Implementation notes: amd64, h9trinity, crypto_hash/shake256

Computer: h9trinity
Architecture: amd64
CPU ID: AuthenticAMD-00610f01-178bfbff
SUPERCOP version: 20200618
Operation: crypto_hash
Primitive: shake256

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
18995	100 0 0	42917 784 808	`usekcp`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200410	20200409
19009	98 0 0	44260 784 752	`usekcp`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200410	20200409
19009	98 0 0	45828 784 752	`usekcp`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200410	20200409
19019	98 0 0	41714 776 736	`usekcp`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200410	20200409
19030	98 0 0	44740 784 736	`usekcp`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200410	20200409
19042	100 0 0	42181 776 776	`usekcp`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200410	20200409
19053	98 0 0	44260 784 752	`usekcp`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200410	20200409
19054	100 0 0	42893 784 808	`usekcp`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200410	20200409
19102	100 0 0	45165 784 808	`usekcp`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200410	20200409
23823	1288 0 0	66257 776 736	`oncore64bits`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200410	20200409
23868	947 0 0	65433 776 752	`oncore64bits`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200410	20200409
23887	813 0 0	63966 776 808	`oncore64bits`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200410	20200409
23890	663 0 0	62615 768 736	`oncore64bits`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200410	20200409
23908	979 0 0	67033 776 752	`oncore64bits`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200410	20200409
23924	815 0 0	63958 776 808	`oncore64bits`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200410	20200409
23958	947 0 0	65433 776 752	`oncore64bits`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200410	20200409
23961	2389 0 0	67798 776 808	`oncore64bits`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200410	20200409
23985	611 0 0	63030 768 776	`oncore64bits`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200410	20200409
25795	245 0 0	10856 832 776	`openssl`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200410	20200409
25852	203 0 0	9980 816 776	`openssl`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200410	20200409
25876	245 0 0	10832 832 776	`openssl`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200410	20200409
25897	201 0 0	12203 824 752	`openssl`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200410	20200409
25897	201 0 0	12203 824 752	`openssl`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200410	20200409
25907	201 0 0	9657 816 736	`openssl`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200410	20200409
25954	201 0 0	12683 824 736	`openssl`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200410	20200409
26058	201 0 0	13771 824 752	`openssl`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200410	20200409
26859	245 0 0	13193 840 776	`openssl`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200410	20200409
27017	4742 0 0	17118 776 808	`gil/singlefile`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200410	20200409
27545	22019 0 0	34422 776 808	`gil/singlefile_unrolled`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200410	20200409
30240	2289 0 0	13745 776 752	`gil/singlefile`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200410	20200409
30268	2289 0 0	13745 776 752	`gil/singlefile`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200410	20200409
30308	2305 0 0	15329 776 752	`gil/singlefile`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200410	20200409
30512	3917 0 0	13957 768 808	`gil/singlefile`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200410	20200409
30555	3849 0 0	13901 768 808	`gil/singlefile`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200410	20200409
31292	21298 0 0	31341 768 808	`gil/singlefile_unrolled`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200410	20200409
32711	21043 0 0	31109 768 808	`gil/singlefile_unrolled`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200410	20200409
33469	2634 0 0	14561 776 736	`gil/singlefile`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200410	20200409
33914	1894 0 0	10799 768 736	`gil/singlefile`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200410	20200409
34121	21153 0 0	30345 752 776	`gil/singlefile_unrolled`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200410	20200409
34159	25361 0 0	36817 776 752	`gil/singlefile_unrolled`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200410	20200409
34163	25361 0 0	36817 776 752	`gil/singlefile_unrolled`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200410	20200409
34232	25377 0 0	38401 776 752	`gil/singlefile_unrolled`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200410	20200409
36048	1935 0 0	11161 752 776	`gil/singlefile`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200410	20200409
37641	28033 0 0	39969 776 736	`gil/singlefile_unrolled`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200410	20200409
37772	24980 0 0	33887 768 736	`gil/singlefile_unrolled`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200410	20200409
53523	5438 0 0	30004 792 808	`oncore32bits`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200410	20200409
53809	2285 0 0	25772 784 752	`oncore32bits`	`clang_-march=native_-O_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200410	20200409
54101	3101 0 0	28156 784 752	`oncore32bits`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200410	20200409
54163	2285 0 0	25772 784 752	`oncore32bits`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200410	20200409
54266	3286 0 0	27212 784 736	`oncore32bits`	`clang_-mcpu=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200410	20200409
58320	1261 0 0	22274 776 736	`oncore32bits`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20200410	20200409
60279	2024 0 0	24251 784 808	`oncore32bits`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200410	20200409
60370	1912 0 0	23327 768 776	`oncore32bits`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200410	20200409
60408	1949 0 0	24124 776 808	`oncore32bits`	`gcc_-march=native_-mtune=native_-O_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20200410	20200409

Compiler output

Implementation: kcp/optimized1600ARMv7A
Security model: unknown
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

keccak.s: keccak.s:1:1: error: unexpected token at start of statement
keccak.s: @
keccak.s: ^
keccak.s: keccak.s:2:1: error: unexpected token at start of statement
keccak.s: @ Implementation by the Keccak, Keyak and Ketje Teams, namely, Guido Bertoni,
keccak.s: ^
keccak.s: keccak.s:3:1: error: unexpected token at start of statement
keccak.s: @ Joan Daemen, Michaël Peeters, Gilles Van Assche and Ronny Van Keer, hereby
keccak.s: keccak.s:4:1: error: unexpected token at start of statement
keccak.s: @ denoted as "the implementer".
keccak.s: ^
keccak.s: keccak.s:5:1: error: unexpected token at start of statement
keccak.s: @
keccak.s: ^
keccak.s: keccak.s:6:1: error: unexpected token at start of statement
keccak.s: @ For more information, feedback or questions, please refer to our websites:
keccak.s: ^
keccak.s: keccak.s:7:1: error: unexpected token at start of statement
keccak.s: @ http://keccak.noekeon.org/
keccak.s: ^
keccak.s: keccak.s:8:1: error: unexpected token at start of statement
keccak.s: @ http://keyak.noekeon.org/
keccak.s: ^
keccak.s: keccak.s:9:1: error: unexpected token at start of statement
keccak.s: @ http://ketje.noekeon.org/
keccak.s: ...

Number of similar (compiler,implementation) pairs: 5, namely:

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	kcp/optimized1600ARMv7A
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	kcp/optimized1600ARMv7A
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	kcp/optimized1600ARMv7A
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	kcp/optimized1600ARMv7A
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	kcp/optimized1600ARMv7A

Compiler output

Implementation: kcp/optimized1600ARMv7A
Security model: unknown
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

keccak.s: keccak.s: Assembler messages:
keccak.s: keccak.s:1: Error: junk at end of line, first unrecognized character is `@'
keccak.s: keccak.s:2: Error: junk at end of line, first unrecognized character is `@'
keccak.s: keccak.s:3: Error: junk at end of line, first unrecognized character is `@'
keccak.s: keccak.s:4: Error: junk at end of line, first unrecognized character is `@'
keccak.s: keccak.s:5: Error: junk at end of line, first unrecognized character is `@'
keccak.s: keccak.s:6: Error: junk at end of line, first unrecognized character is `@'
keccak.s: keccak.s:7: Error: junk at end of line, first unrecognized character is `@'
keccak.s: keccak.s:8: Error: junk at end of line, first unrecognized character is `@'
keccak.s: keccak.s:9: Error: junk at end of line, first unrecognized character is `@'
keccak.s: keccak.s:10: Error: junk at end of line, first unrecognized character is `@'
keccak.s: keccak.s:11: Error: junk at end of line, first unrecognized character is `@'
keccak.s: keccak.s:12: Error: junk at end of line, first unrecognized character is `@'
keccak.s: keccak.s:13: Error: junk at end of line, first unrecognized character is `@'
keccak.s: keccak.s:14: Error: junk at end of line, first unrecognized character is `@'
keccak.s: keccak.s:16: Error: junk at end of line, first unrecognized character is `@'
keccak.s: keccak.s:17: Error: junk at end of line, first unrecognized character is `@'
keccak.s: keccak.s:18: Error: junk at end of line, first unrecognized character is `@'
keccak.s: keccak.s:23: Error: junk at end of line, first unrecognized character is `@'
keccak.s: keccak.s:24: Error: junk at end of line, first unrecognized character is `@'
keccak.s: keccak.s:26: Error: junk at end of line, first unrecognized character is `@'
keccak.s: keccak.s:53: Error: junk at end of line, first unrecognized character is `@'
keccak.s: keccak.s:269: Error: junk at end of line, first unrecognized character is `@'
keccak.s: keccak.s:270: Error: junk at end of line, first unrecognized character is `@'
keccak.s: keccak.s:271: Error: junk at end of line, first unrecognized character is `@'
keccak.s: ...

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	kcp/optimized1600ARMv7A
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	kcp/optimized1600ARMv7A
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	kcp/optimized1600ARMv7A
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	kcp/optimized1600ARMv7A

Compiler output

Implementation: kcp/optimized1600ARMv8A
Security model: unknown
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

keccak.s: keccak.s:258:20: error: unknown token in expression
keccak.s: movi v0.2d, #0
keccak.s: ^
keccak.s: keccak.s:259:20: error: unknown token in expression
keccak.s: movi v1.2d, #0
keccak.s: ^
keccak.s: keccak.s:260:20: error: unknown token in expression
keccak.s: movi v2.2d, #0
keccak.s: ^
keccak.s: keccak.s:261:20: error: unknown token in expression
keccak.s: movi v3.2d, #0
keccak.s: ^
keccak.s: keccak.s:262:13: error: Unexpected '{' in expression
keccak.s: st4 { v0.2d, v1.2d, v2.2d, v3.2d }, [x0], #64 // Clear 8lanes=64 bytes at a time
keccak.s: ^
keccak.s: keccak.s:263:13: error: Unexpected '{' in expression
keccak.s: st4 { v0.2d, v1.2d, v2.2d, v3.2d }, [x0], #64
keccak.s: ^
keccak.s: keccak.s:264:13: error: Unexpected '{' in expression
keccak.s: st4 { v0.2d, v1.2d, v2.2d, v3.2d }, [x0], #64
keccak.s: ^
keccak.s: keccak.s:265:13: error: Unexpected '{' in expression
keccak.s: st1 { v0.d }[0], [x0], #8
keccak.s: ^
keccak.s: keccak.s:276:20: error: expected ']' in brackets expression
keccak.s: ...

Number of similar (compiler,implementation) pairs: 5, namely:

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	kcp/optimized1600ARMv8A
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	kcp/optimized1600ARMv8A
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	kcp/optimized1600ARMv8A
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	kcp/optimized1600ARMv8A
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	kcp/optimized1600ARMv8A

Compiler output

Implementation: kcp/optimized1600ARMv8A
Security model: unknown
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

keccak.s: keccak.s: Assembler messages:
keccak.s: keccak.s:258: Error: no such instruction: `movi v0.2d,'
keccak.s: keccak.s:259: Error: no such instruction: `movi v1.2d,'
keccak.s: keccak.s:260: Error: no such instruction: `movi v2.2d,'
keccak.s: keccak.s:261: Error: no such instruction: `movi v3.2d,'
keccak.s: keccak.s:262: Error: no such instruction: `st4 { v0.2d,v1.2d,v2.2d,v3.2d },[x0],'
keccak.s: keccak.s:263: Error: no such instruction: `st4 { v0.2d,v1.2d,v2.2d,v3.2d },[x0],'
keccak.s: keccak.s:264: Error: no such instruction: `st4 { v0.2d,v1.2d,v2.2d,v3.2d },[x0],'
keccak.s: keccak.s:265: Error: no such instruction: `st1 { v0.d }[0],[x0],'
keccak.s: keccak.s:276: Error: no such instruction: `ldrb w3,[x0,x2]'
keccak.s: keccak.s:277: Error: no such instruction: `eor w3,w3,w1'
keccak.s: keccak.s:278: Error: invalid char '[' beginning operand 2 `[x0'
keccak.s: keccak.s:289: Error: too many memory references for `add'
keccak.s: keccak.s:290: Error: too many memory references for `sub'
keccak.s: keccak.s:291: Error: no such instruction: `b.cc KeccakP1600_AddBytes_Exit//length 0,move along'
keccak.s: keccak.s:293: Error: too many memory references for `sub'
keccak.s: keccak.s:294: Error: no such instruction: `b.cc KeccakP1600_AddBytes_Lanes//Jump if length is negative'
keccak.s: keccak.s:295: Error: no such instruction: `ld4 { v0.2d,v1.2d,v2.2d,v3.2d },[x0]'
keccak.s: keccak.s:296: Error: no such instruction: `ld4 { v4.2d,v5.2d,v6.2d,v7.2d },[x1],'
keccak.s: keccak.s:297: Error: no such instruction: `eor v0.16b,v0.16b,v4.16b'
keccak.s: keccak.s:298: Error: no such instruction: `eor v1.16b,v1.16b,v5.16b'
keccak.s: keccak.s:299: Error: no such instruction: `eor v2.16b,v2.16b,v6.16b'
keccak.s: keccak.s:300: Error: no such instruction: `eor v3.16b,v3.16b,v7.16b'
keccak.s: keccak.s:301: Error: no such instruction: `st4 { v0.2d,v1.2d,v2.2d,v3.2d },[x0],'
keccak.s: keccak.s:302: Error: no such instruction: `b KeccakP1600_AddBytes_8LanesLoop'
keccak.s: ...

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	kcp/optimized1600ARMv8A
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	kcp/optimized1600ARMv8A
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	kcp/optimized1600ARMv8A
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	kcp/optimized1600ARMv8A

Compiler output

Implementation: kcp/optimized1600AVX2
Security model: unknown
Compiler: clang++ -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

KeccakSpongeWidth1600.c: clang: warning: treating 'c' input as 'c++' when in C++ mode, this behavior is deprecated [-Wdeprecated]
SHAKE256.c: clang: warning: treating 'c' input as 'c++' when in C++ mode, this behavior is deprecated [-Wdeprecated]
KeccakP-1600-AVX2.cpp: KeccakP-1600-AVX2.cpp:641:5: error: always_inline function '_mm256_xor_si256' requires target feature 'avx2', but would be inlined into function 'KeccakP1600_Permute_Nrounds' that is compiled without support for 'avx2'
KeccakP-1600-AVX2.cpp: KECCAK_PERMUTE_LOOP(, nrounds)
KeccakP-1600-AVX2.cpp: ^
KeccakP-1600-AVX2.cpp: KeccakP-1600-AVX2.cpp:162:14: note: expanded from macro 'KECCAK_PERMUTE_LOOP'
KeccakP-1600-AVX2.cpp: r0 = XOR(a0, a1); \
KeccakP-1600-AVX2.cpp: ^
KeccakP-1600-AVX2.cpp: KeccakP-1600-AVX2.cpp:52:41: note: expanded from macro 'XOR'
KeccakP-1600-AVX2.cpp: #define XOR(a, b) _mm256_xor_si256(a, b)
KeccakP-1600-AVX2.cpp: ^
KeccakP-1600-AVX2.cpp: KeccakP-1600-AVX2.cpp:641:5: error: always_inline function '_mm256_xor_si256' requires target feature 'avx2', but would be inlined into function 'KeccakP1600_Permute_Nrounds' that is compiled without support for 'avx2'
KeccakP-1600-AVX2.cpp: KeccakP-1600-AVX2.cpp:163:14: note: expanded from macro 'KECCAK_PERMUTE_LOOP'
KeccakP-1600-AVX2.cpp: r0 = XOR(r0, a2); \
KeccakP-1600-AVX2.cpp: ^
KeccakP-1600-AVX2.cpp: KeccakP-1600-AVX2.cpp:52:41: note: expanded from macro 'XOR'
KeccakP-1600-AVX2.cpp: #define XOR(a, b) _mm256_xor_si256(a, b)
KeccakP-1600-AVX2.cpp: ^
KeccakP-1600-AVX2.cpp: KeccakP-1600-AVX2.cpp:641:5: error: always_inline function '_mm256_xor_si256' requires target feature 'avx2', but would be inlined into function 'KeccakP1600_Permute_Nrounds' that is compiled without support for 'avx2'
KeccakP-1600-AVX2.cpp: KeccakP-1600-AVX2.cpp:164:14: note: expanded from macro 'KECCAK_PERMUTE_LOOP'
KeccakP-1600-AVX2.cpp: r0 = XOR(r0, a3); \
KeccakP-1600-AVX2.cpp: ^
KeccakP-1600-AVX2.cpp: KeccakP-1600-AVX2.cpp:52:41: note: expanded from macro 'XOR'
KeccakP-1600-AVX2.cpp: #define XOR(a, b) _mm256_xor_si256(a, b)
KeccakP-1600-AVX2.cpp: ^
KeccakP-1600-AVX2.cpp: KeccakP-1600-AVX2.cpp:641:5: error: always_inline function '_mm256_xor_si256' requires target feature 'avx2', but would be inlined into function 'KeccakP1600_Permute_Nrounds' that is compiled without support for 'avx2'
KeccakP-1600-AVX2.cpp: KeccakP-1600-AVX2.cpp:165:14: note: expanded from macro 'KECCAK_PERMUTE_LOOP'
KeccakP-1600-AVX2.cpp: ...

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

Compiler	Implementations
clang++ -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	kcp/optimized1600AVX2
clang++ -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	kcp/optimized1600AVX2
clang++ -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	kcp/optimized1600AVX2
clang++ -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	kcp/optimized1600AVX2

Compiler output

Implementation: kcp/optimized1600AVX2
Security model: unknown
Compiler: g++ -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

KeccakP-1600-AVX2.cpp: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
KeccakP-1600-AVX2.cpp: from /usr/lib/gcc/x86_64-linux-gnu/7/include/x86intrin.h:48,
KeccakP-1600-AVX2.cpp: from KeccakP-1600-AVX2.cpp:18:
KeccakP-1600-AVX2.cpp: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h: In function 'void KeccakP1600_Permute_Nrounds(void*, unsigned int)':
KeccakP-1600-AVX2.cpp: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:1081:1: error: inlining failed in call to always_inline '__m256i _mm256_permute2x128_si256(__m256i, __m256i, int)': target specific option mismatch
KeccakP-1600-AVX2.cpp: _mm256_permute2x128_si256 (__m256i __X, __m256i __Y, const int __M)
KeccakP-1600-AVX2.cpp: ^~~~~~~~~~~~~~~~~~~~~~~~~
KeccakP-1600-AVX2.cpp: KeccakP-1600-AVX2.cpp:269:12: note: called from here
KeccakP-1600-AVX2.cpp: a4 = _mm256_permute2x128_si256(r0, r1, 0x20); \
KeccakP-1600-AVX2.cpp: ~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
KeccakP-1600-AVX2.cpp: KeccakP-1600-AVX2.cpp:641:5: note: in expansion of macro 'KECCAK_PERMUTE_LOOP'
KeccakP-1600-AVX2.cpp: KECCAK_PERMUTE_LOOP(, nrounds)
KeccakP-1600-AVX2.cpp: ^~~~~~~~~~~~~~~~~~~
KeccakP-1600-AVX2.cpp: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:43:0,
KeccakP-1600-AVX2.cpp: from /usr/lib/gcc/x86_64-linux-gnu/7/include/x86intrin.h:48,
KeccakP-1600-AVX2.cpp: from KeccakP-1600-AVX2.cpp:18:
KeccakP-1600-AVX2.cpp: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx2intrin.h:906:1: error: inlining failed in call to always_inline '__m256i _mm256_unpacklo_epi64(__m256i, __m256i)': target specific option mismatch
KeccakP-1600-AVX2.cpp: _mm256_unpacklo_epi64 (__m256i __A, __m256i __B)
KeccakP-1600-AVX2.cpp: ^~~~~~~~~~~~~~~~~~~~~
KeccakP-1600-AVX2.cpp: KeccakP-1600-AVX2.cpp:268:12: note: called from here
KeccakP-1600-AVX2.cpp: r1 = _mm256_unpacklo_epi64(a24, a34); \
KeccakP-1600-AVX2.cpp: ~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
KeccakP-1600-AVX2.cpp: KeccakP-1600-AVX2.cpp:641:5: note: in expansion of macro 'KECCAK_PERMUTE_LOOP'
KeccakP-1600-AVX2.cpp: KECCAK_PERMUTE_LOOP(, nrounds)
KeccakP-1600-AVX2.cpp: ^~~~~~~~~~~~~~~~~~~
KeccakP-1600-AVX2.cpp: ...

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

Compiler	Implementations
g++ -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	kcp/optimized1600AVX2
g++ -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	kcp/optimized1600AVX2
g++ -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	kcp/optimized1600AVX2
g++ -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	kcp/optimized1600AVX2

Compiler output

Implementation: kcp/optimized1600AVX512
Security model: unknown
Compiler: clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

KeccakP-1600-AVX512.c: KeccakP-1600-AVX512.c:238:9: error: always_inline function '_mm512_mask_storeu_epi64' requires target feature 'avx512f', but would be inlined into function 'KeccakP1600_AddBytes' that is compiled without support for 'avx512f'
KeccakP-1600-AVX512.c: STORE_8Lanes( stateAsLanes, XOR(LOAD_8Lanes(stateAsLanes), LOAD_8Lanes((const UINT64*)data)));
KeccakP-1600-AVX512.c: ^
KeccakP-1600-AVX512.c: KeccakP-1600-AVX512.c:219:37: note: expanded from macro 'STORE_8Lanes'
KeccakP-1600-AVX512.c: #define STORE_8Lanes(a,v) STORE_Lanes(a,0xFF,v)
KeccakP-1600-AVX512.c: ^
KeccakP-1600-AVX512.c: KeccakP-1600-AVX512.c:216:37: note: expanded from macro 'STORE_Lanes'
KeccakP-1600-AVX512.c: #define STORE_Lanes(a,m,v) _mm512_mask_storeu_epi64(a,m,v)
KeccakP-1600-AVX512.c: ^
KeccakP-1600-AVX512.c: KeccakP-1600-AVX512.c:238:37: error: always_inline function '_mm512_xor_si512' requires target feature 'avx512f', but would be inlined into function 'KeccakP1600_AddBytes' that is compiled without support for 'avx512f'
KeccakP-1600-AVX512.c: STORE_8Lanes( stateAsLanes, XOR(LOAD_8Lanes(stateAsLanes), LOAD_8Lanes((const UINT64*)data)));
KeccakP-1600-AVX512.c: ^
KeccakP-1600-AVX512.c: KeccakP-1600-AVX512.c:206:37: note: expanded from macro 'XOR'
KeccakP-1600-AVX512.c: #define XOR(a,b) _mm512_xor_si512(a,b)
KeccakP-1600-AVX512.c: ^
KeccakP-1600-AVX512.c: KeccakP-1600-AVX512.c:238:41: error: always_inline function '_mm512_maskz_loadu_epi64' requires target feature 'avx512f', but would be inlined into function 'KeccakP1600_AddBytes' that is compiled without support for 'avx512f'
KeccakP-1600-AVX512.c: STORE_8Lanes( stateAsLanes, XOR(LOAD_8Lanes(stateAsLanes), LOAD_8Lanes((const UINT64*)data)));
KeccakP-1600-AVX512.c: ^
KeccakP-1600-AVX512.c: KeccakP-1600-AVX512.c:215:37: note: expanded from macro 'LOAD_8Lanes'
KeccakP-1600-AVX512.c: #define LOAD_8Lanes(a) LOAD_Lanes(0xFF,a)
KeccakP-1600-AVX512.c: ^
KeccakP-1600-AVX512.c: KeccakP-1600-AVX512.c:212:37: note: expanded from macro 'LOAD_Lanes'
KeccakP-1600-AVX512.c: #define LOAD_Lanes(m,a) _mm512_maskz_loadu_epi64(m,a)
KeccakP-1600-AVX512.c: ^
KeccakP-1600-AVX512.c: KeccakP-1600-AVX512.c:238:68: error: always_inline function '_mm512_maskz_loadu_epi64' requires target feature 'avx512f', but would be inlined into function 'KeccakP1600_AddBytes' that is compiled without support for 'avx512f'
KeccakP-1600-AVX512.c: ...

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

Compiler	Implementations
clang -march=native -O2 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	kcp/optimized1600AVX512
clang -march=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	kcp/optimized1600AVX512
clang -march=native -O -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	kcp/optimized1600AVX512
clang -march=native -Os -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	kcp/optimized1600AVX512

Compiler output

Implementation: kcp/optimized1600AVX512
Security model: unknown
Compiler: clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE

KeccakP-1600-AVX512.c: KeccakP-1600-AVX512.c:238:9: error: always_inline function '_mm512_mask_storeu_epi64' requires target feature 'avx2', but would be inlined into function 'KeccakP1600_AddBytes' that is compiled without support for 'avx2'
KeccakP-1600-AVX512.c: STORE_8Lanes( stateAsLanes, XOR(LOAD_8Lanes(stateAsLanes), LOAD_8Lanes((const UINT64*)data)));
KeccakP-1600-AVX512.c: ^
KeccakP-1600-AVX512.c: KeccakP-1600-AVX512.c:219:37: note: expanded from macro 'STORE_8Lanes'
KeccakP-1600-AVX512.c: #define STORE_8Lanes(a,v) STORE_Lanes(a,0xFF,v)
KeccakP-1600-AVX512.c: ^
KeccakP-1600-AVX512.c: KeccakP-1600-AVX512.c:216:37: note: expanded from macro 'STORE_Lanes'
KeccakP-1600-AVX512.c: #define STORE_Lanes(a,m,v) _mm512_mask_storeu_epi64(a,m,v)
KeccakP-1600-AVX512.c: ^
KeccakP-1600-AVX512.c: KeccakP-1600-AVX512.c:238:37: error: always_inline function '_mm512_xor_si512' requires target feature 'avx2', but would be inlined into function 'KeccakP1600_AddBytes' that is compiled without support for 'avx2'
KeccakP-1600-AVX512.c: STORE_8Lanes( stateAsLanes, XOR(LOAD_8Lanes(stateAsLanes), LOAD_8Lanes((const UINT64*)data)));
KeccakP-1600-AVX512.c: ^
KeccakP-1600-AVX512.c: KeccakP-1600-AVX512.c:206:37: note: expanded from macro 'XOR'
KeccakP-1600-AVX512.c: #define XOR(a,b) _mm512_xor_si512(a,b)
KeccakP-1600-AVX512.c: ^
KeccakP-1600-AVX512.c: KeccakP-1600-AVX512.c:238:41: error: always_inline function '_mm512_maskz_loadu_epi64' requires target feature 'avx2', but would be inlined into function 'KeccakP1600_AddBytes' that is compiled without support for 'avx2'
KeccakP-1600-AVX512.c: STORE_8Lanes( stateAsLanes, XOR(LOAD_8Lanes(stateAsLanes), LOAD_8Lanes((const UINT64*)data)));
KeccakP-1600-AVX512.c: ^
KeccakP-1600-AVX512.c: KeccakP-1600-AVX512.c:215:37: note: expanded from macro 'LOAD_8Lanes'
KeccakP-1600-AVX512.c: #define LOAD_8Lanes(a) LOAD_Lanes(0xFF,a)
KeccakP-1600-AVX512.c: ^
KeccakP-1600-AVX512.c: KeccakP-1600-AVX512.c:212:37: note: expanded from macro 'LOAD_Lanes'
KeccakP-1600-AVX512.c: #define LOAD_Lanes(m,a) _mm512_maskz_loadu_epi64(m,a)
KeccakP-1600-AVX512.c: ^
KeccakP-1600-AVX512.c: KeccakP-1600-AVX512.c:238:68: error: always_inline function '_mm512_maskz_loadu_epi64' requires target feature 'avx2', but would be inlined into function 'KeccakP1600_AddBytes' that is compiled without support for 'avx2'
KeccakP-1600-AVX512.c: ...

Number of similar (compiler,implementation) pairs: 1, namely:

Compiler	Implementations
clang -mcpu=native -O3 -fomit-frame-pointer -fwrapv -Qunused-arguments -fPIC -fPIE	kcp/optimized1600AVX512

Compiler output

Implementation: kcp/optimized1600AVX512
Security model: unknown
Compiler: gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE

KeccakP-1600-AVX512.c: KeccakP-1600-AVX512.c: In function 'KeccakP1600_AddBytes':
KeccakP-1600-AVX512.c: KeccakP-1600-AVX512.c:216:37: warning: AVX512F vector return without AVX512F enabled changes the ABI [-Wpsabi]
KeccakP-1600-AVX512.c: #define STORE_Lanes(a,m,v) _mm512_mask_storeu_epi64(a,m,v)
KeccakP-1600-AVX512.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
KeccakP-1600-AVX512.c: KeccakP-1600-AVX512.c:219:37: note: in expansion of macro 'STORE_Lanes'
KeccakP-1600-AVX512.c: #define STORE_8Lanes(a,v) STORE_Lanes(a,0xFF,v)
KeccakP-1600-AVX512.c: ^~~~~~~~~~~
KeccakP-1600-AVX512.c: KeccakP-1600-AVX512.c:238:9: note: in expansion of macro 'STORE_8Lanes'
KeccakP-1600-AVX512.c: STORE_8Lanes( stateAsLanes, XOR(LOAD_8Lanes(stateAsLanes), LOAD_8Lanes((const UINT64*)data)));
KeccakP-1600-AVX512.c: ^~~~~~~~~~~~
KeccakP-1600-AVX512.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:45:0,
KeccakP-1600-AVX512.c: from KeccakP-1600-AVX512.c:26:
KeccakP-1600-AVX512.c: /usr/lib/gcc/x86_64-linux-gnu/7/include/avx512fintrin.h:5797:1: error: inlining failed in call to always_inline '_mm512_mask_storeu_epi64': target specific option mismatch
KeccakP-1600-AVX512.c: _mm512_mask_storeu_epi64 (void *__P, __mmask8 __U, __m512i __A)
KeccakP-1600-AVX512.c: ^~~~~~~~~~~~~~~~~~~~~~~~
KeccakP-1600-AVX512.c: KeccakP-1600-AVX512.c:216:37: note: called from here
KeccakP-1600-AVX512.c: #define STORE_Lanes(a,m,v) _mm512_mask_storeu_epi64(a,m,v)
KeccakP-1600-AVX512.c: ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
KeccakP-1600-AVX512.c: KeccakP-1600-AVX512.c:219:37: note: in expansion of macro 'STORE_Lanes'
KeccakP-1600-AVX512.c: #define STORE_8Lanes(a,v) STORE_Lanes(a,0xFF,v)
KeccakP-1600-AVX512.c: ^~~~~~~~~~~
KeccakP-1600-AVX512.c: KeccakP-1600-AVX512.c:238:9: note: in expansion of macro 'STORE_8Lanes'
KeccakP-1600-AVX512.c: STORE_8Lanes( stateAsLanes, XOR(LOAD_8Lanes(stateAsLanes), LOAD_8Lanes((const UINT64*)data)));
KeccakP-1600-AVX512.c: ^~~~~~~~~~~~
KeccakP-1600-AVX512.c: In file included from /usr/lib/gcc/x86_64-linux-gnu/7/include/immintrin.h:45:0,
KeccakP-1600-AVX512.c: ...

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

Compiler	Implementations
gcc -march=native -mtune=native -O2 -fomit-frame-pointer -fwrapv -fPIC -fPIE	kcp/optimized1600AVX512
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	kcp/optimized1600AVX512
gcc -march=native -mtune=native -O -fomit-frame-pointer -fwrapv -fPIC -fPIE	kcp/optimized1600AVX512
gcc -march=native -mtune=native -Os -fomit-frame-pointer -fwrapv -fPIC -fPIE	kcp/optimized1600AVX512