Implementation notes: amd64, bulldozer, crypto_hash/sarmal256

Computer: bulldozer
Architecture: amd64
CPU ID: AuthenticAMD-00600f12-178bfbff
SUPERCOP version: 20120709
Operation: crypto_hash
Primitive: sarmal256

Time	Implementation	Compiler	Benchmark date	SUPERCOP version
18720	`asm64`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20120530	20120525
18914	`asm64`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20120530	20120525
18973	`asm64`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20120530	20120525
19003	`asm64`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20120530	20120525
19104	`asm64`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20120530	20120525
19175	`asm64`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20120530	20120525
19197	`asm64`	`gcc -march=nocona -O -fomit-frame-pointer`	20120530	20120525
19210	`asm64`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20120530	20120525
19217	`asm64`	`gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer`	20120530	20120525
19244	`asm64`	`gcc -m64 -O -fomit-frame-pointer`	20120530	20120525
19272	`asm64`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20120530	20120525
19274	`asm64`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20120530	20120525
19295	`asm64`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20120530	20120525
19357	`opt64`	`gcc -funroll-loops -m64 -march=nocona -O2 -fomit-frame-pointer`	20120530	20120525
19372	`asm64`	`gcc -m64 -Os -fomit-frame-pointer`	20120530	20120525
19440	`opt64`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20120530	20120525
19564	`asm64`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20120530	20120525
19567	`opt64`	`gcc -funroll-loops -m64 -O2 -fomit-frame-pointer`	20120530	20120525
19586	`asm64`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20120530	20120525
19670	`asm64`	`gcc -m64 -march=core-avx-i -O -fomit-frame-pointer`	20120530	20120525
19674	`asm64`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20120530	20120525
19803	`asm64`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20120530	20120525
19837	`asm64`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20120530	20120525
19900	`asm64`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20120530	20120525
19920	`asm64`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20120530	20120525
19927	`asm64`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20120530	20120525
19986	`opt64`	`gcc -funroll-loops -O3 -fomit-frame-pointer`	20120530	20120525
19989	`asm64`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20120530	20120525
20022	`asm64`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20120530	20120525
20024	`asm64`	`gcc -m64 -march=corei7-avx -O -fomit-frame-pointer`	20120530	20120525
20040	`opt64`	`gcc -funroll-loops -O -fomit-frame-pointer`	20120530	20120525
20052	`asm64`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20120530	20120525
20093	`asm64`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20120530	20120525
20113	`asm64`	`gcc -O -fomit-frame-pointer`	20120530	20120525
20128	`opt64`	`gcc -m64 -O2 -fomit-frame-pointer`	20120530	20120525
20145	`asm64`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20120530	20120525
20189	`asm64`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20120530	20120525
20203	`opt64`	`gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer`	20120530	20120525
20228	`asm64`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20120530	20120525
20236	`asm64`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20120530	20120525
20278	`asm64`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20120530	20120525
20294	`asm64`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20120530	20120525
20303	`asm64`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20120530	20120525
20313	`opt64`	`gcc -O2 -fomit-frame-pointer`	20120530	20120525
20325	`asm64`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20120530	20120525
20345	`asm64`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20120530	20120525
20346	`asm64`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20120530	20120525
20368	`asm64`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20120530	20120525
20378	`opt64`	`gcc -m64 -O3 -fomit-frame-pointer`	20120530	20120525
20385	`asm64`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20120530	20120525
20406	`asm64`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20120530	20120525
20410	`asm64`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20120530	20120525
20428	`asm64`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20120530	20120525
20432	`asm64`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20120530	20120525
20447	`opt64`	`gcc -funroll-loops -march=barcelona -O2 -fomit-frame-pointer`	20120530	20120525
20472	`opt64`	`gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer`	20120530	20120525
20474	`asm64`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20120530	20120525
20484	`opt64`	`gcc -funroll-loops -m64 -march=nocona -O -fomit-frame-pointer`	20120530	20120525
20488	`opt64`	`gcc -march=nocona -O3 -fomit-frame-pointer`	20120530	20120525
20537	`asm64`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20120530	20120525
20538	`asm64`	`gcc -march=barcelona -O -fomit-frame-pointer`	20120530	20120525
20540	`asm64`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20120530	20120525
20543	`asm64`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20120530	20120525
20553	`opt64`	`gcc -funroll-loops -m64 -march=barcelona -O2 -fomit-frame-pointer`	20120530	20120525
20575	`asm64`	`gcc -m64 -march=nocona -O3 -fomit-frame-pointer`	20120530	20120525
20643	`asm64`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20120530	20120525
20649	`opt64`	`gcc -funroll-loops -march=nocona -O2 -fomit-frame-pointer`	20120530	20120525
20656	`asm64`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20120530	20120525
20671	`asm64`	`gcc -march=k8 -Os -fomit-frame-pointer`	20120530	20120525
20674	`asm64`	`gcc -funroll-loops`	20120530	20120525
20679	`opt64`	`gcc -funroll-loops -m64 -march=nocona -O3 -fomit-frame-pointer`	20120530	20120525
20708	`opt64`	`gcc -funroll-loops -m64 -O -fomit-frame-pointer`	20120530	20120525
20723	`asm64`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20120530	20120525
20750	`opt64`	`gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer`	20120530	20120525
20753	`opt64`	`gcc -m64 -march=core2 -O3 -fomit-frame-pointer`	20120530	20120525
20792	`asm64`	`gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer`	20120530	20120525
20805	`asm64`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20120530	20120525
20838	`asm64`	`gcc`	20120530	20120525
20850	`asm64`	`cc`	20120530	20120525
20890	`opt64`	`gcc -fno-schedule-insns -O3 -fomit-frame-pointer`	20120530	20120525
20890	`opt64`	`gcc -m64 -march=corei7-avx -O -fomit-frame-pointer`	20120530	20120525
20899	`opt64`	`gcc -funroll-loops -m64 -O3 -fomit-frame-pointer`	20120530	20120525
20923	`opt64`	`gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer`	20120530	20120525
20950	`asm64`	`gcc -march=nocona -Os -fomit-frame-pointer`	20120530	20120525
20970	`opt64`	`gcc -m64 -march=corei7 -O -fomit-frame-pointer`	20120530	20120525
20994	`opt64`	`gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer`	20120530	20120525
21016	`opt64`	`gcc -funroll-loops -O2 -fomit-frame-pointer`	20120530	20120525
21021	`opt64`	`gcc -fno-schedule-insns -O2 -fomit-frame-pointer`	20120530	20120525
21033	`opt64`	`gcc -m64 -march=corei7 -O3 -fomit-frame-pointer`	20120530	20120525
21056	`opt64`	`gcc -m64 -march=core2 -msse4.1 -O -fomit-frame-pointer`	20120530	20120525
21090	`asm64`	`gcc -Os -fomit-frame-pointer`	20120530	20120525
21103	`asm64`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20120530	20120525
21125	`opt64`	`gcc -m64 -march=core-avx-i -O -fomit-frame-pointer`	20120530	20120525
21171	`opt64`	`gcc -m64 -march=core2 -msse4 -O -fomit-frame-pointer`	20120530	20120525
21252	`opt64`	`gcc -funroll-loops -march=nocona -O3 -fomit-frame-pointer`	20120530	20120525
21282	`opt64`	`gcc -m64 -O -fomit-frame-pointer`	20120530	20120525
21289	`opt64`	`gcc -O -fomit-frame-pointer`	20120530	20120525
21294	`opt64`	`gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer`	20120530	20120525
21307	`opt64`	`gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer`	20120530	20120525
21336	`opt64`	`gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer`	20120530	20120525
21502	`opt64`	`gcc -fno-schedule-insns -O -fomit-frame-pointer`	20120530	20120525
21548	`opt64`	`gcc -march=nocona -O2 -fomit-frame-pointer`	20120530	20120525
21553	`opt64`	`gcc -funroll-loops -march=barcelona -O3 -fomit-frame-pointer`	20120530	20120525
21572	`opt64`	`gcc -m64 -march=barcelona -O3 -fomit-frame-pointer`	20120530	20120525
21627	`opt64`	`gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer`	20120530	20120525
21646	`opt64`	`gcc -m64 -march=native -mtune=native -O -fomit-frame-pointer`	20120530	20120525
21664	`opt64`	`gcc -m64 -march=native -mtune=native -O2 -fomit-frame-pointer`	20120530	20120525
21671	`opt64`	`gcc -m64 -march=core2 -O2 -fomit-frame-pointer`	20120530	20120525
21687	`opt64`	`gcc -m64 -march=core2 -O -fomit-frame-pointer`	20120530	20120525
21789	`opt64`	`gcc -m64 -march=nocona -Os -fomit-frame-pointer`	20120530	20120525
21833	`opt64`	`gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer`	20120530	20120525
21844	`opt64`	`gcc -m64 -march=k8 -O2 -fomit-frame-pointer`	20120530	20120525
21912	`opt64`	`gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer`	20120530	20120525
21930	`opt64`	`gcc -funroll-loops -m64 -march=barcelona -O -fomit-frame-pointer`	20120530	20120525
21939	`opt64`	`gcc -funroll-loops -march=k8 -O -fomit-frame-pointer`	20120530	20120525
21940	`opt64`	`gcc -march=k8 -O3 -fomit-frame-pointer`	20120530	20120525
21949	`opt64`	`gcc -m64 -march=k8 -O3 -fomit-frame-pointer`	20120530	20120525
21953	`opt64`	`gcc -m64 -march=native -mtune=native -O3 -fomit-frame-pointer`	20120530	20120525
21962	`opt64`	`gcc -march=barcelona -O3 -fomit-frame-pointer`	20120530	20120525
22035	`opt64`	`gcc -m64 -march=nocona -O2 -fomit-frame-pointer`	20120530	20120525
22138	`opt64`	`gcc -funroll-loops -m64 -march=barcelona -O3 -fomit-frame-pointer`	20120530	20120525
22161	`opt64`	`gcc -march=k8 -O -fomit-frame-pointer`	20120530	20120525
22193	`opt64`	`gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer`	20120530	20120525
22324	`opt64`	`gcc -funroll-loops -march=barcelona -O -fomit-frame-pointer`	20120530	20120525
22383	`opt64`	`gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer`	20120530	20120525
22445	`opt64`	`gcc -funroll-loops -march=nocona -O -fomit-frame-pointer`	20120530	20120525
22473	`opt64`	`gcc -O3 -fomit-frame-pointer`	20120530	20120525
22619	`opt64`	`gcc -march=k8 -O2 -fomit-frame-pointer`	20120530	20120525
22633	`opt64`	`gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer`	20120530	20120525
22736	`opt64`	`gcc -m64 -march=nocona -O -fomit-frame-pointer`	20120530	20120525
22736	`opt64`	`gcc -march=nocona -O -fomit-frame-pointer`	20120530	20120525
22789	`opt64`	`gcc -m64 -march=k8 -O -fomit-frame-pointer`	20120530	20120525
22882	`opt64`	`gcc -m64 -march=corei7 -O2 -fomit-frame-pointer`	20120530	20120525
22920	`opt64`	`gcc -funroll-loops -m64 -Os -fomit-frame-pointer`	20120530	20120525
22950	`opt64`	`gcc -funroll-loops -march=nocona -Os -fomit-frame-pointer`	20120530	20120525
22983	`opt64`	`gcc -march=barcelona -O -fomit-frame-pointer`	20120530	20120525
22985	`opt64`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20120530	20120525
22988	`opt64`	`gcc -funroll-loops -fno-schedule-insns -Os -fomit-frame-pointer`	20120530	20120525
23039	`opt64`	`gcc -funroll-loops -m64 -march=k8 -Os -fomit-frame-pointer`	20120530	20120525
23059	`opt64`	`gcc -m64 -march=native -mtune=native -Os -fomit-frame-pointer`	20120530	20120525
23122	`opt64`	`gcc -m64 -march=k8 -Os -fomit-frame-pointer`	20120530	20120525
23139	`opt64`	`gcc -funroll-loops -march=k8 -Os -fomit-frame-pointer`	20120530	20120525
23148	`opt64`	`gcc -m64 -Os -fomit-frame-pointer`	20120530	20120525
23153	`opt64`	`gcc -funroll-loops -m64 -march=barcelona -Os -fomit-frame-pointer`	20120530	20120525
23190	`opt64`	`gcc -m64 -march=core2 -Os -fomit-frame-pointer`	20120530	20120525
23200	`opt64`	`gcc -funroll-loops -march=barcelona -Os -fomit-frame-pointer`	20120530	20120525
23218	`opt64`	`gcc -m64 -march=core-avx-i -Os -fomit-frame-pointer`	20120530	20120525
23234	`opt64`	`gcc -funroll-loops -m64 -march=nocona -Os -fomit-frame-pointer`	20120530	20120525
23254	`opt64`	`gcc -m64 -march=barcelona -O2 -fomit-frame-pointer`	20120530	20120525
23290	`opt64`	`gcc -Os -fomit-frame-pointer`	20120530	20120525
23318	`opt64`	`gcc -m64 -march=core2 -msse4.1 -Os -fomit-frame-pointer`	20120530	20120525
23394	`opt64`	`gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer`	20120530	20120525
23428	`opt64`	`gcc -m64 -march=corei7-avx -Os -fomit-frame-pointer`	20120530	20120525
23496	`opt64`	`gcc -march=k8 -Os -fomit-frame-pointer`	20120530	20120525
23749	`opt64`	`gcc -m64 -march=core2 -msse4 -Os -fomit-frame-pointer`	20120530	20120525
23959	`opt64`	`gcc -funroll-loops -Os -fomit-frame-pointer`	20120530	20120525
23963	`opt64`	`gcc -m64 -march=barcelona -Os -fomit-frame-pointer`	20120530	20120525
24165	`opt64`	`gcc -march=nocona -Os -fomit-frame-pointer`	20120530	20120525
24247	`opt64`	`gcc -march=barcelona -Os -fomit-frame-pointer`	20120530	20120525
24281	`opt64`	`gcc -fno-schedule-insns -Os -fomit-frame-pointer`	20120530	20120525
24292	`opt64`	`gcc -m64 -march=corei7 -Os -fomit-frame-pointer`	20120530	20120525
24555	`opt64`	`gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer`	20120530	20120525
24782	`asm64`	`gcc -march=barcelona -O2 -fomit-frame-pointer`	20120530	20120525
28236	`opt64`	`gcc -m64 -march=barcelona -O -fomit-frame-pointer`	20120530	20120525
40377	`opt64`	`cc`	20120530	20120525
41284	`opt64`	`gcc -funroll-loops`	20120530	20120525
42663	`opt64`	`gcc`	20120530	20120525

Checksum failure

Implementation: crypto_hash/sarmal256/asm64
Compiler: gcc -m64 -march=k8 -O2 -fomit-frame-pointer

3eb9be88f1271c693d908177f324500a7befe6930fdff907df8c1fffbd8fe0ba

Number of similar (compiler,implementation) pairs: 2, namely:

Compiler	Implementations
gcc -m64 -march=k8 -O2 -fomit-frame-pointer	asm64
gcc -march=k8 -O2 -fomit-frame-pointer	asm64

Test failure

Implementation: crypto_hash/sarmal256/asm64
Compiler: gcc -O2 -fomit-frame-pointer

error 111

Number of similar (compiler,implementation) pairs: 32, namely:

Compiler	Implementations
gcc -O2 -fomit-frame-pointer	asm64
gcc -O3 -fomit-frame-pointer	asm64
gcc -fno-schedule-insns -O2 -fomit-frame-pointer	asm64
gcc -fno-schedule-insns -O3 -fomit-frame-pointer	asm64
gcc -funroll-loops -O2 -fomit-frame-pointer	asm64
gcc -funroll-loops -O3 -fomit-frame-pointer	asm64
gcc -funroll-loops -fno-schedule-insns -O2 -fomit-frame-pointer	asm64
gcc -funroll-loops -fno-schedule-insns -O3 -fomit-frame-pointer	asm64
gcc -funroll-loops -m64 -O2 -fomit-frame-pointer	asm64
gcc -funroll-loops -m64 -O3 -fomit-frame-pointer	asm64
gcc -funroll-loops -m64 -march=k8 -O2 -fomit-frame-pointer	asm64
gcc -funroll-loops -m64 -march=k8 -O3 -fomit-frame-pointer	asm64
gcc -funroll-loops -march=k8 -O2 -fomit-frame-pointer	asm64
gcc -funroll-loops -march=k8 -O3 -fomit-frame-pointer	asm64
gcc -m64 -O2 -fomit-frame-pointer	asm64
gcc -m64 -O3 -fomit-frame-pointer	asm64
gcc -m64 -march=core-avx-i -O2 -fomit-frame-pointer	asm64
gcc -m64 -march=core-avx-i -O3 -fomit-frame-pointer	asm64
gcc -m64 -march=core2 -O2 -fomit-frame-pointer	asm64
gcc -m64 -march=core2 -O3 -fomit-frame-pointer	asm64
gcc -m64 -march=core2 -msse4.1 -O2 -fomit-frame-pointer	asm64
gcc -m64 -march=core2 -msse4.1 -O3 -fomit-frame-pointer	asm64
gcc -m64 -march=core2 -msse4 -O2 -fomit-frame-pointer	asm64
gcc -m64 -march=core2 -msse4 -O3 -fomit-frame-pointer	asm64
gcc -m64 -march=corei7-avx -O2 -fomit-frame-pointer	asm64
gcc -m64 -march=corei7-avx -O3 -fomit-frame-pointer	asm64
gcc -m64 -march=corei7 -O2 -fomit-frame-pointer	asm64
gcc -m64 -march=corei7 -O3 -fomit-frame-pointer	asm64
gcc -m64 -march=k8 -O3 -fomit-frame-pointer	asm64
gcc -m64 -march=k8 -O -fomit-frame-pointer	asm64
gcc -march=k8 -O3 -fomit-frame-pointer	asm64
gcc -march=k8 -O -fomit-frame-pointer	asm64

Test failure

Implementation: crypto_hash/sarmal256/asm64
Compiler: gcc -funroll-loops -O -fomit-frame-pointer

error 111
crypto_hash does not handle overlap

Number of similar (compiler,implementation) pairs: 3, namely:

Compiler	Implementations
gcc -funroll-loops -O -fomit-frame-pointer	asm64
gcc -funroll-loops -fno-schedule-insns -O -fomit-frame-pointer	asm64
gcc -funroll-loops -m64 -O -fomit-frame-pointer	asm64

Test failure

Implementation: crypto_hash/sarmal256/asm64
Compiler: gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer

error 142
Alarm clock

Number of similar (compiler,implementation) pairs: 2, namely:

Compiler	Implementations
gcc -funroll-loops -m64 -march=k8 -O -fomit-frame-pointer	asm64
gcc -funroll-loops -march=k8 -O -fomit-frame-pointer	asm64