Implementation notes: amd64, mace, crypto_aead/norx6444v3

Computer: mace
Architecture: amd64
CPU ID: AuthenticAMD-00040fb2-178bfbff
SUPERCOP version: 20170105
Operation: crypto_aead
Primitive: norx6444v3

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
50009	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=barcelona_-O2_-fomit-frame-pointer`	20161223	20161220
50013	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O2_-fomit-frame-pointer`	20161223	20161220
50050	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=k8_-O2_-fomit-frame-pointer`	20161223	20161220
50222	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O2_-fomit-frame-pointer`	20161223	20161220
50543	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20161223	20161220
50634	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-O3_-fomit-frame-pointer`	20161223	20161220
50687	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-O3_-fomit-frame-pointer`	20161223	20161220
50704	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-O2_-fomit-frame-pointer`	20161223	20161220
50725	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20161223	20161220
50727	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-O2_-fomit-frame-pointer`	20161223	20161220
51392	? ? ?	? ? ?	`ref`	`gcc_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20161223	20161220
51404	? ? ?	? ? ?	`ref`	`gcc_-O3_-fomit-frame-pointer`	20161223	20161220
51495	? ? ?	? ? ?	`ref`	`gcc_-m64_-O3_-fomit-frame-pointer`	20161223	20161220
51822	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-O_-fomit-frame-pointer`	20161223	20161220
51839	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=nocona_-O2_-fomit-frame-pointer`	20161223	20161220
51847	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O3_-fomit-frame-pointer`	20161223	20161220
51866	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=nocona_-O3_-fomit-frame-pointer`	20161223	20161220
51885	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=nocona_-O_-fomit-frame-pointer`	20161223	20161220
51901	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O_-fomit-frame-pointer`	20161223	20161220
51932	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-O_-fomit-frame-pointer`	20161223	20161220
51938	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer`	20161223	20161220
52037	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O2_-fomit-frame-pointer`	20161223	20161220
52361	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=k8_-O_-fomit-frame-pointer`	20161223	20161220
52389	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O_-fomit-frame-pointer`	20161223	20161220
52483	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O_-fomit-frame-pointer`	20161223	20161220
52559	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=barcelona_-O_-fomit-frame-pointer`	20161223	20161220
52589	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=k8_-O3_-fomit-frame-pointer`	20161223	20161220
52608	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O3_-fomit-frame-pointer`	20161223	20161220
52725	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=k8_-O3_-fomit-frame-pointer`	20161223	20161220
52732	? ? ?	? ? ?	`ref`	`gcc_-march=k8_-O3_-fomit-frame-pointer`	20161223	20161220
52743	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=barcelona_-O3_-fomit-frame-pointer`	20161223	20161220
52745	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O3_-fomit-frame-pointer`	20161223	20161220
52765	? ? ?	? ? ?	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv`	20161223	20161220
52778	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer`	20161223	20161220
52969	? ? ?	? ? ?	`ref`	`gcc_-march=barcelona_-O3_-fomit-frame-pointer`	20161223	20161220
53005	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=nocona_-O3_-fomit-frame-pointer`	20161223	20161220
53049	? ? ?	? ? ?	`ref`	`gcc_-march=nocona_-O3_-fomit-frame-pointer`	20161223	20161220
53061	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=barcelona_-O3_-fomit-frame-pointer`	20161223	20161220
53534	? ? ?	? ? ?	`ref`	`gcc_-O2_-fomit-frame-pointer`	20161223	20161220
53654	? ? ?	? ? ?	`ref`	`gcc_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20161223	20161220
53687	? ? ?	? ? ?	`ref`	`gcc_-m64_-O2_-fomit-frame-pointer`	20161223	20161220
54114	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer`	20161223	20161220
54130	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=k8_-O2_-fomit-frame-pointer`	20161223	20161220
54221	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer`	20161223	20161220
54225	? ? ?	? ? ?	`ref`	`gcc_-march=k8_-O2_-fomit-frame-pointer`	20161223	20161220
54280	? ? ?	? ? ?	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv`	20161223	20161220
54337	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-O2_-fomit-frame-pointer`	20161223	20161220
54375	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=corei7_-O2_-fomit-frame-pointer`	20161223	20161220
54380	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer`	20161223	20161220
54906	? ? ?	? ? ?	`ref`	`gcc_-march=barcelona_-O2_-fomit-frame-pointer`	20161223	20161220
54913	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=barcelona_-O2_-fomit-frame-pointer`	20161223	20161220
55086	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=barcelona_-O_-fomit-frame-pointer`	20161223	20161220
55088	? ? ?	? ? ?	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv`	20161223	20161220
55127	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-Os_-fomit-frame-pointer`	20161223	20161220
55181	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=k8_-O_-fomit-frame-pointer`	20161223	20161220
55196	? ? ?	? ? ?	`ref`	`gcc_-march=barcelona_-O_-fomit-frame-pointer`	20161223	20161220
55216	? ? ?	? ? ?	`ref`	`gcc_-march=k8_-O_-fomit-frame-pointer`	20161223	20161220
55244	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer`	20161223	20161220
55978	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=nocona_-O2_-fomit-frame-pointer`	20161223	20161220
56009	? ? ?	? ? ?	`ref`	`gcc_-march=nocona_-O2_-fomit-frame-pointer`	20161223	20161220
56055	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=k8_-Os_-fomit-frame-pointer`	20161223	20161220
56087	? ? ?	? ? ?	`ref`	`gcc_-fno-schedule-insns_-O_-fomit-frame-pointer`	20161223	20161220
56117	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=corei7_-O_-fomit-frame-pointer`	20161223	20161220
56118	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer`	20161223	20161220
56140	? ? ?	? ? ?	`ref`	`gcc_-march=nocona_-O_-fomit-frame-pointer`	20161223	20161220
56169	? ? ?	? ? ?	`ref`	`gcc_-O_-fomit-frame-pointer`	20161223	20161220
56184	? ? ?	? ? ?	`ref`	`gcc_-m64_-O_-fomit-frame-pointer`	20161223	20161220
56193	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=nocona_-O_-fomit-frame-pointer`	20161223	20161220
56246	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-O_-fomit-frame-pointer`	20161223	20161220
56264	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer`	20161223	20161220
56391	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-Os_-fomit-frame-pointer`	20161223	20161220
56407	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20161223	20161220
56429	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=barcelona_-Os_-fomit-frame-pointer`	20161223	20161220
56454	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-Os_-fomit-frame-pointer`	20161223	20161220
56469	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-Os_-fomit-frame-pointer`	20161223	20161220
60098	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=k8_-Os_-fomit-frame-pointer`	20161223	20161220
60249	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer`	20161223	20161220
60708	? ? ?	? ? ?	`ref`	`gcc_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20161223	20161220
60712	? ? ?	? ? ?	`ref`	`gcc_-m64_-Os_-fomit-frame-pointer`	20161223	20161220
60729	? ? ?	? ? ?	`ref`	`gcc_-march=barcelona_-Os_-fomit-frame-pointer`	20161223	20161220
60951	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer`	20161223	20161220
60975	? ? ?	? ? ?	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv`	20161223	20161220
60982	? ? ?	? ? ?	`ref`	`gcc_-march=k8_-Os_-fomit-frame-pointer`	20161223	20161220
61168	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer`	20161223	20161220
61176	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-Os_-fomit-frame-pointer`	20161223	20161220
61176	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=corei7_-Os_-fomit-frame-pointer`	20161223	20161220
61581	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=barcelona_-Os_-fomit-frame-pointer`	20161223	20161220
61644	? ? ?	? ? ?	`ref`	`gcc_-Os_-fomit-frame-pointer`	20161223	20161220
61991	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=nocona_-Os_-fomit-frame-pointer`	20161223	20161220
62879	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-Os_-fomit-frame-pointer`	20161223	20161220
63269	? ? ?	? ? ?	`ref`	`gcc_-march=nocona_-Os_-fomit-frame-pointer`	20161223	20161220
63276	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=nocona_-Os_-fomit-frame-pointer`	20161223	20161220
83020	? ? ?	? ? ?	`ref`	`clang_-mcpu=cortex-a8_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20161223	20161220
83037	? ? ?	? ? ?	`ref`	`clang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20161223	20161220
83044	? ? ?	? ? ?	`ref`	`clang_-O3_-fomit-frame-pointer_-Qunused-arguments`	20161223	20161220
83094	? ? ?	? ? ?	`ref`	`clang_-mcpu=cortex-a9_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20161223	20161220
93908	? ? ?	? ? ?	`ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20161223	20161220
94587	? ? ?	? ? ?	`ref`	`clang_-O3_-fwrapv_-march=native_-fomit-frame-pointer_-Qunused-arguments`	20161223	20161220
433611	? ? ?	? ? ?	`ref`	`gcc`	20161223	20161220
439529	? ? ?	? ? ?	`ref`	`cc`	20161223	20161220
439641	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops`	20161223	20161220

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