Implementation notes: aarch64, hikey960, crypto_aead/scream10v1

Computer: hikey960
Architecture: aarch64
CPU ID: 410fd034
SUPERCOP version: 20190816
Operation: crypto_aead
Primitive: scream10v1
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
1865438612 0 025763 944 896refgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv2019112920190816
2065539996 0 028707 944 864refgcc_-funroll-loops_-O_-fomit-frame-pointer2019112920190816
3286715920 0 021395 944 864refgcc_-fno-schedule-insns_-O2_-fomit-frame-pointer2019112920190816
3579757432 0 023136 816 880refclang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments2019112920190816
3579758844 0 027571 944 896refgcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer2019112920190816
3663007432 0 023136 816 880refclang_-O3_-fwrapv_-mavx2_-fomit-frame-pointer_-Qunused-arguments2019112920190816
3912759996 0 028707 944 864refgcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer2019112920190816
3975627432 0 023136 816 880refclang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments2019112920190816
5577758852 0 026011 944 896refgcc_-O3_-fomit-frame-pointer2019112920190816
5869838840 0 027611 944 896refgcc_-funroll-loops_-O3_-fomit-frame-pointer2019112920190816
6160507404 0 023088 816 880refclang_-O3_-fomit-frame-pointer_-Qunused-arguments2019112920190816
61605010276 0 028787 944 864refgcc_-funroll-loops_-O2_-fomit-frame-pointer2019112920190816
6243755904 0 021451 944 864refgcc_-O2_-fomit-frame-pointer2019112920190816
6243755484 0 020007 928 864refgcc_-fno-schedule-insns_-Os_-fomit-frame-pointer2019112920190816
6244505484 0 020023 928 864refgcc_-funroll-loops_-Os_-fomit-frame-pointer2019112920190816
6327005752 0 021267 944 864refgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv2019112920190816
66600010300 0 028835 944 864refgcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer2019112920190816
6993008864 0 025971 944 896refgcc_-fno-schedule-insns_-O3_-fomit-frame-pointer2019112920190816
9741425484 0 020023 928 864refgcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer2019112920190816
15817505864 0 021411 944 864refgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv2019112920190816
16252615472 0 019991 928 864refgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv2019112920190816
16733255784 0 021291 944 864refgcc_-O_-fomit-frame-pointer2019112920190816
16860155784 0 021291 944 864refgcc_-fno-schedule-insns_-O_-fomit-frame-pointer2019112920190816
278887510492 0 032071 928 864refgcc2019112920190816
30590705484 0 020007 928 864refgcc_-Os_-fomit-frame-pointer2019112920190816
839160010492 0 032071 928 864refgcc_-funroll-loops2019112920190816
859901010492 0 032071 928 864refcc2019112920190816

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: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' [-Wimplicit-function-declaration]
scream.c: A = __builtin_ia32_pshufb128(table, t0);
scream.c: ^~~~~~~~~~~~~~~~~~~~~~~~
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: ^
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:182:10: 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:182:10: 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:183:10: 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:185:10: 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:185:10: note: did you mean '__builtin_ia32_psrldi128'?
scream.c: scream.c:182:10: 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