Implementation notes: x86, thoth, crypto_hash/groestl256

Computer: thoth
Architecture: x86
CPU ID: AuthenticAMD-00000622-0183f9ff
SUPERCOP version: 20160806
Operation: crypto_hash
Primitive: groestl256

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
82668	`mmx`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160726	20160724
87540	`mmx`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160726	20160724
92625	`mmx`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160726	20160724
98157	`mmx`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160726	20160724
140149	`sphlib-small`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160726	20160724
143507	`sphlib-small`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160726	20160724
148482	`sphlib-small`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160726	20160724
169702	`sphlib-small`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160726	20160724
171552	`sphlib`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160726	20160724
173091	`sphlib-adapted`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160726	20160724
173656	`sphlib`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160726	20160724
182529	`sphlib-adapted`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160726	20160724
186571	`sphlib-adapted`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160726	20160724
189624	`sphlib`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160726	20160724
192040	`sphlib-small`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160726	20160724
197403	`sphlib`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160726	20160724
200733	`opt64`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160726	20160724
205651	`sphlib-adapted`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160726	20160724
210987	`sphlib`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160726	20160724
215994	`sphlib-adapted`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160726	20160724
218994	`opt64`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160726	20160724
222810	`opt64`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160726	20160724
246681	`opt64`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160726	20160724
256806	`32bit-2ktable`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160726	20160724
257778	`opt32`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160726	20160724
262801	`32bit-2ktable`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160726	20160724
266298	`opt32`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160726	20160724
266676	`opt32`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160726	20160724
267781	`opt32`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160726	20160724
268464	`32bit-2ktable`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160726	20160724
269514	`32bit-2ktable`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160726	20160724
269686	`opt32`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160726	20160724
289150	`32bit-2ktable`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160726	20160724
468581	`32bit-bytesliced-c-small`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160726	20160724
499158	`32bit-bytesliced-c-fast`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160726	20160724
507940	`32bit-bytesliced-c-small`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160726	20160724
539746	`32bit-bytesliced-c-fast`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160726	20160724
595293	`32bit-bytesliced-c-fast`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160726	20160724
626651	`32bit-bytesliced-c-small`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160726	20160724
676796	`8bit_c`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160726	20160724
706878	`32bit-bytesliced-c-fast`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160726	20160724
735464	`32bit-bytesliced-c-fast`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160726	20160724
768333	`8bit_c`	`gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv`	20160726	20160724
777825	`8bit_c`	`gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv`	20160726	20160724
814474	`8bit_c`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160726	20160724
845859	`8bit_c`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160726	20160724
867950	`32bit-bytesliced-c-small`	`gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv`	20160726	20160724
870372	`32bit-bytesliced-c-small`	`gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv`	20160726	20160724
1614708	`mmx`	`clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments`	20160726	20160724

Compiler output

Implementation: crypto_hash/groestl256/aesni-intr
Compiler: clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments

hash.c: In file included from hash.c:28:
hash.c: ./groestl-intr-aes.h:368:3: error: always_inline function '_mm_shuffle_epi8' requires target feature 'sse3', but would be inlined into function 'INIT' that is compiled without support for 'sse3'
hash.c: Matrix_Transpose_A(xmm12, xmm13, xmm14, xmm15, xmm2, xmm6, xmm7, xmm0);
hash.c: ^
hash.c: ./groestl-intr-aes.h:240:8: note: expanded from macro 'Matrix_Transpose_A'
hash.c: i0 = _mm_shuffle_epi8(i0, t0);\
hash.c: ^
hash.c: ./groestl-intr-aes.h:368:3: error: always_inline function '_mm_shuffle_epi8' requires target feature 'sse3', but would be inlined into function 'INIT' that is compiled without support for 'sse3'
hash.c: ./groestl-intr-aes.h:241:8: note: expanded from macro 'Matrix_Transpose_A'
hash.c: i1 = _mm_shuffle_epi8(i1, t0);\
hash.c: ^
hash.c: ./groestl-intr-aes.h:368:3: error: always_inline function '_mm_shuffle_epi8' requires target feature 'sse3', but would be inlined into function 'INIT' that is compiled without support for 'sse3'
hash.c: ./groestl-intr-aes.h:242:8: note: expanded from macro 'Matrix_Transpose_A'
hash.c: i2 = _mm_shuffle_epi8(i2, t0);\
hash.c: ^
hash.c: ./groestl-intr-aes.h:368:3: error: always_inline function '_mm_shuffle_epi8' requires target feature 'sse3', but would be inlined into function 'INIT' that is compiled without support for 'sse3'
hash.c: ./groestl-intr-aes.h:243:8: note: expanded from macro 'Matrix_Transpose_A'
hash.c: i3 = _mm_shuffle_epi8(i3, t0);\
hash.c: ^
hash.c: ./groestl-intr-aes.h:368:3: error: always_inline function '_mm_unpacklo_epi16' requires target feature 'sse2', but would be inlined into function 'INIT' that is compiled without support for 'sse2'
hash.c: ./groestl-intr-aes.h:248:8: note: expanded from macro 'Matrix_Transpose_A'
hash.c: i0 = _mm_unpacklo_epi16(i0, i1);\
hash.c: ^
hash.c: ./groestl-intr-aes.h:368:3: error: always_inline function '_mm_unpackhi_epi16' requires target feature 'sse2', but would be inlined into function 'INIT' that is compiled without support for 'sse2'
hash.c: ./groestl-intr-aes.h:249:8: note: expanded from macro 'Matrix_Transpose_A'
hash.c: ...

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

Compiler	Implementations
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	aesni-intr

Compiler output

Implementation: crypto_hash/groestl256/vperm-intr
Compiler: clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments

hash.c: In file included from hash.c:34:
hash.c: ./groestl-intr-vperm.h:650:3: error: always_inline function '_mm_andnot_si128' requires target feature 'sse2', but would be inlined into function 'INIT' that is compiled without support for 'sse2'
hash.c: VPERM_Transform_RoundConst();
hash.c: ^
hash.c: ./groestl-intr-vperm.h:633:3: note: expanded from macro 'VPERM_Transform_RoundConst'
hash.c: VPERM_Transform(xmm0, xmm1, VPERM_IPT, xmm4, xmm5, xmm6, xmm7, xmm8, xmm9, xmm10);\
hash.c: ^
hash.c: ./groestl-intr-vperm.h:116:3: note: expanded from macro 'VPERM_Transform'
hash.c: VPERM_Transform_No_Const(a0, a1, t0, t1, t2, t3, c0, c1, c2);\
hash.c: ^
hash.c: ./groestl-intr-vperm.h:77:8: note: expanded from macro 'VPERM_Transform_No_Const'
hash.c: t0 = _mm_andnot_si128(t0, a0);\
hash.c: ^
hash.c: ./groestl-intr-vperm.h:650:3: error: always_inline function '_mm_andnot_si128' requires target feature 'sse2', but would be inlined into function 'INIT' that is compiled without support for 'sse2'
hash.c: ./groestl-intr-vperm.h:633:3: note: expanded from macro 'VPERM_Transform_RoundConst'
hash.c: VPERM_Transform(xmm0, xmm1, VPERM_IPT, xmm4, xmm5, xmm6, xmm7, xmm8, xmm9, xmm10);\
hash.c: ^
hash.c: ./groestl-intr-vperm.h:116:3: note: expanded from macro 'VPERM_Transform'
hash.c: VPERM_Transform_No_Const(a0, a1, t0, t1, t2, t3, c0, c1, c2);\
hash.c: ^
hash.c: ./groestl-intr-vperm.h:78:8: note: expanded from macro 'VPERM_Transform_No_Const'
hash.c: t1 = _mm_andnot_si128(t1, a1);\
hash.c: ^
hash.c: ./groestl-intr-vperm.h:650:3: error: always_inline function '_mm_srli_epi32' requires target feature 'sse2', but would be inlined into function 'INIT' that is compiled without support for 'sse2'
hash.c: ./groestl-intr-vperm.h:633:3: note: expanded from macro 'VPERM_Transform_RoundConst'
hash.c: ...

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

Compiler	Implementations
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	vperm-intr

Compiler output

Implementation: crypto_hash/groestl256/avx-intr
Compiler: clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments

hash.c: In file included from hash.c:9:
hash.c: ./groestl-intr-avx.h:353:3: error: always_inline function '_mm_shuffle_epi8' requires target feature 'sse3', but would be inlined into function 'INIT' that is compiled without support for 'sse3'
hash.c: Matrix_Transpose_A(xmm12, xmm13, xmm14, xmm15, xmm2, xmm6, xmm7, xmm0);
hash.c: ^
hash.c: ./groestl-intr-avx.h:246:8: note: expanded from macro 'Matrix_Transpose_A'
hash.c: i0 = _mm_shuffle_epi8(i0, t0);\
hash.c: ^
hash.c: ./groestl-intr-avx.h:353:3: error: always_inline function '_mm_shuffle_epi8' requires target feature 'sse3', but would be inlined into function 'INIT' that is compiled without support for 'sse3'
hash.c: ./groestl-intr-avx.h:247:8: note: expanded from macro 'Matrix_Transpose_A'
hash.c: i1 = _mm_shuffle_epi8(i1, t0);\
hash.c: ^
hash.c: ./groestl-intr-avx.h:353:3: error: always_inline function '_mm_shuffle_epi8' requires target feature 'sse3', but would be inlined into function 'INIT' that is compiled without support for 'sse3'
hash.c: ./groestl-intr-avx.h:248:8: note: expanded from macro 'Matrix_Transpose_A'
hash.c: i2 = _mm_shuffle_epi8(i2, t0);\
hash.c: ^
hash.c: ./groestl-intr-avx.h:353:3: error: always_inline function '_mm_shuffle_epi8' requires target feature 'sse3', but would be inlined into function 'INIT' that is compiled without support for 'sse3'
hash.c: ./groestl-intr-avx.h:249:8: note: expanded from macro 'Matrix_Transpose_A'
hash.c: i3 = _mm_shuffle_epi8(i3, t0);\
hash.c: ^
hash.c: ./groestl-intr-avx.h:353:3: error: always_inline function '_mm_unpackhi_epi16' requires target feature 'sse2', but would be inlined into function 'INIT' that is compiled without support for 'sse2'
hash.c: ./groestl-intr-avx.h:251:8: note: expanded from macro 'Matrix_Transpose_A'
hash.c: o1 = _mm_unpackhi_epi16(i0, i1);\
hash.c: ^
hash.c: ./groestl-intr-avx.h:353:3: error: always_inline function '_mm_unpacklo_epi16' requires target feature 'sse2', but would be inlined into function 'INIT' that is compiled without support for 'sse2'
hash.c: ./groestl-intr-avx.h:252:8: note: expanded from macro 'Matrix_Transpose_A'
hash.c: ...

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

Compiler	Implementations
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	avx-intr

Compiler output

Implementation: crypto_hash/groestl256/vperm
Compiler: clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments

hash.c: hash.c:104:12: warning: comparison of array 'ctx->gt;chaining' equal to a null pointer is always false [-Wtautological-pointer-compare]
hash.c: if (ctx->gt;chaining == NULL || ctx->gt;buffer == NULL)
hash.c: ~~~~~^~~~~~~~ ~~~~
hash.c: hash.c:104:37: warning: comparison of array 'ctx->gt;buffer' equal to a null pointer is always false [-Wtautological-pointer-compare]
hash.c: if (ctx->gt;chaining == NULL || ctx->gt;buffer == NULL)
hash.c: ~~~~~^~~~~~ ~~~~
hash.c: In file included from hash.c:19:
hash.c: ./groestl-asm-vperm.h:705:3: error: invalid operand for instruction
hash.c: VPERM_Transform_RoundConst();
hash.c: ^
hash.c: ./groestl-asm-vperm.h:685:8: note: expanded from macro 'VPERM_Transform_RoundConst'
hash.c: asm ("movaps xmm0, [ROUND_CONST_Lx]");\
hash.c: ^
hash.c: gt;:1:15: note: instantiated into assembly here
hash.c: movaps xmm0, [ROUND_CONST_Lx]
hash.c: ^~~~~~~~~~~~~~~~
hash.c: In file included from hash.c:19:
hash.c: ./groestl-asm-vperm.h:705:3: error: invalid operand for instruction
hash.c: VPERM_Transform_RoundConst();
hash.c: ^
hash.c: ./groestl-asm-vperm.h:686:3: note: expanded from macro 'VPERM_Transform_RoundConst'
hash.c: VPERM_Transform(0, 1, VPERM_IPT, 4, 5, 6, 7, 8, 9, 10);\
hash.c: ^
hash.c: ./groestl-asm-vperm.h:142:3: note: expanded from macro 'VPERM_Transform'
hash.c: VPERM_Transform_Set_Const(table, c0, c1, c2);\
hash.c: ...

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

Compiler	Implementations
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	vperm

Compiler output

Implementation: crypto_hash/groestl256/opt64
Compiler: clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments

hash.c: hash.c:191:3: warning: non-constant static local variable in inline function may be different in different files [-Wstatic-local-in-inline]
hash.c: static u64 y[COLS1024] __attribute__((aligned(16)));
hash.c: ^
hash.c: hash.c:190:1: note: use 'static' to give inline function 'F1024' internal linkage
hash.c: inline void F1024(u64 *h, const u64 *m) {
hash.c: ^
hash.c: static
hash.c: hash.c:192:3: warning: non-constant static local variable in inline function may be different in different files [-Wstatic-local-in-inline]
hash.c: static u64 z[COLS1024] __attribute__((aligned(16)));
hash.c: ^
hash.c: hash.c:190:1: note: use 'static' to give inline function 'F1024' internal linkage
hash.c: inline void F1024(u64 *h, const u64 *m) {
hash.c: ^
hash.c: static
hash.c: hash.c:193:3: warning: non-constant static local variable in inline function may be different in different files [-Wstatic-local-in-inline]
hash.c: static u64 outQ[COLS1024] __attribute__((aligned(16)));
hash.c: ^
hash.c: hash.c:190:1: note: use 'static' to give inline function 'F1024' internal linkage
hash.c: inline void F1024(u64 *h, const u64 *m) {
hash.c: ^
hash.c: static
hash.c: hash.c:194:3: warning: non-constant static local variable in inline function may be different in different files [-Wstatic-local-in-inline]
hash.c: static u64 inP[COLS1024] __attribute__((aligned(16)));
hash.c: ^
hash.c: hash.c:190:1: note: use 'static' to give inline function 'F1024' internal linkage
hash.c: ...

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

Compiler	Implementations
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments	opt64

Compiler output

Implementation: crypto_hash/groestl256/aesni-intr
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv

hash.c: In file included from hash.c:28:0:
hash.c: groestl-intr-aes.h: In function 'INIT':
hash.c: groestl-intr-aes.h:240:6: warning: SSE vector return without SSE enabled changes the ABI [-Wpsabi]
hash.c: i0 = _mm_shuffle_epi8(i0, t0);\
hash.c: ^
hash.c: groestl-intr-aes.h:368:3: note: in expansion of macro 'Matrix_Transpose_A'
hash.c: Matrix_Transpose_A(xmm12, xmm13, xmm14, xmm15, xmm2, xmm6, xmm7, xmm0);
hash.c: ^
hash.c: In file included from /usr/lib/gcc/i686-linux-gnu/5/include/pmmintrin.h:31:0,
hash.c: from /usr/lib/gcc/i686-linux-gnu/5/include/tmmintrin.h:31,
hash.c: from /usr/lib/gcc/i686-linux-gnu/5/include/smmintrin.h:32,
hash.c: from groestl-intr-aes.h:10,
hash.c: from hash.c:28:
hash.c: /usr/lib/gcc/i686-linux-gnu/5/include/emmintrin.h:975:1: error: inlining failed in call to always_inline '_mm_unpackhi_epi32': target specific option mismatch
hash.c: _mm_unpackhi_epi32 (__m128i __A, __m128i __B)
hash.c: ^
hash.c: In file included from hash.c:28:0:
hash.c: groestl-intr-aes.h:264:8: error: called from here
hash.c: o3 = _mm_unpackhi_epi32(o3, t0);\
hash.c: ^
hash.c: groestl-intr-aes.h:368:3: note: in expansion of macro 'Matrix_Transpose_A'
hash.c: Matrix_Transpose_A(xmm12, xmm13, xmm14, xmm15, xmm2, xmm6, xmm7, xmm0);
hash.c: ^
hash.c: In file included from /usr/lib/gcc/i686-linux-gnu/5/include/pmmintrin.h:31:0,
hash.c: from /usr/lib/gcc/i686-linux-gnu/5/include/tmmintrin.h:31,
hash.c: ...

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv	aesni-intr
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv	aesni-intr
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv	aesni-intr
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv	aesni-intr

Compiler output

Implementation: crypto_hash/groestl256/vperm-intr
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv

hash.c: In file included from hash.c:34:0:
hash.c: groestl-intr-vperm.h: In function 'INIT':
hash.c: groestl-intr-vperm.h:77:6: warning: SSE vector return without SSE enabled changes the ABI [-Wpsabi]
hash.c: t0 = _mm_andnot_si128(t0, a0);\
hash.c: ^
hash.c: groestl-intr-vperm.h:116:3: note: in expansion of macro 'VPERM_Transform_No_Const'
hash.c: VPERM_Transform_No_Const(a0, a1, t0, t1, t2, t3, c0, c1, c2);\
hash.c: ^
hash.c: groestl-intr-vperm.h:633:3: note: in expansion of macro 'VPERM_Transform'
hash.c: VPERM_Transform(xmm0, xmm1, VPERM_IPT, xmm4, xmm5, xmm6, xmm7, xmm8, xmm9, xmm10);\
hash.c: ^
hash.c: groestl-intr-vperm.h:650:3: note: in expansion of macro 'VPERM_Transform_RoundConst'
hash.c: VPERM_Transform_RoundConst();
hash.c: ^
hash.c: In file included from /usr/lib/gcc/i686-linux-gnu/5/include/pmmintrin.h:31:0,
hash.c: from /usr/lib/gcc/i686-linux-gnu/5/include/tmmintrin.h:31,
hash.c: from groestl-intr-vperm.h:13,
hash.c: from hash.c:34:
hash.c: /usr/lib/gcc/i686-linux-gnu/5/include/emmintrin.h:975:1: error: inlining failed in call to always_inline '_mm_unpackhi_epi32': target specific option mismatch
hash.c: _mm_unpackhi_epi32 (__m128i __A, __m128i __B)
hash.c: ^
hash.c: In file included from hash.c:34:0:
hash.c: groestl-intr-vperm.h:523:8: error: called from here
hash.c: o3 = _mm_unpackhi_epi32(o3, t0);\
hash.c: ^
hash.c: ...

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv	vperm-intr
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv	vperm-intr
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv	vperm-intr
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv	vperm-intr

Compiler output

Implementation: crypto_hash/groestl256/avx-intr
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv

hash.c: In file included from hash.c:9:0:
hash.c: groestl-intr-avx.h: In function 'INIT':
hash.c: groestl-intr-avx.h:246:6: warning: SSE vector return without SSE enabled changes the ABI [-Wpsabi]
hash.c: i0 = _mm_shuffle_epi8(i0, t0);\
hash.c: ^
hash.c: groestl-intr-avx.h:353:3: note: in expansion of macro 'Matrix_Transpose_A'
hash.c: Matrix_Transpose_A(xmm12, xmm13, xmm14, xmm15, xmm2, xmm6, xmm7, xmm0);
hash.c: ^
hash.c: In file included from /usr/lib/gcc/i686-linux-gnu/5/include/pmmintrin.h:31:0,
hash.c: from /usr/lib/gcc/i686-linux-gnu/5/include/tmmintrin.h:31,
hash.c: from /usr/lib/gcc/i686-linux-gnu/5/include/smmintrin.h:32,
hash.c: from groestl-intr-avx.h:10,
hash.c: from hash.c:9:
hash.c: /usr/lib/gcc/i686-linux-gnu/5/include/emmintrin.h:999:1: error: inlining failed in call to always_inline '_mm_unpacklo_epi32': target specific option mismatch
hash.c: _mm_unpacklo_epi32 (__m128i __A, __m128i __B)
hash.c: ^
hash.c: In file included from hash.c:9:0:
hash.c: groestl-intr-avx.h:264:8: error: called from here
hash.c: o1 = _mm_unpacklo_epi32(o1, t0);\
hash.c: ^
hash.c: groestl-intr-avx.h:353:3: note: in expansion of macro 'Matrix_Transpose_A'
hash.c: Matrix_Transpose_A(xmm12, xmm13, xmm14, xmm15, xmm2, xmm6, xmm7, xmm0);
hash.c: ^
hash.c: In file included from /usr/lib/gcc/i686-linux-gnu/5/include/pmmintrin.h:31:0,
hash.c: from /usr/lib/gcc/i686-linux-gnu/5/include/tmmintrin.h:31,
hash.c: ...

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv	avx-intr
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv	avx-intr
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv	avx-intr
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv	avx-intr

Compiler output

Implementation: crypto_hash/groestl256/vperm
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv

hash.c: groestl-asm-vperm.h: Assembler messages:
hash.c: groestl-asm-vperm.h:705: Error: too many memory references for `movaps'
hash.c: groestl-asm-vperm.h:705: Error: too many memory references for `movaps'
hash.c: groestl-asm-vperm.h:705: Error: too many memory references for `movaps'
hash.c: groestl-asm-vperm.h:705: Error: too many memory references for `movaps'
hash.c: groestl-asm-vperm.h:705: Error: too many memory references for `movaps'
hash.c: groestl-asm-vperm.h:705: Error: too many memory references for `movaps'
hash.c: groestl-asm-vperm.h:705: Error: too many memory references for `movaps'
hash.c: groestl-asm-vperm.h:705: Error: too many memory references for `movaps'
hash.c: groestl-asm-vperm.h:705: Error: too many memory references for `movaps'
hash.c: groestl-asm-vperm.h:705: Error: too many memory references for `movaps'
hash.c: groestl-asm-vperm.h:705: Error: too many memory references for `movaps'
hash.c: groestl-asm-vperm.h:705: Error: too many memory references for `movaps'
hash.c: groestl-asm-vperm.h:705: Error: too many memory references for `movaps'
hash.c: groestl-asm-vperm.h:705: Error: too many memory references for `movaps'
hash.c: groestl-asm-vperm.h:705: Error: too many memory references for `movaps'
hash.c: groestl-asm-vperm.h:705: Error: too many memory references for `movaps'
hash.c: groestl-asm-vperm.h:705: Error: too many memory references for `movaps'
hash.c: groestl-asm-vperm.h:705: Error: too many memory references for `movaps'
hash.c: groestl-asm-vperm.h:708: Error: too many memory references for `movaps'
hash.c: groestl-asm-vperm.h:709: Error: too many memory references for `movaps'
hash.c: groestl-asm-vperm.h:710: Error: too many memory references for `movaps'
hash.c: groestl-asm-vperm.h:711: Error: too many memory references for `movaps'
hash.c: groestl-asm-vperm.h:715: Error: operand size mismatch for `pand'
hash.c: groestl-asm-vperm.h:715: Error: operand size mismatch for `pand'
hash.c: ...

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv	vperm
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv	vperm
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv	vperm
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv	vperm

Compiler output

Implementation: crypto_hash/groestl256/opt64
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv

hash.c: hash.c:194:14: warning: 'inP' is static but declared in inline function 'F1024' which is not static
hash.c: static u64 inP[COLS1024] __attribute__((aligned(16)));
hash.c: ^
hash.c: hash.c:193:14: warning: 'outQ' is static but declared in inline function 'F1024' which is not static
hash.c: static u64 outQ[COLS1024] __attribute__((aligned(16)));
hash.c: ^
hash.c: hash.c:192:14: warning: 'z' is static but declared in inline function 'F1024' which is not static
hash.c: static u64 z[COLS1024] __attribute__((aligned(16)));
hash.c: ^
hash.c: hash.c:191:14: warning: 'y' is static but declared in inline function 'F1024' which is not static
hash.c: static u64 y[COLS1024] __attribute__((aligned(16)));
hash.c: ^

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv	opt64
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv	opt64
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv	opt64
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv	opt64