Implementation notes: aarch64, supercoplxc, crypto_kem/mceliece348864

Computer: supercoplxc
Architecture: aarch64
CPU ID: 410fd034
SUPERCOP version: 20190816
Operation: crypto_kem
Primitive: mceliece348864
TimeObject sizeTest sizeImplementationCompilerBenchmark dateSUPERCOP version
193080082608 0 0119304 952 1552vecgcc_-funroll-loops_-O2_-fomit-frame-pointer2019112520190816
1975520101708 0 0138503 864 1584vecclang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2019112520190816
199056083192 0 0119960 952 1552vecgcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer2019112520190816
2089680218332 0 0255448 952 1568vecgcc_-funroll-loops_-O3_-fomit-frame-pointer2019112520190816
2107680217764 0 0254880 952 1568vecgcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer2019112520190816
212104099056 0 0135847 864 1584vecclang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments2019112520190816
215776099056 0 0135847 864 1584vecclang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments2019112520190816
2164880101332 0 0138103 864 1584vecclang_-O3_-fomit-frame-pointer_-Qunused-arguments2019112520190816
2168720155464 0 0191296 952 1568vecgcc_-O3_-fomit-frame-pointer2019112520190816
221048099056 0 0135847 864 1584vecclang_-O3_-fwrapv_-mavx2_-fomit-frame-pointer_-Qunused-arguments2019112520190816
2271040153004 0 0188840 952 1568vecgcc_-fno-schedule-insns_-O3_-fomit-frame-pointer2019112520190816
241712086984 0 0124912 952 1552vecgcc_-funroll-loops_-O_-fomit-frame-pointer2019112520190816
253432086984 0 0124912 952 1552vecgcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer2019112520190816
346776039468 0 073342 936 1544vecgcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer2019112520190816
347968039468 0 073342 936 1544vecgcc_-funroll-loops_-Os_-fomit-frame-pointer2019112520190816
362072039300 0 073134 936 1544vecgcc_-Os_-fomit-frame-pointer2019112520190816
362136039300 0 073134 936 1544vecgcc_-fno-schedule-insns_-Os_-fomit-frame-pointer2019112520190816
368704043664 0 078312 952 1552vecgcc_-O2_-fomit-frame-pointer2019112520190816
402160043728 0 078320 952 1552vecgcc_-fno-schedule-insns_-O2_-fomit-frame-pointer2019112520190816
426688046064 0 080776 952 1552vecgcc_-O_-fomit-frame-pointer2019112520190816
426808046064 0 080776 952 1552vecgcc_-fno-schedule-insns_-O_-fomit-frame-pointer2019112520190816
2244200069976 0 0107952 936 1560veccc2019112520190816
2246208069976 0 0107952 936 1560vecgcc2019112520190816
2248696069976 0 0107952 936 1560vecgcc_-funroll-loops2019112520190816
11437992037868 0 074807 864 1584refclang_-mcpu=native_-mfpu=neon_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments2019112520190816
11579616036020 0 072935 864 1584refclang_-O3_-fomit-frame-pointer_-Qunused-arguments2019112520190816
11862632037940 0 074871 864 1584refclang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments2019112520190816
11862720037940 0 074871 864 1584refclang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments2019112520190816
11928640037940 0 074871 864 1584refclang_-O3_-fwrapv_-mavx2_-fomit-frame-pointer_-Qunused-arguments2019112520190816
11982984030820 0 067520 952 1552refgcc_-funroll-loops_-O2_-fomit-frame-pointer2019112520190816
12426400030648 0 067416 952 1552refgcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer2019112520190816
140061040159460 0 0196706 960 1568refgcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer2019112520190816
140165280160140 0 0197426 960 1568refgcc_-funroll-loops_-O3_-fomit-frame-pointer2019112520190816
143144960102064 0 0138002 960 1568refgcc_-O3_-fomit-frame-pointer2019112520190816
14942912099952 0 0135882 960 1568refgcc_-fno-schedule-insns_-O3_-fomit-frame-pointer2019112520190816
16016272031144 0 069032 952 1552refgcc_-funroll-loops_-O_-fomit-frame-pointer2019112520190816
16070400031144 0 069032 952 1552refgcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer2019112520190816
29558440010256 0 044022 936 1544refgcc_-fno-schedule-insns_-Os_-fomit-frame-pointer2019112520190816
29625504011668 0 046344 952 1552refgcc_-O2_-fomit-frame-pointer2019112520190816
29626584011708 0 046320 952 1552refgcc_-fno-schedule-insns_-O2_-fomit-frame-pointer2019112520190816
29646200010256 0 044022 936 1544refgcc_-Os_-fomit-frame-pointer2019112520190816
29646488010376 0 044206 936 1544refgcc_-funroll-loops_-Os_-fomit-frame-pointer2019112520190816
29665528010376 0 044206 936 1544refgcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer2019112520190816
32871400012504 0 047184 952 1552refgcc_-O_-fomit-frame-pointer2019112520190816
33018816012504 0 047184 952 1552refgcc_-fno-schedule-insns_-O_-fomit-frame-pointer2019112520190816

Test failure

Implementation: crypto_kem/mceliece348864/ref
Compiler: cc
error 142
Alarm clock

Number of similar (compiler,implementation) pairs: 3, namely:
CompilerImplementations
cc ref
gcc ref
gcc -funroll-loops ref

Compiler output

Implementation: crypto_kem/mceliece348864/avx
Compiler: cc
benes.c: In file included from util.h:9,
benes.c: from benes.c:5:
benes.c: vec128.h:12:10: fatal error: smmintrin.h: No such file or directory
benes.c: #include <smmintrin.h>
benes.c: ^~~~~~~~~~~~~
benes.c: compilation terminated.

Number of similar (compiler,implementation) pairs: 38, namely:
CompilerImplementations
cc avx sse
gcc avx sse
gcc -O2 -fomit-frame-pointer avx sse
gcc -O3 -fomit-frame-pointer avx sse
gcc -O -fomit-frame-pointer avx sse
gcc -Os -fomit-frame-pointer avx sse
gcc -fno-schedule-insns -O2 -fomit-frame-pointer avx sse
gcc -fno-schedule-insns -O3 -fomit-frame-pointer avx sse
gcc -fno-schedule-insns -O -fomit-frame-pointer avx sse
gcc -fno-schedule-insns -Os -fomit-frame-pointer avx sse
gcc -funroll-loops avx sse
gcc -funroll-loops -O2 -fomit-frame-pointer avx sse
gcc -funroll-loops -O3 -fomit-frame-pointer avx sse
gcc -funroll-loops -O -fomit-frame-pointer avx sse
gcc -funroll-loops -Os -fomit-frame-pointer avx sse
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer avx sse
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer avx sse
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer avx sse
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer avx sse

Compiler output

Implementation: crypto_kem/mceliece348864/avx
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments
benes.c: In file included from benes.c:5:
benes.c: In file included from ./util.h:9:
benes.c: In file included from ./vec128.h:12:
benes.c: In file included from /usr/lib/llvm-7/lib/clang/7.0.1/include/smmintrin.h:27:
benes.c: In file included from /usr/lib/llvm-7/lib/clang/7.0.1/include/tmmintrin.h:27:
benes.c: In file included from /usr/lib/llvm-7/lib/clang/7.0.1/include/pmmintrin.h:27:
benes.c: In file included from /usr/lib/llvm-7/lib/clang/7.0.1/include/emmintrin.h:27:
benes.c: In file included from /usr/lib/llvm-7/lib/clang/7.0.1/include/xmmintrin.h:27:
benes.c: /usr/lib/llvm-7/lib/clang/7.0.1/include/mmintrin.h:64:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
benes.c: return (__m64)__builtin_ia32_vec_init_v2si(__i, 0);
benes.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
benes.c: /usr/lib/llvm-7/lib/clang/7.0.1/include/mmintrin.h:143:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
benes.c: return (__m64)__builtin_ia32_packsswb((__v4hi)__m1, (__v4hi)__m2);
benes.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
benes.c: /usr/lib/llvm-7/lib/clang/7.0.1/include/mmintrin.h:173:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
benes.c: return (__m64)__builtin_ia32_packssdw((__v2si)__m1, (__v2si)__m2);
benes.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
benes.c: /usr/lib/llvm-7/lib/clang/7.0.1/include/mmintrin.h:203:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
benes.c: return (__m64)__builtin_ia32_packuswb((__v4hi)__m1, (__v4hi)__m2);
benes.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
benes.c: /usr/lib/llvm-7/lib/clang/7.0.1/include/mmintrin.h:230:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
benes.c: return (__m64)__builtin_ia32_punpckhbw((__v8qi)__m1, (__v8qi)__m2);
benes.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
benes.c: /usr/lib/llvm-7/lib/clang/7.0.1/include/mmintrin.h:253:12: error: invalid conversion between vector type '__m64' (vector of 1 'long long' value) and integer type 'int' of different size
benes.c: return (__m64)__builtin_ia32_punpckhwd((__v4hi)__m1, (__v4hi)__m2);
benes.c: ...

Number of similar (compiler,implementation) pairs: 10, namely:
CompilerImplementations
clang -O3 -fomit-frame-pointer -Qunused-arguments avx sse
clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments avx sse
clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments avx sse
clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments avx sse
clang -mcpu=native -mfpu=neon -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments avx sse