Implementation notes: amd64, morningstar, crypto_aead/norx6444v3

Computer: morningstar
Architecture: amd64
CPU ID: AuthenticAMD-00100f42-178bfbff
SUPERCOP version: 20170904
Operation: crypto_aead
Primitive: norx6444v3

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
49406	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O2_-fomit-frame-pointer`	20170728	20170718
49413	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=barcelona_-O2_-fomit-frame-pointer`	20170728	20170718
49432	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O2_-fomit-frame-pointer`	20170728	20170718
49469	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=k8_-O2_-fomit-frame-pointer`	20170728	20170718
49770	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-O3_-fomit-frame-pointer`	20170728	20170718
49776	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-O3_-fomit-frame-pointer`	20170728	20170718
49835	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20170728	20170718
49947	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-O2_-fomit-frame-pointer`	20170728	20170718
49964	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-O2_-fomit-frame-pointer`	20170728	20170718
49969	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20170728	20170718
50537	? ? ?	? ? ?	`ref`	`gcc_-m64_-O3_-fomit-frame-pointer`	20170728	20170718
50592	? ? ?	? ? ?	`ref`	`gcc_-O3_-fomit-frame-pointer`	20170728	20170718
50595	? ? ?	? ? ?	`ref`	`gcc_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20170728	20170718
50930	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O3_-fomit-frame-pointer`	20170728	20170718
50963	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=nocona_-O3_-fomit-frame-pointer`	20170728	20170718
51393	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=nocona_-O_-fomit-frame-pointer`	20170728	20170718
51483	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O_-fomit-frame-pointer`	20170728	20170718
51515	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-O_-fomit-frame-pointer`	20170728	20170718
51528	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-O_-fomit-frame-pointer`	20170728	20170718
51532	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O2_-fomit-frame-pointer`	20170728	20170718
51544	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer`	20170728	20170718
51559	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=barcelona_-O3_-fomit-frame-pointer`	20170728	20170718
51560	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=nocona_-O2_-fomit-frame-pointer`	20170728	20170718
51628	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O3_-fomit-frame-pointer`	20170728	20170718
51632	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-Os_-fomit-frame-pointer`	20170728	20170718
51652	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=k8_-O3_-fomit-frame-pointer`	20170728	20170718
51681	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O3_-fomit-frame-pointer`	20170728	20170718
51771	? ? ?	? ? ?	`ref`	`gcc_-march=k8_-O3_-fomit-frame-pointer`	20170728	20170718
51823	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=k8_-O3_-fomit-frame-pointer`	20170728	20170718
52029	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O_-fomit-frame-pointer`	20170728	20170718
52045	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=barcelona_-O_-fomit-frame-pointer`	20170728	20170718
52069	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-Os_-fomit-frame-pointer`	20170728	20170718
52069	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=k8_-O_-fomit-frame-pointer`	20170728	20170718
52077	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O_-fomit-frame-pointer`	20170728	20170718
52133	? ? ?	? ? ?	`ref`	`gcc_-march=barcelona_-O3_-fomit-frame-pointer`	20170728	20170718
52141	? ? ?	? ? ?	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv`	20170728	20170718
52159	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-Os_-fomit-frame-pointer`	20170728	20170718
52165	? ? ?	? ? ?	`ref`	`gcc_-march=nocona_-O3_-fomit-frame-pointer`	20170728	20170718
52167	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=barcelona_-O3_-fomit-frame-pointer`	20170728	20170718
52171	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=nocona_-O3_-fomit-frame-pointer`	20170728	20170718
52173	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer`	20170728	20170718
52176	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-Os_-fomit-frame-pointer`	20170728	20170718
52242	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=barcelona_-Os_-fomit-frame-pointer`	20170728	20170718
52317	? ? ?	? ? ?	`ref`	`gcc_-m64_-O2_-fomit-frame-pointer`	20170728	20170718
52319	? ? ?	? ? ?	`ref`	`gcc_-O2_-fomit-frame-pointer`	20170728	20170718
52345	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=k8_-Os_-fomit-frame-pointer`	20170728	20170718
52496	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20170728	20170718
52553	? ? ?	? ? ?	`ref`	`gcc_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20170728	20170718
52662	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-O2_-fomit-frame-pointer`	20170728	20170718
52664	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=corei7_-O2_-fomit-frame-pointer`	20170728	20170718
52752	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer`	20170728	20170718
53144	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer`	20170728	20170718
53371	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=k8_-O2_-fomit-frame-pointer`	20170728	20170718
53512	? ? ?	? ? ?	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv`	20170728	20170718
53570	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer`	20170728	20170718
53653	? ? ?	? ? ?	`ref`	`gcc_-march=barcelona_-O2_-fomit-frame-pointer`	20170728	20170718
53800	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=barcelona_-O_-fomit-frame-pointer`	20170728	20170718
53811	? ? ?	? ? ?	`ref`	`gcc_-march=barcelona_-O_-fomit-frame-pointer`	20170728	20170718
53846	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=barcelona_-O2_-fomit-frame-pointer`	20170728	20170718
53851	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer`	20170728	20170718
53909	? ? ?	? ? ?	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv`	20170728	20170718
54295	? ? ?	? ? ?	`ref`	`gcc_-march=k8_-O2_-fomit-frame-pointer`	20170728	20170718
54296	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=nocona_-O_-fomit-frame-pointer`	20170728	20170718
54326	? ? ?	? ? ?	`ref`	`gcc_-march=nocona_-O_-fomit-frame-pointer`	20170728	20170718
54338	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=corei7_-O_-fomit-frame-pointer`	20170728	20170718
54368	? ? ?	? ? ?	`ref`	`gcc_-march=k8_-O_-fomit-frame-pointer`	20170728	20170718
54394	? ? ?	? ? ?	`ref`	`gcc_-m64_-O_-fomit-frame-pointer`	20170728	20170718
54435	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer`	20170728	20170718
54448	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=k8_-O_-fomit-frame-pointer`	20170728	20170718
54450	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer`	20170728	20170718
54459	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-O_-fomit-frame-pointer`	20170728	20170718
54501	? ? ?	? ? ?	`ref`	`gcc_-fno-schedule-insns_-O_-fomit-frame-pointer`	20170728	20170718
54594	? ? ?	? ? ?	`ref`	`gcc_-O_-fomit-frame-pointer`	20170728	20170718
54763	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=nocona_-O2_-fomit-frame-pointer`	20170728	20170718
55034	? ? ?	? ? ?	`ref`	`gcc_-march=nocona_-O2_-fomit-frame-pointer`	20170728	20170718
57633	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer`	20170728	20170718
57643	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer`	20170728	20170718
57679	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=corei7_-Os_-fomit-frame-pointer`	20170728	20170718
57693	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=k8_-Os_-fomit-frame-pointer`	20170728	20170718
57723	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-Os_-fomit-frame-pointer`	20170728	20170718
57747	? ? ?	? ? ?	`ref`	`gcc_-march=k8_-Os_-fomit-frame-pointer`	20170728	20170718
57787	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=barcelona_-Os_-fomit-frame-pointer`	20170728	20170718
57853	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer`	20170728	20170718
57909	? ? ?	? ? ?	`ref`	`gcc_-march=barcelona_-Os_-fomit-frame-pointer`	20170728	20170718
57981	? ? ?	? ? ?	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv`	20170728	20170718
58039	? ? ?	? ? ?	`ref`	`gcc_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20170728	20170718
58046	? ? ?	? ? ?	`ref`	`gcc_-Os_-fomit-frame-pointer`	20170728	20170718
58083	? ? ?	? ? ?	`ref`	`gcc_-m64_-Os_-fomit-frame-pointer`	20170728	20170718
58432	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=nocona_-Os_-fomit-frame-pointer`	20170728	20170718
58632	? ? ?	? ? ?	`ref`	`gcc_-march=nocona_-Os_-fomit-frame-pointer`	20170728	20170718
58685	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=nocona_-Os_-fomit-frame-pointer`	20170728	20170718
59006	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-Os_-fomit-frame-pointer`	20170728	20170718
63391	? ? ?	? ? ?	`ref`	`clang_-mcpu=cortex-a9_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20170907	20170904
63428	? ? ?	? ? ?	`ref`	`clang_-O3_-fomit-frame-pointer_-Qunused-arguments`	20170907	20170904
63461	? ? ?	? ? ?	`ref`	`clang_-mcpu=cortex-a8_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20170907	20170904
63493	? ? ?	? ? ?	`ref`	`clang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20170907	20170904
71416	? ? ?	? ? ?	`ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments`	20170907	20170904
71453	? ? ?	? ? ?	`ref`	`clang_-O3_-fwrapv_-march=native_-fomit-frame-pointer_-Qunused-arguments`	20170907	20170904
293977	? ? ?	? ? ?	`ref`	`cc`	20170728	20170718
294138	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops`	20170728	20170718
296329	? ? ?	? ? ?	`ref`	`gcc`	20170728	20170718

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