Implementation notes: amd64, hydra7, crypto_stream/chacha12

Computer: hydra7
Microarchitecture: amd64; Sandy Bridge+AES (206a7)
Architecture: amd64
CPU ID: GenuineIntel-000206a7-bfebfbff
SUPERCOP version: 20240107
Operation: crypto_stream
Primitive: chacha12

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
2343	3318 0 0	15392 780 992	`moon/avx/64`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
2353	3331 0 0	16933 804 1024	`moon/avx/64`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
2358	3339 0 0	16612 796 1024	`moon/avx/64`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
2390	3331 0 0	18261 804 1024	`moon/avx/64`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
2642	3803 0 0	17076 796 1024	`moon/ssse3/64`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
2647	3795 0 0	17397 804 1024	`moon/ssse3/64`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
2651	3795 0 0	18725 804 1024	`moon/ssse3/64`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
2652	3782 0 0	15856 780 992	`moon/ssse3/64`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
2821	5009 0 4	18732 796 1056	`dolbeau/amd64-avx2`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
2921	6889 0 4	22325 804 1056	`dolbeau/amd64-avx2`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
3000	5129 0 4	19253 804 1056	`dolbeau/amd64-avx2`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
3001	4668 0 4	18357 804 1056	`amd64-ssse3`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
3002	4626 0 4	17972 796 1056	`amd64-ssse3`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
3022	4668 0 4	19701 804 1056	`amd64-ssse3`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
3026	4474 0 4	16608 780 1024	`amd64-ssse3`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
3187	4763 0 4	17256 780 1024	`dolbeau/amd64-avx2`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
3241	3994 0 0	17605 804 1024	`moon/sse2/64`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
3241	3981 0 0	16064 780 992	`moon/sse2/64`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
3245	3994 0 0	18933 804 1024	`moon/sse2/64`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
3255	4002 0 0	17284 796 1024	`moon/sse2/64`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
3722	4860 0 4	19845 804 1056	`e/amd64-xmm6`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
3735	4818 0 4	18100 796 1056	`e/amd64-xmm6`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
3742	4666 0 4	16768 780 1024	`e/amd64-xmm6`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
3745	4860 0 4	18517 804 1056	`e/amd64-xmm6`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
3921	17922 2368 0	1770596 147036 10496	`T:cryptopp`	`g++_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
3956	17459 2368 0	1769042 147044 10496	`T:cryptopp`	`g++_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
4014	17133 2368 0	1767837 147044 10496	`T:cryptopp`	`g++_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
4053	8184 2880 0	1761705 147700 10464	`T:cryptopp`	`g++_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
8312	2883 0 4	16164 796 1056	`e/amd64-3`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
8327	2925 0 4	16581 804 1056	`e/amd64-3`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
8329	2733 0 4	14800 780 1024	`e/amd64-3`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
8354	2925 0 4	17909 804 1056	`e/amd64-3`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
9147	2605 0 4	16300 796 1056	`e/merged`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
9259	3331 0 4	18757 804 1056	`e/ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
9389	3881 0 4	19285 804 1056	`e/merged`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
9423	2471 0 4	14936 780 1024	`e/merged`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
9448	2697 0 4	16789 804 1056	`e/merged`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
9694	3331 0 4	18757 804 1056	`e/regs`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
12598	2579 0 4	16693 804 1056	`e/regs`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
13345	2567 0 4	16268 796 1056	`e/regs`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
13912	2320 0 4	14792 780 1024	`e/regs`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
14380	2595 0 4	16709 804 1056	`e/ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
15325	2466 0 4	16172 796 1056	`e/ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212
15989	2149 0 4	14616 780 1024	`e/ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231213	20231212

Test failure

Implementation: krovetz/vec128
Security model: constbranchindex
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

error 111

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	krovetz/vec128
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	krovetz/vec128
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	krovetz/vec128
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	krovetz/vec128
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	moon/avx2/64
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	moon/avx2/64
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	moon/avx2/64
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	moon/avx2/64
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	moon/xop/64
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	moon/xop/64
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	moon/xop/64
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	moon/xop/64

Compiler output

Implementation: dolbeau/mipsel-msa
Security model: constbranchindex
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

chacha.c: chacha.c:11:10: fatal error: arm_neon.h: No such file or directory
chacha.c: 11 | #include <arm_neon.h>
chacha.c: | ^~~~~~~~~~~~
chacha.c: compilation terminated.

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/mipsel-msa
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/mipsel-msa
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/mipsel-msa
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/mipsel-msa

Compiler output

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

stream.c: stream.c:126:2: error: #error -- Implementation supports only microarchitectures with support for Advanced Vector Extensions (AVX2 or AVX512).
stream.c: 126 | #error -- Implementation supports only microarchitectures with support for Advanced Vector Extensions (AVX2 or AVX512).
stream.c: | ^~~~~

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

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

Compiler output

Implementation: krovetz/avx2
Security model: constbranchindex
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

stream.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:47,
stream.c: from stream.c:8:
stream.c: stream.c: In function 'crypto_stream_chacha12_krovetz_avx2_constbranchindex_xor':
stream.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/avx2intrin.h:574:1: error: inlining failed in call to 'always_inline' '_mm256_or_si256': target specific option mismatch
stream.c: 574 | _mm256_or_si256 (__m256i __A, __m256i __B)
stream.c: | ^~~~~~~~~~~~~~~
stream.c: stream.c:63:18: note: called from here
stream.c: 63 | __m256i s3 = _mm256_or_si256(
stream.c: | ^~~~~~~~~~~~~~~~
stream.c: 64 | _mm256_slli_si256(_mm256_broadcastq_epi64(*(__m128i *)n), 8),
stream.c: | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
stream.c: 65 | _mm256_set_epi32(0,0,0,1,0,0,0,0)
stream.c: | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
stream.c: 66 | );
stream.c: | ~
stream.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:47,
stream.c: from stream.c:8:
stream.c: /usr/lib/gcc/x86_64-linux-gnu/11/include/avx2intrin.h:655:1: error: inlining failed in call to 'always_inline' '_mm256_slli_si256': target specific option mismatch
stream.c: 655 | _mm256_slli_si256 (__m256i __A, const int __N)
stream.c: | ^~~~~~~~~~~~~~~~~
stream.c: stream.c:63:18: note: called from here
stream.c: 63 | __m256i s3 = _mm256_or_si256(
stream.c: | ^~~~~~~~~~~~~~~~
stream.c: 64 | _mm256_slli_si256(_mm256_broadcastq_epi64(*(__m128i *)n), 8),
stream.c: | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
stream.c: ...

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	krovetz/avx2
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	krovetz/avx2
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	krovetz/avx2
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	krovetz/avx2