Implementation notes: amd64, rome0, crypto_aead/aes256cpfbv1

Computer: rome0
Microarchitecture: amd64; Zen2 (830f10)
Architecture: amd64
CPU ID: AuthenticAMD-00830f10-178bfbff
SUPERCOP version: 20230530
Operation: crypto_aead
Primitive: aes256cpfbv1

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
11980	15831 0 0	38696 780 1080	`T:aesni`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230521	20221122
21889	8984 0 0	29399 772 1080	`T:aesni`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230521	20221122
22756	9544 0 0	30712 780 1080	`T:aesni`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230521	20221122
59473	3825 0 0	27224 780 1080	`T:ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230521	20221122
63519	2368 0 0	25040 812 1048	`T:ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230521	20221122
63678	2368 0 0	24912 812 1048	`T:ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230521	20221122
68143	3066 0 0	25936 812 1016	`T:ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230521	20221122
68156	1844 0 0	21974 804 1016	`T:ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230521	20221122
76054	2940 0 0	24648 780 1080	`T:ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230521	20221122
81477	2082 0 0	22462 804 1016	`T:ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230521	20221122
83676	2111 0 0	23119 772 1080	`T:ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230521	20221122
111081	1778 0 0	21235 756 1048	`T:ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230521	20221122
117445	15826 0 0	34691 756 1048	`T:gladman`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230521	20221122
119951	17620 0 0	39736 812 1048	`T:gladman`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230521	20221122
119990	17620 0 0	39608 812 1048	`T:gladman`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230521	20221122
120535	16517 0 0	36390 804 1016	`T:gladman`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230521	20221122
123102	18593 0 0	40896 812 1016	`T:gladman`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230521	20221122
126675	16441 0 0	35990 804 1016	`T:gladman`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230521	20221122
128594	17148 0 0	37551 772 1080	`T:gladman`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230521	20221122
132869	18767 0 0	41600 780 1080	`T:gladman`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230521	20221122
136780	17576 0 0	38744 780 1080	`T:gladman`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230521	20221122
142391	16204 0 0	36655 772 1080	`T:aesref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230521	20221122
157658	19697 0 0	42552 780 1080	`T:aesref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230521	20221122
161226	15673 0 0	37688 812 1048	`T:aesref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230521	20221122
161871	17153 0 0	39296 812 1048	`T:aesref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230521	20221122
162494	15292 0 0	34886 804 1016	`T:aesref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230521	20221122
163594	16734 0 0	37936 780 1080	`T:aesref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230521	20221122
164775	15675 0 0	35550 804 1016	`T:aesref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230521	20221122
170158	17703 0 0	40048 812 1016	`T:aesref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230521	20221122
195236	15663 0 0	34579 756 1048	`T:aesref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230521	20221122

Test failure

Implementation: T:aesni
Security model: timingleaks
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

error 111
crypto_aead_decrypt does not match m

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

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:aesni
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:aesni
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:aesni

Compiler output

Implementation: T:aesni
Security model: timingleaks
Compiler: clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

try.c: /usr/bin/ld: libcrypto_aead_aes256cpfbv1.a(encrypt.o): in function `crypto_aead_aes256cpfbv1_aesni_timingleaks_encrypt':
try.c: encrypt.c:(.text+0x...): undefined reference to `safe_store_partial'
try.c: /usr/bin/ld: libcrypto_aead_aes256cpfbv1.a(cpfbkey.o): in function `AES_128_Key_Expansion_and_encryption':
try.c: cpfbkey.c:(.text+0x...): undefined reference to `key_expansion_128'
try.c: /usr/bin/ld: cpfbkey.c:(.text+0x...): undefined reference to `key_expansion_128'
try.c: /usr/bin/ld: cpfbkey.c:(.text+0x...): undefined reference to `key_expansion_128'
try.c: /usr/bin/ld: cpfbkey.c:(.text+0x...): undefined reference to `key_expansion_128'
try.c: /usr/bin/ld: cpfbkey.c:(.text+0x...): undefined reference to `key_expansion_128'
try.c: /usr/bin/ld: libcrypto_aead_aes256cpfbv1.a(cpfbkey.o):cpfbkey.c:(.text+0x...): more undefined references to `key_expansion_128' follow
try.c: /usr/bin/ld: libcrypto_aead_aes256cpfbv1.a(cpfbkey.o): in function `AES_256_Key_Expansion':
try.c: cpfbkey.c:(.text+0x...): undefined reference to `KEY_256_ASSIST_1'
try.c: /usr/bin/ld: cpfbkey.c:(.text+0x...): undefined reference to `KEY_256_ASSIST_2'
try.c: /usr/bin/ld: cpfbkey.c:(.text+0x...): undefined reference to `KEY_256_ASSIST_1'
try.c: /usr/bin/ld: cpfbkey.c:(.text+0x...): undefined reference to `KEY_256_ASSIST_2'
try.c: /usr/bin/ld: cpfbkey.c:(.text+0x...): undefined reference to `KEY_256_ASSIST_1'
try.c: /usr/bin/ld: cpfbkey.c:(.text+0x...): undefined reference to `KEY_256_ASSIST_2'
try.c: /usr/bin/ld: cpfbkey.c:(.text+0x...): undefined reference to `KEY_256_ASSIST_1'
try.c: /usr/bin/ld: cpfbkey.c:(.text+0x...): undefined reference to `KEY_256_ASSIST_2'
try.c: /usr/bin/ld: cpfbkey.c:(.text+0x...): undefined reference to `KEY_256_ASSIST_1'
try.c: /usr/bin/ld: cpfbkey.c:(.text+0x...): undefined reference to `KEY_256_ASSIST_2'
try.c: /usr/bin/ld: cpfbkey.c:(.text+0x...): undefined reference to `KEY_256_ASSIST_1'
try.c: /usr/bin/ld: cpfbkey.c:(.text+0x...): undefined reference to `KEY_256_ASSIST_2'
try.c: /usr/bin/ld: cpfbkey.c:(.text+0x...): undefined reference to `KEY_256_ASSIST_1'
try.c: /usr/bin/ld: libcrypto_aead_aes256cpfbv1.a(cpfbkey.o): in function `AES_256_Key_Expansion_2':
try.c: cpfbkey.c:(.text+0x...): undefined reference to `KEY_256_ASSIST_1'
try.c: ...

Number of similar (compiler,implementation) pairs: 2, namely:

Compiler	Implementations
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:aesni
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:aesni

Compiler output

Implementation: T:aesni
Security model: timingleaks
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

cpfbkey.c: cpfbkey.c:50:9: error: '__builtin_ia32_aeskeygenassist128' needs target feature aes
cpfbkey.c: temp2 = _mm_aeskeygenassist_si128 (temp1,0x1);
cpfbkey.c: ^
cpfbkey.c: /usr/lib/llvm-11/lib/clang/11.0.1/include/__wmmintrin_aes.h:136:12: note: expanded from macro '_mm_aeskeygenassist_si128'
cpfbkey.c: (__m128i)__builtin_ia32_aeskeygenassist128((__v2di)(__m128i)(C), (int)(R))
cpfbkey.c: ^
cpfbkey.c: cpfbkey.c:52:6: error: always_inline function '_mm_aesenc_si128' requires target feature 'aes', but would be inlined into function 'AES_128_Key_Expansion_and_encryption' that is compiled without support for 'aes'
cpfbkey.c: k1 = _mm_aesenc_si128(k1,temp1);
cpfbkey.c: ^
cpfbkey.c: cpfbkey.c:53:6: error: always_inline function '_mm_aesenc_si128' requires target feature 'aes', but would be inlined into function 'AES_128_Key_Expansion_and_encryption' that is compiled without support for 'aes'
cpfbkey.c: k2 = _mm_aesenc_si128(k2,temp1);
cpfbkey.c: ^
cpfbkey.c: cpfbkey.c:54:9: error: '__builtin_ia32_aeskeygenassist128' needs target feature aes
cpfbkey.c: temp2 = _mm_aeskeygenassist_si128 (temp1,0x2);
cpfbkey.c: ^
cpfbkey.c: /usr/lib/llvm-11/lib/clang/11.0.1/include/__wmmintrin_aes.h:136:12: note: expanded from macro '_mm_aeskeygenassist_si128'
cpfbkey.c: (__m128i)__builtin_ia32_aeskeygenassist128((__v2di)(__m128i)(C), (int)(R))
cpfbkey.c: ^
cpfbkey.c: cpfbkey.c:56:6: error: always_inline function '_mm_aesenc_si128' requires target feature 'aes', but would be inlined into function 'AES_128_Key_Expansion_and_encryption' that is compiled without support for 'aes'
cpfbkey.c: k1 = _mm_aesenc_si128(k1,temp1);
cpfbkey.c: ^
cpfbkey.c: cpfbkey.c:57:6: error: always_inline function '_mm_aesenc_si128' requires target feature 'aes', but would be inlined into function 'AES_128_Key_Expansion_and_encryption' that is compiled without support for 'aes'
cpfbkey.c: k2 = _mm_aesenc_si128(k2,temp1);
cpfbkey.c: ^
cpfbkey.c: cpfbkey.c:58:9: error: '__builtin_ia32_aeskeygenassist128' needs target feature aes
cpfbkey.c: ...

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

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

Compiler output

Implementation: T:evp
Security model: timingleaks
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

encrypt.c: encrypt.c:170:89: error: array has incomplete element type 'EVP_CIPHER_CTX' (aka 'struct evp_cipher_ctx_st')
encrypt.c: static void gen_kappa(unsigned char* nonce, unsigned char* kappa, EVP_CIPHER_CTX ctx_key[1]){
encrypt.c: ^
encrypt.c: /usr/include/openssl/ossl_typ.h:90:16: note: forward declaration of 'struct evp_cipher_ctx_st'
encrypt.c: typedef struct evp_cipher_ctx_st EVP_CIPHER_CTX;
encrypt.c: ^
encrypt.c: encrypt.c:188:25: error: array has incomplete element type 'EVP_CIPHER_CTX' (aka 'struct evp_cipher_ctx_st')
encrypt.c: EVP_CIPHER_CTX ctx_k[1];
encrypt.c: ^
encrypt.c: /usr/include/openssl/ossl_typ.h:90:16: note: forward declaration of 'struct evp_cipher_ctx_st'
encrypt.c: typedef struct evp_cipher_ctx_st EVP_CIPHER_CTX;
encrypt.c: ^
encrypt.c: encrypt.c:189:31: error: array has incomplete element type 'EVP_CIPHER_CTX' (aka 'struct evp_cipher_ctx_st')
encrypt.c: EVP_CIPHER_CTX ctx_kappa_0[1];
encrypt.c: ^
encrypt.c: /usr/include/openssl/ossl_typ.h:90:16: note: forward declaration of 'struct evp_cipher_ctx_st'
encrypt.c: typedef struct evp_cipher_ctx_st EVP_CIPHER_CTX;
encrypt.c: ^
encrypt.c: encrypt.c:190:31: error: array has incomplete element type 'EVP_CIPHER_CTX' (aka 'struct evp_cipher_ctx_st')
encrypt.c: EVP_CIPHER_CTX ctx_kappa_m[1];
encrypt.c: ^
encrypt.c: /usr/include/openssl/ossl_typ.h:90:16: note: forward declaration of 'struct evp_cipher_ctx_st'
encrypt.c: typedef struct evp_cipher_ctx_st EVP_CIPHER_CTX;
encrypt.c: ^
encrypt.c: encrypt.c:330:25: error: array has incomplete element type 'EVP_CIPHER_CTX' (aka 'struct evp_cipher_ctx_st')
encrypt.c: ...

Number of similar (compiler,implementation) pairs: 5, namely:

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:evp
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:evp
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:evp
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:evp
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:evp

Compiler output

Implementation: T:evp
Security model: timingleaks
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

encrypt.c: encrypt.c:170:82: error: array type has incomplete element type 'EVP_CIPHER_CTX' {aka 'struct evp_cipher_ctx_st'}
encrypt.c: 170 | static void gen_kappa(unsigned char* nonce, unsigned char* kappa, EVP_CIPHER_CTX ctx_key[1]){
encrypt.c: | ^~~~~~~
encrypt.c: encrypt.c: In function 'crypto_aead_aes256cpfbv1_evp_timingleaks_encrypt':
encrypt.c: encrypt.c:188:20: error: array type has incomplete element type 'EVP_CIPHER_CTX' {aka 'struct evp_cipher_ctx_st'}
encrypt.c: 188 | EVP_CIPHER_CTX ctx_k[1];
encrypt.c: | ^~~~~
encrypt.c: encrypt.c:189:20: error: array type has incomplete element type 'EVP_CIPHER_CTX' {aka 'struct evp_cipher_ctx_st'}
encrypt.c: 189 | EVP_CIPHER_CTX ctx_kappa_0[1];
encrypt.c: | ^~~~~~~~~~~
encrypt.c: encrypt.c:190:20: error: array type has incomplete element type 'EVP_CIPHER_CTX' {aka 'struct evp_cipher_ctx_st'}
encrypt.c: 190 | EVP_CIPHER_CTX ctx_kappa_m[1];
encrypt.c: | ^~~~~~~~~~~
encrypt.c: encrypt.c:204:31: error: type of formal parameter 3 is incomplete
encrypt.c: 204 | gen_kappa(nonce, kappa_0, ctx_k);
encrypt.c: | ^~~~~
encrypt.c: encrypt.c:265:28: error: type of formal parameter 3 is incomplete
encrypt.c: 265 | gen_kappa(nonce, kappa_m, ctx_k);
encrypt.c: | ^~~~~
encrypt.c: encrypt.c: In function 'crypto_aead_aes256cpfbv1_evp_timingleaks_decrypt':
encrypt.c: encrypt.c:330:20: error: array type has incomplete element type 'EVP_CIPHER_CTX' {aka 'struct evp_cipher_ctx_st'}
encrypt.c: 330 | EVP_CIPHER_CTX ctx_k[1];
encrypt.c: | ^~~~~
encrypt.c: encrypt.c:331:20: error: array type has incomplete element type 'EVP_CIPHER_CTX' {aka 'struct evp_cipher_ctx_st'}
encrypt.c: 331 | EVP_CIPHER_CTX ctx_kappa_0[1];
encrypt.c: ...

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

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