Implementation notes: amd64, hydra4, crypto_stream/chacha20

Computer: hydra4
Microarchitecture: amd64; K10 32nm (300f10)
Architecture: amd64
CPU ID: AuthenticAMD-00300f10-178bfbff
SUPERCOP version: 20240107
Operation: crypto_stream
Primitive: chacha20

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
6083	3952 0 0	18264 812 952	`moon/sse2/64`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
6083	3952 0 0	19096 812 952	`moon/sse2/64`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
6087	3941 0 0	15779 756 984	`moon/sse2/64`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
6106	3941 0 0	16254 804 952	`moon/sse2/64`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
6119	3952 0 0	16790 804 952	`moon/sse2/64`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
6120	3974 0 0	19008 780 1016	`moon/sse2/64`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
6121	3974 0 0	17768 780 1016	`moon/sse2/64`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
6122	3962 0 0	16935 772 1016	`moon/sse2/64`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
6140	3952 0 0	19096 812 952	`moon/sse2/64`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
8338	4621 0 1	18936 812 952	`e/amd64-xmm6`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
8338	4621 0 1	19768 812 952	`e/amd64-xmm6`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
8357	4544 0 4	16403 756 1016	`e/amd64-xmm6`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
8379	4621 0 1	17494 804 952	`e/amd64-xmm6`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
8379	4743 0 4	19808 780 1048	`e/amd64-xmm6`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
8380	4621 0 1	19768 812 952	`e/amd64-xmm6`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
8380	4743 0 4	18536 780 1048	`e/amd64-xmm6`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
8382	4557 0 1	16894 804 952	`e/amd64-xmm6`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
8384	4690 0 4	17703 772 1048	`e/amd64-xmm6`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
8978	13401 2240 0	1734000 146876 10488	`T:cryptopp`	`g++_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
9021	12968 2240 0	1732561 146892 10488	`T:cryptopp`	`g++_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
9063	9707 1608 0	1431736 146284 10392	`T:cryptopp`	`clang++_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
9063	12738 2240 0	1731071 146892 10488	`T:cryptopp`	`g++_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
9065	9673 1608 0	1430836 146284 10392	`T:cryptopp`	`clang++_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
9100	5427 976 0	1425209 145644 10392	`T:cryptopp`	`clang++_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
9129	5692 2880 0	1724649 147532 10456	`T:cryptopp`	`g++_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
9266	12867 3664 0	1435605 148252 10392	`T:cryptopp`	`clang++_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
10432	2628 0 1	14958 804 952	`e/amd64-3`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
10435	2808 0 4	16584 780 1048	`e/amd64-3`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
10436	2688 0 1	17800 812 952	`e/amd64-3`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
10437	2609 0 4	14419 756 1016	`e/amd64-3`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
10439	2688 0 1	15526 804 952	`e/amd64-3`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
10439	2808 0 4	17856 780 1048	`e/amd64-3`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
10440	2755 0 4	15751 772 1048	`e/amd64-3`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
10441	2688 0 1	17800 812 952	`e/amd64-3`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
10443	2688 0 1	16968 812 952	`e/amd64-3`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
10960	2306 0 4	15319 772 1048	`e/merged`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
11018	3200 0 4	18264 780 1048	`e/merged`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
11078	2528 0 4	16336 780 1048	`e/merged`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
11511	2951 0 4	18024 780 1048	`e/regs`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
11618	2983 0 4	18056 780 1048	`e/ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
11988	3173 0 1	17448 812 952	`e/merged`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
11997	3173 0 1	18312 812 952	`e/merged`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
12018	3173 0 1	18312 812 952	`e/merged`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
12051	2294 0 1	15142 804 952	`e/merged`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
12211	2132 0 1	14446 804 952	`e/merged`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
12311	2248 0 4	14083 756 1016	`e/merged`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
13441	2837 0 1	17128 812 952	`e/regs`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
13508	2837 0 1	17960 812 952	`e/regs`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
13583	2789 0 1	17064 812 952	`e/ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
13585	2789 0 1	17928 812 952	`e/ref`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
13637	2837 0 1	17960 812 952	`e/regs`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
13674	2789 0 1	17928 812 952	`e/ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
15623	2004 0 1	14342 804 952	`e/regs`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
15879	2121 0 4	15159 772 1048	`e/regs`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
16534	2359 0 4	16176 780 1048	`e/regs`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
16960	2174 0 1	15046 804 952	`e/regs`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
18606	1945 0 1	14278 804 952	`e/ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
18616	2142 0 1	15014 804 952	`e/ref`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20231214	20231212
19564	2092 0 4	15127 772 1048	`e/ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
19929	2423 0 4	16240 780 1048	`e/ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
20721	2044 0 4	13891 756 1016	`e/regs`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212
22675	1847 0 4	13699 756 1016	`e/ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231214	20231212

Test failure

Implementation: amd64-ssse3
Security model: constbranchindex
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

error 111

Number of similar (compiler,implementation) pairs: 72, namely:

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	amd64-ssse3
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	amd64-ssse3
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	amd64-ssse3
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	amd64-ssse3
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	amd64-ssse3
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	amd64-ssse3
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	amd64-ssse3
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	amd64-ssse3
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	amd64-ssse3
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	dolbeau/generic-gccsimd128
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	dolbeau/generic-gccsimd128
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	dolbeau/generic-gccsimd128
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	dolbeau/generic-gccsimd128
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	dolbeau/generic-gccsimd128
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/generic-gccsimd128
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/generic-gccsimd128
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/generic-gccsimd128
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/generic-gccsimd128
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	dolbeau/generic-gccsimd256
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	dolbeau/generic-gccsimd256
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	dolbeau/generic-gccsimd256
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	dolbeau/generic-gccsimd256
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	dolbeau/generic-gccsimd256
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/generic-gccsimd256
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/generic-gccsimd256
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/generic-gccsimd256
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/generic-gccsimd256
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/ssse3/64
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	moon/ssse3/64
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	moon/ssse3/64
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	moon/ssse3/64
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	moon/ssse3/64
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	moon/ssse3/64
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	moon/ssse3/64
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	moon/ssse3/64
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	moon/ssse3/64
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 -march=native -O2 -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_chacha20_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_chacha20_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_chacha20_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: 5, namely:

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	dolbeau/amd64-avx2
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	dolbeau/amd64-avx2
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	dolbeau/amd64-avx2
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	dolbeau/amd64-avx2
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	dolbeau/amd64-avx2

Compiler output

Implementation: dolbeau/amd64-avx2
Security model: constbranchindex
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

chacha.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/10/include/immintrin.h:35,
chacha.c: from chacha.c:11:
chacha.c: u4.h: In function 'crypto_stream_chacha20_dolbeau_amd64_avx2_constbranchindex_ECRYPT_encrypt_bytes':
chacha.c: /usr/lib/gcc/x86_64-linux-gnu/10/include/tmmintrin.h:136:1: error: inlining failed in call to 'always_inline' '_mm_shuffle_epi8': target specific option mismatch
chacha.c: 136 | _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
chacha.c: | ^~~~~~~~~~~~~~~~
chacha.c: In file included from chacha.c:103:
chacha.c: u4.h:14:86: note: called from here
chacha.c: 14 | 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:17:36: note: in expansion of macro 'VEC4_QUARTERROUND_SHUFFLE'
chacha.c: 17 | #define VEC4_QUARTERROUND(a,b,c,d) VEC4_QUARTERROUND_SHUFFLE(a,b,c,d)
chacha.c: | ^~~~~~~~~~~~~~~~~~~~~~~~~
chacha.c: u4.h:129:7: note: in expansion of macro 'VEC4_QUARTERROUND'
chacha.c: 129 | VEC4_QUARTERROUND( 3, 4, 9,14);
chacha.c: | ^~~~~~~~~~~~~~~~~
chacha.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/10/include/immintrin.h:35,
chacha.c: from chacha.c:11:
chacha.c: /usr/lib/gcc/x86_64-linux-gnu/10/include/tmmintrin.h:136:1: error: inlining failed in call to 'always_inline' '_mm_shuffle_epi8': target specific option mismatch
chacha.c: 136 | _mm_shuffle_epi8 (__m128i __X, __m128i __Y)
chacha.c: | ^~~~~~~~~~~~~~~~
chacha.c: In file included from chacha.c:103:
chacha.c: u4.h:12:86: note: called from here
chacha.c: 12 | 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: ...

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/amd64-avx2
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/amd64-avx2
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/amd64-avx2
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	dolbeau/amd64-avx2

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:

Compiler	Implementations
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:

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: 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:

Compiler	Implementations
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_chacha20_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:

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