Test results for amd64, gemini, crypto_aead/aes128poetv1aes4

[Page version: 20241028 05:30:40]

Measurements for amd64, gemini, crypto_aead Test results for amd64, gemini, crypto_aead Test results for crypto_aead/aes128poetv1aes4

Computer: gemini
Microarchitecture: amd64; Goldmont Plus (706a8)
Architecture: amd64
CPU ID: GenuineIntel-000706a8-bfebfbff
SUPERCOP version: 20241022
Operation: crypto_aead
Primitive: aes128poetv1aes4

Time	Object size	Test size	Implementation	Compiler	Benchmark date	SUPERCOP version
14265	13751 0 0	29200 828 1016	`T:ni`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20240630	20240625
14278	13751 0 0	31504 828 1016	`T:ni`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20240630	20240625
15940	11947 0 0	25542 820 1016	`T:ni`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20240630	20240625
24292	14751 0 0	29424 796 1080	`T:ni`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20240630	20240625
25636	15356 0 0	31176 796 1080	`T:ni`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20240630	20240625
31416	12015 0 0	26279 788 1080	`T:ni`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20240630	20240625
37737	4451 0 0	17595 772 1048	`T:ni`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20240630	20240625
40158	6167 0 0	20550 820 1016	`T:ni`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20240630	20240625
171258	20764 0 0	34395 828 1016	`T:ref`	`clang -march=native -Os -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20240630	20240625
178681	27526 0 0	43352 796 1080	`T:ref`	`gcc -march=native -mtune=native -O3 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20240630	20240625
188030	22888 0 0	37568 796 1080	`T:ref`	`gcc -march=native -mtune=native -O2 -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20240630	20240625
190351	20330 0 0	33419 772 1048	`T:ref`	`gcc -march=native -mtune=native -Os -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20240630	20240625
198752	21948 0 0	36199 788 1080	`T:ref`	`gcc -march=native -mtune=native -O -fwrapv -fPIC -fPIE -gdwarf-4 -Wall`	20240630	20240625
222862	25864 0 0	42437 836 1016	`T:ref`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20240630	20240625
227825	24548 0 0	40093 836 1016	`T:ref`	`clang -march=native -O2 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20240630	20240625
245116	21338 0 0	35643 828 1016	`T:ref`	`clang -march=native -O -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20240630	20240625
246906	25172 0 0	43021 836 1016	`T:ref`	`clang -march=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall`	20240630	20240625

Compiler output

poet.c: poet.c:488:26: error: '__builtin_ia32_vec_set_v16qi' needs target feature sse4.1
poet.c:     ctx->l = aes_encrypt(one, expanded_key);
poet.c:                          ^
poet.c: poet.c:182:24: note: expanded from macro 'one'
poet.c: #define one            _mm_insert_epi8(zero, 1, 15)
poet.c:                        ^
poet.c: /usr/lib/llvm-11/lib/clang/11.0.1/include/smmintrin.h:928:12: note: expanded from macro '_mm_insert_epi8'
poet.c:   (__m128i)__builtin_ia32_vec_set_v16qi((__v16qi)(__m128i)(X), \
poet.c:            ^
poet.c: poet.c:490:25: error: '__builtin_ia32_vec_set_v16qi' needs target feature sse4.1
poet.c:     k_axu = aes_encrypt(two, expanded_key);
poet.c:                         ^
poet.c: poet.c:183:24: note: expanded from macro 'two'
poet.c: #define two            _mm_insert_epi8(zero, 2, 15)
poet.c:                        ^
poet.c: /usr/lib/llvm-11/lib/clang/11.0.1/include/smmintrin.h:928:12: note: expanded from macro '_mm_insert_epi8'
poet.c:   (__m128i)__builtin_ia32_vec_set_v16qi((__v16qi)(__m128i)(X), \
poet.c:            ^
poet.c: poet.c:493:25: error: '__builtin_ia32_vec_set_v16qi' needs target feature sse4.1
poet.c:     k_axu = aes_encrypt(three, expanded_key);
poet.c:                         ^
poet.c: poet.c:184:24: note: expanded from macro 'three'
poet.c: #define three          _mm_insert_epi8(zero, 3, 15)
poet.c:                        ^
poet.c: /usr/lib/llvm-11/lib/clang/11.0.1/include/smmintrin.h:928:12: note: expanded from macro '_mm_insert_epi8'
poet.c: ...

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

Implementation	Compiler
`T:ni`	`clang -mcpu=native -O3 -fwrapv -Qunused-arguments -fPIC -fPIE -gdwarf-4 -Wall (Debian_Clang_11.0.1)`