Implementation notes: amd64, manny613, crypto_kem/newhope1024cca

Computer: manny613
Architecture: amd64
CPU ID: GenuineIntel-000306e4-bfebfbff
SUPERCOP version: 20180818
Operation: crypto_kem
Primitive: newhope1024cca

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
964824	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=barcelona_-O3_-fomit-frame-pointer`	20180903	20180818
965040	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O3_-fomit-frame-pointer`	20180903	20180818
970772	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O3_-fomit-frame-pointer`	20180903	20180818
971668	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=k8_-O3_-fomit-frame-pointer`	20180903	20180818
979068	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core-avx-i_-O3_-fomit-frame-pointer`	20180903	20180818
982420	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=corei7-avx_-O3_-fomit-frame-pointer`	20180903	20180818
984500	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=native_-mtune=native_-O3_-fomit-frame-pointer`	20180903	20180818
987296	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O3_-fomit-frame-pointer`	20180903	20180818
987664	? ? ?	? ? ?	`ref`	`icc_-xSSE4.2_-O2_-fomit-frame-pointer`	20180903	20180818
992844	? ? ?	? ? ?	`ref`	`gcc_-march=barcelona_-O3_-fomit-frame-pointer`	20180903	20180818
992876	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=barcelona_-O3_-fomit-frame-pointer`	20180903	20180818
994280	? ? ?	? ? ?	`ref`	`icc_-xSSE4.1_-O2_-fomit-frame-pointer`	20180903	20180818
995640	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-O3_-fomit-frame-pointer`	20180903	20180818
996040	? ? ?	? ? ?	`ref`	`icc`	20180903	20180818
996808	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=k8_-O3_-fomit-frame-pointer`	20180903	20180818
997040	? ? ?	? ? ?	`ref`	`gcc_-march=k8_-O3_-fomit-frame-pointer`	20180903	20180818
1004980	? ? ?	? ? ?	`ref`	`gcc_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20180903	20180818
1005220	? ? ?	? ? ?	`ref`	`gcc_-O3_-fomit-frame-pointer`	20180903	20180818
1007960	? ? ?	? ? ?	`ref`	`gcc_-m64_-O3_-fomit-frame-pointer`	20180903	20180818
1020356	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-O3_-fomit-frame-pointer`	20180903	20180818
1020548	? ? ?	? ? ?	`ref`	`icc_-xCORE-AVX-I_-O2_-fomit-frame-pointer`	20180903	20180818
1021100	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-O3_-fomit-frame-pointer`	20180903	20180818
1021584	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20180903	20180818
1021652	? ? ?	? ? ?	`ref`	`icc_-xAVX_-O2_-fomit-frame-pointer`	20180903	20180818
1026148	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=corei7_-O3_-fomit-frame-pointer`	20180903	20180818
1028792	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-msse4_-O3_-fomit-frame-pointer`	20180903	20180818
1070212	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O2_-fomit-frame-pointer`	20180903	20180818
1073764	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=k8_-O2_-fomit-frame-pointer`	20180903	20180818
1075020	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O2_-fomit-frame-pointer`	20180903	20180818
1075848	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=barcelona_-O2_-fomit-frame-pointer`	20180903	20180818
1085988	? ? ?	? ? ?	`ref`	`icc_-xSSE4.1_-O3_-fomit-frame-pointer`	20180903	20180818
1089632	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=nocona_-O3_-fomit-frame-pointer`	20180903	20180818
1090344	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O3_-fomit-frame-pointer`	20180903	20180818
1092788	? ? ?	? ? ?	`ref`	`icc_-xSSE4.2_-O3_-fomit-frame-pointer`	20180903	20180818
1115692	? ? ?	? ? ?	`ref`	`gcc_-march=nocona_-O3_-fomit-frame-pointer`	20180903	20180818
1116228	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=nocona_-O3_-fomit-frame-pointer`	20180903	20180818
1121804	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-O2_-fomit-frame-pointer`	20180903	20180818
1122860	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20180903	20180818
1122892	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-O2_-fomit-frame-pointer`	20180903	20180818
1127960	? ? ?	? ? ?	`ref`	`icc_-no-vec`	20180903	20180818
1145028	? ? ?	? ? ?	`ref`	`icc_-xAVX_-O3_-fomit-frame-pointer`	20180903	20180818
1147780	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-O_-fomit-frame-pointer`	20180903	20180818
1148080	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-O_-fomit-frame-pointer`	20180903	20180818
1150072	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer`	20180903	20180818
1150452	? ? ?	? ? ?	`ref`	`icc_-xCORE-AVX-I_-O3_-fomit-frame-pointer`	20180903	20180818
1151256	? ? ?	? ? ?	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv`	20180903	20180818
1175724	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-O_-fomit-frame-pointer`	20180903	20180818
1175944	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-O_-fomit-frame-pointer`	20180903	20180818
1176532	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=k8_-O_-fomit-frame-pointer`	20180903	20180818
1177176	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=barcelona_-O_-fomit-frame-pointer`	20180903	20180818
1181940	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=nocona_-O2_-fomit-frame-pointer`	20180903	20180818
1182072	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O2_-fomit-frame-pointer`	20180903	20180818
1196984	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-O_-fomit-frame-pointer`	20180903	20180818
1198992	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=nocona_-O_-fomit-frame-pointer`	20180903	20180818
1345196	? ? ?	? ? ?	`ref`	`gcc_-march=barcelona_-O2_-fomit-frame-pointer`	20180903	20180818
1348444	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=barcelona_-O2_-fomit-frame-pointer`	20180903	20180818
1366660	? ? ?	? ? ?	`ref`	`gcc_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20180903	20180818
1367540	? ? ?	? ? ?	`ref`	`gcc_-O2_-fomit-frame-pointer`	20180903	20180818
1368504	? ? ?	? ? ?	`ref`	`gcc_-m64_-O2_-fomit-frame-pointer`	20180903	20180818
1399672	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=k8_-O_-fomit-frame-pointer`	20180903	20180818
1399968	? ? ?	? ? ?	`ref`	`gcc_-march=k8_-O_-fomit-frame-pointer`	20180903	20180818
1424112	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core-avx-i_-O_-fomit-frame-pointer`	20180903	20180818
1425440	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=corei7-avx_-O_-fomit-frame-pointer`	20180903	20180818
1428224	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=native_-mtune=native_-O_-fomit-frame-pointer`	20180903	20180818
1458100	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=k8_-O2_-fomit-frame-pointer`	20180903	20180818
1459792	? ? ?	? ? ?	`ref`	`gcc_-march=k8_-O2_-fomit-frame-pointer`	20180903	20180818
1462376	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=corei7_-O2_-fomit-frame-pointer`	20180903	20180818
1462388	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core-avx-i_-O2_-fomit-frame-pointer`	20180903	20180818
1462612	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=corei7-avx_-O2_-fomit-frame-pointer`	20180903	20180818
1462788	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=native_-mtune=native_-O2_-fomit-frame-pointer`	20180903	20180818
1467072	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-msse4_-O2_-fomit-frame-pointer`	20180903	20180818
1468508	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O2_-fomit-frame-pointer`	20180903	20180818
1470280	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-O2_-fomit-frame-pointer`	20180903	20180818
1472944	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-msse4_-O_-fomit-frame-pointer`	20180903	20180818
1473852	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-O_-fomit-frame-pointer`	20180903	20180818
1474260	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=corei7_-O_-fomit-frame-pointer`	20180903	20180818
1479768	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-msse4.1_-O_-fomit-frame-pointer`	20180903	20180818
1489456	? ? ?	? ? ?	`ref`	`gcc_-fno-schedule-insns_-O_-fomit-frame-pointer`	20180903	20180818
1491864	? ? ?	? ? ?	`ref`	`gcc_-O_-fomit-frame-pointer`	20180903	20180818
1494864	? ? ?	? ? ?	`ref`	`gcc_-m64_-O_-fomit-frame-pointer`	20180903	20180818
1535304	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=barcelona_-O_-fomit-frame-pointer`	20180903	20180818
1536212	? ? ?	? ? ?	`ref`	`gcc_-march=barcelona_-O_-fomit-frame-pointer`	20180903	20180818
1548720	? ? ?	? ? ?	`ref`	`gcc_-march=nocona_-O2_-fomit-frame-pointer`	20180903	20180818
1549684	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=nocona_-O2_-fomit-frame-pointer`	20180903	20180818
1551528	? ? ?	? ? ?	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv`	20180903	20180818
1565028	? ? ?	? ? ?	`ref`	`gcc_-march=nocona_-O_-fomit-frame-pointer`	20180903	20180818
1565096	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=nocona_-O_-fomit-frame-pointer`	20180903	20180818
1592168	? ? ?	? ? ?	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv`	20180903	20180818
1634096	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-Os_-fomit-frame-pointer`	20180903	20180818
1634640	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-Os_-fomit-frame-pointer`	20180903	20180818
1634868	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20180903	20180818
1673828	? ? ?	? ? ?	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv`	20180903	20180818
1698984	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=k8_-Os_-fomit-frame-pointer`	20180903	20180818
1699768	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=barcelona_-Os_-fomit-frame-pointer`	20180903	20180818
1699808	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=nocona_-Os_-fomit-frame-pointer`	20180903	20180818
1700352	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=k8_-Os_-fomit-frame-pointer`	20180903	20180818
1701596	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-march=barcelona_-Os_-fomit-frame-pointer`	20180903	20180818
1704644	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops_-m64_-march=nocona_-Os_-fomit-frame-pointer`	20180903	20180818
1713752	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=barcelona_-Os_-fomit-frame-pointer`	20180903	20180818
1715688	? ? ?	? ? ?	`ref`	`gcc_-march=barcelona_-Os_-fomit-frame-pointer`	20180903	20180818
1716160	? ? ?	? ? ?	`ref`	`gcc_-march=k8_-Os_-fomit-frame-pointer`	20180903	20180818
1717392	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=k8_-Os_-fomit-frame-pointer`	20180903	20180818
1753484	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=nocona_-Os_-fomit-frame-pointer`	20180903	20180818
1757264	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=corei7_-Os_-fomit-frame-pointer`	20180903	20180818
1760908	? ? ?	? ? ?	`ref`	`gcc_-march=nocona_-Os_-fomit-frame-pointer`	20180903	20180818
1761056	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=corei7-avx_-Os_-fomit-frame-pointer`	20180903	20180818
1762092	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-msse4.1_-Os_-fomit-frame-pointer`	20180903	20180818
1762812	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core-avx-i_-Os_-fomit-frame-pointer`	20180903	20180818
1763248	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=native_-mtune=native_-Os_-fomit-frame-pointer`	20180903	20180818
1763292	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-Os_-fomit-frame-pointer`	20180903	20180818
1765344	? ? ?	? ? ?	`ref`	`gcc_-m64_-march=core2_-msse4_-Os_-fomit-frame-pointer`	20180903	20180818
1769608	? ? ?	? ? ?	`ref`	`gcc_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20180903	20180818
1775712	? ? ?	? ? ?	`ref`	`gcc_-Os_-fomit-frame-pointer`	20180903	20180818
1777192	? ? ?	? ? ?	`ref`	`gcc_-m64_-Os_-fomit-frame-pointer`	20180903	20180818
4548860	? ? ?	? ? ?	`ref`	`cc`	20180903	20180818
4556524	? ? ?	? ? ?	`ref`	`gcc_-funroll-loops`	20180903	20180818
4567532	? ? ?	? ? ?	`ref`	`gcc`	20180903	20180818

Test failure

Implementation: avx2
Security model: unknown
Compiler: gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer

error 111

Number of similar (compiler,implementation) pairs: 16, namely:

Compiler	Implementations
gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer	avx2
gcc -m64 -march=core-avx2 -O -fomit-frame-pointer	avx2
gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer	avx2
icc	avx2
icc -no-vec	avx2
icc -xAVX -O2 -fomit-frame-pointer	avx2
icc -xAVX -O3 -fomit-frame-pointer	avx2
icc -xCORE-AVX-I -O2 -fomit-frame-pointer	avx2
icc -xCORE-AVX-I -O3 -fomit-frame-pointer	avx2
icc -xSSE4.1 -O2 -fomit-frame-pointer	avx2
icc -xSSE4.1 -O3 -fomit-frame-pointer	avx2
icc -xSSE4.2 -O2 -fomit-frame-pointer	avx2
icc -xSSE4.2 -O3 -fomit-frame-pointer	avx2
gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer	ref
gcc -m64 -march=core-avx2 -O -fomit-frame-pointer	ref
gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer	ref

Compiler output

Implementation: avx2
Security model: unknown
Compiler: cc

KeccakP-1600-times4-SIMD256.c: In file included from KeccakP-1600-times4-SIMD256.c:19:0:
KeccakP-1600-times4-SIMD256.c: /usr/lib/gcc/x86_64-redhat-linux/4.8.5/include/smmintrin.h:31:3: error: #error "SSE4.1 instruction set not enabled"
KeccakP-1600-times4-SIMD256.c: # error "SSE4.1 instruction set not enabled"
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: In file included from KeccakP-1600-times4-SIMD256.c:20:0:
KeccakP-1600-times4-SIMD256.c: /usr/lib/gcc/x86_64-redhat-linux/4.8.5/include/wmmintrin.h:34:3: error: #error "AES/PCLMUL instructions not enabled"
KeccakP-1600-times4-SIMD256.c: # error "AES/PCLMUL instructions not enabled"
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:35:1: error: unknown type name '__m256i'
KeccakP-1600-times4-SIMD256.c: typedef __m256i V256;
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c: In function 'KeccakP1600times4_AddLanesAll':
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:58:67: error: '__m256' undeclared (first use in this function)
KeccakP-1600-times4-SIMD256.c: #define PERM128( a, b, c ) (V256)_mm256_permute2f128_ps((__m256)(a), (__m256)(b), c)
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:70:48: note: in expansion of macro 'PERM128'
KeccakP-1600-times4-SIMD256.c: #define INTLEAVE() lanesL01 = PERM128( lanes0, lanes2, 0x20 ), \
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:139:33: note: in expansion of macro 'INTLEAVE'
KeccakP-1600-times4-SIMD256.c: INTLEAVE(),\
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:146:9: note: in expansion of macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: Xor_In4( 0 );
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:58:67: note: each undeclared identifier is reported only once for each function it appears in
KeccakP-1600-times4-SIMD256.c: ...

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

Compiler	Implementations
cc	avx2

Compiler output

Implementation: avx2
Security model: unknown
Compiler: gcc

Number of similar (compiler,implementation) pairs: 86, namely:

Compiler	Implementations
gcc	avx2
gcc -O2 -fomit-frame-pointer	avx2
gcc -O3 -fomit-frame-pointer	avx2
gcc -O -fomit-frame-pointer	avx2
gcc -Os -fomit-frame-pointer	avx2
gcc -fno-schedule-insns -O2 -fomit-frame-pointer	avx2
gcc -fno-schedule-insns -O3 -fomit-frame-pointer	avx2
gcc -fno-schedule-insns -O -fomit-frame-pointer	avx2
gcc -fno-schedule-insns -Os -fomit-frame-pointer	avx2
gcc -funroll-loops	avx2
gcc -funroll-loops -O2 -fomit-frame-pointer	avx2
gcc -funroll-loops -O3 -fomit-frame-pointer	avx2
gcc -funroll-loops -O -fomit-frame-pointer	avx2
gcc -funroll-loops -Os -fomit-frame-pointer	avx2
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer	avx2
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer	avx2
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer	avx2
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer	avx2
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer	avx2
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer	avx2
gcc -funroll-loops -m64 -O -fomit-frame-pointer	avx2
gcc -funroll-loops -m64 -Os -fomit-frame-pointer	avx2
gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer	avx2
gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer	avx2
gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer	avx2
gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer	avx2
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer	avx2
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer	avx2
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer	avx2
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer	avx2
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer	avx2
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer	avx2
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer	avx2
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer	avx2
gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer	avx2
gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer	avx2
gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer	avx2
gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer	avx2
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer	avx2
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer	avx2
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer	avx2
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer	avx2
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer	avx2
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer	avx2
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer	avx2
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer	avx2
gcc -m64 -O2 -fomit-frame-pointer	avx2
gcc -m64 -O3 -fomit-frame-pointer	avx2
gcc -m64 -O -fomit-frame-pointer	avx2
gcc -m64 -Os -fomit-frame-pointer	avx2
gcc -m64 -march=core2 -O2 -fomit-frame-pointer	avx2
gcc -m64 -march=core2 -O3 -fomit-frame-pointer	avx2
gcc -m64 -march=core2 -O -fomit-frame-pointer	avx2
gcc -m64 -march=core2 -Os -fomit-frame-pointer	avx2
gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer	avx2
gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer	avx2
gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer	avx2
gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer	avx2
gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer	avx2
gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer	avx2
gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer	avx2
gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer	avx2
gcc -m64 -march=corei7 -O2 -fomit-frame-pointer	avx2
gcc -m64 -march=corei7 -O3 -fomit-frame-pointer	avx2
gcc -m64 -march=corei7 -O -fomit-frame-pointer	avx2
gcc -m64 -march=corei7 -Os -fomit-frame-pointer	avx2
gcc -m64 -march=k8 -O2 -fomit-frame-pointer	avx2
gcc -m64 -march=k8 -O3 -fomit-frame-pointer	avx2
gcc -m64 -march=k8 -O -fomit-frame-pointer	avx2
gcc -m64 -march=k8 -Os -fomit-frame-pointer	avx2
gcc -m64 -march=nocona -O2 -fomit-frame-pointer	avx2
gcc -m64 -march=nocona -O3 -fomit-frame-pointer	avx2
gcc -m64 -march=nocona -O -fomit-frame-pointer	avx2
gcc -m64 -march=nocona -Os -fomit-frame-pointer	avx2
gcc -march=barcelona -O2 -fomit-frame-pointer	avx2
gcc -march=barcelona -O3 -fomit-frame-pointer	avx2
gcc -march=barcelona -O -fomit-frame-pointer	avx2
gcc -march=barcelona -Os -fomit-frame-pointer	avx2
gcc -march=k8 -O2 -fomit-frame-pointer	avx2
gcc -march=k8 -O3 -fomit-frame-pointer	avx2
gcc -march=k8 -O -fomit-frame-pointer	avx2
gcc -march=k8 -Os -fomit-frame-pointer	avx2
gcc -march=nocona -O2 -fomit-frame-pointer	avx2
gcc -march=nocona -O3 -fomit-frame-pointer	avx2
gcc -march=nocona -O -fomit-frame-pointer	avx2
gcc -march=nocona -Os -fomit-frame-pointer	avx2

Compiler output

Implementation: avx2
Security model: unknown
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer

KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c: In function 'KeccakP1600times4_AddLanesAll':
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:135:40: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
KeccakP-1600-times4-SIMD256.c: #define Xor_In4( argIndex ) lanes0 = LOAD256u( curData0[argIndex]),\
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:146:9: note: in expansion of macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: Xor_In4( 0 );
KeccakP-1600-times4-SIMD256.c: ^~~~~~~
KeccakP-1600-times4-SIMD256.c: In file included from /home_nfs/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/immintrin.h:43,
KeccakP-1600-times4-SIMD256.c: from KeccakP-1600-times4-SIMD256.c:21:
KeccakP-1600-times4-SIMD256.c: /home_nfs/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
KeccakP-1600-times4-SIMD256.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~~~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:55:41: note: called from here
KeccakP-1600-times4-SIMD256.c: #define XOReq256(a, b) a = _mm256_xor_si256(a, b)
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~~~~~~~~~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:143:33: note: in expansion of macro 'XOReq256'
KeccakP-1600-times4-SIMD256.c: XOReq256( stateAsLanes[argIndex+3], lanes3 )
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:149:9: note: in expansion of macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: Xor_In4( 12 );
KeccakP-1600-times4-SIMD256.c: ^~~~~~~
KeccakP-1600-times4-SIMD256.c: In file included from /home_nfs/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/immintrin.h:43,
KeccakP-1600-times4-SIMD256.c: from KeccakP-1600-times4-SIMD256.c:21:
KeccakP-1600-times4-SIMD256.c: /home_nfs/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
KeccakP-1600-times4-SIMD256.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
KeccakP-1600-times4-SIMD256.c: ...
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c: In function 'KeccakP1600times4_AddLanesAll':
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:135:40: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
KeccakP-1600-times4-SIMD256.c: #define Xor_In4( argIndex ) lanes0 = LOAD256u( curData0[argIndex]),\
KeccakP-1600-times4-SIMD256.c: ^
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:146:9: note: in expansion of macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: Xor_In4( 0 );
KeccakP-1600-times4-SIMD256.c: ^~~~~~~
KeccakP-1600-times4-SIMD256.c: In file included from /home_nfs/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/immintrin.h:43,
KeccakP-1600-times4-SIMD256.c: from KeccakP-1600-times4-SIMD256.c:21:
KeccakP-1600-times4-SIMD256.c: /home_nfs/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
KeccakP-1600-times4-SIMD256.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~~~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:55:41: note: called from here
KeccakP-1600-times4-SIMD256.c: #define XOReq256(a, b) a = _mm256_xor_si256(a, b)
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~~~~~~~~~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:143:33: note: in expansion of macro 'XOReq256'
KeccakP-1600-times4-SIMD256.c: XOReq256( stateAsLanes[argIndex+3], lanes3 )
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:149:9: note: in expansion of macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: Xor_In4( 12 );
KeccakP-1600-times4-SIMD256.c: ^~~~~~~
KeccakP-1600-times4-SIMD256.c: In file included from /home_nfs/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/immintrin.h:43,
KeccakP-1600-times4-SIMD256.c: from KeccakP-1600-times4-SIMD256.c:21:
KeccakP-1600-times4-SIMD256.c: /home_nfs/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
KeccakP-1600-times4-SIMD256.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
KeccakP-1600-times4-SIMD256.c: ...

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

Compiler	Implementations
gcc -m64 -march=barcelona -O2 -fomit-frame-pointer	avx2
gcc -m64 -march=barcelona -O3 -fomit-frame-pointer	avx2
gcc -m64 -march=barcelona -O -fomit-frame-pointer	avx2
gcc -m64 -march=barcelona -Os -fomit-frame-pointer	avx2

Compiler output

Implementation: avx2
Security model: unknown
Compiler: gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer

KeccakP-1600-times4-SIMD256.c: In file included from /home_nfs/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/immintrin.h:43,
KeccakP-1600-times4-SIMD256.c: from KeccakP-1600-times4-SIMD256.c:21:
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c: In function 'KeccakP1600times4_AddLanesAll':
KeccakP-1600-times4-SIMD256.c: /home_nfs/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
KeccakP-1600-times4-SIMD256.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~~~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:55:41: note: called from here
KeccakP-1600-times4-SIMD256.c: #define XOReq256(a, b) a = _mm256_xor_si256(a, b)
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~~~~~~~~~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:143:33: note: in expansion of macro 'XOReq256'
KeccakP-1600-times4-SIMD256.c: XOReq256( stateAsLanes[argIndex+3], lanes3 )
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:149:9: note: in expansion of macro 'Xor_In4'
KeccakP-1600-times4-SIMD256.c: Xor_In4( 12 );
KeccakP-1600-times4-SIMD256.c: ^~~~~~~
KeccakP-1600-times4-SIMD256.c: In file included from /home_nfs/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/immintrin.h:43,
KeccakP-1600-times4-SIMD256.c: from KeccakP-1600-times4-SIMD256.c:21:
KeccakP-1600-times4-SIMD256.c: /home_nfs/bdolbeaur/gcc-8.2.0-full+isl/lib/gcc/x86_64-pc-linux-gnu/8.2.0/include/avx2intrin.h:913:1: error: inlining failed in call to always_inline '_mm256_xor_si256': target specific option mismatch
KeccakP-1600-times4-SIMD256.c: _mm256_xor_si256 (__m256i __A, __m256i __B)
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~~~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:55:41: note: called from here
KeccakP-1600-times4-SIMD256.c: #define XOReq256(a, b) a = _mm256_xor_si256(a, b)
KeccakP-1600-times4-SIMD256.c: ^~~~~~~~~~~~~~~~~~~~~~
KeccakP-1600-times4-SIMD256.c: KeccakP-1600-times4-SIMD256.c:142:33: note: in expansion of macro 'XOReq256'
KeccakP-1600-times4-SIMD256.c: XOReq256( stateAsLanes[argIndex+2], lanes2 ),\
KeccakP-1600-times4-SIMD256.c: ...

Number of similar (compiler,implementation) pairs: 16, namely:

Compiler	Implementations
gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer	avx2
gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer	avx2
gcc -m64 -march=core-avx-i -O -fomit-frame-pointer	avx2
gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer	avx2
gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer	avx2
gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer	avx2
gcc -m64 -march=corei7-avx -O -fomit-frame-pointer	avx2
gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer	avx2
gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer	avx2
gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer	avx2
gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer	avx2
gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer	avx2
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv	avx2
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv	avx2
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv	avx2
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv	avx2