Implementation notes: amd64, hertz, crypto_hash/photonbeetlehash256rate32v1

Computer: hertz
Microarchitecture: amd64; Zen 4 (a60f12)
Architecture: amd64
CPU ID: AuthenticAMD-00a60f12-178bfbff
SUPERCOP version: 20240425
Operation: crypto_hash
Primitive: photonbeetlehash256rate32v1

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
296383	71921 0 0	89542 828 968	`T:table3`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240429	20240425
303085	13212 0 0	30966 828 968	`T:table2`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240429	20240425
305764	72401 0 0	90150 828 968	`T:table3`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240429	20240425
340073	12949 0 0	26629 804 1032	`T:table2`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231219	20231217
376742	72421 0 0	86101 804 1032	`T:table3`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231219	20231217
405292	10900 0 0	28526 828 968	`T:table2`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240429	20240425
529755	10428 0 0	21928 820 968	`T:table2`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240429	20240425
545359	69884 0 0	81384 820 968	`T:table3`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240429	20240425
548034	9741 0 0	21365 804 968	`T:table2`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231219	20231217
553999	69133 0 0	80757 804 968	`T:table3`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231219	20231217
559921	68952 0 0	79160 780 936	`T:table3`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231219	20231217
702848	9549 0 0	19752 780 936	`T:table2`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231219	20231217
797141	7461 0 0	25174 828 968	`T:bitslice_sb32`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240429	20240425
798229	7461 0 0	25062 828 968	`T:bitslice_sb32`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240429	20240425
801097	7762 0 0	19320 820 968	`T:bitslice_sb32`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240429	20240425
820630	6620 0 0	24358 828 968	`T:bitslice_sb64`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240429	20240425
821668	6986 0 0	18536 820 968	`T:bitslice_sb64`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240429	20240425
829709	6604 0 0	24230 828 968	`T:bitslice_sb64`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240429	20240425
914174	6369 0 0	23991 828 968	`T:bitslice_sb8`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240429	20240425
921099	6369 0 0	24103 828 968	`T:bitslice_sb8`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240429	20240425
926734	6692 0 32	18341 804 1000	`T:bitslice_sb64`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231219	20231217
967160	6654 0 0	18309 804 968	`T:bitslice_sb32`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231219	20231217
1022746	6945 0 0	18536 820 968	`T:bitslice_sb8`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240429	20240425
1045015	6837 0 0	20549 804 1032	`T:bitslice_sb8`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231219	20231217
1069024	6530 0 0	18149 804 968	`T:bitslice_sb8`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231219	20231217
1887128	6854 0 0	17072 780 936	`T:bitslice_sb32`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231219	20231217
1923701	7125 0 0	17368 780 936	`T:bitslice_sb8`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231219	20231217
1944036	6615 0 32	16840 780 968	`T:bitslice_sb64`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231219	20231217
2594598	7909 16 16	25648 860 1000	`T:ref`	`clang_-march=native_-O2_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240429	20240425
3735082	8377 16 16	26240 860 1000	`T:ref`	`clang_-march=native_-O3_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240429	20240425
22223062	8900 16 12	22685 828 1064	`T:ref`	`gcc_-march=native_-mtune=native_-O3_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231219	20231217
31711535	2020 16 12	12280 804 968	`T:ref`	`gcc_-march=native_-mtune=native_-Os_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231219	20231217
33850976	2764 16 12	14477 828 1000	`T:ref`	`gcc_-march=native_-mtune=native_-O2_-fomit-frame-pointer_-fwrapv_-fPIC_-fPIE`	20231219	20231217
56313363	3729 16 16	15368 844 1000	`T:ref`	`clang_-march=native_-Os_-fomit-frame-pointer_-fwrapv_-Qunused-arguments_-fPIC_-fPIE`	20240429	20240425

Compiler output

Implementation: T:bitslice_sb32
Security model: timingleaks
Compiler: gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE

hash.c: In function 'XOR',
hash.c: inlined from 'HASH' at hash.c:92:2,
hash.c: inlined from 'crypto_hash_photonbeetlehash256rate32v1_bitslice_sb32_timingleaks' at hash.c:143:3:
hash.c: hash.c:56:27: warning: writing 4 bytes into a region of size 0 [-Wstringop-overflow=]
hash.c: 56 | out_32[i] = in_left_32[i] ^ in_right_32[i];
hash.c: | ~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
hash.c: hash.c: In function 'crypto_hash_photonbeetlehash256rate32v1_bitslice_sb32_timingleaks':
hash.c: hash.c:123:17: note: at offset 32 into destination object 'State' of size 32
hash.c: 123 | uint8_t State[STATE_INBYTES] = { 0 };
hash.c: | ^~~~~
hash.c: In function 'XOR',
hash.c: inlined from 'HASH' at hash.c:92:2,
hash.c: inlined from 'crypto_hash_photonbeetlehash256rate32v1_bitslice_sb32_timingleaks' at hash.c:143:3:
hash.c: hash.c:56:27: warning: writing 4 bytes into a region of size 0 [-Wstringop-overflow=]
hash.c: 56 | out_32[i] = in_left_32[i] ^ in_right_32[i];
hash.c: | ~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
hash.c: hash.c: In function 'crypto_hash_photonbeetlehash256rate32v1_bitslice_sb32_timingleaks':
hash.c: hash.c:123:17: note: at offset 36 into destination object 'State' of size 32
hash.c: 123 | uint8_t State[STATE_INBYTES] = { 0 };
hash.c: | ^~~~~
hash.c: In function 'XOR',
hash.c: inlined from 'HASH' at hash.c:92:2,
hash.c: inlined from 'crypto_hash_photonbeetlehash256rate32v1_bitslice_sb32_timingleaks' at hash.c:143:3:
hash.c: hash.c:56:27: warning: writing 4 bytes into a region of size 0 [-Wstringop-overflow=]
hash.c: 56 | out_32[i] = in_left_32[i] ^ in_right_32[i];
hash.c: ...

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

Compiler	Implementations
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:bitslice_sb32

Compiler output

Implementation: T:bitslice_sb64
Security model: timingleaks
Compiler: gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE

hash.c: In function 'XOR',
hash.c: inlined from 'HASH' at hash.c:92:2,
hash.c: inlined from 'crypto_hash_photonbeetlehash256rate32v1_bitslice_sb64_timingleaks' at hash.c:143:3:
hash.c: hash.c:56:27: warning: writing 8 bytes into a region of size 0 [-Wstringop-overflow=]
hash.c: 56 | out_64[i] = in_left_64[i] ^ in_right_64[i];
hash.c: | ~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
hash.c: hash.c: In function 'crypto_hash_photonbeetlehash256rate32v1_bitslice_sb64_timingleaks':
hash.c: hash.c:123:17: note: at offset 32 into destination object 'State' of size 32
hash.c: 123 | uint8_t State[STATE_INBYTES] = { 0 };
hash.c: | ^~~~~
hash.c: In function 'XOR',
hash.c: inlined from 'HASH' at hash.c:92:2,
hash.c: inlined from 'crypto_hash_photonbeetlehash256rate32v1_bitslice_sb64_timingleaks' at hash.c:143:3:
hash.c: hash.c:56:27: warning: writing 8 bytes into a region of size 0 [-Wstringop-overflow=]
hash.c: 56 | out_64[i] = in_left_64[i] ^ in_right_64[i];
hash.c: | ~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
hash.c: hash.c: In function 'crypto_hash_photonbeetlehash256rate32v1_bitslice_sb64_timingleaks':
hash.c: hash.c:123:17: note: at offset 40 into destination object 'State' of size 32
hash.c: 123 | uint8_t State[STATE_INBYTES] = { 0 };
hash.c: | ^~~~~
hash.c: In function 'XOR',
hash.c: inlined from 'HASH' at hash.c:92:2,
hash.c: inlined from 'crypto_hash_photonbeetlehash256rate32v1_bitslice_sb64_timingleaks' at hash.c:143:3:
hash.c: hash.c:56:27: warning: writing 8 bytes into a region of size 0 [-Wstringop-overflow=]
hash.c: 56 | out_64[i] = in_left_64[i] ^ in_right_64[i];
hash.c: ...

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

Compiler	Implementations
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:bitslice_sb64

Compiler output

Implementation: T:bitslice_sb8
Security model: timingleaks
Compiler: gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE

hash.c: In function 'XOR',
hash.c: inlined from 'HASH' at hash.c:77:2,
hash.c: inlined from 'crypto_hash_photonbeetlehash256rate32v1_bitslice_sb8_timingleaks' at hash.c:129:3:
hash.c: hash.c:49:52: warning: writing 32 bytes into a region of size 0 [-Wstringop-overflow=]
hash.c: 49 | for (i = 0; i < iolen_inbytes; i++) out[i] = in_left[i] ^ in_right[i];
hash.c: | ~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~
hash.c: hash.c: In function 'crypto_hash_photonbeetlehash256rate32v1_bitslice_sb8_timingleaks':
hash.c: hash.c:109:17: note: at offset 32 into destination object 'State' of size 32
hash.c: 109 | uint8_t State[STATE_INBYTES] = { 0 };
hash.c: | ^~~~~
hash.c: In function 'XOR',
hash.c: inlined from 'HASH' at hash.c:77:2,
hash.c: inlined from 'crypto_hash_photonbeetlehash256rate32v1_bitslice_sb8_timingleaks' at hash.c:129:3:
hash.c: hash.c:49:52: warning: writing 32 bytes into a region of size 0 [-Wstringop-overflow=]
hash.c: 49 | for (i = 0; i < iolen_inbytes; i++) out[i] = in_left[i] ^ in_right[i];
hash.c: | ~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~
hash.c: hash.c: In function 'crypto_hash_photonbeetlehash256rate32v1_bitslice_sb8_timingleaks':
hash.c: hash.c:109:17: note: at offset [64, 96] into destination object 'State' of size 32
hash.c: 109 | uint8_t State[STATE_INBYTES] = { 0 };
hash.c: | ^~~~~

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

Compiler	Implementations
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:bitslice_sb8

Compiler output

Implementation: T:ref
Security model: timingleaks
Compiler: gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE

hash.c: In function 'XOR',
hash.c: inlined from 'HASH' at hash.c:77:2,
hash.c: inlined from 'crypto_hash_photonbeetlehash256rate32v1_ref_timingleaks' at hash.c:135:3:
hash.c: hash.c:49:52: warning: writing 32 bytes into a region of size 0 [-Wstringop-overflow=]
hash.c: 49 | for (i = 0; i < iolen_inbytes; i++) out[i] = in_left[i] ^ in_right[i];
hash.c: | ~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~
hash.c: hash.c: In function 'crypto_hash_photonbeetlehash256rate32v1_ref_timingleaks':
hash.c: hash.c:115:17: note: at offset 32 into destination object 'State' of size 32
hash.c: 115 | uint8_t State[STATE_INBYTES] = { 0 };
hash.c: | ^~~~~
hash.c: In function 'XOR',
hash.c: inlined from 'HASH' at hash.c:77:2,
hash.c: inlined from 'crypto_hash_photonbeetlehash256rate32v1_ref_timingleaks' at hash.c:135:3:
hash.c: hash.c:49:52: warning: writing 32 bytes into a region of size 0 [-Wstringop-overflow=]
hash.c: 49 | for (i = 0; i < iolen_inbytes; i++) out[i] = in_left[i] ^ in_right[i];
hash.c: | ~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~
hash.c: hash.c: In function 'crypto_hash_photonbeetlehash256rate32v1_ref_timingleaks':
hash.c: hash.c:115:17: note: at offset [64, 96] into destination object 'State' of size 32
hash.c: 115 | uint8_t State[STATE_INBYTES] = { 0 };
hash.c: | ^~~~~

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

Compiler	Implementations
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:ref

Compiler output

Implementation: T:table2
Security model: timingleaks
Compiler: gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE

hash.c: In function 'XOR',
hash.c: inlined from 'HASH' at hash.c:77:2,
hash.c: inlined from 'crypto_hash_photonbeetlehash256rate32v1_table2_timingleaks' at hash.c:128:3:
hash.c: hash.c:49:52: warning: writing 32 bytes into a region of size 0 [-Wstringop-overflow=]
hash.c: 49 | for (i = 0; i < iolen_inbytes; i++) out[i] = in_left[i] ^ in_right[i];
hash.c: | ~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~
hash.c: hash.c: In function 'crypto_hash_photonbeetlehash256rate32v1_table2_timingleaks':
hash.c: hash.c:108:17: note: at offset 32 into destination object 'State' of size 32
hash.c: 108 | uint8_t State[STATE_INBYTES] = { 0 };
hash.c: | ^~~~~
hash.c: In function 'XOR',
hash.c: inlined from 'HASH' at hash.c:77:2,
hash.c: inlined from 'crypto_hash_photonbeetlehash256rate32v1_table2_timingleaks' at hash.c:128:3:
hash.c: hash.c:49:52: warning: writing 32 bytes into a region of size 0 [-Wstringop-overflow=]
hash.c: 49 | for (i = 0; i < iolen_inbytes; i++) out[i] = in_left[i] ^ in_right[i];
hash.c: | ~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~
hash.c: hash.c: In function 'crypto_hash_photonbeetlehash256rate32v1_table2_timingleaks':
hash.c: hash.c:108:17: note: at offset [64, 96] into destination object 'State' of size 32
hash.c: 108 | uint8_t State[STATE_INBYTES] = { 0 };
hash.c: | ^~~~~

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

Compiler	Implementations
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:table2

Compiler output

Implementation: T:table3
Security model: timingleaks
Compiler: gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE

hash.c: In function 'XOR',
hash.c: inlined from 'HASH' at hash.c:77:2,
hash.c: inlined from 'crypto_hash_photonbeetlehash256rate32v1_table3_timingleaks' at hash.c:128:3:
hash.c: hash.c:49:52: warning: writing 32 bytes into a region of size 0 [-Wstringop-overflow=]
hash.c: 49 | for (i = 0; i < iolen_inbytes; i++) out[i] = in_left[i] ^ in_right[i];
hash.c: | ~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~
hash.c: hash.c: In function 'crypto_hash_photonbeetlehash256rate32v1_table3_timingleaks':
hash.c: hash.c:108:17: note: at offset 32 into destination object 'State' of size 32
hash.c: 108 | uint8_t State[STATE_INBYTES] = { 0 };
hash.c: | ^~~~~
hash.c: In function 'XOR',
hash.c: inlined from 'HASH' at hash.c:77:2,
hash.c: inlined from 'crypto_hash_photonbeetlehash256rate32v1_table3_timingleaks' at hash.c:128:3:
hash.c: hash.c:49:52: warning: writing 32 bytes into a region of size 0 [-Wstringop-overflow=]
hash.c: 49 | for (i = 0; i < iolen_inbytes; i++) out[i] = in_left[i] ^ in_right[i];
hash.c: | ~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~
hash.c: hash.c: In function 'crypto_hash_photonbeetlehash256rate32v1_table3_timingleaks':
hash.c: hash.c:108:17: note: at offset [64, 96] into destination object 'State' of size 32
hash.c: 108 | uint8_t State[STATE_INBYTES] = { 0 };
hash.c: | ^~~~~

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

Compiler	Implementations
gcc -march=native -mtune=native -O3 -fomit-frame-pointer -fwrapv -fPIC -fPIE	T:table3