Implementation notes: amd64, hydra4, crypto_stream/aes128ctr

Computer: hydra4
Microarchitecture: amd64; K10 32nm (300f10)
Architecture: amd64
CPU ID: AuthenticAMD-00300f10-178bfbff
SUPERCOP version: 20240625
Operation: crypto_stream
Primitive: aes128ctr

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
34528	428 0 0	16179 868 952	`T:openssl`	`clang_-mcpu=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
34754	651 0 0	16296 852 984	`T:openssl`	`gcc_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
34768	423 0 0	13369 860 952	`T:openssl`	`clang_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
34904	472 0 0	14848 852 984	`T:openssl`	`gcc_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
34960	437 0 0	13905 860 952	`T:openssl`	`clang_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
35013	358 0 0	12819 828 984	`T:openssl`	`gcc_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
35016	437 0 0	14096 852 984	`T:openssl`	`gcc_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
35029	428 0 0	16179 868 952	`T:openssl`	`clang_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
35096	428 0 0	15315 868 952	`T:openssl`	`clang_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
37043	11934 2064 0	1417679 145212 10328	`T:cryptopp`	`clang++_-march=native_-O2_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
37074	19361 2800 0	1715344 145180 10424	`T:cryptopp`	`g++_-march=native_-mtune=native_-O2_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
37114	18691 2800 0	1712822 145180 10424	`T:cryptopp`	`g++_-march=native_-mtune=native_-O_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
37287	9332 1480 0	1413776 145204 10328	`T:cryptopp`	`clang++_-march=native_-Os_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
37331	8298 3272 0	1705844 146244 10392	`T:cryptopp`	`g++_-march=native_-mtune=native_-Os_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
37385	12022 2064 0	1418595 145212 10328	`T:cryptopp`	`clang++_-march=native_-O3_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
37592	17826 6592 0	1426288 148612 10328	`T:cryptopp`	`clang++_-march=native_-O_-fwrapv_-Qunused-arguments_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625
50332	20501 2800 0	1717291 145164 10424	`T:cryptopp`	`g++_-march=native_-mtune=native_-O3_-fwrapv_-fPIC_-fPIE_-gdwarf-4_-Wall`	20240628	20240625

Compiler output

aesenc-int.c: aesenc-int.c:29:25: warning: unused variable 'temp2' [-Wunused-variable]
aesenc-int.c:   __m128i temp0, temp1, temp2, temp4;
aesenc-int.c:                         ^
aesenc-int.c: aesenc-int.c:59:20: warning: unused function 'aesni_encrypt1' [-Wunused-function]
aesenc-int.c: static inline void aesni_encrypt1(unsigned char *out, unsigned char *n, __m128i rkeys[16]) {
aesenc-int.c:                    ^
aesenc-int.c: aesenc-int.c:75:20: warning: unused function 'incle' [-Wunused-function]
aesenc-int.c: static inline void incle(unsigned char n[16]) {
aesenc-int.c:                    ^
aesenc-int.c: aesenc-int.c:173:1: warning: unused function 'aesni_encrypt4' [-Wunused-function]
aesenc-int.c: FUNC(4, MAKE4)
aesenc-int.c: ^
aesenc-int.c: aesenc-int.c:150:22: note: expanded from macro 'FUNC'
aesenc-int.c:   static inline void aesni_encrypt##N(unsigned char *out, unsigned char *n, __m128i rkeys[11]) { \
aesenc-int.c:                      ^
aesenc-int.c: <scratch space>:224:1: note: expanded from here
aesenc-int.c: aesni_encrypt4
aesenc-int.c: ^
aesenc-int.c: aesenc-int.c:174:1: warning: unused function 'aesni_encrypt6' [-Wunused-function]
aesenc-int.c: FUNC(6, MAKE6)
aesenc-int.c: ^
aesenc-int.c: aesenc-int.c:150:22: note: expanded from macro 'FUNC'
aesenc-int.c:   static inline void aesni_encrypt##N(unsigned char *out, unsigned char *n, __m128i rkeys[11]) { \
aesenc-int.c:                      ^
aesenc-int.c: <scratch space>:273:1: note: expanded from here
aesenc-int.c: ...

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

Implementation	Compiler
`T:dolbeau/aesenc-int`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`T:dolbeau/aesenc-int`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`T:dolbeau/aesenc-int`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`T:dolbeau/aesenc-int`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`
`T:dolbeau/aesenc-int`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`

Compiler output

aesenc-int.c: aesenc-int.c: In function 'aesni_key128_expand':
aesenc-int.c: aesenc-int.c:29:25: warning: unused variable 'temp2' [-Wunused-variable]
aesenc-int.c:    29 |   __m128i temp0, temp1, temp2, temp4;
aesenc-int.c:       |                         ^~~~~
aesenc-int.c: aesenc-int.c: In function 'aesni_encrypt1':
aesenc-int.c: aesenc-int.c:63: warning: ignoring '#pragma unroll ' [-Wunknown-pragmas]
aesenc-int.c:    63 | #pragma unroll(9)
aesenc-int.c:       |
aesenc-int.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/10/include/immintrin.h:39,
aesenc-int.c:                  from aesenc-int.c:12:
aesenc-int.c: aesenc-int.c: In function 'aesni_key128_expand':
aesenc-int.c: /usr/lib/gcc/x86_64-linux-gnu/10/include/wmmintrin.h:87:1: error: inlining failed in call to 'always_inline' '_mm_aeskeygenassist_si128': target specific option mismatch
aesenc-int.c:    87 | _mm_aeskeygenassist_si128 (__m128i __X, const int __C)
aesenc-int.c:       | ^~~~~~~~~~~~~~~~~~~~~~~~~
aesenc-int.c: aesenc-int.c:36:11: note: called from here
aesenc-int.c:    36 |   temp1 = _mm_aeskeygenassist_si128(temp0, IMM);        \
aesenc-int.c:       |           ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
aesenc-int.c: aesenc-int.c:54:3: note: in expansion of macro 'BLOCK1'
aesenc-int.c:    54 |   BLOCK1(0x36);
aesenc-int.c:       |   ^~~~~~
aesenc-int.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/10/include/immintrin.h:39,
aesenc-int.c:                  from aesenc-int.c:12:
aesenc-int.c: /usr/lib/gcc/x86_64-linux-gnu/10/include/wmmintrin.h:87:1: error: inlining failed in call to 'always_inline' '_mm_aeskeygenassist_si128': target specific option mismatch
aesenc-int.c:    87 | _mm_aeskeygenassist_si128 (__m128i __X, const int __C)
aesenc-int.c:       | ^~~~~~~~~~~~~~~~~~~~~~~~~
aesenc-int.c: ...

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

Implementation	Compiler
`T:dolbeau/aesenc-int`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`T:dolbeau/aesenc-int`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`T:dolbeau/aesenc-int`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`
`T:dolbeau/aesenc-int`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (10.2.1_20210110)`