Implementation notes: amd64, speed2supercop, crypto_stream/salsa208

Computer: speed2supercop
Microarchitecture: amd64; Haswell+AES (306c3)
Architecture: amd64
CPU ID: GenuineIntel-000306c3-1fc9cbf5
SUPERCOP version: 20240107
Operation: crypto_stream
Primitive: salsa208

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
1056	7796 0 4	20693 752 872	`dolbeau/amd64-xmm6int`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
1056	8868 0 4	23677 752 872	`dolbeau/amd64-xmm6int`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
1064	7872 0 4	20236 744 872	`dolbeau/amd64-xmm6int`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
1188	7603 0 4	18768 728 840	`dolbeau/amd64-xmm6int`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
2300	4608 0 0	16884 744 864	`amd64_xmm6`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
2308	4608 0 0	15720 728 832	`amd64_xmm6`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
2308	5472 0 4	18317 752 872	`e/amd64-xmm6`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
2308	5472 0 4	20229 752 872	`e/amd64-xmm6`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
2308	5431 0 4	17732 744 872	`e/amd64-xmm6`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
2316	5268 0 4	16392 728 840	`e/amd64-xmm6`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
2352	4608 0 0	17437 752 864	`amd64_xmm6`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
2436	4608 0 0	19317 752 864	`amd64_xmm6`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
2476	5780 0 4	16904 728 840	`e/amd64-xmm5`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
2484	5943 0 4	18244 744 872	`e/amd64-xmm5`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
2512	5984 0 4	20741 752 872	`e/amd64-xmm5`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
2516	5984 0 4	18829 752 872	`e/amd64-xmm5`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
3152	16941 2368 0	1691724 146816 10296	`T:cryptopp`	`g++_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
3152	16127 2368 0	1688493 146824 10296	`T:cryptopp`	`g++_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
3164	16996 2368 0	1690078 146824 10296	`T:cryptopp`	`g++_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
3180	7327 2880 0	1682002 147472 10264	`T:cryptopp`	`g++_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
4140	2324 0 4	14612 744 872	`e/amd64-xmm2`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
4200	2161 0 4	13272 728 840	`e/amd64-xmm2`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
4204	2365 0 4	15197 752 872	`e/amd64-xmm2`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
4204	2365 0 4	17109 752 872	`e/amd64-xmm2`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
4316	2429 0 4	17173 752 872	`e/amd64-xmm`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
4328	2429 0 4	15261 752 872	`e/amd64-xmm`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
4332	2388 0 4	14676 744 872	`e/amd64-xmm`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
4332	2225 0 4	13336 728 840	`e/amd64-xmm`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
4556	2708 0 4	15573 752 872	`e/merged`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
4596	3716 0 4	18477 752 872	`e/merged`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
4788	2631 0 4	14940 744 872	`e/merged`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
4804	3262 0 4	18029 752 872	`e/ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
4860	2328 0 4	13448 728 840	`e/merged`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
4868	3278 0 4	18045 752 872	`e/regs`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
4876	2960 0 4	15805 752 872	`e/amd64-3`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
4876	2756 0 4	13848 728 840	`e/amd64-3`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
4884	2960 0 4	17717 752 872	`e/amd64-3`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
4900	2919 0 4	15220 744 872	`e/amd64-3`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
4916	2308 0 4	13400 728 840	`e/amd64-2`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
4920	2512 0 4	17269 752 872	`e/amd64-2`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
4928	2512 0 4	15357 752 872	`e/amd64-2`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
4928	2471 0 4	14772 744 872	`e/amd64-2`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
5624	3024 0 4	17781 752 872	`e/amd64-1`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
5636	3024 0 4	15869 752 872	`e/amd64-1`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
5636	2983 0 4	15284 744 872	`e/amd64-1`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
5708	2820 0 4	13912 728 840	`e/amd64-1`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
6684	1944 0 0	18621 752 864	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
7472	2670 0 4	15541 752 872	`e/regs`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
7656	2518 0 4	14836 744 872	`e/regs`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
7944	2654 0 4	15525 752 872	`e/ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
8708	2386 0 4	14692 744 872	`e/ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
8956	2124 0 4	13240 728 840	`e/regs`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
9496	989 0 0	15781 752 864	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
9508	935 0 0	15172 744 864	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
10116	750 0 0	13800 728 832	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107
10636	1968 0 4	13096 728 840	`e/ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240114	20240107

Compiler output

Implementation: amd64_xmm6
Security model: constbranchindex
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

try.c: /usr/bin/ld: warning: stream.o: missing .note.GNU-stack section implies executable stack
try.c: /usr/bin/ld: NOTE: This behaviour is deprecated and will be removed in a future version of the linker
try.c: /usr/bin/ld: warning: stream.o: missing .note.GNU-stack section implies executable stack
try.c: /usr/bin/ld: NOTE: This behaviour is deprecated and will be removed in a future version of the linker
measure.c: /usr/bin/ld: warning: stream.o: missing .note.GNU-stack section implies executable stack
measure.c: /usr/bin/ld: NOTE: This behaviour is deprecated and will be removed in a future version of the linker

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	amd64_xmm6
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	amd64_xmm6
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	amd64_xmm6
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	amd64_xmm6

Compiler output

Implementation: e/amd64-1
Security model: constbranchindex
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

try.c: /usr/bin/ld: warning: salsa20.o: missing .note.GNU-stack section implies executable stack
try.c: /usr/bin/ld: NOTE: This behaviour is deprecated and will be removed in a future version of the linker
try.c: /usr/bin/ld: warning: salsa20.o: missing .note.GNU-stack section implies executable stack
try.c: /usr/bin/ld: NOTE: This behaviour is deprecated and will be removed in a future version of the linker
measure.c: /usr/bin/ld: warning: salsa20.o: missing .note.GNU-stack section implies executable stack
measure.c: /usr/bin/ld: NOTE: This behaviour is deprecated and will be removed in a future version of the linker

Number of similar (compiler,implementation) pairs: 28, namely:

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	e/amd64-1
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	e/amd64-1
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	e/amd64-1
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	e/amd64-1
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	e/amd64-2
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	e/amd64-2
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	e/amd64-2
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	e/amd64-2
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	e/amd64-3
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	e/amd64-3
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	e/amd64-3
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	e/amd64-3
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	e/amd64-xmm
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	e/amd64-xmm
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	e/amd64-xmm
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	e/amd64-xmm
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	e/amd64-xmm2
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	e/amd64-xmm2
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	e/amd64-xmm2
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	e/amd64-xmm2
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	e/amd64-xmm5
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	e/amd64-xmm5
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	e/amd64-xmm5
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	e/amd64-xmm5
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	e/amd64-xmm6
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	e/amd64-xmm6
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	e/amd64-xmm6
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	e/amd64-xmm6