Implementation notes: armeabi, novena, crypto_aead/iscream14v2

Computer: novena
Architecture: armeabi
CPU ID: unknown CPU ID
SUPERCOP version: 20220506
Operation: crypto_aead
Primitive: iscream14v2
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
11521006920 1024 022827 1444 776T:refgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022060520220506
13521166100 1024 034765 1448 792T:refclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022060520220506
16865458036 1024 028333 1448 784T:refclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022060520220506
18201577552 1024 033333 1448 776T:refclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022060520220506
20617784048 1024 027987 1444 776T:refclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022060520220506
24446122548 1024 017195 1444 776T:refgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022060520220506
25086172068 1024 015787 1436 776T:refgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022060520220506
26238272296 1024 016639 1444 776T:refgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022060520220506
27510363252 1024 027115 1444 776T:refclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022060520220506

Compiler output

Implementation: T:neon
Security model: timingleaks
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
iscream.c: In file included from iscream.c:10:
iscream.c: In file included from ./tae.h:7:
iscream.c: /usr/lib/llvm-11/lib/clang/11.0.1/include/arm_neon.h:32:2: error: "NEON support not enabled"
iscream.c: #error "NEON support not enabled"
iscream.c: ^
iscream.c: In file included from iscream.c:10:
iscream.c: ./tae.h:13:9: error: unknown type name 'uint8x16_t'; did you mean 'uint16_t'?
iscream.c: typedef uint8x16_t v16qu;
iscream.c: ^~~~~~~~~~
iscream.c: uint16_t
iscream.c: /usr/include/arm-linux-gnueabihf/bits/stdint-uintn.h:25:20: note: 'uint16_t' declared here
iscream.c: typedef __uint16_t uint16_t;
iscream.c: ^
iscream.c: In file included from iscream.c:13:
iscream.c: ./helper.h:15:3: error: unknown type name 'uint8x16x2_t'; did you mean 'uint16_t'?
iscream.c: INTERLEAVE( 0, 8);
iscream.c: ^
iscream.c: ./helper.h:10:5: note: expanded from macro 'INTERLEAVE'
iscream.c: uint8x16x2_t c__ = vzipq_u8 (X(i), X(j)); \
iscream.c: ^
iscream.c: /usr/include/arm-linux-gnueabihf/bits/stdint-uintn.h:25:20: note: 'uint16_t' declared here
iscream.c: typedef __uint16_t uint16_t;
iscream.c: ^
iscream.c: In file included from iscream.c:13:
iscream.c: ./helper.h:15:3: warning: implicit declaration of function 'vzipq_u8' is invalid in C99 [-Wimplicit-function-declaration]
iscream.c: ...
Number of similar (compiler,implementation) pairs: 4, namely:
CompilerImplementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:neon
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:neon
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:neon
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:neon

Compiler output

Implementation: T:neon
Security model: timingleaks
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
iscream.c: iscream.c:181:10: error: use of unknown builtin '__builtin_shuffle' [-Wimplicit-function-declaration]
iscream.c: A = __builtin_shuffle(table, t0);
iscream.c: ^
iscream.c: iscream.c:181:8: error: assigning to 'v16qu' (aka 'uint8x16_t') from incompatible type 'int'
iscream.c: A = __builtin_shuffle(table, t0);
iscream.c: ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
iscream.c: iscream.c:182:8: error: assigning to 'v16qu' (aka 'uint8x16_t') from incompatible type 'int'
iscream.c: C = __builtin_shuffle(table, t1);
iscream.c: ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
iscream.c: iscream.c:186:8: error: assigning to 'v16qu' (aka 'uint8x16_t') from incompatible type 'int'
iscream.c: B = __builtin_shuffle(table, t0);
iscream.c: ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
iscream.c: iscream.c:187:8: error: assigning to 'v16qu' (aka 'uint8x16_t') from incompatible type 'int'
iscream.c: D = __builtin_shuffle(table, t1);
iscream.c: ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
iscream.c: iscream.c:191:7: error: cannot convert between scalar type 'int' and vector type 'v16qu' (aka 'uint8x16_t') as implicit conversion would cause truncation
iscream.c: A ^= __builtin_shuffle(table, in[0]);
iscream.c: ^
iscream.c: iscream.c:192:7: error: cannot convert between scalar type 'int' and vector type 'v16qu' (aka 'uint8x16_t') as implicit conversion would cause truncation
iscream.c: C ^= __builtin_shuffle(table, in[2]);
iscream.c: ^
iscream.c: iscream.c:196:7: error: cannot convert between scalar type 'int' and vector type 'v16qu' (aka 'uint8x16_t') as implicit conversion would cause truncation
iscream.c: B ^= __builtin_shuffle(table, in[0]);
iscream.c: ^
iscream.c: iscream.c:197:7: error: cannot convert between scalar type 'int' and vector type 'v16qu' (aka 'uint8x16_t') as implicit conversion would cause truncation
iscream.c: ...
Number of similar (compiler,implementation) pairs: 1, namely:
CompilerImplementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:neon

Compiler output

Implementation: T:neon
Security model: timingleaks
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE
iscream.c: In file included from tae.h:7,
iscream.c: from iscream.c:10:
iscream.c: helper.h: In function ‘write128’:
iscream.c: /usr/lib/gcc/arm-linux-gnueabihf/10/include/arm_neon.h:9856:1: error: inlining failed in call to ‘always_inline’ ‘vzipq_u8’: target specific option mismatch
iscream.c: 9856 | vzipq_u8 (uint8x16_t __a, uint8x16_t __b)
iscream.c: | ^~~~~~~~
iscream.c: In file included from iscream.c:13:
iscream.c: helper.h:10:24: note: called from here
iscream.c: 10 | uint8x16x2_t c__ = vzipq_u8 (X(i), X(j)); \
iscream.c: | ^~~~~~~~~~~~~~~~~~~~~
iscream.c: helper.h:49:3: note: in expansion of macro ‘INTERLEAVE’
iscream.c: 49 | INTERLEAVE(14, 15);
iscream.c: | ^~~~~~~~~~
iscream.c: In file included from tae.h:7,
iscream.c: from iscream.c:10:
iscream.c: /usr/lib/gcc/arm-linux-gnueabihf/10/include/arm_neon.h:9856:1: error: inlining failed in call to ‘always_inline’ ‘vzipq_u8’: target specific option mismatch
iscream.c: 9856 | vzipq_u8 (uint8x16_t __a, uint8x16_t __b)
iscream.c: | ^~~~~~~~
iscream.c: In file included from iscream.c:13:
iscream.c: helper.h:10:24: note: called from here
iscream.c: 10 | uint8x16x2_t c__ = vzipq_u8 (X(i), X(j)); \
iscream.c: | ^~~~~~~~~~~~~~~~~~~~~
iscream.c: helper.h:48:3: note: in expansion of macro ‘INTERLEAVE’
iscream.c: 48 | INTERLEAVE(12, 13);
iscream.c: | ^~~~~~~~~~
iscream.c: ...
Number of similar (compiler,implementation) pairs: 4, namely:
CompilerImplementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE T:neon
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE T:neon
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE T:neon
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE T:neon

Compiler output

Implementation: T:sse
Security model: timingleaks
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
iscream.c: iscream.c:181:10: error: use of unknown builtin '__builtin_ia32_psrldi128' [-Wimplicit-function-declaration]
iscream.c: t0 = shift_right(in[0]) & V(0xf);
iscream.c: ^
iscream.c: iscream.c:16:32: note: expanded from macro 'shift_right'
iscream.c: #define shift_right(x) ((v16qi)__builtin_ia32_psrldi128((v4si)x, 4))
iscream.c: ^
iscream.c: iscream.c:181:10: error: invalid conversion between vector type 'v16qi' (vector of 16 'char' values) and integer type 'int' of different size
iscream.c: t0 = shift_right(in[0]) & V(0xf);
iscream.c: ^~~~~~~~~~~~~~~~~~
iscream.c: iscream.c:16:25: note: expanded from macro 'shift_right'
iscream.c: #define shift_right(x) ((v16qi)__builtin_ia32_psrldi128((v4si)x, 4))
iscream.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
iscream.c: iscream.c:182:10: error: invalid conversion between vector type 'v16qi' (vector of 16 'char' values) and integer type 'int' of different size
iscream.c: t1 = shift_right(in[2]) & V(0xf);
iscream.c: ^~~~~~~~~~~~~~~~~~
iscream.c: iscream.c:16:25: note: expanded from macro 'shift_right'
iscream.c: #define shift_right(x) ((v16qi)__builtin_ia32_psrldi128((v4si)x, 4))
iscream.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
iscream.c: iscream.c:184:10: error: use of unknown builtin '__builtin_ia32_pshufb128' [-Wimplicit-function-declaration]
iscream.c: A = __builtin_ia32_pshufb128(table, t0);
iscream.c: ^
iscream.c: iscream.c:184:10: note: did you mean '__builtin_ia32_psrldi128'?
iscream.c: iscream.c:181:10: note: '__builtin_ia32_psrldi128' declared here
iscream.c: t0 = shift_right(in[0]) & V(0xf);
iscream.c: ^
iscream.c: ...
Number of similar (compiler,implementation) pairs: 5, namely:
CompilerImplementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:sse
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:sse
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:sse
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:sse
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE T:sse

Compiler output

Implementation: T:sse
Security model: timingleaks
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE
iscream.c: iscream.c: In function ‘LBox16P’:
iscream.c: iscream.c:16:32: warning: implicit declaration of function ‘__builtin_ia32_psrldi128’ [-Wimplicit-function-declaration]
iscream.c: 16 | #define shift_right(x) ((v16qi)__builtin_ia32_psrldi128((v4si)x, 4))
iscream.c: | ^~~~~~~~~~~~~~~~~~~~~~~~
iscream.c: iscream.c:181:10: note: in expansion of macro ‘shift_right’
iscream.c: 181 | t0 = shift_right(in[0]) & V(0xf);
iscream.c: | ^~~~~~~~~~~
iscream.c: iscream.c:181:5: error: cannot convert a value of type ‘int’ to vector type ‘__vector(16) char’ which has different size
iscream.c: 181 | t0 = shift_right(in[0]) & V(0xf);
iscream.c: | ^~
iscream.c: iscream.c:182:5: error: cannot convert a value of type ‘int’ to vector type ‘__vector(16) char’ which has different size
iscream.c: 182 | t1 = shift_right(in[2]) & V(0xf);
iscream.c: | ^~
iscream.c: iscream.c:184:10: warning: implicit declaration of function ‘__builtin_ia32_pshufb128’; did you mean ‘__builtin_arm_qsub8’? [-Wimplicit-function-declaration]
iscream.c: 184 | A = __builtin_ia32_pshufb128(table, t0);
iscream.c: | ^~~~~~~~~~~~~~~~~~~~~~~~
iscream.c: | __builtin_arm_qsub8
iscream.c: iscream.c:184:10: error: incompatible types when assigning to type ‘v16qi’ {aka ‘__vector(16) char’} from type ‘int’
iscream.c: iscream.c:185:10: error: incompatible types when assigning to type ‘v16qi’ {aka ‘__vector(16) char’} from type ‘int’
iscream.c: 185 | C = __builtin_ia32_pshufb128(table, t1);
iscream.c: | ^~~~~~~~~~~~~~~~~~~~~~~~
iscream.c: iscream.c:189:10: error: incompatible types when assigning to type ‘v16qi’ {aka ‘__vector(16) char’} from type ‘int’
iscream.c: 189 | B = __builtin_ia32_pshufb128(table, t0);
iscream.c: | ^~~~~~~~~~~~~~~~~~~~~~~~
iscream.c: iscream.c:190:10: error: incompatible types when assigning to type ‘v16qi’ {aka ‘__vector(16) char’} from type ‘int’
iscream.c: ...
Number of similar (compiler,implementation) pairs: 4, namely:
CompilerImplementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE T:sse
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE T:sse
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE T:sse
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE T:sse