Implementation notes: amd64, saber214, crypto_decode/1277x2627

Computer: saber214
Microarchitecture: amd64; Bulldozer (600f20)
Architecture: amd64
CPU ID: AuthenticAMD-00600f20-1789c3f5
SUPERCOP version: 20240107
Operation: crypto_decode
Primitive: 1277x2627

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
17559	9601 0 0	22828 816 744	`portable`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
17863	7126 0 0	17964 816 728	`portable`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
29165	3737 0 0	16972 816 744	`int16`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
29420	2741 0 0	13572 816 728	`int16`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
30375	2548 0 0	12132 816 728	`int16`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
30444	2352 0 0	11526 808 728	`int16`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
30775	3716 0 0	15652 816 728	`int16`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
32177	2814 0 0	13069 768 800	`int16`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231212	20231212
32568	7485 0 0	19436 816 728	`portable`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
34496	2711 0 0	13206 776 800	`int16`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231212	20231212
34922	4497 0 0	16462 776 800	`int16`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231212	20231212
36426	2678 0 0	11993 752 768	`int16`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231212	20231212
45428	3387 0 0	12574 808 728	`portable`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
45895	3395 0 0	12972 816 728	`portable`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
46131	3956 0 0	15910 776 800	`portable`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231212	20231212
48690	3400 0 0	13886 776 800	`portable`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231212	20231212
97935	1911 0 0	13822 776 800	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231212	20231212
98529	2802 0 0	14740 816 728	`ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
100510	2657 0 0	15892 816 744	`ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
100569	2083 0 0	12924 816 728	`ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
103744	1626 0 0	12062 776 800	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231212	20231212
105128	2098 0 0	12373 768 800	`portable`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231212	20231212
106434	1162 0 0	10310 808 728	`ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
107683	2054 0 0	11385 752 768	`portable`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231212	20231212
109580	1169 0 0	10740 816 728	`ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
127562	1685 0 0	11869 768 800	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231212	20231212
133568	1542 0 0	10745 752 768	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231212	20231212

Compiler output

Implementation: avx
Security model: constbranchindex
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

decode.c: decode.c:245:10: error: always_inline function '_mm256_srli_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_decode_1277x2627_avx_constbranchindex' that is compiled without support for 'avx2'
decode.c: S1 = _mm256_srli_epi16(S0,8);
decode.c: ^
decode.c: decode.c:260:10: error: always_inline function '_mm256_unpacklo_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_decode_1277x2627_avx_constbranchindex' that is compiled without support for 'avx2'
decode.c: B0 = _mm256_unpacklo_epi16(A0,A1);
decode.c: ^
decode.c: decode.c:261:10: error: always_inline function '_mm256_unpackhi_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_decode_1277x2627_avx_constbranchindex' that is compiled without support for 'avx2'
decode.c: B1 = _mm256_unpackhi_epi16(A0,A1);
decode.c: ^
decode.c: decode.c:264:10: error: '__builtin_ia32_permti256' needs target feature avx2
decode.c: C0 = _mm256_permute2x128_si256(B0,B1,0x20);
decode.c: ^
decode.c: /usr/lib/llvm-14/lib/clang/14.0.0/include/avx2intrin.h:821:13: note: expanded from macro '_mm256_permute2x128_si256'
decode.c: ((__m256i)__builtin_ia32_permti256((__m256i)(V1), (__m256i)(V2), (int)(M)))
decode.c: ^
decode.c: decode.c:265:10: error: '__builtin_ia32_permti256' needs target feature avx2
decode.c: C1 = _mm256_permute2x128_si256(B0,B1,0x31);
decode.c: ^
decode.c: /usr/lib/llvm-14/lib/clang/14.0.0/include/avx2intrin.h:821:13: note: expanded from macro '_mm256_permute2x128_si256'
decode.c: ((__m256i)__builtin_ia32_permti256((__m256i)(V1), (__m256i)(V2), (int)(M)))
decode.c: ^
decode.c: decode.c:298:10: error: always_inline function '_mm256_srli_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_decode_1277x2627_avx_constbranchindex' that is compiled without support for 'avx2'
decode.c: S1 = _mm256_srli_epi16(S0,8);
decode.c: ^
decode.c: decode.c:313:10: error: always_inline function '_mm256_unpacklo_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_decode_1277x2627_avx_constbranchindex' that is compiled without support for 'avx2'
decode.c: ...

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

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx

Compiler output

Implementation: avx
Security model: constbranchindex
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

decode.c: decode.c:243:15: error: always_inline function '_mm256_loadu_si256' requires target feature 'avx', but would be inlined into function 'crypto_decode_1277x2627_avx_constbranchindex' that is compiled without support for 'avx'
decode.c: A2 = A0 = _mm256_loadu_si256((__m256i *) &R6[i]);
decode.c: ^
decode.c: decode.c:243:15: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
decode.c: decode.c:244:10: error: always_inline function '_mm256_loadu_si256' requires target feature 'avx', but would be inlined into function 'crypto_decode_1277x2627_avx_constbranchindex' that is compiled without support for 'avx'
decode.c: S0 = _mm256_loadu_si256((__m256i *) (s+2*i));
decode.c: ^
decode.c: decode.c:244:10: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
decode.c: decode.c:245:10: error: always_inline function '_mm256_srli_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_decode_1277x2627_avx_constbranchindex' that is compiled without support for 'avx2'
decode.c: S1 = _mm256_srli_epi16(S0,8);
decode.c: ^
decode.c: decode.c:245:10: error: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
decode.c: decode.c:246:11: error: always_inline function '_mm256_set1_epi16' requires target feature 'avx', but would be inlined into function 'crypto_decode_1277x2627_avx_constbranchindex' that is compiled without support for 'avx'
decode.c: S0 &= _mm256_set1_epi16(255);
decode.c: ^
decode.c: decode.c:246:11: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
decode.c: decode.c:247:14: warning: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI [-Wpsabi]
decode.c: A0 = sub(mulhiconst(A0,-259),mulhiconst(mulloconst(A0,-5225),3211)); /* -1671...1605 */
decode.c: ^
decode.c: decode.c:247:45: warning: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI [-Wpsabi]
decode.c: A0 = sub(mulhiconst(A0,-259),mulhiconst(mulloconst(A0,-5225),3211)); /* -1671...1605 */
decode.c: ^
decode.c: decode.c:247:34: warning: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI [-Wpsabi]
decode.c: A0 = sub(mulhiconst(A0,-259),mulhiconst(mulloconst(A0,-5225),3211)); /* -1671...1605 */
decode.c: ^
decode.c: ...

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

Compiler	Implementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	avx

Compiler output

Implementation: avx
Security model: constbranchindex
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

decode.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:47,
decode.c: from decode.c:3:
decode.c: decode.c: In function 'add':
decode.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/avx2intrin.h:112:1: error: inlining failed in call to 'always_inline' '_mm256_add_epi16': target specific option mismatch
decode.c: 112 | _mm256_add_epi16 (__m256i __A, __m256i __B)
decode.c: | ^~~~~~~~~~~~~~~~
decode.c: decode.c:22:10: note: called from here
decode.c: 22 | return _mm256_add_epi16(x,y);
decode.c: | ^~~~~~~~~~~~~~~~~~~~~

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

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