	20190910
18830	15843 2456 0	1717881 148071 10808	`cryptopp`	`clang++_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190910	20190910
19498	35598 3040 0	1727423 148015 10904	`cryptopp`	`g++_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190910	20190910
1820462	3558 0 16	23661 808 944	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190910	20190910
2440340	1826 0 16	18569 824 880	`ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190910	20190910
11088642	3817 0 16	24291 832 928	`ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190910	20190910
11257748	3817 0 16	23971 832 928	`ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190910	20190910
11277554	3817 0 16	23971 832 928	`ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20190910	20190910
17430162	2477 0 16	19732 800 944	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190910	20190910
18580732	2231 0 16	19372 800 944	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20190910	20190910

Test failure

Implementation: ref
Security model: unknown
Compiler: gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE

error 111

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

Compiler	Implementations
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	ref

Compiler output

Implementation: dolbeau/aesenc-int
Security model: unknown
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

Number of similar (compiler,implementation) pairs: 3, namely:

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	dolbeau/aesenc-int
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	dolbeau/aesenc-int
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	dolbeau/aesenc-int

Compiler output

Implementation: dolbeau/aesenc-int
Security model: unknown
Compiler: clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

aesenc-int.c: aesenc-int.c:40:34: warning: incompatible pointer types passing 'const unsigned int *' to parameter of type 'const __m128i *' [-Wincompatible-pointer-types]
aesenc-int.c: __m128i key0 = _mm_loadu_si128((const unsigned int *)(key+0));
aesenc-int.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
aesenc-int.c: /usr/lib/clang/8.0.1/include/emmintrin.h:3567:32: note: passing argument to parameter '__p' here
aesenc-int.c: _mm_loadu_si128(__m128i const *__p)
aesenc-int.c: ^
aesenc-int.c: aesenc-int.c:41:34: warning: incompatible pointer types passing 'const unsigned int *' to parameter of type 'const __m128i *' [-Wincompatible-pointer-types]
aesenc-int.c: __m128i key1 = _mm_loadu_si128((const unsigned int *)(key+16));
aesenc-int.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
aesenc-int.c: /usr/lib/clang/8.0.1/include/emmintrin.h:3567:32: note: passing argument to parameter '__p' here
aesenc-int.c: _mm_loadu_si128(__m128i const *__p)
aesenc-int.c: ^
aesenc-int.c: aesenc-int.c:630:5: warning: loop not unrolled: the optimizer was unable to perform the requested transformation; the transformation might be disabled or specified as part of an unsupported transformation ordering [-Wpass-failed=transform-warning]
aesenc-int.c: int crypto_aead_encrypt(
aesenc-int.c: ^
aesenc-int.c: ./crypto_aead.h:6:29: note: expanded from macro 'crypto_aead_encrypt'
aesenc-int.c: #define crypto_aead_encrypt crypto_aead_aes256gcmv1_encrypt
aesenc-int.c: ^
aesenc-int.c: ./crypto_aead_aes256gcmv1.h:18:41: note: expanded from macro 'crypto_aead_aes256gcmv1_encrypt'
aesenc-int.c: #define crypto_aead_aes256gcmv1_encrypt crypto_aead_aes256gcmv1_dolbeau_aesenc_int_encrypt
aesenc-int.c: ^
aesenc-int.c: aesenc-int.c:630:5: warning: loop not unrolled: the optimizer was unable to perform the requested transformation; the transformation might be disabled or specified as part of an unsupported transformation ordering [-Wpass-failed=transform-warning]
aesenc-int.c: ./crypto_aead.h:6:29: note: expanded from macro 'crypto_aead_encrypt'
aesenc-int.c: #define crypto_aead_encrypt crypto_aead_aes256gcmv1_encrypt
aesenc-int.c: ^
aesenc-int.c: ...

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

Compiler	Implementations
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	dolbeau/aesenc-int

Compiler output

Implementation: dolbeau/aesenc-int
Security model: unknown
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

aesenc-int.c: aesenc-int.c: In function 'aesni_key256_expand':
aesenc-int.c: aesenc-int.c:40:34: warning: passing argument 1 of '_mm_loadu_si128' from incompatible pointer type [-Wincompatible-pointer-types]
aesenc-int.c: 40 | __m128i key0 = _mm_loadu_si128((const unsigned int *)(key+0));
aesenc-int.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
aesenc-int.c: | |
aesenc-int.c: | const unsigned int *
aesenc-int.c: In file included from /usr/lib/gcc/x86_64-pc-linux-gnu/9.1.0/include/xmmintrin.h:1255,
aesenc-int.c: from /usr/lib/gcc/x86_64-pc-linux-gnu/9.1.0/include/immintrin.h:29,
aesenc-int.c: from aesenc-int.c:11:
aesenc-int.c: /usr/lib/gcc/x86_64-pc-linux-gnu/9.1.0/include/emmintrin.h:701:35: note: expected 'const __vector(2) long long int *' but argument is of type 'const unsigned int *'
aesenc-int.c: 701 | _mm_loadu_si128 (__m128i_u const *__P)
aesenc-int.c: | ~~~~~~~~~~~~~~~~~^~~
aesenc-int.c: aesenc-int.c:41:34: warning: passing argument 1 of '_mm_loadu_si128' from incompatible pointer type [-Wincompatible-pointer-types]
aesenc-int.c: 41 | __m128i key1 = _mm_loadu_si128((const unsigned int *)(key+16));
aesenc-int.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
aesenc-int.c: | |
aesenc-int.c: | const unsigned int *
aesenc-int.c: In file included from /usr/lib/gcc/x86_64-pc-linux-gnu/9.1.0/include/xmmintrin.h:1255,
aesenc-int.c: from /usr/lib/gcc/x86_64-pc-linux-gnu/9.1.0/include/immintrin.h:29,
aesenc-int.c: from aesenc-int.c:11:
aesenc-int.c: /usr/lib/gcc/x86_64-pc-linux-gnu/9.1.0/include/emmintrin.h:701:35: note: expected 'const __vector(2) long long int *' but argument is of type 'const unsigned int *'
aesenc-int.c: 701 | _mm_loadu_si128 (__m128i_u const *__P)
aesenc-int.c: | ~~~~~~~~~~~~~~~~~^~~

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/aesenc-int
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/aesenc-int
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/aesenc-int
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/aesenc-int

Compiler output

Implementation: dolbeau/vaesenc-int
Security model: unknown
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

vaesenc-int.c: vaesenc-int.c:260:34: warning: incompatible pointer types passing 'const __m128i *' to parameter of type 'const __m256i *' [-Wincompatible-pointer-types]
vaesenc-int.c: __m256i nv = _mm256_load_si256((const __m128i *)n);
vaesenc-int.c: ^~~~~~~~~~~~~~~~~~
vaesenc-int.c: /usr/lib/clang/8.0.1/include/avxintrin.h:3153:34: note: passing argument to parameter '__p' here
vaesenc-int.c: _mm256_load_si256(__m256i const *__p)
vaesenc-int.c: ^
vaesenc-int.c: vaesenc-int.c:391:18: error: '__builtin_ia32_pclmulqdq256' needs target feature vpclmulqdq
vaesenc-int.c: __m256i tmp3 = _mm256_clmulepi64_epi128(A, B, 0x00);
vaesenc-int.c: ^
vaesenc-int.c: /usr/lib/clang/8.0.1/include/vpclmulqdqintrin.h:32:12: note: expanded from macro '_mm256_clmulepi64_epi128'
vaesenc-int.c: (__m256i)__builtin_ia32_pclmulqdq256((__v4di)(__m256i)(A), \
vaesenc-int.c: ^
vaesenc-int.c: vaesenc-int.c:392:18: error: '__builtin_ia32_pclmulqdq256' needs target feature vpclmulqdq
vaesenc-int.c: __m256i tmp4 = _mm256_clmulepi64_epi128(A, B, 0x10);
vaesenc-int.c: ^
vaesenc-int.c: /usr/lib/clang/8.0.1/include/vpclmulqdqintrin.h:32:12: note: expanded from macro '_mm256_clmulepi64_epi128'
vaesenc-int.c: (__m256i)__builtin_ia32_pclmulqdq256((__v4di)(__m256i)(A), \
vaesenc-int.c: ^
vaesenc-int.c: vaesenc-int.c:393:18: error: '__builtin_ia32_pclmulqdq256' needs target feature vpclmulqdq
vaesenc-int.c: __m256i tmp5 = _mm256_clmulepi64_epi128(A, B, 0x01);
vaesenc-int.c: ^
vaesenc-int.c: /usr/lib/clang/8.0.1/include/vpclmulqdqintrin.h:32:12: note: expanded from macro '_mm256_clmulepi64_epi128'
vaesenc-int.c: (__m256i)__builtin_ia32_pclmulqdq256((__v4di)(__m256i)(A), \
vaesenc-int.c: ^
vaesenc-int.c: vaesenc-int.c:394:18: error: '__builtin_ia32_pclmulqdq256' needs target feature vpclmulqdq
vaesenc-int.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	dolbeau/vaesenc-int
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	dolbeau/vaesenc-int
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	dolbeau/vaesenc-int
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	dolbeau/vaesenc-int

Compiler output

Implementation: dolbeau/vaesenc-int
Security model: unknown
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

vaesenc-int.c: vaesenc-int.c: In function 'aesni_encryptv2':
vaesenc-int.c: vaesenc-int.c:260:34: warning: passing argument 1 of '_mm256_load_si256' from incompatible pointer type [-Wincompatible-pointer-types]
vaesenc-int.c: 260 | __m256i nv = _mm256_load_si256((const __m128i *)n);
vaesenc-int.c: | ^~~~~~~~~~~~~~~~~~
vaesenc-int.c: | |
vaesenc-int.c: | const __vector(2) long long int *
vaesenc-int.c: In file included from /usr/lib/gcc/x86_64-pc-linux-gnu/9.1.0/include/immintrin.h:51,
vaesenc-int.c: from vaesenc-int.c:11:
vaesenc-int.c: /usr/lib/gcc/x86_64-pc-linux-gnu/9.1.0/include/avxintrin.h:907:35: note: expected 'const __vector(4) long long int *' but argument is of type 'const __vector(2) long long int *'
vaesenc-int.c: 907 | _mm256_load_si256 (__m256i const *__P)
vaesenc-int.c: | ~~~~~~~~~~~~~~~^~~
vaesenc-int.c: In file included from /usr/lib/gcc/x86_64-pc-linux-gnu/9.1.0/include/immintrin.h:121,
vaesenc-int.c: from vaesenc-int.c:11:
vaesenc-int.c: vaesenc-int.c: In function 'mulvv2':
vaesenc-int.c: /usr/lib/gcc/x86_64-pc-linux-gnu/9.1.0/include/vpclmulqdqintrin.h:65:1: error: inlining failed in call to always_inline '_mm256_clmulepi64_epi128': target specific option mismatch
vaesenc-int.c: 65 | _mm256_clmulepi64_epi128 (__m256i __A, __m256i __B, const int __C)
vaesenc-int.c: | ^~~~~~~~~~~~~~~~~~~~~~~~
vaesenc-int.c: vaesenc-int.c:394:18: note: called from here
vaesenc-int.c: 394 | __m256i tmp6 = _mm256_clmulepi64_epi128(A, B, 0x11);
vaesenc-int.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
vaesenc-int.c: In file included from /usr/lib/gcc/x86_64-pc-linux-gnu/9.1.0/include/immintrin.h:121,
vaesenc-int.c: from vaesenc-int.c:11:
vaesenc-int.c: /usr/lib/gcc/x86_64-pc-linux-gnu/9.1.0/include/vpclmulqdqintrin.h:65:1: error: inlining failed in call to always_inline '_mm256_clmulepi64_epi128': target specific option mismatch
vaesenc-int.c: 65 | _mm256_clmulepi64_epi128 (__m256i __A, __m256i __B, const int __C)
vaesenc-int.c: | ^~~~~~~~~~~~~~~~~~~~~~~~
vaesenc-int.c: ...

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/vaesenc-int
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/vaesenc-int
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/vaesenc-int
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/vaesenc-int

Compiler output

Implementation: openssl
Security model: unknown
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

decrypt.c: decrypt.c:13:18: error: variable has incomplete type 'EVP_CIPHER_CTX' (aka 'struct evp_cipher_ctx_st')
decrypt.c: EVP_CIPHER_CTX x;
decrypt.c: ^
decrypt.c: /usr/include/openssl/ossl_typ.h:90:16: note: forward declaration of 'struct evp_cipher_ctx_st'
decrypt.c: typedef struct evp_cipher_ctx_st EVP_CIPHER_CTX;
decrypt.c: ^
decrypt.c: 1 error generated.

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	openssl
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	openssl
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	openssl
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	openssl

Compiler output

Implementation: openssl
Security model: unknown
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

decrypt.c: decrypt.c: In function 'crypto_aead_aes256gcmv1_openssl_decrypt':
decrypt.c: decrypt.c:13:18: error: storage size of 'x' isn't known
decrypt.c: 13 | EVP_CIPHER_CTX x;
decrypt.c: | ^

Number of similar (compiler,implementation) pairs: 4, namely:

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	openssl
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	openssl
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	openssl
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	openssl