Implementation notes: aarch64, pi3aplus, crypto_stream/aes256estream

Computer: pi3aplus
Microarchitecture: aarch64; Cortex-A53 (410fd034)
Architecture: aarch64
CPU ID: 410fd034
SUPERCOP version: 20240425
Operation: crypto_stream
Primitive: aes256estream

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
38406	8159 4096 4	20456 4960 808	`T:e/hongjun/v1`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240427	20240425
39095	7595 4096 4	18591 4944 792	`T:e/hongjun/v1`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240427	20240425
39538	6215 4096 4	18536 4960 808	`T:e/hongjun/v0`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240427	20240425
40221	5215 4096 4	16207 4944 792	`T:e/hongjun/v0`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240427	20240425
44234	7251 4096 1	20029 4864 808	`T:e/hongjun/v1`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240427	20240425
44705	4775 4096 1	17549 4864 808	`T:e/hongjun/v0`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240427	20240425
69139	7355 4096 4	17487 4928 784	`T:e/hongjun/v1`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240427	20240425
70771	4855 4096 4	14983 4928 784	`T:e/hongjun/v0`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240427	20240425
89110	7751 4096 4	18839 4944 792	`T:e/hongjun/v1`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240427	20240425
89865	5187 4096 4	16279 4944 792	`T:e/hongjun/v0`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20240427	20240425

Compiler output

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

aes-ctr.c: In file included from aes-ctr.c:1:
aes-ctr.c: In file included from ./e/aes-ctr.c:17:
aes-ctr.c: In file included from ./e/aestab.c:41:
aes-ctr.c: ./e/aesopt.h:168:2: error: Could not detect endianness
aes-ctr.c: #error Could not detect endianness
aes-ctr.c: ^
aes-ctr.c: In file included from aes-ctr.c:1:
aes-ctr.c: In file included from ./e/aes-ctr.c:17:
aes-ctr.c: In file included from ./e/aestab.c:194:
aes-ctr.c: ./e/aestab.h:106:60: warning: implicit declaration of function 'bytes2word' is invalid in C99 [-Wimplicit-function-declaration]
aes-ctr.c: Extern Align Const aes_32t t_dec(r,c)[RC_LENGTH] = rc_data(w0);
aes-ctr.c: ^
aes-ctr.c: ./e/aestab.h:106:60: error: initializer element is not a compile-time constant
aes-ctr.c: Extern Align Const aes_32t t_dec(r,c)[RC_LENGTH] = rc_data(w0);
aes-ctr.c: ~~~~~~~~^~~
aes-ctr.c: ./e/aestab.c:148:5: note: expanded from macro 'rc_data'
aes-ctr.c: w(0x01), w(0x02), w(0x04), w(0x08), w(0x10),w(0x20), w(0x40), w(0x80),\
aes-ctr.c: ^~~~~~~
aes-ctr.c: ./e/aestab.c:153:17: note: expanded from macro 'w0'
aes-ctr.c: #define w0(p) bytes2word(p, 0, 0, 0)
aes-ctr.c: ^~~~~~~~~~~~~~~~~~~~~~
aes-ctr.c: In file included from aes-ctr.c:1:
aes-ctr.c: In file included from ./e/aes-ctr.c:17:
aes-ctr.c: In file included from ./e/aestab.c:194:
aes-ctr.c: ./e/aestab.h:124:39: error: initializer element is not a compile-time constant
aes-ctr.c: ...

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

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

Compiler output

Implementation: T:e/gladman
Security model: timingleaks
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

aes-ctr.c: In file included from e/aestab.c:41,
aes-ctr.c: from e/aes-ctr.c:17,
aes-ctr.c: from aes-ctr.c:1:
aes-ctr.c: e/aesopt.h:168:2: error: #error Could not detect endianness
aes-ctr.c: #error Could not detect endianness
aes-ctr.c: ^~~~~
aes-ctr.c: In file included from e/aes-ctr.c:17,
aes-ctr.c: from aes-ctr.c:1:
aes-ctr.c: e/aestab.c:153:17: warning: implicit declaration of function 'bytes2word' [-Wimplicit-function-declaration]
aes-ctr.c: #define w0(p) bytes2word(p, 0, 0, 0)
aes-ctr.c: ^~~~~~~~~~
aes-ctr.c: e/aestab.c:148:5: note: in expansion of macro 'w0'
aes-ctr.c: w(0x01), w(0x02), w(0x04), w(0x08), w(0x10),w(0x20), w(0x40), w(0x80),\
aes-ctr.c: ^
aes-ctr.c: e/aestab.h:106:52: note: in expansion of macro 'rc_data'
aes-ctr.c: Extern Align Const aes_32t t_dec(r,c)[RC_LENGTH] = rc_data(w0);
aes-ctr.c: ^~~~~~~
aes-ctr.c: e/aestab.c:153:17: error: initializer element is not constant
aes-ctr.c: #define w0(p) bytes2word(p, 0, 0, 0)
aes-ctr.c: ^~~~~~~~~~
aes-ctr.c: e/aestab.c:148:5: note: in expansion of macro 'w0'
aes-ctr.c: w(0x01), w(0x02), w(0x04), w(0x08), w(0x10),w(0x20), w(0x40), w(0x80),\
aes-ctr.c: ^
aes-ctr.c: e/aestab.h:106:52: note: in expansion of macro 'rc_data'
aes-ctr.c: Extern Align Const aes_32t t_dec(r,c)[RC_LENGTH] = rc_data(w0);
aes-ctr.c: ...

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:e/gladman
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:e/gladman
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:e/gladman
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:e/gladman

Namespace violations

Implementation: T:e/hongjun/v0
Security model: timingleaks
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

aes-ctr.o T0 D
aes-ctr.o T1 D
aes-ctr.o T2 D
aes-ctr.o T3 D
aes-ctr.o aes256_enc_block T
aes-ctr.o partial_precompute_tworounds T

Number of similar (compiler,implementation) pairs: 5, namely:

Compiler	Implementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:e/hongjun/v0
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:e/hongjun/v0
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:e/hongjun/v0
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:e/hongjun/v0
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:e/hongjun/v0

Namespace violations

Implementation: T:e/hongjun/v1
Security model: timingleaks
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

aes-ctr.o T0 D
aes-ctr.o T1 D
aes-ctr.o T2 D
aes-ctr.o T3 D
aes-ctr.o partial_precompute_tworounds T

Number of similar (compiler,implementation) pairs: 5, namely:

Compiler	Implementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	T:e/hongjun/v1
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:e/hongjun/v1
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:e/hongjun/v1
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:e/hongjun/v1
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:e/hongjun/v1