Implementation notes: amd64, wooden, crypto_stream/chacha8

Computer: wooden
Microarchitecture: amd64; Goldmont (506c9)
Architecture: amd64
CPU ID: GenuineIntel-000506c9-bfebfbff
SUPERCOP version: 20221122
Operation: crypto_stream
Primitive: chacha8
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
22753761 0 018464 780 1016moon/ssse3/64gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022101020221005
22773753 0 020264 812 952moon/ssse3/64clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
22773742 0 016086 804 952moon/ssse3/64clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
22773742 0 015539 756 984moon/ssse3/64gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022101020221005
22783761 0 017216 780 1016moon/ssse3/64gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022101020221005
22793753 0 017944 812 952moon/ssse3/64clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
22793753 0 018792 812 952moon/ssse3/64clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
22793767 0 016759 772 1016moon/ssse3/64gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022101020221005
22813753 0 016550 804 952moon/ssse3/64clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
24155261 0 121776 812 952dolbeau/amd64-avx2clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
24205261 0 119472 812 952dolbeau/amd64-avx2clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
24204253 0 116606 804 952dolbeau/amd64-avx2clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
25113952 0 018152 812 952moon/sse2/64clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
25113941 0 016294 804 952moon/sse2/64clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
25113952 0 019000 812 952moon/sse2/64clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
25123960 0 018672 780 1016moon/sse2/64gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022101020221005
25133966 0 016967 772 1016moon/sse2/64gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022101020221005
25143960 0 017424 780 1016moon/sse2/64gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022101020221005
25153952 0 020472 812 952moon/sse2/64clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
25153941 0 015747 756 984moon/sse2/64gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022101020221005
25163952 0 016758 804 952moon/sse2/64clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
25734774 0 117630 804 952dolbeau/amd64-avx2clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
27984429 0 119528 812 952amd64-ssse3clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
27984559 0 418080 780 1048amd64-ssse3gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022101020221005
27984559 0 419344 780 1048amd64-ssse3gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022101020221005
28004429 0 118664 812 952amd64-ssse3clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
28004429 0 120968 812 952amd64-ssse3clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
28024429 0 117318 804 952amd64-ssse3clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
28114511 0 417559 772 1048amd64-ssse3gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022101020221005
28154360 0 416195 756 1016amd64-ssse3gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022101020221005
28174365 0 116758 804 952amd64-ssse3clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
29056410 0 421144 780 1048dolbeau/amd64-avx2gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022101020221005
29175370 0 418872 780 1048dolbeau/amd64-avx2gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022101020221005
30364672 0 416507 756 1016dolbeau/amd64-avx2gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022101020221005
30444621 0 118808 812 952e/amd64-xmm6clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
30444621 0 121128 812 952e/amd64-xmm6clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
30464557 0 116886 804 952e/amd64-xmm6clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
30484703 0 417687 772 1048e/amd64-xmm6gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022101020221005
30504621 0 117446 804 952e/amd64-xmm6clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
30554621 0 119688 812 952e/amd64-xmm6clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
30634751 0 419488 780 1048e/amd64-xmm6gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022101020221005
30644751 0 418240 780 1048e/amd64-xmm6gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022101020221005
30654552 0 416355 756 1016e/amd64-xmm6gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022101020221005
31985245 0 418247 772 1048dolbeau/amd64-avx2gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022101020221005
357417894 2368 01696571 146956 10488T:cryptoppg++_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022101020221005
359212793 1736 01396415 146372 10392T:cryptoppclang++_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
359217963 2368 01695585 146964 10488T:cryptoppg++_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022101020221005
36146767 976 01386804 145724 10392T:cryptoppclang++_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
361611274 1608 01392643 146364 10392T:cryptoppclang++_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
36927194 2880 01686472 147612 10456T:cryptoppg++_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022101020221005
371617034 2368 01693804 146964 10488T:cryptoppg++_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022101020221005
409216327 3792 01399160 148340 10392T:cryptoppclang++_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
41032885 0 119384 812 952e/mergedclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
42321740 0 114070 804 952e/mergedclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
42592237 0 116432 812 952e/mergedclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
68372816 0 416304 780 1048e/amd64-3gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022101020221005
68372816 0 417552 780 1048e/amd64-3gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022101020221005
68382688 0 115494 804 952e/amd64-3clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
68402768 0 415751 772 1048e/amd64-3gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022101020221005
68412688 0 117736 812 952e/amd64-3clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
68412617 0 414387 756 1016e/amd64-3gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022101020221005
68422688 0 116856 812 952e/amd64-3clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
68422688 0 119176 812 952e/amd64-3clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
68472628 0 114934 804 952e/amd64-3clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
75162918 0 417672 780 1048e/regsgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022101020221005
77802950 0 417704 780 1048e/refgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022101020221005
77932421 0 116616 812 952e/refclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
78102458 0 415960 780 1048e/mergedgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022101020221005
78553802 0 418536 780 1048e/mergedgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022101020221005
79192421 0 118920 812 952e/refclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
79322509 0 116688 812 952e/regsclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
79673173 0 118232 812 952e/mergedclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
80442509 0 118992 812 952e/regsclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
82562294 0 115110 804 952e/mergedclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
85672258 0 414051 756 1016e/mergedgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022101020221005
87132364 0 415367 772 1048e/mergedgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022101020221005
90052789 0 117848 812 952e/refclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
91852837 0 117896 812 952e/regsclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
110601714 0 114046 804 952e/refclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
111782310 0 415832 780 1048e/regsgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022101020221005
116411919 0 114238 804 952e/regsclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
120742223 0 415223 772 1048e/regsgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022101020221005
122942206 0 115030 804 952e/regsclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
129232390 0 415912 780 1048e/refgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022101020221005
131012190 0 115014 804 952e/refclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2022101020221005
155492047 0 413843 756 1016e/regsgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022101020221005
160432162 0 415175 772 1048e/refgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022101020221005
189441851 0 413651 756 1016e/refgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2022101020221005

Test failure

Implementation: krovetz/vec128
Security model: constbranchindex
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
error 111

Number of similar (compiler,implementation) pairs: 36, namely:
CompilerImplementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE krovetz/vec128
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE krovetz/vec128
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE krovetz/vec128
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE krovetz/vec128
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE krovetz/vec128
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
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE moon/avx/64
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE moon/avx/64
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE moon/avx/64
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE moon/avx/64
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE moon/avx/64
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE moon/avx/64
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE moon/avx/64
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE moon/avx/64
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE moon/avx/64
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE moon/avx2/64
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE moon/avx2/64
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE moon/avx2/64
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE moon/avx2/64
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE moon/avx2/64
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
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE moon/xop/64
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE moon/xop/64
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE moon/xop/64
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE moon/xop/64
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE moon/xop/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/amd64-avx2
Security model: constbranchindex
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
chacha.c: In file included from chacha.c:103:
chacha.c: ./u4.h:122:7: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'crypto_stream_chacha8_dolbeau_amd64_avx2_constbranchindex_ECRYPT_encrypt_bytes' that is compiled without support for 'ssse3'
chacha.c: VEC4_QUARTERROUND( 0, 4, 8,12);
chacha.c: ^
chacha.c: ./u4.h:17:36: note: expanded from macro 'VEC4_QUARTERROUND'
chacha.c: #define VEC4_QUARTERROUND(a,b,c,d) VEC4_QUARTERROUND_SHUFFLE(a,b,c,d)
chacha.c: ^
chacha.c: ./u4.h:12:86: note: expanded from macro 'VEC4_QUARTERROUND_SHUFFLE'
chacha.c: x_##a = _mm_add_epi32(x_##a, x_##b); t_##a = _mm_xor_si128(x_##d, x_##a); x_##d = _mm_shuffle_epi8(t_##a, rot16); \
chacha.c: ^
chacha.c: ./u4.h:122:7: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'crypto_stream_chacha8_dolbeau_amd64_avx2_constbranchindex_ECRYPT_encrypt_bytes' that is compiled without support for 'ssse3'
chacha.c: ./u4.h:17:36: note: expanded from macro 'VEC4_QUARTERROUND'
chacha.c: #define VEC4_QUARTERROUND(a,b,c,d) VEC4_QUARTERROUND_SHUFFLE(a,b,c,d)
chacha.c: ^
chacha.c: ./u4.h:14:86: note: expanded from macro 'VEC4_QUARTERROUND_SHUFFLE'
chacha.c: x_##a = _mm_add_epi32(x_##a, x_##b); t_##a = _mm_xor_si128(x_##d, x_##a); x_##d = _mm_shuffle_epi8(t_##a, rot8); \
chacha.c: ^
chacha.c: ./u4.h:123:7: error: always_inline function '_mm_shuffle_epi8' requires target feature 'ssse3', but would be inlined into function 'crypto_stream_chacha8_dolbeau_amd64_avx2_constbranchindex_ECRYPT_encrypt_bytes' that is compiled without support for 'ssse3'
chacha.c: VEC4_QUARTERROUND( 1, 5, 9,13);
chacha.c: ^
chacha.c: ./u4.h:17:36: note: expanded from macro 'VEC4_QUARTERROUND'
chacha.c: #define VEC4_QUARTERROUND(a,b,c,d) VEC4_QUARTERROUND_SHUFFLE(a,b,c,d)
chacha.c: ^
chacha.c: ./u4.h:12:86: note: expanded from macro 'VEC4_QUARTERROUND_SHUFFLE'
chacha.c: x_##a = _mm_add_epi32(x_##a, x_##b); t_##a = _mm_xor_si128(x_##d, x_##a); x_##d = _mm_shuffle_epi8(t_##a, rot16); \
chacha.c: ...

Number of similar (compiler,implementation) pairs: 1, namely:
CompilerImplementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE dolbeau/amd64-avx2

Compiler output

Implementation: dolbeau/mipsel-msa
Security model: constbranchindex
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
chacha.c: In file included from chacha.c:11:
chacha.c: /usr/lib/llvm-11/lib/clang/11.0.1/include/arm_neon.h:28:2: error: "NEON intrinsics not available with the soft-float ABI. Please use -mfloat-abi=softfp or -mfloat-abi=hard"
chacha.c: #error "NEON intrinsics not available with the soft-float ABI. Please use -mfloat-abi=softfp or -mfloat-abi=hard"
chacha.c: ^
chacha.c: 1 error generated.

Number of similar (compiler,implementation) pairs: 5, namely:
CompilerImplementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE dolbeau/mipsel-msa
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE dolbeau/mipsel-msa
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE dolbeau/mipsel-msa
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE dolbeau/mipsel-msa
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE dolbeau/mipsel-msa

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:
CompilerImplementations
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: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
stream.c: stream.c:126:2: error: -- Implementation supports only microarchitectures with support for Advanced Vector Extensions (AVX2 or AVX512).
stream.c: #error -- Implementation supports only microarchitectures with support for Advanced Vector Extensions (AVX2 or AVX512).
stream.c: ^
stream.c: 1 error generated.

Number of similar (compiler,implementation) pairs: 5, namely:
CompilerImplementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE goll_gueron
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE goll_gueron
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE goll_gueron
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE goll_gueron
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE goll_gueron

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:
CompilerImplementations
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: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE
stream.c: stream.c:56:43: error: passing '__m128i *' to parameter of incompatible type '__m128i' (vector of 2 'long long' values); dereference with *
stream.c: __m256i s0 = _mm_broadcastsi128_si256((__m128i *)sigma);
stream.c: ^~~~~~~~~~~~~~~~
stream.c: *
stream.c: /usr/lib/llvm-11/lib/clang/11.0.1/include/avx2intrin.h:743:65: note: expanded from macro '_mm_broadcastsi128_si256'
stream.c: #define _mm_broadcastsi128_si256(X) _mm256_broadcastsi128_si256(X)
stream.c: ^
stream.c: /usr/lib/llvm-11/lib/clang/11.0.1/include/avx2intrin.h:738:37: note: passing argument to parameter '__X' here
stream.c: _mm256_broadcastsi128_si256(__m128i __X)
stream.c: ^
stream.c: 1 error generated.

Number of similar (compiler,implementation) pairs: 5, namely:
CompilerImplementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE krovetz/avx2
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE krovetz/avx2
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE krovetz/avx2
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE krovetz/avx2
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE krovetz/avx2

Compiler output

Implementation: krovetz/avx2
Security model: constbranchindex
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE
stream.c: stream.c: In function 'crypto_stream_chacha8_krovetz_avx2_constbranchindex_xor':
stream.c: stream.c:58:13: warning: AVX vector return without AVX enabled changes the ABI [-Wpsabi]
stream.c: 58 | __m256i s0 = _mm256_broadcastsi128_si256(*(__m128i *)sigma);
stream.c: | ^~
stream.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/10/include/immintrin.h:53,
stream.c: from stream.c:8:
stream.c: /usr/lib/gcc/x86_64-linux-gnu/10/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/10/include/immintrin.h:53,
stream.c: from stream.c:8:
stream.c: /usr/lib/gcc/x86_64-linux-gnu/10/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: ...

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