Implementation notes: amd64, saber214, crypto_decode/953x2115

Computer: saber214
Microarchitecture: amd64; Bulldozer (600f20)
Architecture: amd64
CPU ID: AuthenticAMD-00600f20-1789c3f5
SUPERCOP version: 20240107
Operation: crypto_decode
Primitive: 953x2115

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
13196	6639 0 0	19868 816 744	`portable`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
13342	5663 0 0	16500 816 728	`portable`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
20636	2187 0 0	13020 816 728	`int16`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
20691	2985 0 0	16220 816 744	`int16`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
21453	2046 0 0	11222 808 728	`int16`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
22039	2987 0 0	14940 816 728	`int16`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
22266	2187 0 0	11756 816 728	`int16`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
23573	2501 0 0	12757 768 800	`int16`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231212	20231212
23720	3601 0 0	15566 776 800	`int16`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231212	20231212
23914	6986 0 0	18940 816 728	`portable`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
24094	2461 0 0	12958 776 800	`int16`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231212	20231212
26837	2356 0 0	11633 752 768	`int16`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231212	20231212
34307	2931 0 0	12508 816 728	`portable`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
35474	3044 0 0	13534 776 800	`portable`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231212	20231212
36132	4517 0 0	16470 776 800	`portable`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231212	20231212
37073	2798 0 0	11966 808 728	`portable`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
73178	2380 0 0	14324 816 728	`ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
74081	1830 0 0	13734 776 800	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231212	20231212
74585	1875 0 0	12716 816 728	`ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
75720	2363 0 0	15604 816 744	`ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
77759	1618 0 0	12062 776 800	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231212	20231212
78608	1872 0 0	12149 768 800	`portable`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231212	20231212
79540	1162 0 0	10310 808 728	`ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
81313	1811 0 0	11145 752 768	`portable`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231212	20231212
82177	1169 0 0	10740 816 728	`ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231212	20231212
94651	1673 0 0	11853 768 800	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231212	20231212
100363	1530 0 0	10729 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:261:10: error: always_inline function '_mm256_cvtepu8_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_decode_953x2115_avx_constbranchindex' that is compiled without support for 'avx2'
decode.c: S0 = _mm256_cvtepu8_epi16(_mm_loadu_si128((__m128i *) (s+i)));
decode.c: ^
decode.c: decode.c:275:10: error: always_inline function '_mm256_unpacklo_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_decode_953x2115_avx_constbranchindex' that is compiled without support for 'avx2'
decode.c: B0 = _mm256_unpacklo_epi16(A0,A1);
decode.c: ^
decode.c: decode.c:276:10: error: always_inline function '_mm256_unpackhi_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_decode_953x2115_avx_constbranchindex' that is compiled without support for 'avx2'
decode.c: B1 = _mm256_unpackhi_epi16(A0,A1);
decode.c: ^
decode.c: decode.c:279:10: 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:280:10: 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:312:10: error: always_inline function '_mm256_cvtepu8_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_decode_953x2115_avx_constbranchindex' that is compiled without support for 'avx2'
decode.c: S0 = _mm256_cvtepu8_epi16(_mm_loadu_si128((__m128i *) (s+i)));
decode.c: ^
decode.c: decode.c:326:10: error: always_inline function '_mm256_unpacklo_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_decode_953x2115_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:260:15: error: always_inline function '_mm256_loadu_si256' requires target feature 'avx', but would be inlined into function 'crypto_decode_953x2115_avx_constbranchindex' that is compiled without support for 'avx'
decode.c: A2 = A0 = _mm256_loadu_si256((__m256i *) &R5[i]);
decode.c: ^
decode.c: decode.c:260:15: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
decode.c: decode.c:261:10: error: always_inline function '_mm256_cvtepu8_epi16' requires target feature 'avx2', but would be inlined into function 'crypto_decode_953x2115_avx_constbranchindex' that is compiled without support for 'avx2'
decode.c: S0 = _mm256_cvtepu8_epi16(_mm_loadu_si128((__m128i *) (s+i)));
decode.c: ^
decode.c: decode.c:261:10: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
decode.c: decode.c:262:14: 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,-116),mulhiconst(mulloconst(A0,29687),468)); /* -263...234 */
decode.c: ^
decode.c: decode.c:262:45: 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,-116),mulhiconst(mulloconst(A0,29687),468)); /* -263...234 */
decode.c: ^
decode.c: decode.c:262:34: 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,-116),mulhiconst(mulloconst(A0,29687),468)); /* -263...234 */
decode.c: ^
decode.c: decode.c:262:10: 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,-116),mulhiconst(mulloconst(A0,29687),468)); /* -263...234 */
decode.c: ^
decode.c: decode.c:263:10: warning: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI [-Wpsabi]
decode.c: A0 = add(A0,S0); /* -263...489 */
decode.c: ^
decode.c: decode.c:264:10: warning: AVX vector argument of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI [-Wpsabi]
decode.c: A0 = subconst(A0,468); /* -731...21 */
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