Implementation notes: amd64, glyme, crypto_aead/norx6441v2

Computer: glyme
Architecture: amd64
CPU ID: GenuineIntel-00020652-bfebfbff
SUPERCOP version: 201720170105
Operation: crypto_aead
Primitive: norx6441v2
TimeImplementationCompilerBenchmark dateSUPERCOP version
23216xmmgcc -m64 -march=corei7 -O3 -fomit-frame-pointer2017020420170105
23216xmmgcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer2017020420170105
23216xmmgcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2017020420170105
23340xmmgcc -m64 -march=core2 -O3 -fomit-frame-pointer2017020420170105
23340xmmgcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer2017020420170105
23412xmmgcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer2017020420170105
23740xmmgcc -m64 -march=core2 -O -fomit-frame-pointer2017020420170105
23740xmmgcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer2017020420170105
23740xmmgcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer2017020420170105
23740xmmgcc -m64 -march=corei7 -O -fomit-frame-pointer2017020420170105
23740xmmgcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2017020420170105
23760xmmgcc -m64 -march=native -mtune=native -O -fomit-frame-pointer2017020420170105
24500xmmgcc -m64 -march=corei7 -O2 -fomit-frame-pointer2017020420170105
24500xmmgcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer2017020420170105
24508xmmgcc -m64 -march=core2 -O2 -fomit-frame-pointer2017020420170105
24508xmmgcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2017020420170105
24616xmmgcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2017020420170105
24632xmmgcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer2017020420170105
25296xmmclang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments2017020420170105
25296xmmclang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2017020420170105
28100xmmgcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer2017020420170105
28100xmmgcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer2017020420170105
28116xmmgcc -m64 -march=nocona -O3 -fomit-frame-pointer2017020420170105
28116xmmgcc -march=nocona -O3 -fomit-frame-pointer2017020420170105
28216xmmgcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer2017020420170105
28216xmmgcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer2017020420170105
29092xmmgcc -m64 -march=nocona -O2 -fomit-frame-pointer2017020420170105
29092xmmgcc -march=nocona -O2 -fomit-frame-pointer2017020420170105
29124xmmgcc -funroll-loops -march=nocona -O -fomit-frame-pointer2017020420170105
29128xmmgcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer2017020420170105
29148xmmgcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer2017020420170105
29148xmmgcc -funroll-loops -march=k8 -O -fomit-frame-pointer2017020420170105
29304xmmgcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer2017020420170105
29304xmmgcc -funroll-loops -march=barcelona -O -fomit-frame-pointer2017020420170105
29332xmmgcc -m64 -march=nocona -O -fomit-frame-pointer2017020420170105
29332xmmgcc -march=nocona -O -fomit-frame-pointer2017020420170105
29344xmmgcc -m64 -march=k8 -O -fomit-frame-pointer2017020420170105
29344xmmgcc -march=k8 -O -fomit-frame-pointer2017020420170105
29380xmmgcc -fno-schedule-insns -O -fomit-frame-pointer2017020420170105
29484xmmgcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer2017020420170105
29492xmmgcc -funroll-loops -O -fomit-frame-pointer2017020420170105
29492xmmgcc -funroll-loops -m64 -O -fomit-frame-pointer2017020420170105
29500xmmgcc -m64 -O -fomit-frame-pointer2017020420170105
29644xmmgcc -O -fomit-frame-pointer2017020420170105
29728xmmgcc -m64 -march=barcelona -O -fomit-frame-pointer2017020420170105
29728xmmgcc -march=barcelona -O -fomit-frame-pointer2017020420170105
29800xmmgcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer2017020420170105
29816xmmgcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer2017020420170105
29828xmmgcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer2017020420170105
29840xmmgcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer2017020420170105
30156xmmgcc -march=barcelona -O3 -fomit-frame-pointer2017020420170105
30160xmmgcc -m64 -march=barcelona -O3 -fomit-frame-pointer2017020420170105
30172xmmgcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer2017020420170105
30200xmmgcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer2017020420170105
30204xmmgcc -funroll-loops -O3 -fomit-frame-pointer2017020420170105
30208xmmgcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer2017020420170105
30208xmmgcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer2017020420170105
30216xmmgcc -m64 -march=k8 -O3 -fomit-frame-pointer2017020420170105
30216xmmgcc -march=k8 -O3 -fomit-frame-pointer2017020420170105
30224xmmgcc -funroll-loops -m64 -O3 -fomit-frame-pointer2017020420170105
30232xmmgcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer2017020420170105
30240xmmgcc -funroll-loops -O2 -fomit-frame-pointer2017020420170105
30240xmmgcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer2017020420170105
30240xmmgcc -funroll-loops -m64 -O2 -fomit-frame-pointer2017020420170105
30324xmmgcc -O3 -fomit-frame-pointer2017020420170105
30324xmmgcc -fno-schedule-insns -O3 -fomit-frame-pointer2017020420170105
30324xmmgcc -m64 -O3 -fomit-frame-pointer2017020420170105
30640xmmgcc -m64 -march=barcelona -O2 -fomit-frame-pointer2017020420170105
30640xmmgcc -march=barcelona -O2 -fomit-frame-pointer2017020420170105
31084xmmgcc -O2 -fomit-frame-pointer2017020420170105
31084xmmgcc -m64 -O2 -fomit-frame-pointer2017020420170105
31112xmmgcc -fno-schedule-insns -O2 -fomit-frame-pointer2017020420170105
31280xmmgcc -march=k8 -O2 -fomit-frame-pointer2017020420170105
31284xmmgcc -m64 -march=k8 -O2 -fomit-frame-pointer2017020420170105
37696refgcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer2017020420170105
37784refgcc -funroll-loops -O3 -fomit-frame-pointer2017020420170105
37784refgcc -funroll-loops -m64 -O3 -fomit-frame-pointer2017020420170105
38028refgcc -m64 -march=barcelona -O3 -fomit-frame-pointer2017020420170105
38060refgcc -march=barcelona -O3 -fomit-frame-pointer2017020420170105
38176refgcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer2017020420170105
38188refgcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer2017020420170105
38344refgcc -fno-schedule-insns -O3 -fomit-frame-pointer2017020420170105
38380refgcc -O3 -fomit-frame-pointer2017020420170105
38380refgcc -funroll-loops -O2 -fomit-frame-pointer2017020420170105
38380refgcc -funroll-loops -m64 -O2 -fomit-frame-pointer2017020420170105
38380refgcc -m64 -O3 -fomit-frame-pointer2017020420170105
38408refgcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer2017020420170105
38424refgcc -m64 -march=corei7 -O3 -fomit-frame-pointer2017020420170105
38424refgcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer2017020420170105
38424refgcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv2017020420170105
38596refgcc -m64 -march=core2 -O3 -fomit-frame-pointer2017020420170105
38636refgcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer2017020420170105
38704refgcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer2017020420170105
38784refgcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer2017020420170105
38788refgcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer2017020420170105
38864xmmclang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2017020420170105
38864refgcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer2017020420170105
38888xmmclang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2017020420170105
38904xmmclang -O3 -fomit-frame-pointer -Qunused-arguments2017020420170105
38908xmmclang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2017020420170105
38920refgcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer2017020420170105
38940refgcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer2017020420170105
39008refgcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer2017020420170105
39008refgcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer2017020420170105
39072refgcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer2017020420170105
39084refgcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer2017020420170105
39152refgcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer2017020420170105
39156refgcc -m64 -march=k8 -O3 -fomit-frame-pointer2017020420170105
39156refgcc -march=k8 -O3 -fomit-frame-pointer2017020420170105
39168refgcc -funroll-loops -march=k8 -O -fomit-frame-pointer2017020420170105
39176refgcc -funroll-loops -march=barcelona -O -fomit-frame-pointer2017020420170105
39356refgcc -m64 -march=nocona -O3 -fomit-frame-pointer2017020420170105
39356refgcc -march=nocona -O3 -fomit-frame-pointer2017020420170105
39400refgcc -funroll-loops -march=nocona -O -fomit-frame-pointer2017020420170105
39472refgcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer2017020420170105
39596refgcc -funroll-loops -m64 -O -fomit-frame-pointer2017020420170105
39624refgcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer2017020420170105
39660refgcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer2017020420170105
39668refgcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer2017020420170105
39800refgcc -funroll-loops -O -fomit-frame-pointer2017020420170105
39872refgcc -march=k8 -O2 -fomit-frame-pointer2017020420170105
39908refgcc -m64 -march=k8 -O2 -fomit-frame-pointer2017020420170105
39912refgcc -m64 -march=corei7 -O2 -fomit-frame-pointer2017020420170105
39952refgcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer2017020420170105
39952refgcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv2017020420170105
39984refgcc -m64 -march=barcelona -O2 -fomit-frame-pointer2017020420170105
40008refgcc -O2 -fomit-frame-pointer2017020420170105
40008refgcc -m64 -O2 -fomit-frame-pointer2017020420170105
40016refgcc -march=barcelona -O2 -fomit-frame-pointer2017020420170105
40060refgcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer2017020420170105
40060refgcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer2017020420170105
40068refgcc -O -fomit-frame-pointer2017020420170105
40068refgcc -m64 -O -fomit-frame-pointer2017020420170105
40072refgcc -m64 -march=core2 -O -fomit-frame-pointer2017020420170105
40072refgcc -m64 -march=corei7 -O -fomit-frame-pointer2017020420170105
40076refgcc -fno-schedule-insns -O2 -fomit-frame-pointer2017020420170105
40080refgcc -m64 -march=core2 -O2 -fomit-frame-pointer2017020420170105
40080refgcc -m64 -march=native -mtune=native -O -fomit-frame-pointer2017020420170105
40100refgcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer2017020420170105
40100refgcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer2017020420170105
40116refgcc -fno-schedule-insns -O -fomit-frame-pointer2017020420170105
40176refgcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv2017020420170105
40304refgcc -march=nocona -O -fomit-frame-pointer2017020420170105
40340refgcc -m64 -march=barcelona -O -fomit-frame-pointer2017020420170105
40340refgcc -march=barcelona -O -fomit-frame-pointer2017020420170105
40628refgcc -m64 -march=k8 -O -fomit-frame-pointer2017020420170105
40628refgcc -m64 -march=nocona -O -fomit-frame-pointer2017020420170105
40628refgcc -march=k8 -O -fomit-frame-pointer2017020420170105
40864refgcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer2017020420170105
40880refgcc -funroll-loops -march=k8 -Os -fomit-frame-pointer2017020420170105
41048refgcc -m64 -march=nocona -O2 -fomit-frame-pointer2017020420170105
41052refgcc -funroll-loops -Os -fomit-frame-pointer2017020420170105
41052refgcc -funroll-loops -m64 -Os -fomit-frame-pointer2017020420170105
41072refgcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer2017020420170105
41288refgcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer2017020420170105
41288refgcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer2017020420170105
41460refgcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer2017020420170105
41460refgcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer2017020420170105
41476refgcc -march=nocona -O2 -fomit-frame-pointer2017020420170105
41480refgcc -m64 -march=core2 -Os -fomit-frame-pointer2017020420170105
41540refgcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2017020420170105
41684refgcc -m64 -march=corei7 -Os -fomit-frame-pointer2017020420170105
41692refgcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer2017020420170105
41728refgcc -march=k8 -Os -fomit-frame-pointer2017020420170105
41756refgcc -m64 -march=k8 -Os -fomit-frame-pointer2017020420170105
41772refgcc -march=barcelona -Os -fomit-frame-pointer2017020420170105
41812refgcc -m64 -march=barcelona -Os -fomit-frame-pointer2017020420170105
41872refgcc -fno-schedule-insns -Os -fomit-frame-pointer2017020420170105
41916xmmgcc -m64 -march=corei7 -Os -fomit-frame-pointer2017020420170105
41916xmmgcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer2017020420170105
41916xmmgcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv2017020420170105
41924xmmgcc -m64 -march=core2 -Os -fomit-frame-pointer2017020420170105
41924xmmgcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer2017020420170105
41968refgcc -Os -fomit-frame-pointer2017020420170105
41968refgcc -m64 -Os -fomit-frame-pointer2017020420170105
42256xmmgcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer2017020420170105
42420refgcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer2017020420170105
42432refgcc -march=nocona -Os -fomit-frame-pointer2017020420170105
42448refgcc -m64 -march=nocona -Os -fomit-frame-pointer2017020420170105
42460refgcc -funroll-loops -march=nocona -Os -fomit-frame-pointer2017020420170105
42988refclang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2017020420170105
43036refclang -O3 -fomit-frame-pointer -Qunused-arguments2017020420170105
43100refclang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments2017020420170105
43100refclang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2017020420170105
43132refclang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2017020420170105
43132refclang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments2017020420170105
47120xmmgcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer2017020420170105
47120xmmgcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer2017020420170105
47956xmmgcc -m64 -march=barcelona -Os -fomit-frame-pointer2017020420170105
48028xmmgcc -march=barcelona -Os -fomit-frame-pointer2017020420170105
48428xmmgcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer2017020420170105
48456xmmgcc -funroll-loops -march=nocona -Os -fomit-frame-pointer2017020420170105
48468xmmgcc -march=nocona -Os -fomit-frame-pointer2017020420170105
48472xmmgcc -m64 -march=nocona -Os -fomit-frame-pointer2017020420170105
49940xmmgcc -funroll-loops -Os -fomit-frame-pointer2017020420170105
49940xmmgcc -funroll-loops -m64 -Os -fomit-frame-pointer2017020420170105
49940xmmgcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer2017020420170105
49944xmmgcc -Os -fomit-frame-pointer2017020420170105
49944xmmgcc -fno-schedule-insns -Os -fomit-frame-pointer2017020420170105
49944xmmgcc -m64 -Os -fomit-frame-pointer2017020420170105
49944xmmgcc -m64 -march=k8 -Os -fomit-frame-pointer2017020420170105
49944xmmgcc -march=k8 -Os -fomit-frame-pointer2017020420170105
50060xmmgcc -funroll-loops -march=k8 -Os -fomit-frame-pointer2017020420170105
50332xmmgcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer2017020420170105
245236xmmcc2017020420170105
251664xmmgcc2017020420170105
252284xmmgcc -funroll-loops2017020420170105
253100refgcc -funroll-loops2017020420170105
253300refgcc2017020420170105
262188refcc2017020420170105

Compiler output

Implementation: crypto_aead/norx6441v2/ymm
Compiler: cc
norx.c: norx.c:388:5: 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: INITIALISE(A, B, C, D, nonce, key);
norx.c: ^
norx.c: norx.c:289:28: note: expanded from macro 'INITIALISE'
norx.c: A = _mm256_blend_epi32(_mm256_set_epi64x(U3, U2, 0, 0), \
norx.c: ^
norx.c: norx.c:388:5: error: always_inline function '_mm256_castsi128_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:290:28: note: expanded from macro 'INITIALISE'
norx.c: _mm256_castsi128_si256(LOADU128(NONCE)), 0x0F); \
norx.c: ^
norx.c: norx.c:388:5: 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: norx.c:291:9: note: expanded from macro 'INITIALISE'
norx.c: B = LOADU(KEY); \
norx.c: ^
norx.c: norx.c:53:19: note: expanded from macro 'LOADU'
norx.c: #define LOADU(in) _mm256_loadu_si256((__m256i*)(in))
norx.c: ^
norx.c: norx.c:388:5: 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:292:9: note: expanded from macro 'INITIALISE'
norx.c: C = _mm256_set_epi64x(U11, U10, U9, U8); \
norx.c: ^
norx.c: norx.c:388:5: 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:293:9: note: expanded from macro 'INITIALISE'
norx.c: D = _mm256_set_epi64x(U15, U14, U13, U12); \
norx.c: ^
norx.c: ...

Number of similar (compiler,implementation) pairs: 5, namely:
CompilerImplementations
cc ymm
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/norx6441v2/ymm
Compiler: clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments
norx.c: norx.c:388:5: 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: INITIALISE(A, B, C, D, nonce, key);
norx.c: ^
norx.c: norx.c:289:28: note: expanded from macro 'INITIALISE'
norx.c: A = _mm256_blend_epi32(_mm256_set_epi64x(U3, U2, 0, 0), \
norx.c: ^
norx.c: norx.c:388:5: error: always_inline function '_mm256_castsi128_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:290:28: note: expanded from macro 'INITIALISE'
norx.c: _mm256_castsi128_si256(LOADU128(NONCE)), 0x0F); \
norx.c: ^
norx.c: norx.c:388:5: 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: norx.c:291:9: note: expanded from macro 'INITIALISE'
norx.c: B = LOADU(KEY); \
norx.c: ^
norx.c: norx.c:53:19: note: expanded from macro 'LOADU'
norx.c: #define LOADU(in) _mm256_loadu_si256((__m256i*)(in))
norx.c: ^
norx.c: norx.c:388:5: 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:292:9: note: expanded from macro 'INITIALISE'
norx.c: C = _mm256_set_epi64x(U11, U10, U9, U8); \
norx.c: ^
norx.c: norx.c:388:5: 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:293:9: note: expanded from macro 'INITIALISE'
norx.c: D = _mm256_set_epi64x(U15, U14, U13, U12); \
norx.c: ^
norx.c: ...

Number of similar (compiler,implementation) pairs: 2, namely:
CompilerImplementations
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/norx6441v2/ymm
Compiler: gcc
norx.c: In file included from /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/immintrin.h:43:0,
norx.c: from norx.c:25:
norx.c: norx.c: In function 'norx_aead_encrypt':
norx.c: norx.c:290:28: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
norx.c: _mm256_castsi128_si256(LOADU128(NONCE)), 0x0F); \
norx.c: ^
norx.c: norx.c:388:5: note: in expansion of macro 'INITIALISE'
norx.c: INITIALISE(A, B, C, D, nonce, key);
norx.c: ^~~~~~~~~~
norx.c: /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/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:294:7: note: 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:388:5: note: in expansion of macro 'INITIALISE'
norx.c: INITIALISE(A, B, C, D, nonce, key);
norx.c: ^~~~~~~~~~
norx.c: In file included from /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/immintrin.h:41:0,
norx.c: from norx.c:25:
norx.c: /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/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:72:19: note: called from here
norx.c: #define XOR(A, B) _mm256_xor_si256((A), (B))
norx.c: ...

Number of similar (compiler,implementation) pairs: 2, namely:
CompilerImplementations
gcc ymm
gcc -funroll-loops ymm

Compiler output

Implementation: crypto_aead/norx6441v2/ymm
Compiler: gcc -O2 -fomit-frame-pointer
norx.c: norx.c: In function 'norx_aead_encrypt':
norx.c: norx.c:289:7: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
norx.c: A = _mm256_blend_epi32(_mm256_set_epi64x(U3, U2, 0, 0), \
norx.c: ^
norx.c: norx.c:388:5: note: in expansion of macro 'INITIALISE'
norx.c: INITIALISE(A, B, C, D, nonce, key);
norx.c: ^~~~~~~~~~
norx.c: In file included from /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/immintrin.h:43:0,
norx.c: from norx.c:25:
norx.c: /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/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:294:7: note: 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:388:5: note: in expansion of macro 'INITIALISE'
norx.c: INITIALISE(A, B, C, D, nonce, key);
norx.c: ^~~~~~~~~~
norx.c: In file included from /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/immintrin.h:41:0,
norx.c: from norx.c:25:
norx.c: /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/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:72:19: note: called from here
norx.c: #define XOR(A, B) _mm256_xor_si256((A), (B))
norx.c: ...

Number of similar (compiler,implementation) pairs: 92, namely:
CompilerImplementations
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 -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 -O3 -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 -O3 -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 -O3 -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/norx6441v2/ymm
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer
norx.c: norx.c: In function 'norx_aead_encrypt':
norx.c: norx.c:289:7: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
norx.c: A = _mm256_blend_epi32(_mm256_set_epi64x(U3, U2, 0, 0), \
norx.c: ^
norx.c: norx.c:388:5: note: in expansion of macro 'INITIALISE'
norx.c: INITIALISE(A, B, C, D, nonce, key);
norx.c: ^~~~~~~~~~
norx.c: In file included from /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/immintrin.h:43:0,
norx.c: from norx.c:25:
norx.c: /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/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:294:7: note: 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:388:5: note: in expansion of macro 'INITIALISE'
norx.c: INITIALISE(A, B, C, D, nonce, key);
norx.c: ^~~~~~~~~~
norx.c: In file included from /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/immintrin.h:41:0,
norx.c: from norx.c:25:
norx.c: /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/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:72:19: note: called from here
norx.c: #define XOR(A, B) _mm256_xor_si256((A), (B))
norx.c: ...
norx.c: norx.c: In function 'norx_aead_encrypt':
norx.c: norx.c:289:7: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
norx.c: A = _mm256_blend_epi32(_mm256_set_epi64x(U3, U2, 0, 0), \
norx.c: ^
norx.c: norx.c:388:5: note: in expansion of macro 'INITIALISE'
norx.c: INITIALISE(A, B, C, D, nonce, key);
norx.c: ^~~~~~~~~~
norx.c: In file included from /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/immintrin.h:43:0,
norx.c: from norx.c:25:
norx.c: /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/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:294:7: note: 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:388:5: note: in expansion of macro 'INITIALISE'
norx.c: INITIALISE(A, B, C, D, nonce, key);
norx.c: ^~~~~~~~~~
norx.c: In file included from /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/include/immintrin.h:41:0,
norx.c: from norx.c:25:
norx.c: /usr/local/lib/gcc6/gcc/x86_64-portbld-freebsd11.0/6.3.0/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:72:19: note: called from here
norx.c: #define XOR(A, B) _mm256_xor_si256((A), (B))
norx.c: ...

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