Test results for aarch64, pi3aplus, crypto_hashblocks/sha512

[Page version: 20250510 09:23:11]

Measurements for aarch64, pi3aplus, crypto_hashblocks Test results for aarch64, pi3aplus, crypto_hashblocks Test results for crypto_hashblocks/sha512

Computer: pi3aplus
Microarchitecture: aarch64; Cortex-A53 (410fd034)
Architecture: aarch64
CPU ID: 410fd034
SUPERCOP version: 20250415
Operation: crypto_hashblocks
Primitive: sha512

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
16222	3220 0 0	13100 768 736	`wflip`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250501	20250415
16263	2612 0 0	11580 768 736	`wflip`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250501	20250415
16968	11364 0 0	21260 768 736	`ref`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250408	20250307
17064	11352 0 0	21260 768 736	`inplace`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250408	20250307
18117	3968 0 0	13892 768 736	`compact`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250408	20250307
18167	2716 0 0	10652 752 720	`wflip`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250501	20250415
18312	11328 0 0	20308 768 736	`ref`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250408	20250307
18471	3488 0 0	12500 768 736	`compact`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250408	20250307
20496	10876 0 0	18844 752 720	`ref`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250408	20250307
20558	10872 0 0	18836 752 720	`inplace`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250408	20250307
21402	11328 0 0	20324 768 736	`inplace`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250408	20250307
21746	3444 0 0	11420 752 720	`compact`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250408	20250307
24433	4244 0 0	13075 760 728	`wflip`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250501	20250415
26631	11100 0 0	19971 760 728	`inplace`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250408	20250307
26786	11128 0 0	19995 760 728	`ref`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250408	20250307
27906	1964 0 0	11868 768 736	`compact4`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250408	20250307
30147	3628 0 0	12515 760 728	`compact`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250408	20250307
30898	1416 0 0	10420 768 736	`compact4`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250408	20250307
36829	1228 0 0	9188 752 720	`compact4`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250408	20250307
39176	1404 0 0	10412 768 736	`compact3`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250408	20250307
40255	1916 0 0	11820 768 736	`compact3`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250408	20250307
46563	1400 0 0	10259 760 728	`compact4`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250408	20250307
46621	2072 0 0	12004 768 736	`compact2`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250408	20250307
46895	1600 0 0	10604 768 736	`compact2`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250408	20250307
73197	1564 0 0	9548 752 720	`compact2`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250408	20250307
74998	1696 0 0	10579 760 728	`compact2`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250408	20250307
76796	1364 0 0	9316 752 720	`compact3`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250408	20250307
78737	1576 0 0	10443 760 728	`compact3`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20250408	20250307

Compiler output

blocks.c: blocks.c:15:2: warning: #warning "FEAT_SHA512 is not enabled in the compiler. To enable FEAT_SHA512, use for instance \"-mcpu=neoverse-v2+crypto+sha3\" on Graviton 4 or NVidia Grace." [-Wcpp]
blocks.c:    15 | #warning "FEAT_SHA512 is not enabled in the compiler. To enable FEAT_SHA512, use for instance \"-mcpu=neoverse-v2+crypto+sha3\" on Graviton 4 or NVidia Grace."
blocks.c:       |  ^~~~~~~
blocks.c: In file included from blocks.c:11:
blocks.c: /usr/lib/gcc/aarch64-linux-gnu/12/include/arm_neon.h: In function 'crypto_hashblocks_sha512_dolbeau_arm_sha512_constbranchindex':
blocks.c: /usr/lib/gcc/aarch64-linux-gnu/12/include/arm_neon.h:29671:1: error: inlining failed in call to 'always_inline' 'vsha512h2q_u64': target specific option mismatch
blocks.c: 29671 | vsha512h2q_u64 (uint64x2_t __a, uint64x2_t __b, uint64x2_t __c)
blocks.c:       | ^~~~~~~~~~~~~~
blocks.c: blocks.c:59:8: note: called from here
blocks.c:    59 |   ef = vsha512h2q_u64(half_round_v2, ab, gh);                           \
blocks.c:       |        ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
blocks.c: blocks.c:212:5: note: in expansion of macro 'F4_v2'
blocks.c:   212 |     F4_v2(w12, GETK(76), w14, GETK(78), ef, gh, ab, cd);
blocks.c:       |     ^~~~~
blocks.c: /usr/lib/gcc/aarch64-linux-gnu/12/include/arm_neon.h:29664:1: error: inlining failed in call to 'always_inline' 'vsha512hq_u64': target specific option mismatch
blocks.c: 29664 | vsha512hq_u64 (uint64x2_t __a, uint64x2_t __b, uint64x2_t __c)
blocks.c:       | ^~~~~~~~~~~~~
blocks.c: blocks.c:58:19: note: called from here
blocks.c:    58 |   half_round_v2 = vsha512hq_u64(k2plusw2_swapped_plusef_v2, vextq_u64(cd, ef, 1), vextq_u64(ab, cd, 1)); \
blocks.c:       |                   ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
blocks.c: blocks.c:212:5: note: in expansion of macro 'F4_v2'
blocks.c:   212 |     F4_v2(w12, GETK(76), w14, GETK(78), ef, gh, ab, cd);
blocks.c:       |     ^~~~~
blocks.c: /usr/lib/gcc/aarch64-linux-gnu/12/include/arm_neon.h:29671:1: error: inlining failed in call to 'always_inline' 'vsha512h2q_u64': target specific option mismatch
blocks.c: 29671 | vsha512h2q_u64 (uint64x2_t __a, uint64x2_t __b, uint64x2_t __c)
blocks.c: ...

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

Implementation	Compiler
`dolbeau/arm-sha512`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`dolbeau/arm-sha512`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`dolbeau/arm-sha512`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`dolbeau/arm-sha512`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`

Passed TIMECOP

TIMECOP iterations: 10

Number of similar (implementation,compiler) pairs: 28, namely:

Implementation	Compiler
`compact`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`compact`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`compact`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`compact`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`compact2`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`compact2`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`compact2`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`compact2`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`compact3`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`compact3`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`compact3`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`compact3`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`compact4`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`compact4`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`compact4`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`compact4`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`inplace`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`inplace`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`inplace`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`inplace`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`ref`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`ref`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`ref`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`ref`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`wflip`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`wflip`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`wflip`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`
`wflip`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (12.2.0)`