Implementation notes: amd64, hydra3, crypto_aead/norx6444v3

Computer: hydra3
Architecture: amd64
CPU ID: AuthenticAMD-00100fa0-178bfbff
SUPERCOP version: 20171218
Operation: crypto_aead
Primitive: norx6444v3

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
44051	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O2_-fomit-frame-pointer`	20170918	20170725
44059	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=k8_-O2_-fomit-frame-pointer`	20170918	20170725
44078	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=barcelona_-O2_-fomit-frame-pointer`	20170918	20170725
44080	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O2_-fomit-frame-pointer`	20170918	20170725
44451	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20170918	20170725
44461	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-O3_-fomit-frame-pointer`	20170918	20170725
44463	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-O3_-fomit-frame-pointer`	20170918	20170725
44522	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-O2_-fomit-frame-pointer`	20170918	20170725
44532	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-O2_-fomit-frame-pointer`	20170918	20170725
44545	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20170918	20170725
45030	? ? ?	? ? ?	`ref`	`gcc_-m64_-O3_-fomit-frame-pointer`	20170918	20170725
45032	? ? ?	? ? ?	`ref`	`gcc_-O3_-fomit-frame-pointer`	20170918	20170725
45055	? ? ?	? ? ?	`ref`	`gcc_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20170918	20170725
45458	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=nocona_-O3_-fomit-frame-pointer`	20170918	20170725
45466	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O3_-fomit-frame-pointer`	20170918	20170725
45829	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=nocona_-O_-fomit-frame-pointer`	20170918	20170725
45898	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O_-fomit-frame-pointer`	20170918	20170725
45921	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=k8_-Os_-fomit-frame-pointer`	20170918	20170725
45929	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-Os_-fomit-frame-pointer`	20170918	20170725
45953	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer`	20170918	20170725
45979	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O3_-fomit-frame-pointer`	20170918	20170725
45984	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-Os_-fomit-frame-pointer`	20170918	20170725
46023	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-Os_-fomit-frame-pointer`	20170918	20170725
46023	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20170918	20170725
46024	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=barcelona_-O3_-fomit-frame-pointer`	20170918	20170725
46044	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O2_-fomit-frame-pointer`	20170918	20170725
46052	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O3_-fomit-frame-pointer`	20170918	20170725
46065	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-O_-fomit-frame-pointer`	20170918	20170725
46065	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-Os_-fomit-frame-pointer`	20170918	20170725
46086	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-O_-fomit-frame-pointer`	20170918	20170725
46086	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=nocona_-O2_-fomit-frame-pointer`	20170918	20170725
46090	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=k8_-O3_-fomit-frame-pointer`	20170918	20170725
46094	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=barcelona_-Os_-fomit-frame-pointer`	20170918	20170725
46202	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=k8_-O3_-fomit-frame-pointer`	20170918	20170725
46227	? ? ?	? ? ?	`ref`	`gcc_-march=k8_-O3_-fomit-frame-pointer`	20170918	20170725
46357	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=barcelona_-O_-fomit-frame-pointer`	20170918	20170725
46412	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=k8_-O_-fomit-frame-pointer`	20170918	20170725
46442	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O_-fomit-frame-pointer`	20170918	20170725
46454	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer`	20170918	20170725
46455	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O_-fomit-frame-pointer`	20170918	20170725
46481	? ? ?	? ? ?	`ref`	`gcc_-march=barcelona_-O3_-fomit-frame-pointer`	20170918	20170725
46483	? ? ?	? ? ?	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv`	20170918	20170725
46498	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=barcelona_-O3_-fomit-frame-pointer`	20170918	20170725
46538	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=nocona_-O3_-fomit-frame-pointer`	20170918	20170725
46540	? ? ?	? ? ?	`ref`	`gcc_-march=nocona_-O3_-fomit-frame-pointer`	20170918	20170725
46816	? ? ?	? ? ?	`ref`	`gcc_-m64_-O2_-fomit-frame-pointer`	20170918	20170725
46820	? ? ?	? ? ?	`ref`	`gcc_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20170918	20170725
46824	? ? ?	? ? ?	`ref`	`gcc_-O2_-fomit-frame-pointer`	20170918	20170725
46868	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=corei7_-O2_-fomit-frame-pointer`	20170918	20170725
46883	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer`	20170918	20170725
46908	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer`	20170918	20170725
47066	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-O2_-fomit-frame-pointer`	20170918	20170725
47195	? ? ?	? ? ?	`ref`	`gcc_-march=k8_-O2_-fomit-frame-pointer`	20170918	20170725
47198	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=k8_-O2_-fomit-frame-pointer`	20170918	20170725
47468	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=barcelona_-O_-fomit-frame-pointer`	20170918	20170725
47477	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer`	20170918	20170725
47586	? ? ?	? ? ?	`ref`	`gcc_-march=barcelona_-O_-fomit-frame-pointer`	20170918	20170725
47645	? ? ?	? ? ?	`ref`	`gcc_-march=k8_-O_-fomit-frame-pointer`	20170918	20170725
47690	? ? ?	? ? ?	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv`	20170918	20170725
47804	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=barcelona_-O2_-fomit-frame-pointer`	20170918	20170725
47809	? ? ?	? ? ?	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv`	20170918	20170725
47847	? ? ?	? ? ?	`ref`	`gcc_-march=barcelona_-O2_-fomit-frame-pointer`	20170918	20170725
47868	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer`	20170918	20170725
48087	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=k8_-O_-fomit-frame-pointer`	20170918	20170725
48225	? ? ?	? ? ?	`ref`	`gcc_-march=nocona_-O2_-fomit-frame-pointer`	20170918	20170725
48251	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=nocona_-O2_-fomit-frame-pointer`	20170918	20170725
48321	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=corei7_-O_-fomit-frame-pointer`	20170918	20170725
48490	? ? ?	? ? ?	`ref`	`gcc_-march=nocona_-O_-fomit-frame-pointer`	20170918	20170725
48657	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=nocona_-O_-fomit-frame-pointer`	20170918	20170725
48693	? ? ?	? ? ?	`ref`	`gcc_-O_-fomit-frame-pointer`	20170918	20170725
48693	? ? ?	? ? ?	`ref`	`gcc_-fno-schedule-insns_-O_-fomit-frame-pointer`	20170918	20170725
49135	? ? ?	? ? ?	`ref`	`gcc_-m64_-O_-fomit-frame-pointer`	20170918	20170725
49406	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer`	20170918	20170725
49459	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer`	20170918	20170725
49477	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-O_-fomit-frame-pointer`	20170918	20170725
51391	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=k8_-Os_-fomit-frame-pointer`	20170918	20170725
51394	? ? ?	? ? ?	`ref`	`gcc_-march=k8_-Os_-fomit-frame-pointer`	20170918	20170725
51527	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=corei7_-Os_-fomit-frame-pointer`	20170918	20170725
51561	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer`	20170918	20170725
51561	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer`	20170918	20170725
51564	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer`	20170918	20170725
51597	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=barcelona_-Os_-fomit-frame-pointer`	20170918	20170725
51597	? ? ?	? ? ?	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv`	20170918	20170725
51612	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-Os_-fomit-frame-pointer`	20170918	20170725
51691	? ? ?	? ? ?	`ref`	`gcc_-march=barcelona_-Os_-fomit-frame-pointer`	20170918	20170725
51714	? ? ?	? ? ?	`ref`	`gcc_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20170918	20170725
51774	? ? ?	? ? ?	`ref`	`gcc_-Os_-fomit-frame-pointer`	20170918	20170725
51851	? ? ?	? ? ?	`ref`	`gcc_-march=nocona_-Os_-fomit-frame-pointer`	20170918	20170725
51871	? ? ?	? ? ?	`ref`	`gcc_-m64_-Os_-fomit-frame-pointer`	20170918	20170725
51894	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=nocona_-Os_-fomit-frame-pointer`	20170918	20170725
51907	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=nocona_-Os_-fomit-frame-pointer`	20170918	20170725
51922	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-Os_-fomit-frame-pointer`	20170918	20170725
56527	? ? ?	? ? ?	`ref`	`clang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20170918	20170725
56545	? ? ?	? ? ?	`ref`	`clang_-mcpu=cortex-a9_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20170918	20170725
56565	? ? ?	? ? ?	`ref`	`clang_-O3_-fomit-frame-pointer_-Qunused-arguments`	20170918	20170725
56600	? ? ?	? ? ?	`ref`	`clang_-mcpu=cortex-a8_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20170918	20170725
63703	? ? ?	? ? ?	`ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20170918	20170725
63757	? ? ?	? ? ?	`ref`	`clang_-O3_-fwrapv_-march=native_-fomit-frame-pointer_-Qunused-arguments`	20170918	20170725
262176	? ? ?	? ? ?	`ref`	`gcc`	20170918	20170725
262209	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops`	20170918	20170725
262223	? ? ?	? ? ?	`ref`	`cc`	20170918	20170725

Test failure

Implementation: crypto_aead/norx6444v3/ref
Compiler: gcc -m64 -march=core2 -O3 -fomit-frame-pointer

error 111

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

Compiler	Implementations
gcc -m64 -march=core2 -O3 -fomit-frame-pointer	ref

Compiler output

Implementation: crypto_aead/norx6444v3/ymm
Compiler: cc

Number of similar (compiler,implementation) pairs: 92, namely:

Compiler	Implementations
cc	ymm
gcc	ymm
gcc -O2 -fomit-frame-pointer	ymm
gcc -O3 -fomit-frame-pointer	ymm
gcc -O -fomit-frame-pointer	ymm
gcc -Os -fomit-frame-pointer	ymm
gcc -fno-schedule-insns -O2 -fomit-frame-pointer	ymm
gcc -fno-schedule-insns -O3 -fomit-frame-pointer	ymm
gcc -fno-schedule-insns -O -fomit-frame-pointer	ymm
gcc -fno-schedule-insns -Os -fomit-frame-pointer	ymm
gcc -funroll-loops	ymm
gcc -funroll-loops -O2 -fomit-frame-pointer	ymm
gcc -funroll-loops -O3 -fomit-frame-pointer	ymm
gcc -funroll-loops -O -fomit-frame-pointer	ymm
gcc -funroll-loops -Os -fomit-frame-pointer	ymm
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer	ymm
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer	ymm
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer	ymm
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer	ymm
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer	ymm
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer	ymm
gcc -funroll-loops -m64 -O -fomit-frame-pointer	ymm
gcc -funroll-loops -m64 -Os -fomit-frame-pointer	ymm
gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer	ymm
gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer	ymm
gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer	ymm
gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer	ymm
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer	ymm
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer	ymm
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer	ymm
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer	ymm
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer	ymm
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer	ymm
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer	ymm
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer	ymm
gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer	ymm
gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer	ymm
gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer	ymm
gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer	ymm
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer	ymm
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer	ymm
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer	ymm
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer	ymm
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer	ymm
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer	ymm
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer	ymm
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer	ymm
gcc -m64 -O2 -fomit-frame-pointer	ymm
gcc -m64 -O3 -fomit-frame-pointer	ymm
gcc -m64 -O -fomit-frame-pointer	ymm
gcc -m64 -Os -fomit-frame-pointer	ymm
gcc -m64 -march=core2 -O2 -fomit-frame-pointer	ymm
gcc -m64 -march=core2 -O3 -fomit-frame-pointer	ymm
gcc -m64 -march=core2 -O -fomit-frame-pointer	ymm
gcc -m64 -march=core2 -Os -fomit-frame-pointer	ymm
gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer	ymm
gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer	ymm
gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer	ymm
gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer	ymm
gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer	ymm
gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer	ymm
gcc -m64 -march=corei7 -O2 -fomit-frame-pointer	ymm
gcc -m64 -march=corei7 -O -fomit-frame-pointer	ymm
gcc -m64 -march=corei7 -Os -fomit-frame-pointer	ymm
gcc -m64 -march=k8 -O2 -fomit-frame-pointer	ymm
gcc -m64 -march=k8 -O3 -fomit-frame-pointer	ymm
gcc -m64 -march=k8 -O -fomit-frame-pointer	ymm
gcc -m64 -march=k8 -Os -fomit-frame-pointer	ymm
gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer	ymm
gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer	ymm
gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer	ymm
gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer	ymm
gcc -m64 -march=nocona -O2 -fomit-frame-pointer	ymm
gcc -m64 -march=nocona -O3 -fomit-frame-pointer	ymm
gcc -m64 -march=nocona -O -fomit-frame-pointer	ymm
gcc -m64 -march=nocona -Os -fomit-frame-pointer	ymm
gcc -march=barcelona -O2 -fomit-frame-pointer	ymm
gcc -march=barcelona -O3 -fomit-frame-pointer	ymm
gcc -march=barcelona -O -fomit-frame-pointer	ymm
gcc -march=barcelona -Os -fomit-frame-pointer	ymm
gcc -march=k8 -O2 -fomit-frame-pointer	ymm
gcc -march=k8 -O3 -fomit-frame-pointer	ymm
gcc -march=k8 -O -fomit-frame-pointer	ymm
gcc -march=k8 -Os -fomit-frame-pointer	ymm
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv	ymm
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv	ymm
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv	ymm
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv	ymm
gcc -march=nocona -O2 -fomit-frame-pointer	ymm
gcc -march=nocona -O3 -fomit-frame-pointer	ymm
gcc -march=nocona -O -fomit-frame-pointer	ymm
gcc -march=nocona -Os -fomit-frame-pointer	ymm

Compiler output

Implementation: crypto_aead/norx6444v3/ymm
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments

norx.c: norx.c:653:21: error: always_inline function '_mm256_loadu_si256' requires target feature 'sse4.2', but would be inlined into function 'norx_aead_encrypt' that is compiled without support for 'sse4.2'
norx.c: const __m256i K = LOADU(key);
norx.c: ^
norx.c: norx.c:45:19: note: expanded from macro 'LOADU'
norx.c: #define LOADU(in) _mm256_loadu_si256((__m256i*)(in))
norx.c: ^
norx.c: norx.c:657:3: error: always_inline function '_mm256_loadu_si256' requires target feature 'sse4.2', but would be inlined into function 'norx_aead_encrypt' that is compiled without support for 'sse4.2'
norx.c: INITIALISE(A, B, C, D, nonce, K);
norx.c: ^
norx.c: norx.c:254:7: note: expanded from macro 'INITIALISE'
norx.c: A = LOADU(NONCE); \
norx.c: ^
norx.c: norx.c:45:19: note: expanded from macro 'LOADU'
norx.c: #define LOADU(in) _mm256_loadu_si256((__m256i*)(in))
norx.c: ^
norx.c: norx.c:657:3: error: always_inline function '_mm256_set_epi64x' requires target feature 'sse4.2', but would be inlined into function 'norx_aead_encrypt' that is compiled without support for 'sse4.2'
norx.c: norx.c:256:7: note: expanded from macro 'INITIALISE'
norx.c: C = _mm256_set_epi64x(U11, U10, U9, U8); \
norx.c: ^
norx.c: norx.c:657:3: error: always_inline function '_mm256_set_epi64x' requires target feature 'sse4.2', but would be inlined into function 'norx_aead_encrypt' that is compiled without support for 'sse4.2'
norx.c: norx.c:257:7: note: expanded from macro 'INITIALISE'
norx.c: D = _mm256_set_epi64x(U15, U14, U13, U12); \
norx.c: ^
norx.c: norx.c:657:3: error: always_inline function '_mm256_xor_si256' requires target feature 'sse4.2', but would be inlined into function 'norx_aead_encrypt' that is compiled without support for 'sse4.2'
norx.c: norx.c:258:7: note: expanded from macro 'INITIALISE'
norx.c: ...

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

Compiler	Implementations
clang -O3 -fomit-frame-pointer -Qunused-arguments	ymm
clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	ymm
clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	ymm
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	ymm

Compiler output

Implementation: crypto_aead/norx6444v3/ymm
Compiler: clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments

norx.c: norx.c:653:21: error: always_inline function '_mm256_loadu_si256' requires target feature 'xsave', but would be inlined into function 'norx_aead_encrypt' that is compiled without support for 'xsave'
norx.c: const __m256i K = LOADU(key);
norx.c: ^
norx.c: norx.c:45:19: note: expanded from macro 'LOADU'
norx.c: #define LOADU(in) _mm256_loadu_si256((__m256i*)(in))
norx.c: ^
norx.c: norx.c:657:3: error: always_inline function '_mm256_loadu_si256' requires target feature 'xsave', but would be inlined into function 'norx_aead_encrypt' that is compiled without support for 'xsave'
norx.c: INITIALISE(A, B, C, D, nonce, K);
norx.c: ^
norx.c: norx.c:254:7: note: expanded from macro 'INITIALISE'
norx.c: A = LOADU(NONCE); \
norx.c: ^
norx.c: norx.c:45:19: note: expanded from macro 'LOADU'
norx.c: #define LOADU(in) _mm256_loadu_si256((__m256i*)(in))
norx.c: ^
norx.c: norx.c:657:3: error: always_inline function '_mm256_set_epi64x' requires target feature 'xsave', but would be inlined into function 'norx_aead_encrypt' that is compiled without support for 'xsave'
norx.c: norx.c:256:7: note: expanded from macro 'INITIALISE'
norx.c: C = _mm256_set_epi64x(U11, U10, U9, U8); \
norx.c: ^
norx.c: norx.c:657:3: error: always_inline function '_mm256_set_epi64x' requires target feature 'xsave', but would be inlined into function 'norx_aead_encrypt' that is compiled without support for 'xsave'
norx.c: norx.c:257:7: note: expanded from macro 'INITIALISE'
norx.c: D = _mm256_set_epi64x(U15, U14, U13, U12); \
norx.c: ^
norx.c: norx.c:657:3: error: always_inline function '_mm256_xor_si256' requires target feature 'xsave', but would be inlined into function 'norx_aead_encrypt' that is compiled without support for 'xsave'
norx.c: norx.c:258:7: note: expanded from macro 'INITIALISE'
norx.c: ...

Number of similar (compiler,implementation) pairs: 2, namely:

Compiler	Implementations
clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments	ymm
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	ymm

Compiler output

Implementation: crypto_aead/norx6444v3/ymm
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer

norx.c: norx.c: In function 'norx_aead_encrypt':
norx.c: norx.c:653:17: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
norx.c: const __m256i K = LOADU(key);
norx.c: ^
norx.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:43:0,
norx.c: from norx.c:19:
norx.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
norx.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
norx.c: ^
norx.c: norx.c:258:5: error: called from here
norx.c: D = XOR(D, _mm256_set_epi64x(NORX_T, NORX_P, NORX_L, NORX_W)); \
norx.c: ^
norx.c: norx.c:657:3: note: in expansion of macro 'INITIALISE'
norx.c: INITIALISE(A, B, C, D, nonce, K);
norx.c: ^
norx.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:41:0,
norx.c: from norx.c:19:
norx.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/avxintrin.h:1270:1: error: inlining failed in call to always_inline '_mm256_set_epi64x': target specific option mismatch
norx.c: _mm256_set_epi64x (long long __A, long long __B, long long __C,
norx.c: ^
norx.c: norx.c:63:19: error: called from here
norx.c: #define XOR(A, B) _mm256_xor_si256((A), (B))
norx.c: ^
norx.c: norx.c:258:7: note: in expansion of macro 'XOR'
norx.c: D = XOR(D, _mm256_set_epi64x(NORX_T, NORX_P, NORX_L, NORX_W)); \
norx.c: ...
norx.c: norx.c: In function 'norx_aead_encrypt':
norx.c: norx.c:653:17: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
norx.c: const __m256i K = LOADU(key);
norx.c: ^
norx.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:43:0,
norx.c: from norx.c:19:
norx.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
norx.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
norx.c: ^
norx.c: norx.c:258:5: error: called from here
norx.c: D = XOR(D, _mm256_set_epi64x(NORX_T, NORX_P, NORX_L, NORX_W)); \
norx.c: ^
norx.c: norx.c:657:3: note: in expansion of macro 'INITIALISE'
norx.c: INITIALISE(A, B, C, D, nonce, K);
norx.c: ^
norx.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/5/include/immintrin.h:41:0,
norx.c: from norx.c:19:
norx.c: /usr/lib/gcc/x86_64-linux-gnu/5/include/avxintrin.h:1270:1: error: inlining failed in call to always_inline '_mm256_set_epi64x': target specific option mismatch
norx.c: _mm256_set_epi64x (long long __A, long long __B, long long __C,
norx.c: ^
norx.c: norx.c:63:19: error: called from here
norx.c: #define XOR(A, B) _mm256_xor_si256((A), (B))
norx.c: ^
norx.c: norx.c:258:7: note: in expansion of macro 'XOR'
norx.c: D = XOR(D, _mm256_set_epi64x(NORX_T, NORX_P, NORX_L, NORX_W)); \
norx.c: ...

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

Compiler	Implementations
gcc -m64 -march=barcelona -O2 -fomit-frame-pointer	ymm
gcc -m64 -march=barcelona -O3 -fomit-frame-pointer	ymm
gcc -m64 -march=barcelona -O -fomit-frame-pointer	ymm
gcc -m64 -march=barcelona -Os -fomit-frame-pointer	ymm