Implementation notes: aarch64, hikey960, crypto_aead/scream10v3

Computer: hikey960
Architecture: aarch64
CPU ID: 410fd034
SUPERCOP version: 20190816
Operation: crypto_aead
Primitive: scream10v3
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
1865438564 0 027531 976 904refgcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer2019112920190816
32867110004 0 028755 976 872refgcc_-funroll-loops_-O2_-fomit-frame-pointer2019112920190816
3413256928 0 022640 816 888refclang_-O3_-fomit-frame-pointer_-Qunused-arguments2019112920190816
3738708564 0 025907 976 904refgcc_-fno-schedule-insns_-O3_-fomit-frame-pointer2019112920190816
4329526944 0 022680 816 888refclang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments2019112920190816
4794136944 0 022680 816 888refclang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments2019112920190816
55777510028 0 028803 976 872refgcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer2019112920190816
5910759868 0 028819 976 872refgcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer2019112920190816
5994008580 0 027595 976 904refgcc_-funroll-loops_-O3_-fomit-frame-pointer2019112920190816
6077256944 0 022680 816 888refclang_-O3_-fwrapv_-mavx2_-fomit-frame-pointer_-Qunused-arguments2019112920190816
6077255424 0 020183 960 872refgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv2019112920190816
6160505796 0 021579 976 872refgcc_-O2_-fomit-frame-pointer2019112920190816
6160505436 0 020215 960 872refgcc_-funroll-loops_-Os_-fomit-frame-pointer2019112920190816
6243755644 0 021395 976 872refgcc_-O_-fomit-frame-pointer2019112920190816
6660008604 0 026003 976 904refgcc_-O3_-fomit-frame-pointer2019112920190816
6744068348 0 025739 976 904refgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2019112920190816
7477405748 0 021531 976 872refgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2019112920190816
8652825436 0 020199 960 872refgcc_-fno-schedule-insns_-Os_-fomit-frame-pointer2019112920190816
13563885436 0 020199 960 872refgcc_-Os_-fomit-frame-pointer2019112920190816
15900755780 0 021491 976 872refgcc_-fno-schedule-insns_-O2_-fomit-frame-pointer2019112920190816
16733255644 0 021395 976 872refgcc_-fno-schedule-insns_-O_-fomit-frame-pointer2019112920190816
18150689868 0 028819 976 872refgcc_-funroll-loops_-O_-fomit-frame-pointer2019112920190816
275557511016 0 036935 960 872refgcc_-funroll-loops2019112920190816
29848715436 0 020215 960 872refgcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer2019112920190816
30802505628 0 021379 976 872refgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2019112920190816
895877611016 0 036935 960 872refgcc2019112920190816
934593511016 0 036935 960 872refcc2019112920190816

Compiler output

Implementation: sse
Security model: unknown
Compiler: cc
scream.c: scream.c: In function 'LBox16P':
scream.c: scream.c:16:32: warning: implicit declaration of function '__builtin_ia32_psrldi128' [-Wimplicit-function-declaration]
scream.c: #define shift_right(x) ((v16qi)__builtin_ia32_psrldi128((v4si)x, 4))
scream.c: ^
scream.c: scream.c:199:10: note: in expansion of macro 'shift_right'
scream.c: t0 = shift_right(in[0]) & V(0xf);
scream.c: ^~~~~~~~~~~
scream.c: scream.c:199:5: 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:200:5: 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:202:10: warning: implicit declaration of function '__builtin_ia32_pshufb128' [-Wimplicit-function-declaration]
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^~~~~~~~~~~~~~~~~~~~~~~~
scream.c: scream.c:202:8: 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:203:8: 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:207:8: 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: ^
scream.c: ...
Number of similar (compiler,implementation) pairs: 23, namely:
CompilerImplementations
cc sse
gcc sse
gcc -O2 -fomit-frame-pointer sse
gcc -O3 -fomit-frame-pointer sse
gcc -O -fomit-frame-pointer sse
gcc -Os -fomit-frame-pointer sse
gcc -fno-schedule-insns -O2 -fomit-frame-pointer sse
gcc -fno-schedule-insns -O3 -fomit-frame-pointer sse
gcc -fno-schedule-insns -O -fomit-frame-pointer sse
gcc -fno-schedule-insns -Os -fomit-frame-pointer sse
gcc -funroll-loops sse
gcc -funroll-loops -O2 -fomit-frame-pointer sse
gcc -funroll-loops -O3 -fomit-frame-pointer sse
gcc -funroll-loops -O -fomit-frame-pointer sse
gcc -funroll-loops -Os -fomit-frame-pointer sse
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer sse
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer sse
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer sse
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer sse
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv sse
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv sse
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv sse
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv sse

Compiler output

Implementation: sse
Security model: unknown
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments
scream.c: scream.c:199:10: error: use of unknown builtin '__builtin_ia32_psrldi128' [-Wimplicit-function-declaration]
scream.c: t0 = shift_right(in[0]) & V(0xf);
scream.c: ^
scream.c: scream.c:16:32: note: expanded from macro 'shift_right'
scream.c: #define shift_right(x) ((v16qi)__builtin_ia32_psrldi128((v4si)x, 4))
scream.c: ^
scream.c: scream.c:199:10: error: invalid conversion between vector type 'v16qi' (vector of 16 'char' values) and integer type 'int' of different size
scream.c: t0 = shift_right(in[0]) & V(0xf);
scream.c: ^~~~~~~~~~~~~~~~~~
scream.c: scream.c:16:25: note: expanded from macro 'shift_right'
scream.c: #define shift_right(x) ((v16qi)__builtin_ia32_psrldi128((v4si)x, 4))
scream.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
scream.c: scream.c:200:10: error: invalid conversion between vector type 'v16qi' (vector of 16 'char' values) and integer type 'int' of different size
scream.c: t1 = shift_right(in[2]) & V(0xf);
scream.c: ^~~~~~~~~~~~~~~~~~
scream.c: scream.c:16:25: note: expanded from macro 'shift_right'
scream.c: #define shift_right(x) ((v16qi)__builtin_ia32_psrldi128((v4si)x, 4))
scream.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
scream.c: scream.c:202:10: error: use of unknown builtin '__builtin_ia32_pshufb128' [-Wimplicit-function-declaration]
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^
scream.c: scream.c:202:10: note: did you mean '__builtin_ia32_psrldi128'?
scream.c: scream.c:199:10: note: '__builtin_ia32_psrldi128' declared here
scream.c: t0 = shift_right(in[0]) & V(0xf);
scream.c: ^
scream.c: ...
Number of similar (compiler,implementation) pairs: 4, namely:
CompilerImplementations
clang -O3 -fomit-frame-pointer -Qunused-arguments sse
clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments sse
clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments sse
clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments sse