Implementation notes: amd64, cherry, crypto_stream/chacha8

Computer: cherry
Microarchitecture: amd64; Silvermont (406c4)
Architecture: amd64
CPU ID: GenuineIntel-000406c4-bfebfbff
SUPERCOP version: 20240107
Operation: crypto_stream
Primitive: chacha8
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
38193960 0 018672 780 1016moon/sse2/64gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121320231212
38203960 0 017424 780 1016moon/sse2/64gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121320231212
38293952 0 017840 812 952moon/sse2/64clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
38303952 0 016758 804 952moon/sse2/64clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
38303941 0 016230 804 952moon/sse2/64clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
38313952 0 019440 812 952moon/sse2/64clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
38393941 0 015747 756 984moon/sse2/64gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121320231212
38903952 0 019064 812 952moon/sse2/64clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
38933966 0 016967 772 1016moon/sse2/64gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121320231212
41715357 0 119240 812 952dolbeau/amd64-avx2clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
41715357 0 120888 812 952dolbeau/amd64-avx2clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
41984501 0 116846 804 952dolbeau/amd64-avx2clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
45264774 0 117630 804 952dolbeau/amd64-avx2clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
55644751 0 419488 780 1048e/amd64-xmm6gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121320231212
55654751 0 418240 780 1048e/amd64-xmm6gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121320231212
55674703 0 417687 772 1048e/amd64-xmm6gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121320231212
55714621 0 117446 804 952e/amd64-xmm6clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
55784621 0 119720 812 952e/amd64-xmm6clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
55834557 0 116886 804 952e/amd64-xmm6clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
55904621 0 120128 812 952e/amd64-xmm6clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
55954621 0 118496 812 952e/amd64-xmm6clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
56004552 0 416355 756 1016e/amd64-xmm6gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121320231212
58544666 0 416491 756 1016dolbeau/amd64-avx2gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121320231212
59576394 0 421128 780 1048dolbeau/amd64-avx2gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121320231212
59743753 0 017632 812 952moon/ssse3/64clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
59743753 0 018856 812 952moon/ssse3/64clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
59743761 0 017216 780 1016moon/ssse3/64gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121320231212
59743761 0 018464 780 1016moon/ssse3/64gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121320231212
59763767 0 016759 772 1016moon/ssse3/64gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121320231212
59775370 0 418888 780 1048dolbeau/amd64-avx2gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121320231212
59773742 0 015539 756 984moon/ssse3/64gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121320231212
59783742 0 016022 804 952moon/ssse3/64clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
59813753 0 019232 812 952moon/ssse3/64clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
59823753 0 016550 804 952moon/ssse3/64clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
60925245 0 418247 772 1048dolbeau/amd64-avx2gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121320231212
63344360 0 416195 756 1016amd64-ssse3gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121320231212
63354559 0 418080 780 1048amd64-ssse3gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121320231212
63374559 0 419344 780 1048amd64-ssse3gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121320231212
63394429 0 119968 812 952amd64-ssse3clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
63484429 0 118336 812 952amd64-ssse3clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
63504429 0 119560 812 952amd64-ssse3clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
63594429 0 117318 804 952amd64-ssse3clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
63604365 0 116758 804 952amd64-ssse3clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
63674511 0 417559 772 1048amd64-ssse3gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121320231212
83486764 976 01387092 145724 10392T:cryptoppclang++_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
834911296 1608 01392603 146364 10392T:cryptoppclang++_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
835317964 2368 01695889 146964 10488T:cryptoppg++_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121320231212
835317895 2368 01696859 146956 10488T:cryptoppg++_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121320231212
839712814 1736 01395735 146372 10392T:cryptoppclang++_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
84192688 0 116544 812 952e/amd64-3clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
84192688 0 115494 804 952e/amd64-3clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
84202628 0 114934 804 952e/amd64-3clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
84212688 0 118176 812 952e/amd64-3clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
84212617 0 414387 756 1016e/amd64-3gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121320231212
84222688 0 117768 812 952e/amd64-3clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
84232816 0 417552 780 1048e/amd64-3gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121320231212
84262816 0 416304 780 1048e/amd64-3gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121320231212
84262768 0 415751 772 1048e/amd64-3gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121320231212
846417034 2368 01694092 146964 10488T:cryptoppg++_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121320231212
85217195 2880 01686760 147612 10456T:cryptoppg++_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121320231212
907416327 3792 01399448 148340 10392T:cryptoppclang++_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
94262173 0 114486 804 952e/mergedclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
96342645 0 118144 812 952e/mergedclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
96472645 0 116496 812 952e/mergedclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
98292458 0 415976 780 1048e/mergedgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121320231212
98423802 0 418536 780 1048e/mergedgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121320231212
101502918 0 417672 780 1048e/regsgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121320231212
102162950 0 417704 780 1048e/refgcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121320231212
102543173 0 118264 812 952e/mergedclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
107202364 0 415367 772 1048e/mergedgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121320231212
108452294 0 115110 804 952e/mergedclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
109012258 0 414051 756 1016e/mergedgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121320231212
113602477 0 116328 812 952e/refclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
115412557 0 116408 812 952e/regsclang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
115472557 0 118056 812 952e/regsclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
118192477 0 117976 812 952e/refclang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
122752789 0 117880 812 952e/refclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
123632837 0 117928 812 952e/regsclang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
145002310 0 415848 780 1048e/regsgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121320231212
151472003 0 114318 804 952e/regsclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
158952223 0 415223 772 1048e/regsgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121320231212
159752206 0 115030 804 952e/regsclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
163241955 0 114270 804 952e/refclang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
166872390 0 415928 780 1048e/refgcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121320231212
178112190 0 115014 804 952e/refclang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE2023121320231212
215002162 0 415175 772 1048e/refgcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121320231212
225362047 0 413843 756 1016e/regsgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121320231212
267181852 0 413651 756 1016e/refgcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE2023121320231212

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