[openssl-users] compared performances on Mac OS X 10.6.8

[Patrick Proniewski]

Hello,

I've compiled OpenSSL 1.0.2a on Mac OS X 10.6.8, and used `openssl speed` to compare performances with stock OpenSSL (0.9.8). In many tests, 1.0.2a is a bit faster, or as fast as 0.9.8y, but on the 6 AES tests, the old one is almost twice as fast as the new one:

OpenSSL 1.0.2a 19 Mar 2015
built on: reproducible build, date unspecified
options:bn(64,32) rc4(8x,mmx) des(idx,cisc,16,long) aes(partial) idea(int) blowfish(ptr) 
compiler: cc -I. -I.. -I../include  -fPIC -fno-common -DOPENSSL_PIC -DZLIB -DOPENSSL_THREADS -D_REENTRANT -DDSO_DLFCN -DHAVE_DLFCN_H -arch i386 -O3 -fomit-frame-pointer -DL_ENDIAN -DOPENSSL_BN_ASM_PART_WORDS -DOPENSSL_IA32_SSE2 -DOPENSSL_BN_ASM_MONT -DOPENSSL_BN_ASM_GF2m -DSHA1_ASM -DSHA256_ASM -DSHA512_ASM -DMD5_ASM -DRMD160_ASM -DAES_ASM -DVPAES_ASM -DWHIRLPOOL_ASM -DGHASH_ASM
../..
aes-128 cbc      93494.07k   102637.16k   104677.80k   105762.76k   106145.31k
aes-192 cbc      78912.98k    84939.17k    86991.87k    88263.00k    88350.72k
aes-256 cbc      68691.56k    73564.65k    74554.37k    75421.01k    75803.31k
../..
aes-128 ige      89849.59k    94381.10k    97713.32k    98399.23k    97045.16k
aes-192 ige      76133.38k    80632.62k    81332.31k    82033.66k    81988.27k
aes-256 ige      66744.15k    69558.66k    70501.12k    70079.15k    70041.60k
../..


OpenSSL 0.9.8y 5 Feb 2013
built on: Jun 27 2013
options:bn(64,64) md2(int) rc4(ptr,char) des(idx,cisc,16,int) aes(partial) blowfish(ptr2) 
compiler: -arch x86_64 -fmessage-length=0 -pipe -Wno-trigraphs -fpascal-strings -fasm-blocks -O3 -D_REENTRANT -DDSO_DLFCN -DHAVE_DLFCN_H -DL_ENDIAN -DMD32_REG_T=int -DOPENSSL_NO_IDEA -DOPENSSL_PIC -DOPENSSL_THREADS -DZLIB -mmacosx-version-min=10.6
../..
aes-128 cbc     149709.21k   157970.02k   159079.54k   160057.16k   159908.25k
aes-192 cbc     132826.18k   138516.09k   139301.84k   139847.86k   139845.95k
aes-256 cbc     119058.45k   123144.42k   123989.61k   124192.42k   124275.21k
../..
aes-128 ige     157970.54k   168814.05k   171997.82k   171239.04k   172713.37k
aes-192 ige     139152.02k   145860.99k   148705.55k   148606.98k   150433.13k
aes-256 ige     124678.17k   130624.07k   132307.43k   131849.37k   132539.38k


Is it a compilation issue? (I've tested both -arch on 1.0.2a with same results).

thanks,
patpro