Implementation notes: amd64, skylake, crypto_aead/trivia0v2

Computer: skylake
Architecture: amd64
CPU ID: GenuineIntel-000506e3-bfebfbff
SUPERCOP version: 20161026
Operation: crypto_aead
Primitive: trivia0v2

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
45464	`sse4`	`clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161217	20161026
45660	`sse4`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161217	20161026
46944	`sse4`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161217	20161026
46960	`sse4`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161217	20161026
56626	`sse4`	`gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer`	20161217	20161026
56988	`sse4`	`gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer`	20161217	20161026
57704	`sse4`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20161217	20161026
58124	`sse4`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161217	20161026
58258	`sse4`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161217	20161026
67818	`sse4`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161217	20161026
67840	`sse4`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161217	20161026
68476	`sse4`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20161217	20161026
70240	`sse4`	`gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer`	20161217	20161026
70580	`sse4`	`gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer`	20161217	20161026
72056	`sse4`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161217	20161026
72626	`sse4`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20161217	20161026
73334	`sse4`	`gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer`	20161217	20161026
73422	`sse4`	`gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer`	20161217	20161026
73672	`sse4`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161217	20161026
77292	`sse4`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20161217	20161026
77618	`sse4`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161217	20161026
77760	`sse4`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161217	20161026
77894	`sse4`	`gcc -m64 -march=core-avx-i -O -fomit-frame-pointer`	20161217	20161026
78034	`sse4`	`gcc -m64 -march=corei7-avx -O -fomit-frame-pointer`	20161217	20161026
162326	`ref`	`clang -O3 -fomit-frame-pointer -Qunused-arguments`	20161217	20161026
162648	`ref`	`clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161217	20161026
162830	`ref`	`clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161217	20161026
162912	`ref`	`clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments`	20161217	20161026
162932	`ref`	`clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161217	20161026
162978	`ref`	`clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments`	20161217	20161026
164062	`ref`	`clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161217	20161026
164734	`ref`	`clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments`	20161217	20161026
179254	`ref`	`clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments`	20161217	20161026
180428	`ref`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20161217	20161026
210134	`ref`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20161217	20161026
210308	`ref`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20161217	20161026
211598	`ref`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20161217	20161026
211638	`ref`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20161217	20161026
212020	`ref`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161217	20161026
212974	`ref`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20161217	20161026
213098	`ref`	`gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer`	20161217	20161026
213106	`ref`	`gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer`	20161217	20161026
213440	`ref`	`gcc -O3 -fomit-frame-pointer`	20161217	20161026
213684	`ref`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20161217	20161026
214008	`ref`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20161217	20161026
214444	`ref`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20161217	20161026
214494	`ref`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20161217	20161026
214582	`ref`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20161217	20161026
214756	`ref`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20161217	20161026
214784	`ref`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20161217	20161026
214784	`ref`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20161217	20161026
215026	`ref`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20161217	20161026
215144	`ref`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20161217	20161026
215268	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161217	20161026
215294	`ref`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20161217	20161026
215398	`ref`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20161217	20161026
215458	`ref`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20161217	20161026
215686	`ref`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20161217	20161026
215704	`ref`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20161217	20161026
215782	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20161217	20161026
215838	`ref`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20161217	20161026
215914	`ref`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20161217	20161026
216628	`ref`	`gcc -m64 -march=core-avx2 -O3 -fomit-frame-pointer`	20161217	20161026
216762	`ref`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20161217	20161026
217120	`ref`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20161217	20161026
217190	`ref`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20161217	20161026
217454	`ref`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20161217	20161026
217524	`ref`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20161217	20161026
218612	`ref`	`gcc -m64 -O3 -fomit-frame-pointer`	20161217	20161026
220000	`ref`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20161217	20161026
229024	`ref`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20161217	20161026
229324	`ref`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20161217	20161026
229534	`ref`	`gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer`	20161217	20161026
231106	`ref`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20161217	20161026
231854	`ref`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20161217	20161026
232708	`ref`	`gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer`	20161217	20161026
232732	`ref`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20161217	20161026
233356	`ref`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20161217	20161026
233668	`ref`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20161217	20161026
233880	`ref`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20161217	20161026
233980	`ref`	`gcc -O2 -fomit-frame-pointer`	20161217	20161026
234148	`ref`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20161217	20161026
234840	`ref`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20161217	20161026
234878	`ref`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20161217	20161026
235568	`ref`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20161217	20161026
236058	`ref`	`gcc -m64 -march=core-avx2 -O2 -fomit-frame-pointer`	20161217	20161026
236176	`ref`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20161217	20161026
236702	`ref`	`gcc -m64 -O2 -fomit-frame-pointer`	20161217	20161026
271802	`ref`	`gcc -march=k8 -O -fomit-frame-pointer`	20161217	20161026
271824	`ref`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20161217	20161026
272296	`ref`	`gcc -march=barcelona -O -fomit-frame-pointer`	20161217	20161026
273132	`ref`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20161217	20161026
273318	`ref`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20161217	20161026
273596	`ref`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20161217	20161026
274608	`ref`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20161217	20161026
275444	`ref`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20161217	20161026
278376	`ref`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20161217	20161026
280412	`ref`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20161217	20161026
282056	`ref`	`gcc -O -fomit-frame-pointer`	20161217	20161026
282348	`ref`	`gcc -m64 -march=core-avx-i -O -fomit-frame-pointer`	20161217	20161026
282648	`ref`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20161217	20161026
282686	`ref`	`gcc -funroll-loops -O -fomit-frame-pointer`	20161217	20161026
283420	`ref`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20161217	20161026
283530	`ref`	`gcc -m64 -O -fomit-frame-pointer`	20161217	20161026
285906	`ref`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20161217	20161026
288330	`ref`	`gcc -m64 -march=core-avx2 -O -fomit-frame-pointer`	20161217	20161026
288774	`ref`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20161217	20161026
291010	`ref`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20161217	20161026
297906	`ref`	`gcc -m64 -march=corei7-avx -O -fomit-frame-pointer`	20161217	20161026
298182	`ref`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20161217	20161026
298246	`ref`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20161217	20161026
298950	`ref`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20161217	20161026
299078	`ref`	`gcc -march=nocona -O -fomit-frame-pointer`	20161217	20161026
299196	`ref`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20161217	20161026
299238	`ref`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20161217	20161026
398078	`ref`	`gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer`	20161217	20161026
400240	`ref`	`gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer`	20161217	20161026
409518	`ref`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20161217	20161026
411336	`ref`	`gcc -Os -fomit-frame-pointer`	20161217	20161026
412864	`ref`	`gcc -m64 -Os -fomit-frame-pointer`	20161217	20161026
413600	`ref`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20161217	20161026
414184	`ref`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20161217	20161026
414410	`ref`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20161217	20161026
414464	`ref`	`gcc -march=k8 -Os -fomit-frame-pointer`	20161217	20161026
414990	`ref`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20161217	20161026
415528	`ref`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20161217	20161026
416590	`ref`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20161217	20161026
417344	`ref`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20161217	20161026
440402	`ref`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20161217	20161026
443806	`ref`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20161217	20161026
447936	`ref`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20161217	20161026
453010	`ref`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20161217	20161026
453762	`ref`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20161217	20161026
455448	`ref`	`gcc -m64 -march=core-avx2 -Os -fomit-frame-pointer`	20161217	20161026
455982	`ref`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20161217	20161026
456050	`ref`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20161217	20161026
457200	`ref`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20161217	20161026
464150	`ref`	`gcc -march=nocona -Os -fomit-frame-pointer`	20161217	20161026
469084	`ref`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20161217	20161026
507068	`ref`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20161217	20161026
512704	`ref`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20161217	20161026
513804	`ref`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20161217	20161026
1727172	`ref`	`gcc -funroll-loops`	20161217	20161026
1732920	`ref`	`cc`	20161217	20161026
1739268	`ref`	`gcc`	20161217	20161026

Compiler output

Implementation: crypto_aead/trivia0v2/sse4
Compiler: cc

encrypt.c: encrypt.c: In function 'Field_Mult_32':
encrypt.c: encrypt.c:306:4: error: '__builtin_ia32_pclmulqdq128' needs isa option -m32 -mpclmul
encrypt.c: x = _mm_clmulepi64_si128(x,y,0x0);
encrypt.c: ^
encrypt.c: encrypt.c:313:4: error: '__builtin_ia32_pclmulqdq128' needs isa option -m32 -mpclmul
encrypt.c: x = _mm_clmulepi64_si128(x,y,0x0);
encrypt.c: ^
encrypt.c: encrypt.c:319:4: error: '__builtin_ia32_pclmulqdq128' needs isa option -m32 -mpclmul
encrypt.c: x = _mm_clmulepi64_si128(x,y,0x0);
encrypt.c: ^

Number of similar (compiler,implementation) pairs: 3, namely:

Compiler	Implementations
cc	sse4
gcc	sse4
gcc -funroll-loops	sse4

Compiler output

Implementation: crypto_aead/trivia0v2/sse4
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments

encrypt.c: encrypt.c:229:1: warning: '/*' within block comment [-Wcomment]
encrypt.c: /*----------------------------------------------------------------*/
encrypt.c: ^
encrypt.c: encrypt.c:306:6: error: '__builtin_ia32_pclmulqdq128' needs target feature pclmul
encrypt.c: x = _mm_clmulepi64_si128(x,y,0x0);
encrypt.c: ^
encrypt.c: /usr/bin/../lib/clang/3.9.0/include/__wmmintrin_pclmul.h:55:13: note: expanded from macro '_mm_clmulepi64_si128'
encrypt.c: ((__m128i)__builtin_ia32_pclmulqdq128((__v2di)(__m128i)(__X), \
encrypt.c: ^
encrypt.c: encrypt.c:313:6: error: '__builtin_ia32_pclmulqdq128' needs target feature pclmul
encrypt.c: x = _mm_clmulepi64_si128(x,y,0x0);
encrypt.c: ^
encrypt.c: /usr/bin/../lib/clang/3.9.0/include/__wmmintrin_pclmul.h:55:13: note: expanded from macro '_mm_clmulepi64_si128'
encrypt.c: ((__m128i)__builtin_ia32_pclmulqdq128((__v2di)(__m128i)(__X), \
encrypt.c: ^
encrypt.c: encrypt.c:319:6: error: '__builtin_ia32_pclmulqdq128' needs target feature pclmul
encrypt.c: x = _mm_clmulepi64_si128(x,y,0x0);
encrypt.c: ^
encrypt.c: /usr/bin/../lib/clang/3.9.0/include/__wmmintrin_pclmul.h:55:13: note: expanded from macro '_mm_clmulepi64_si128'
encrypt.c: ((__m128i)__builtin_ia32_pclmulqdq128((__v2di)(__m128i)(__X), \
encrypt.c: ^
encrypt.c: 1 warning and 3 errors generated.

Number of similar (compiler,implementation) pairs: 6, namely:

Compiler	Implementations
clang -O3 -fomit-frame-pointer -Qunused-arguments	sse4
clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments	sse4
clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments	sse4
clang -mcpu=cortex-a8 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	sse4
clang -mcpu=cortex-a9 -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	sse4
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	sse4

Compiler output

Implementation: crypto_aead/trivia0v2/sse4
Compiler: clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments

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

Compiler	Implementations
clang -O3 -fwrapv -march=native -fomit-frame-pointer -Qunused-arguments	sse4
clang -O3 -fwrapv -march=x86-64 -mcpu=core-avx2 -mavx2 -maes -mpclmul -fomit-frame-pointer -Qunused-arguments	sse4
clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments	sse4
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	sse4

Compiler output

Implementation: crypto_aead/trivia0v2/sse4
Compiler: gcc -O2 -fomit-frame-pointer

Number of similar (compiler,implementation) pairs: 72, namely:

Compiler	Implementations
gcc -O2 -fomit-frame-pointer	sse4
gcc -O3 -fomit-frame-pointer	sse4
gcc -O -fomit-frame-pointer	sse4
gcc -Os -fomit-frame-pointer	sse4
gcc -fno-schedule-insns -O2 -fomit-frame-pointer	sse4
gcc -fno-schedule-insns -O3 -fomit-frame-pointer	sse4
gcc -fno-schedule-insns -O -fomit-frame-pointer	sse4
gcc -fno-schedule-insns -Os -fomit-frame-pointer	sse4
gcc -funroll-loops -O2 -fomit-frame-pointer	sse4
gcc -funroll-loops -O3 -fomit-frame-pointer	sse4
gcc -funroll-loops -O -fomit-frame-pointer	sse4
gcc -funroll-loops -Os -fomit-frame-pointer	sse4
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer	sse4
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer	sse4
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer	sse4
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer	sse4
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer	sse4
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer	sse4
gcc -funroll-loops -m64 -O -fomit-frame-pointer	sse4
gcc -funroll-loops -m64 -Os -fomit-frame-pointer	sse4
gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer	sse4
gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer	sse4
gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer	sse4
gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer	sse4
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer	sse4
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer	sse4
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer	sse4
gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer	sse4
gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer	sse4
gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer	sse4
gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer	sse4
gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer	sse4
gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer	sse4
gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer	sse4
gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer	sse4
gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer	sse4
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer	sse4
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer	sse4
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer	sse4
gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer	sse4
gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer	sse4
gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer	sse4
gcc -funroll-loops -march=nocona -O -fomit-frame-pointer	sse4
gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer	sse4
gcc -m64 -O2 -fomit-frame-pointer	sse4
gcc -m64 -O3 -fomit-frame-pointer	sse4
gcc -m64 -O -fomit-frame-pointer	sse4
gcc -m64 -Os -fomit-frame-pointer	sse4
gcc -m64 -march=core2 -O2 -fomit-frame-pointer	sse4
gcc -m64 -march=core2 -O3 -fomit-frame-pointer	sse4
gcc -m64 -march=core2 -O -fomit-frame-pointer	sse4
gcc -m64 -march=core2 -Os -fomit-frame-pointer	sse4
gcc -m64 -march=k8 -O2 -fomit-frame-pointer	sse4
gcc -m64 -march=k8 -O3 -fomit-frame-pointer	sse4
gcc -m64 -march=k8 -O -fomit-frame-pointer	sse4
gcc -m64 -march=k8 -Os -fomit-frame-pointer	sse4
gcc -m64 -march=nocona -O2 -fomit-frame-pointer	sse4
gcc -m64 -march=nocona -O3 -fomit-frame-pointer	sse4
gcc -m64 -march=nocona -O -fomit-frame-pointer	sse4
gcc -m64 -march=nocona -Os -fomit-frame-pointer	sse4
gcc -march=barcelona -O2 -fomit-frame-pointer	sse4
gcc -march=barcelona -O3 -fomit-frame-pointer	sse4
gcc -march=barcelona -O -fomit-frame-pointer	sse4
gcc -march=barcelona -Os -fomit-frame-pointer	sse4
gcc -march=k8 -O2 -fomit-frame-pointer	sse4
gcc -march=k8 -O3 -fomit-frame-pointer	sse4
gcc -march=k8 -O -fomit-frame-pointer	sse4
gcc -march=k8 -Os -fomit-frame-pointer	sse4
gcc -march=nocona -O2 -fomit-frame-pointer	sse4
gcc -march=nocona -O3 -fomit-frame-pointer	sse4
gcc -march=nocona -O -fomit-frame-pointer	sse4
gcc -march=nocona -Os -fomit-frame-pointer	sse4

Compiler output

Implementation: crypto_aead/trivia0v2/sse4
Compiler: gcc -m64 -march=barcelona -O2 -fomit-frame-pointer

encrypt.c: In file included from encrypt.c:26:0:
encrypt.c: encrypt.c: In function 'Field_Mult_32':
encrypt.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/smmintrin.h:447:1: error: inlining failed in call to always_inline '_mm_extract_epi32': target specific option mismatch
encrypt.c: _mm_extract_epi32 (__m128i __X, const int __N)
encrypt.c: ^~~~~~~~~~~~~~~~~
encrypt.c: encrypt.c:321:6: note: called from here
encrypt.c: b = _mm_extract_epi32(x, 0x0);
encrypt.c: ^~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: In file included from encrypt.c:24:0:
encrypt.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/wmmintrin.h:116:1: error: inlining failed in call to always_inline '_mm_clmulepi64_si128': target specific option mismatch
encrypt.c: _mm_clmulepi64_si128 (__m128i __X, __m128i __Y, const int __I)
encrypt.c: ^~~~~~~~~~~~~~~~~~~~
encrypt.c: encrypt.c:319:4: note: called from here
encrypt.c: x = _mm_clmulepi64_si128(x,y,0x0);
encrypt.c: ~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: In file included from encrypt.c:26:0:
encrypt.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/smmintrin.h:447:1: error: inlining failed in call to always_inline '_mm_extract_epi32': target specific option mismatch
encrypt.c: _mm_extract_epi32 (__m128i __X, const int __N)
encrypt.c: ^~~~~~~~~~~~~~~~~
encrypt.c: encrypt.c:315:6: note: called from here
encrypt.c: b = _mm_extract_epi32(x, 0x1);
encrypt.c: ^~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: In file included from encrypt.c:24:0:
encrypt.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/wmmintrin.h:116:1: error: inlining failed in call to always_inline '_mm_clmulepi64_si128': target specific option mismatch
encrypt.c: _mm_clmulepi64_si128 (__m128i __X, __m128i __Y, const int __I)
encrypt.c: ...
encrypt.c: In file included from encrypt.c:26:0:
encrypt.c: encrypt.c: In function 'Field_Mult_32':
encrypt.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/smmintrin.h:447:1: error: inlining failed in call to always_inline '_mm_extract_epi32': target specific option mismatch
encrypt.c: _mm_extract_epi32 (__m128i __X, const int __N)
encrypt.c: ^~~~~~~~~~~~~~~~~
encrypt.c: encrypt.c:321:6: note: called from here
encrypt.c: b = _mm_extract_epi32(x, 0x0);
encrypt.c: ^~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: In file included from encrypt.c:24:0:
encrypt.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/wmmintrin.h:116:1: error: inlining failed in call to always_inline '_mm_clmulepi64_si128': target specific option mismatch
encrypt.c: _mm_clmulepi64_si128 (__m128i __X, __m128i __Y, const int __I)
encrypt.c: ^~~~~~~~~~~~~~~~~~~~
encrypt.c: encrypt.c:319:4: note: called from here
encrypt.c: x = _mm_clmulepi64_si128(x,y,0x0);
encrypt.c: ~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: In file included from encrypt.c:26:0:
encrypt.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/smmintrin.h:447:1: error: inlining failed in call to always_inline '_mm_extract_epi32': target specific option mismatch
encrypt.c: _mm_extract_epi32 (__m128i __X, const int __N)
encrypt.c: ^~~~~~~~~~~~~~~~~
encrypt.c: encrypt.c:315:6: note: called from here
encrypt.c: b = _mm_extract_epi32(x, 0x1);
encrypt.c: ^~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: In file included from encrypt.c:24:0:
encrypt.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/wmmintrin.h:116:1: error: inlining failed in call to always_inline '_mm_clmulepi64_si128': target specific option mismatch
encrypt.c: _mm_clmulepi64_si128 (__m128i __X, __m128i __Y, const int __I)
encrypt.c: ...

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

Compiler	Implementations
gcc -m64 -march=barcelona -O2 -fomit-frame-pointer	sse4
gcc -m64 -march=barcelona -O3 -fomit-frame-pointer	sse4
gcc -m64 -march=barcelona -O -fomit-frame-pointer	sse4
gcc -m64 -march=barcelona -Os -fomit-frame-pointer	sse4

Compiler output

Implementation: crypto_aead/trivia0v2/sse4
Compiler: gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer

encrypt.c: In file included from encrypt.c:24:0:
encrypt.c: encrypt.c: In function 'Field_Mult_32':
encrypt.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/wmmintrin.h:116:1: error: inlining failed in call to always_inline '_mm_clmulepi64_si128': target specific option mismatch
encrypt.c: _mm_clmulepi64_si128 (__m128i __X, __m128i __Y, const int __I)
encrypt.c: ^~~~~~~~~~~~~~~~~~~~
encrypt.c: encrypt.c:319:4: note: called from here
encrypt.c: x = _mm_clmulepi64_si128(x,y,0x0);
encrypt.c: ~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: In file included from encrypt.c:24:0:
encrypt.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/wmmintrin.h:116:1: error: inlining failed in call to always_inline '_mm_clmulepi64_si128': target specific option mismatch
encrypt.c: _mm_clmulepi64_si128 (__m128i __X, __m128i __Y, const int __I)
encrypt.c: ^~~~~~~~~~~~~~~~~~~~
encrypt.c: encrypt.c:313:4: note: called from here
encrypt.c: x = _mm_clmulepi64_si128(x,y,0x0);
encrypt.c: ~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: In file included from encrypt.c:24:0:
encrypt.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/wmmintrin.h:116:1: error: inlining failed in call to always_inline '_mm_clmulepi64_si128': target specific option mismatch
encrypt.c: _mm_clmulepi64_si128 (__m128i __X, __m128i __Y, const int __I)
encrypt.c: ^~~~~~~~~~~~~~~~~~~~
encrypt.c: encrypt.c:306:4: note: called from here
encrypt.c: x = _mm_clmulepi64_si128(x,y,0x0);
encrypt.c: ~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
encrypt.c: In file included from encrypt.c:24:0:
encrypt.c: /usr/lib/gcc/x86_64-pc-linux-gnu/6.2.1/include/wmmintrin.h:116:1: error: inlining failed in call to always_inline '_mm_clmulepi64_si128': target specific option mismatch
encrypt.c: _mm_clmulepi64_si128 (__m128i __X, __m128i __Y, const int __I)
encrypt.c: ...

Number of similar (compiler,implementation) pairs: 12, namely:

Compiler	Implementations
gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer	sse4
gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer	sse4
gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer	sse4
gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer	sse4
gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer	sse4
gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer	sse4
gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer	sse4
gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer	sse4
gcc -m64 -march=corei7 -O2 -fomit-frame-pointer	sse4
gcc -m64 -march=corei7 -O3 -fomit-frame-pointer	sse4
gcc -m64 -march=corei7 -O -fomit-frame-pointer	sse4
gcc -m64 -march=corei7 -Os -fomit-frame-pointer	sse4