Implementation notes: amd64, rumba3, crypto_aead/led80n6t4silcv3

Computer: rumba3
Microarchitecture: amd64; Zen (800f11)
Architecture: amd64
CPU ID: AuthenticAMD-00800f11-178bfbff
SUPERCOP version: 20221122
Operation: crypto_aead
Primitive: led80n6t4silcv3

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
802462	7493 0 32	24316 812 1120	`T:vperm`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230526	20221122
822928	6667 0 32	22260 812 1120	`T:vperm`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230526	20221122
1741607	5728 0 32	19423 788 1088	`T:vperm`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230526	20221122
1774748	6050 0 32	21003 804 1120	`T:vperm`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230526	20221122
36272905	6816 4 4	23559 816 1120	`T:ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230526	20221122
48179560	7784 4 4	25003 848 1056	`T:ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230526	20221122
48341129	6387 4 4	22467 848 1024	`T:ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230526	20221122
49331783	7427 4 4	24275 848 1056	`T:ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230526	20221122
68552246	4394 4 4	19887 816 1120	`T:ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230526	20221122
71954905	4237 4 4	18988 800 1120	`T:ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230526	20221122
94360012	3734 4 4	18381 840 1088	`T:ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230526	20221122
94795620	4224 4 4	18211 848 1024	`T:ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20230526	20221122
352329799	3647 4 4	17266 792 1088	`T:ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20230526	20221122

Compiler output

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

silc.c: silc.c:174:34: warning: implicit conversion from 'int' to 'char' changes value from 128 to -128 [-Wconstant-conversion]
silc.c: state = XORDQW(tmpState, SHR(state, 8));
silc.c: ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~
silc.c: ./common.h:30:126: note: expanded from macro 'SHR'
silc.c: #define SHR(x,n) _mm_shuffle_epi8((x), _mm_set_epi8(127+(n), 126+(n), 125+(n), 124+(n), 123+(n), 122+(n), 121+(n), 120+(n), 119+(n), 118+(n), 117+(n), 116+(n), 115+(n), 114+(n), 113+(n), 112+(n))) // shift to the right
silc.c: ~~~~~~~~~~~~ ^
silc.c: ./common.h:18:43: note: expanded from macro 'XORDQW'
silc.c: #define XORDQW(x, y) _mm_xor_si128((x), (y))
silc.c: ^
silc.c: silc.c:174:34: warning: implicit conversion from 'int' to 'char' changes value from 129 to -127 [-Wconstant-conversion]
silc.c: state = XORDQW(tmpState, SHR(state, 8));
silc.c: ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~
silc.c: ./common.h:30:117: note: expanded from macro 'SHR'
silc.c: #define SHR(x,n) _mm_shuffle_epi8((x), _mm_set_epi8(127+(n), 126+(n), 125+(n), 124+(n), 123+(n), 122+(n), 121+(n), 120+(n), 119+(n), 118+(n), 117+(n), 116+(n), 115+(n), 114+(n), 113+(n), 112+(n))) // shift to the right
silc.c: ~~~~~~~~~~~~ ^
silc.c: ./common.h:18:43: note: expanded from macro 'XORDQW'
silc.c: #define XORDQW(x, y) _mm_xor_si128((x), (y))
silc.c: ^
silc.c: silc.c:174:34: warning: implicit conversion from 'int' to 'char' changes value from 130 to -126 [-Wconstant-conversion]
silc.c: state = XORDQW(tmpState, SHR(state, 8));
silc.c: ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~
silc.c: ./common.h:30:108: note: expanded from macro 'SHR'
silc.c: #define SHR(x,n) _mm_shuffle_epi8((x), _mm_set_epi8(127+(n), 126+(n), 125+(n), 124+(n), 123+(n), 122+(n), 121+(n), 120+(n), 119+(n), 118+(n), 117+(n), 116+(n), 115+(n), 114+(n), 113+(n), 112+(n))) // shift to the right
silc.c: ~~~~~~~~~~~~ ^
silc.c: ./common.h:18:43: note: expanded from macro 'XORDQW'
silc.c: ...

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

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

Compiler output

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

led.c: led.c:172:16: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'MixColumnWithSbox' that is compiled without support for 'ssse3'
led.c: dqword tmp1 = PSHUFB(LOAD(Mbox1), sum);
led.c: ^
led.c: ./common.h:42:22: note: expanded from macro 'PSHUFB'
led.c: #define PSHUFB(s, x) _mm_shuffle_epi8((s), (x)) /*return s(x)*/
led.c: ^
led.c: led.c:174:16: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'MixColumnWithSbox' that is compiled without support for 'ssse3'
led.c: dqword tmp2 = PSHUFB(LOAD(Mbox2), sum);
led.c: ^
led.c: ./common.h:42:22: note: expanded from macro 'PSHUFB'
led.c: #define PSHUFB(s, x) _mm_shuffle_epi8((s), (x)) /*return s(x)*/
led.c: ^
led.c: led.c:181:9: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'MixColumnWithSbox' that is compiled without support for 'ssse3'
led.c: tmp1 = PSHUFB(LOAD(Mbox3), tmp3);
led.c: ^
led.c: ./common.h:42:22: note: expanded from macro 'PSHUFB'
led.c: #define PSHUFB(s, x) _mm_shuffle_epi8((s), (x)) /*return s(x)*/
led.c: ^
led.c: led.c:182:9: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'MixColumnWithSbox' that is compiled without support for 'ssse3'
led.c: tmp2 = PSHUFB(LOAD(Mbox4), tmp3);
led.c: ^
led.c: ./common.h:42:22: note: expanded from macro 'PSHUFB'
led.c: #define PSHUFB(s, x) _mm_shuffle_epi8((s), (x)) /*return s(x)*/
led.c: ^
led.c: led.c:190:9: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'MixColumnWithSbox' that is compiled without support for 'ssse3'
led.c: ...

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

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