Test results for amd64, titan0, crypto_sort/uint64

[Page version: 20260312 22:59:58]

Measurements for amd64, titan0, crypto_sort Test results for amd64, titan0, crypto_sort Test results for crypto_sort/uint64

Computer: titan0
Microarchitecture: amd64; Haswell+AES (306c3)
Architecture: amd64
CPU ID: GenuineIntel-000306c3-bfebfbff
SUPERCOP version: 20260217
Operation: crypto_sort
Primitive: uint64

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
26456	766 0 0	58707 1288 1472	`useint64`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20260302	20260217
26611	492 0 0	55125 1280 1504	`avx2useint64`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20260302	20260217
26866	448 0 0	55516 1216 1536	`avx2useint64`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20260302	20260217
26969	882 0 0	59435 1288 1472	`avx2useint64`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20260302	20260217
27011	532 0 0	55981 1224 1536	`avx2useint64`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20260302	20260217
27061	372 0 0	54500 1208 1504	`avx2useint64`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20260302	20260217
27353	766 0 0	59307 1288 1472	`useint64`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20260302	20260217
27407	790 0 0	58501 1224 1536	`avx2useint64`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20260302	20260217
27559	580 0 0	57179 1288 1472	`useint64`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20260302	20260217
27663	293 0 0	54467 1288 1472	`avx2useint64`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20260302	20260217
27672	585 0 0	58301 1224 1536	`useint64`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20260302	20260217
27806	882 0 0	58835 1288 1472	`avx2useint64`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20260302	20260217
28429	205 0 0	55653 1224 1536	`useint64`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20260302	20260217
28637	192 0 0	55252 1216 1536	`useint64`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20260302	20260217
28839	361 0 0	55037 1280 1504	`useint64`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20260302	20260217
28881	167 0 0	54339 1288 1472	`useint64`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20260302	20260217
29437	208 0 0	54340 1208 1504	`useint64`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20260302	20260217
80180	1413 0 0	27806 1320 1568	`T:stdsort`	`g++ -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20260302	20260217
80527	1892 0 0	27911 1368 1472	`T:stdsort`	`clang++ -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20260302	20260217
80711	1361 0 0	25376 1320 1568	`T:stdsort`	`g++ -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20260302	20260217
80938	1653 0 0	27283 1368 1472	`T:stdsort`	`clang++ -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20260302	20260217
81465	1588 0 0	23482 1376 1472	`T:stdsort`	`clang++ -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20260302	20260217
81735	1331 0 0	23900 1368 1504	`T:stdsort`	`clang++ -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20260302	20260217
85576	968 0 0	23273 1296 1536	`T:stdsort`	`g++ -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20260302	20260217
87134	1216 0 0	24689 1312 1568	`T:stdsort`	`g++ -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20260302	20260217

Compiler output

sort.c: sort.c:16:20: error: always_inline function '_mm256_set1_epi64x' requires target feature 'avx', but would be inlined into function 'uint64_sort' that is compiled without support for 'avx'
sort.c:   int64x4 vecxor = int64x4_broadcast(0x8000000000000000ULL);
sort.c:                    ^
sort.c: sort.c:8:27: note: expanded from macro 'int64x4_broadcast'
sort.c: #define int64x4_broadcast _mm256_set1_epi64x
sort.c:                           ^
sort.c: sort.c:16:20: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
sort.c: sort.c:8:27: note: expanded from macro 'int64x4_broadcast'
sort.c: #define int64x4_broadcast _mm256_set1_epi64x
sort.c:                           ^
sort.c: sort.c:18:18: error: always_inline function '_mm256_loadu_si256' requires target feature 'avx', but would be inlined into function 'uint64_sort' that is compiled without support for 'avx'
sort.c:     int64x4 x0 = int64x4_load(x+j);
sort.c:                  ^
sort.c: sort.c:6:25: note: expanded from macro 'int64x4_load'
sort.c: #define int64x4_load(z) _mm256_loadu_si256((__m256i *) (z))
sort.c:                         ^
sort.c: sort.c:18:18: error: AVX vector return of type '__m256i' (vector of 4 'long long' values) without 'avx' enabled changes the ABI
sort.c: sort.c:6:25: note: expanded from macro 'int64x4_load'
sort.c: #define int64x4_load(z) _mm256_loadu_si256((__m256i *) (z))
sort.c:                         ^
sort.c: sort.c:19:18: error: always_inline function '_mm256_loadu_si256' requires target feature 'avx', but would be inlined into function 'uint64_sort' that is compiled without support for 'avx'
sort.c:     int64x4 x1 = int64x4_load(x+j+4);
sort.c:                  ^
sort.c: sort.c:6:25: note: expanded from macro 'int64x4_load'
sort.c: #define int64x4_load(z) _mm256_loadu_si256((__m256i *) (z))
sort.c: ...

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

Implementation	Compiler
`avx2useint64`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`

Passed TIMECOP

TIMECOP iterations: 10

Number of similar (implementation,compiler) pairs: 17, namely:

Implementation	Compiler
`avx2useint64`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`avx2useint64`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`avx2useint64`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`avx2useint64`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`avx2useint64`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`avx2useint64`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`avx2useint64`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`avx2useint64`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`useint64`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`useint64`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`useint64`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`useint64`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`useint64`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Ubuntu_Clang_14.0.0)`
`useint64`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`useint64`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`useint64`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`
`useint64`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall (11.4.0)`