Implementation notes: aarch64, hikey960, crypto_hashblocks/sha512

Computer: hikey960
Architecture: aarch64
CPU ID: 410fd034
SUPERCOP version: 20190816
Operation: crypto_hashblocks
Primitive: sha512

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
0	11000 0 0	22618 920 776	`inplace`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv`	20191126	20190816
0	13804 0 0	24752 816 760	`ref`	`clang_-O3_-fwrapv_-mavx2_-fomit-frame-pointer_-Qunused-arguments`	20191126	20190816
6663	11024 0 0	22650 920 776	`inplace`	`gcc_-O3_-fomit-frame-pointer`	20191126	20190816
8883	11096 0 0	20993 912 744	`inplace`	`gcc_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20191126	20190816
8883	11000 0 0	22626 920 776	`ref`	`gcc_-O3_-fomit-frame-pointer`	20191126	20190816
8883	11100 0 0	20993 912 744	`ref`	`gcc_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20191126	20190816
8883	10884 0 0	22490 920 776	`ref`	`gcc_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20191126	20190816
8883	10804 0 0	20173 896 744	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20191126	20190816
11105	11100 0 0	24081 912 744	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20191126	20190816
12489	11080 0 0	24033 912 744	`inplace`	`gcc_-funroll-loops_-O2_-fomit-frame-pointer`	20191126	20190816
12489	11096 0 0	24081 912 744	`inplace`	`gcc_-funroll-loops_-fno-schedule-insns_-O2_-fomit-frame-pointer`	20191126	20190816
12489	10800 0 0	20165 896 744	`inplace`	`gcc_-funroll-loops_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20191126	20190816
16650	13736 0 0	24688 816 760	`inplace`	`clang_-O3_-fwrapv_-mavx2_-fomit-frame-pointer_-Qunused-arguments`	20191126	20190816
16650	13736 0 0	24688 816 760	`inplace`	`clang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments`	20191126	20190816
16650	11008 0 0	24298 920 776	`inplace`	`gcc_-funroll-loops_-O3_-fomit-frame-pointer`	20191126	20190816
16650	10800 0 0	20165 896 744	`inplace`	`gcc_-funroll-loops_-Os_-fomit-frame-pointer`	20191126	20190816
16650	10880 0 0	24130 920 776	`inplace`	`gcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20191126	20190816
16650	10936 0 0	24161 912 744	`inplace`	`gcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer`	20191126	20190816
16650	10948 0 0	20977 912 744	`inplace`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv`	20191126	20190816
16650	11092 0 0	21025 912 744	`ref`	`gcc_-O2_-fomit-frame-pointer`	20191126	20190816
16650	10804 0 0	20141 896 744	`ref`	`gcc_-Os_-fomit-frame-pointer`	20191126	20190816
16650	10804 0 0	20141 896 744	`ref`	`gcc_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20191126	20190816
16650	11068 0 0	24017 912 744	`ref`	`gcc_-funroll-loops_-O2_-fomit-frame-pointer`	20191126	20190816
16650	10972 0 0	24266 920 776	`ref`	`gcc_-funroll-loops_-O3_-fomit-frame-pointer`	20191126	20190816
16650	10804 0 0	20173 896 744	`ref`	`gcc_-funroll-loops_-Os_-fomit-frame-pointer`	20191126	20190816
16650	10884 0 0	24138 920 776	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20191126	20190816
16650	10976 0 0	22594 920 776	`ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv`	20191126	20190816
16652	11096 0 0	21033 912 744	`inplace`	`gcc_-O2_-fomit-frame-pointer`	20191126	20190816
17766	10800 0 0	20133 896 744	`inplace`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv`	20191126	20190816
17766	10944 0 0	24161 912 744	`ref`	`gcc_-funroll-loops_-O_-fomit-frame-pointer`	20191126	20190816
18729	11072 0 0	21001 912 744	`ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv`	20191126	20190816
20815	10800 0 0	20133 896 744	`inplace`	`gcc_-fno-schedule-insns_-Os_-fomit-frame-pointer`	20191126	20190816
23363	10804 0 0	20141 896 744	`ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv`	20191126	20190816
23386	13736 0 0	24688 816 760	`inplace`	`clang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments`	20191126	20190816
23386	10944 0 0	24161 912 744	`ref`	`gcc_-funroll-loops_-fno-schedule-insns_-O_-fomit-frame-pointer`	20191126	20190816
24975	13736 0 0	24672 816 760	`inplace`	`clang_-O3_-fomit-frame-pointer_-Qunused-arguments`	20191126	20190816
24975	10800 0 0	20133 896 744	`inplace`	`gcc_-Os_-fomit-frame-pointer`	20191126	20190816
24975	10880 0 0	22482 920 776	`inplace`	`gcc_-fno-schedule-insns_-O3_-fomit-frame-pointer`	20191126	20190816
24975	13804 0 0	24728 816 760	`ref`	`clang_-O3_-fomit-frame-pointer_-Qunused-arguments`	20191126	20190816
24975	13804 0 0	24752 816 760	`ref`	`clang_-O3_-fwrapv_-mavx_-fomit-frame-pointer_-Qunused-arguments`	20191126	20190816
24975	10944 0 0	20961 912 744	`ref`	`gcc_-O_-fomit-frame-pointer`	20191126	20190816
24975	10948 0 0	20969 912 744	`ref`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv`	20191126	20190816
24978	10944 0 0	20969 912 744	`inplace`	`gcc_-fno-schedule-insns_-O_-fomit-frame-pointer`	20191126	20190816
24978	10936 0 0	24161 912 744	`inplace`	`gcc_-funroll-loops_-O_-fomit-frame-pointer`	20191126	20190816
24978	10944 0 0	20961 912 744	`ref`	`gcc_-fno-schedule-insns_-O_-fomit-frame-pointer`	20191126	20190816
33300	24844 0 0	37021 896 744	`inplace`	`cc`	20191126	20190816
33300	24844 0 0	37021 896 744	`inplace`	`gcc`	20191126	20190816
33300	24844 0 0	37021 896 744	`inplace`	`gcc_-funroll-loops`	20191126	20190816
33304	28684 0 0	40853 896 744	`ref`	`cc`	20191126	20190816
35079	11076 0 0	21017 912 744	`inplace`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv`	20191126	20190816
35079	13804 0 0	24752 816 760	`ref`	`clang_-O3_-fwrapv_-mavx_-maes_-mpclmul_-fomit-frame-pointer_-Qunused-arguments`	20191126	20190816
49950	10944 0 0	20969 912 744	`inplace`	`gcc_-O_-fomit-frame-pointer`	20191126	20190816
58275	28684 0 0	40853 896 744	`ref`	`gcc_-funroll-loops`	20191126	20190816
116550	28684 0 0	40853 896 744	`ref`	`gcc`	20191126	20190816

Compiler output

Implementation: dolbeau/intelavx2rorxasm
Security model: unknown
Compiler: cc

try.c: crypto_hashblocks_sha512.a(blocks.o): In function `crypto_hashblocks_sha512_dolbeau_intelavx2rorxasm':
try.c: blocks.c:(.text+0x...): undefined reference to `sha512_rorx'
try.c: collect2: error: ld returned 1 exit status

Number of similar (compiler,implementation) pairs: 23, namely:

Compiler	Implementations
cc	dolbeau/intelavx2rorxasm
gcc	dolbeau/intelavx2rorxasm
gcc -O2 -fomit-frame-pointer	dolbeau/intelavx2rorxasm
gcc -O3 -fomit-frame-pointer	dolbeau/intelavx2rorxasm
gcc -O -fomit-frame-pointer	dolbeau/intelavx2rorxasm
gcc -Os -fomit-frame-pointer	dolbeau/intelavx2rorxasm
gcc -fno-schedule-insns -O2 -fomit-frame-pointer	dolbeau/intelavx2rorxasm
gcc -fno-schedule-insns -O3 -fomit-frame-pointer	dolbeau/intelavx2rorxasm
gcc -fno-schedule-insns -O -fomit-frame-pointer	dolbeau/intelavx2rorxasm
gcc -fno-schedule-insns -Os -fomit-frame-pointer	dolbeau/intelavx2rorxasm
gcc -funroll-loops	dolbeau/intelavx2rorxasm
gcc -funroll-loops -O2 -fomit-frame-pointer	dolbeau/intelavx2rorxasm
gcc -funroll-loops -O3 -fomit-frame-pointer	dolbeau/intelavx2rorxasm
gcc -funroll-loops -O -fomit-frame-pointer	dolbeau/intelavx2rorxasm
gcc -funroll-loops -Os -fomit-frame-pointer	dolbeau/intelavx2rorxasm
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer	dolbeau/intelavx2rorxasm
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer	dolbeau/intelavx2rorxasm
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer	dolbeau/intelavx2rorxasm
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer	dolbeau/intelavx2rorxasm
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv	dolbeau/intelavx2rorxasm
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv	dolbeau/intelavx2rorxasm
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv	dolbeau/intelavx2rorxasm
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv	dolbeau/intelavx2rorxasm

Compiler output

Implementation: dolbeau/intelavx2rorxasm
Security model: unknown
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments

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

Compiler	Implementations
clang -O3 -fomit-frame-pointer -Qunused-arguments	dolbeau/intelavx2rorxasm
clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments	dolbeau/intelavx2rorxasm
clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments	dolbeau/intelavx2rorxasm
clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments	dolbeau/intelavx2rorxasm

Compiler output

Implementation: dolbeau/intelavxasm
Security model: unknown
Compiler: cc

try.c: crypto_hashblocks_sha512.a(blocks.o): In function `crypto_hashblocks_sha512_dolbeau_intelavxasm':
try.c: blocks.c:(.text+0x...): undefined reference to `sha512_avx'
try.c: collect2: error: ld returned 1 exit status

Number of similar (compiler,implementation) pairs: 23, namely:

Compiler	Implementations
cc	dolbeau/intelavxasm
gcc	dolbeau/intelavxasm
gcc -O2 -fomit-frame-pointer	dolbeau/intelavxasm
gcc -O3 -fomit-frame-pointer	dolbeau/intelavxasm
gcc -O -fomit-frame-pointer	dolbeau/intelavxasm
gcc -Os -fomit-frame-pointer	dolbeau/intelavxasm
gcc -fno-schedule-insns -O2 -fomit-frame-pointer	dolbeau/intelavxasm
gcc -fno-schedule-insns -O3 -fomit-frame-pointer	dolbeau/intelavxasm
gcc -fno-schedule-insns -O -fomit-frame-pointer	dolbeau/intelavxasm
gcc -fno-schedule-insns -Os -fomit-frame-pointer	dolbeau/intelavxasm
gcc -funroll-loops	dolbeau/intelavxasm
gcc -funroll-loops -O2 -fomit-frame-pointer	dolbeau/intelavxasm
gcc -funroll-loops -O3 -fomit-frame-pointer	dolbeau/intelavxasm
gcc -funroll-loops -O -fomit-frame-pointer	dolbeau/intelavxasm
gcc -funroll-loops -Os -fomit-frame-pointer	dolbeau/intelavxasm
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer	dolbeau/intelavxasm
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer	dolbeau/intelavxasm
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer	dolbeau/intelavxasm
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer	dolbeau/intelavxasm
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv	dolbeau/intelavxasm
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv	dolbeau/intelavxasm
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv	dolbeau/intelavxasm
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv	dolbeau/intelavxasm

Compiler output

Implementation: dolbeau/intelavxasm
Security model: unknown
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments

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

Compiler	Implementations
clang -O3 -fomit-frame-pointer -Qunused-arguments	dolbeau/intelavxasm
clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments	dolbeau/intelavxasm
clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments	dolbeau/intelavxasm
clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments	dolbeau/intelavxasm

Compiler output

Implementation: dolbeau/intelsse4asm
Security model: unknown
Compiler: cc

try.c: crypto_hashblocks_sha512.a(blocks.o): In function `crypto_hashblocks_sha512_dolbeau_intelsse4asm':
try.c: blocks.c:(.text+0x...): undefined reference to `sha512_sse4'
try.c: collect2: error: ld returned 1 exit status

Number of similar (compiler,implementation) pairs: 23, namely:

Compiler	Implementations
cc	dolbeau/intelsse4asm
gcc	dolbeau/intelsse4asm
gcc -O2 -fomit-frame-pointer	dolbeau/intelsse4asm
gcc -O3 -fomit-frame-pointer	dolbeau/intelsse4asm
gcc -O -fomit-frame-pointer	dolbeau/intelsse4asm
gcc -Os -fomit-frame-pointer	dolbeau/intelsse4asm
gcc -fno-schedule-insns -O2 -fomit-frame-pointer	dolbeau/intelsse4asm
gcc -fno-schedule-insns -O3 -fomit-frame-pointer	dolbeau/intelsse4asm
gcc -fno-schedule-insns -O -fomit-frame-pointer	dolbeau/intelsse4asm
gcc -fno-schedule-insns -Os -fomit-frame-pointer	dolbeau/intelsse4asm
gcc -funroll-loops	dolbeau/intelsse4asm
gcc -funroll-loops -O2 -fomit-frame-pointer	dolbeau/intelsse4asm
gcc -funroll-loops -O3 -fomit-frame-pointer	dolbeau/intelsse4asm
gcc -funroll-loops -O -fomit-frame-pointer	dolbeau/intelsse4asm
gcc -funroll-loops -Os -fomit-frame-pointer	dolbeau/intelsse4asm
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer	dolbeau/intelsse4asm
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer	dolbeau/intelsse4asm
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer	dolbeau/intelsse4asm
gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer	dolbeau/intelsse4asm
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv	dolbeau/intelsse4asm
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv	dolbeau/intelsse4asm
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv	dolbeau/intelsse4asm
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv	dolbeau/intelsse4asm

Compiler output

Implementation: dolbeau/intelsse4asm
Security model: unknown
Compiler: clang -O3 -fomit-frame-pointer -Qunused-arguments

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

Compiler	Implementations
clang -O3 -fomit-frame-pointer -Qunused-arguments	dolbeau/intelsse4asm
clang -O3 -fwrapv -mavx2 -fomit-frame-pointer -Qunused-arguments	dolbeau/intelsse4asm
clang -O3 -fwrapv -mavx -fomit-frame-pointer -Qunused-arguments	dolbeau/intelsse4asm
clang -O3 -fwrapv -mavx -maes -mpclmul -fomit-frame-pointer -Qunused-arguments	dolbeau/intelsse4asm