Implementation notes: aarch64, par3, crypto_aead/scream12v2

Computer: par3
Architecture: aarch64
CPU ID: unknown CPU ID
SUPERCOP version: 20170718
Operation: crypto_aead
Primitive: scream12v2

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
677692	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=native_-mtune=native_-O3`	20170720	20170718
706726	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=native_-mtune=native_-O2`	20170720	20170718
709320	? ? ?	? ? ?	`ref`	`gcc_-march=native_-mtune=native_-O3`	20170720	20170718
1781452	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=native_-mtune=native_-Os`	20170720	20170718
1922054	? ? ?	? ? ?	`ref`	`gcc_-march=native_-mtune=native_-O2`	20170720	20170718
2043168	? ? ?	? ? ?	`ref`	`gcc_-march=native_-mtune=native_-Os`	20170720	20170718

Compiler output

Implementation: crypto_aead/scream12v2/sse
Compiler: gcc -funroll-loops -march=native -mtune=native -O2

scream.c: scream.c: In function 'LBox16P':
scream.c: scream.c:16:32: warning: implicit declaration of function '__builtin_ia32_psrldi128'; did you mean '__builtin_fabsd128'? [-Wimplicit-function-declaration]
scream.c: #define shift_right(x) ((v16qi)__builtin_ia32_psrldi128((v4si)x, 4))
scream.c: ^
scream.c: scream.c:182:10: note: in expansion of macro 'shift_right'
scream.c: t0 = shift_right(in[0]) & V(0xf);
scream.c: ^~~~~~~~~~~
scream.c: scream.c:182:5: error: can't convert a value of type 'int' to vector type '__vector(16) char' which has different size
scream.c: t0 = shift_right(in[0]) & V(0xf);
scream.c: ^~
scream.c: scream.c:183:5: error: can't convert a value of type 'int' to vector type '__vector(16) char' which has different size
scream.c: t1 = shift_right(in[2]) & V(0xf);
scream.c: ^~
scream.c: scream.c:185:10: warning: implicit declaration of function '__builtin_ia32_pshufb128'; did you mean '__builtin_fabsf128'? [-Wimplicit-function-declaration]
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^~~~~~~~~~~~~~~~~~~~~~~~
scream.c: __builtin_fabsf128
scream.c: scream.c:185:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:186:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: C = __builtin_ia32_pshufb128(table, t1);
scream.c: ^
scream.c: scream.c:190:8: error: incompatible types when assigning to type 'v16qi {aka __vector(16) char}' from type 'int'
scream.c: B = __builtin_ia32_pshufb128(table, t0);
scream.c: ...

Number of similar (compiler,implementation) pairs: 6, namely:

Compiler	Implementations
gcc -funroll-loops -march=native -mtune=native -O2	sse
gcc -funroll-loops -march=native -mtune=native -O3	sse
gcc -funroll-loops -march=native -mtune=native -Os	sse
gcc -march=native -mtune=native -O2	sse
gcc -march=native -mtune=native -O3	sse
gcc -march=native -mtune=native -Os	sse