Skip to content

Instantly share code, notes, and snippets.

@scottt

scottt/openssl-aesni-speed-test-result

Last active January 4, 2022 04:45
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save scottt/d7741527ca8ea59a57c1dd566e2014ae to your computer and use it in GitHub Desktop.
Save scottt/d7741527ca8ea59a57c1dd566e2014ae to your computer and use it in GitHub Desktop.
Download ZIP
Raw
openssl-aesni-speed-test-result
# openssl speed -elapsed -evp aes-128-gcm
You have chosen to measure elapsed time instead of user CPU time.
Doing aes-128-gcm for 3s on 16 size blocks: 55740342 aes-128-gcm's in 3.00s
Doing aes-128-gcm for 3s on 64 size blocks: 36792402 aes-128-gcm's in 3.00s
Doing aes-128-gcm for 3s on 256 size blocks: 19513330 aes-128-gcm's in 3.00s
Doing aes-128-gcm for 3s on 1024 size blocks: 6431553 aes-128-gcm's in 3.00s
Doing aes-128-gcm for 3s on 8192 size blocks: 943229 aes-128-gcm's in 3.00s
Doing aes-128-gcm for 3s on 16384 size blocks: 478375 aes-128-gcm's in 3.00s
OpenSSL 1.1.1c 28 May 2019
built on: Wed May 29 17:53:30 2019 UTC
options:bn(64,64) rc4(16x,int) des(int) aes(partial) idea(int) blowfish(ptr)
compiler: /tmp/build/80754af9/openssl_1559152327778/_build_env/bin/x86_64-conda_cos6-linux-gnu-cc -DNDEBUG -D_FORTIFY_SOURCE=2 -O2 -I/home/ec2-user/miniconda3 -march=nocona -mtune=haswell -ftree-vectorize -fPIC -fstack-protector-strong -fno-plt -O2 -ffunction-sections -pipe -I/home/ec2-user/miniconda3/include -fdebug-prefix-map=/tmp/build/80754af9/openssl_1559152327778/work=/usr/local/src/conda/openssl-1.1.1c -fdebug-prefix-map=/home/ec2-user/miniconda3=/usr/local/src/conda-prefix -Wa,--noexecstack -fPIC -pthread -m64 -Wa,--noexecstack -march=nocona -mtune=haswell -ftree-vectorize -fPIC -fstack-protector-strong -fno-plt -O2 -ffunction-sections -pipe -I/home/ec2-user/miniconda3/include -fdebug-prefix-map=/tmp/build/80754af9/openssl_1559152327778/work=/usr/local/src/conda/openssl-1.1.1c -fdebug-prefix-map=/home/ec2-user/miniconda3=/usr/local/src/conda-prefix -Wa,--noexecstack -DOPENSSL_USE_NODELETE -DL_ENDIAN -DOPENSSL_PIC -DOPENSSL_CPUID_OBJ -DOPENSSL_IA32_SSE2 -DOPENSSL_BN_ASM_MONT -DOPENSSL_BN_ASM_MONT5 -DOPENSSL_BN_ASM_GF2m -DSHA1_ASM -DSHA256_ASM -DSHA512_ASM -DKECCAK1600_ASM -DRC4_ASM -DMD5_ASM -DAES_ASM -DVPAES_ASM -DBSAES_ASM -DGHASH_ASM -DECP_NISTZ256_ASM -DX25519_ASM -DPOLY1305_ASM -DNDEBUG -DNDEBUG -D_FORTIFY_SOURCE=2 -O2 -I/home/ec2-user/miniconda3
The 'numbers' are in 1000s of bytes per second processed.
type 16 bytes 64 bytes 256 bytes 1024 bytes 8192 bytes 16384 bytes
aes-128-gcm 297281.82k 784904.58k 1665137.49k 2195303.42k 2575643.99k 2612565.33k
# env OPENSSL_ia32cap="~0x200000200000000" openssl speed -elapsed -evp aes-128-gcm
You have chosen to measure elapsed time instead of user CPU time.
Doing aes-128-gcm for 3s on 16 size blocks: 13087909 aes-128-gcm's in 3.00s
Doing aes-128-gcm for 3s on 64 size blocks: 3845232 aes-128-gcm's in 3.00s
Doing aes-128-gcm for 3s on 256 size blocks: 2179309 aes-128-gcm's in 3.00s
Doing aes-128-gcm for 3s on 1024 size blocks: 574998 aes-128-gcm's in 3.00s
Doing aes-128-gcm for 3s on 8192 size blocks: 74545 aes-128-gcm's in 3.00s
Doing aes-128-gcm for 3s on 16384 size blocks: 37301 aes-128-gcm's in 3.00s
OpenSSL 1.1.1c 28 May 2019
built on: Wed May 29 17:53:30 2019 UTC
options:bn(64,64) rc4(16x,int) des(int) aes(partial) idea(int) blowfish(ptr)
compiler: /tmp/build/80754af9/openssl_1559152327778/_build_env/bin/x86_64-conda_cos6-linux-gnu-cc -DNDEBUG -D_FORTIFY_SOURCE=2 -O2 -I/home/ec2-user/miniconda3 -march=nocona -mtune=haswell -ftree-vectorize -fPIC -fstack-protector-strong -fno-plt -O2 -ffunction-sections -pipe -I/home/ec2-user/miniconda3/include -fdebug-prefix-map=/tmp/build/80754af9/openssl_1559152327778/work=/usr/local/src/conda/openssl-1.1.1c -fdebug-prefix-map=/home/ec2-user/miniconda3=/usr/local/src/conda-prefix -Wa,--noexecstack -fPIC -pthread -m64 -Wa,--noexecstack -march=nocona -mtune=haswell -ftree-vectorize -fPIC -fstack-protector-strong -fno-plt -O2 -ffunction-sections -pipe -I/home/ec2-user/miniconda3/include -fdebug-prefix-map=/tmp/build/80754af9/openssl_1559152327778/work=/usr/local/src/conda/openssl-1.1.1c -fdebug-prefix-map=/home/ec2-user/miniconda3=/usr/local/src/conda-prefix -Wa,--noexecstack -DOPENSSL_USE_NODELETE -DL_ENDIAN -DOPENSSL_PIC -DOPENSSL_CPUID_OBJ -DOPENSSL_IA32_SSE2 -DOPENSSL_BN_ASM_MONT -DOPENSSL_BN_ASM_MONT5 -DOPENSSL_BN_ASM_GF2m -DSHA1_ASM -DSHA256_ASM -DSHA512_ASM -DKECCAK1600_ASM -DRC4_ASM -DMD5_ASM -DAES_ASM -DVPAES_ASM -DBSAES_ASM -DGHASH_ASM -DECP_NISTZ256_ASM -DX25519_ASM -DPOLY1305_ASM -DNDEBUG -DNDEBUG -D_FORTIFY_SOURCE=2 -O2 -I/home/ec2-user/miniconda3
The 'numbers' are in 1000s of bytes per second processed.
type 16 bytes 64 bytes 256 bytes 1024 bytes 8192 bytes 16384 bytes
aes-128-gcm 69802.18k 82031.62k 185967.70k 196265.98k 203557.55k 203713.19k
# openssl speed -elapsed -evp aes-256-gcm
You have chosen to measure elapsed time instead of user CPU time.
Doing aes-256-gcm for 3s on 16 size blocks: 46762512 aes-256-gcm's in 3.00s
Doing aes-256-gcm for 3s on 64 size blocks: 32863099 aes-256-gcm's in 3.00s
Doing aes-256-gcm for 3s on 256 size blocks: 16724184 aes-256-gcm's in 3.00s
Doing aes-256-gcm for 3s on 1024 size blocks: 5146377 aes-256-gcm's in 3.00s
Doing aes-256-gcm for 3s on 8192 size blocks: 728474 aes-256-gcm's in 3.00s
Doing aes-256-gcm for 3s on 16384 size blocks: 369769 aes-256-gcm's in 3.00s
OpenSSL 1.1.1c 28 May 2019
built on: Wed May 29 17:53:30 2019 UTC
options:bn(64,64) rc4(16x,int) des(int) aes(partial) idea(int) blowfish(ptr)
compiler: /tmp/build/80754af9/openssl_1559152327778/_build_env/bin/x86_64-conda_cos6-linux-gnu-cc -DNDEBUG -D_FORTIFY_SOURCE=2 -O2 -I/home/ec2-user/miniconda3 -march=nocona -mtune=haswell -ftree-vectorize -fPIC -fstack-protector-strong -fno-plt -O2 -ffunction-sections -pipe -I/home/ec2-user/miniconda3/include -fdebug-prefix-map=/tmp/build/80754af9/openssl_1559152327778/work=/usr/local/src/conda/openssl-1.1.1c -fdebug-prefix-map=/home/ec2-user/miniconda3=/usr/local/src/conda-prefix -Wa,--noexecstack -fPIC -pthread -m64 -Wa,--noexecstack -march=nocona -mtune=haswell -ftree-vectorize -fPIC -fstack-protector-strong -fno-plt -O2 -ffunction-sections -pipe -I/home/ec2-user/miniconda3/include -fdebug-prefix-map=/tmp/build/80754af9/openssl_1559152327778/work=/usr/local/src/conda/openssl-1.1.1c -fdebug-prefix-map=/home/ec2-user/miniconda3=/usr/local/src/conda-prefix -Wa,--noexecstack -DOPENSSL_USE_NODELETE -DL_ENDIAN -DOPENSSL_PIC -DOPENSSL_CPUID_OBJ -DOPENSSL_IA32_SSE2 -DOPENSSL_BN_ASM_MONT -DOPENSSL_BN_ASM_MONT5 -DOPENSSL_BN_ASM_GF2m -DSHA1_ASM -DSHA256_ASM -DSHA512_ASM -DKECCAK1600_ASM -DRC4_ASM -DMD5_ASM -DAES_ASM -DVPAES_ASM -DBSAES_ASM -DGHASH_ASM -DECP_NISTZ256_ASM -DX25519_ASM -DPOLY1305_ASM -DNDEBUG -DNDEBUG -D_FORTIFY_SOURCE=2 -O2 -I/home/ec2-user/miniconda3
The 'numbers' are in 1000s of bytes per second processed.
type 16 bytes 64 bytes 256 bytes 1024 bytes 8192 bytes 16384 bytes
aes-256-gcm 249400.06k 701079.45k 1427130.37k 1756630.02k 1989219.67k 2019431.77k
# env OPENSSL_ia32cap="~0x2000002000000000" openssl speed -elapsed -evp aes-256-gcm
You have chosen to measure elapsed time instead of user CPU time.
Doing aes-256-gcm for 3s on 16 size blocks: 41321165 aes-256-gcm's in 3.00s
Doing aes-256-gcm for 3s on 64 size blocks: 32321467 aes-256-gcm's in 3.00s
Doing aes-256-gcm for 3s on 256 size blocks: 16786457 aes-256-gcm's in 3.00s
Doing aes-256-gcm for 3s on 1024 size blocks: 5137533 aes-256-gcm's in 3.00s
Doing aes-256-gcm for 3s on 8192 size blocks: 732877 aes-256-gcm's in 3.00s
Doing aes-256-gcm for 3s on 16384 size blocks: 370310 aes-256-gcm's in 3.00s
OpenSSL 1.1.1c 28 May 2019
built on: Wed May 29 17:53:30 2019 UTC
options:bn(64,64) rc4(16x,int) des(int) aes(partial) idea(int) blowfish(ptr)
compiler: /tmp/build/80754af9/openssl_1559152327778/_build_env/bin/x86_64-conda_cos6-linux-gnu-cc -DNDEBUG -D_FORTIFY_SOURCE=2 -O2 -I/home/ec2-user/miniconda3 -march=nocona -mtune=haswell -ftree-vectorize -fPIC -fstack-protector-strong -fno-plt -O2 -ffunction-sections -pipe -I/home/ec2-user/miniconda3/include -fdebug-prefix-map=/tmp/build/80754af9/openssl_1559152327778/work=/usr/local/src/conda/openssl-1.1.1c -fdebug-prefix-map=/home/ec2-user/miniconda3=/usr/local/src/conda-prefix -Wa,--noexecstack -fPIC -pthread -m64 -Wa,--noexecstack -march=nocona -mtune=haswell -ftree-vectorize -fPIC -fstack-protector-strong -fno-plt -O2 -ffunction-sections -pipe -I/home/ec2-user/miniconda3/include -fdebug-prefix-map=/tmp/build/80754af9/openssl_1559152327778/work=/usr/local/src/conda/openssl-1.1.1c -fdebug-prefix-map=/home/ec2-user/miniconda3=/usr/local/src/conda-prefix -Wa,--noexecstack -DOPENSSL_USE_NODELETE -DL_ENDIAN -DOPENSSL_PIC -DOPENSSL_CPUID_OBJ -DOPENSSL_IA32_SSE2 -DOPENSSL_BN_ASM_MONT -DOPENSSL_BN_ASM_MONT5 -DOPENSSL_BN_ASM_GF2m -DSHA1_ASM -DSHA256_ASM -DSHA512_ASM -DKECCAK1600_ASM -DRC4_ASM -DMD5_ASM -DAES_ASM -DVPAES_ASM -DBSAES_ASM -DGHASH_ASM -DECP_NISTZ256_ASM -DX25519_ASM -DPOLY1305_ASM -DNDEBUG -DNDEBUG -D_FORTIFY_SOURCE=2 -O2 -I/home/ec2-user/miniconda3
The 'numbers' are in 1000s of bytes per second processed.
type 16 bytes 64 bytes 256 bytes 1024 bytes 8192 bytes 16384 bytes
aes-256-gcm 220379.55k 689524.63k 1432444.33k 1753611.26k 2001242.79k 2022386.35k
Raw
proc-cpuinfo
processor : 0
vendor_id : GenuineIntel
cpu family : 6
model : 63
model name : Intel(R) Xeon(R) CPU E5-2676 v3 @ 2.40GHz
stepping : 2
microcode : 0x43
cpu MHz : 2394.685
cache size : 30720 KB
physical id : 0
siblings : 1
core id : 0
cpu cores : 1
apicid : 0
initial apicid : 0
fpu : yes
fpu_exception : yes
cpuid level : 13
wp : yes
flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx rdtscp lm constant_tsc rep_good nopl xtopology cpuid pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm cpuid_fault invpcid_single pti fsgsbase bmi1 avx2 smep bmi2 erms invpcid xsaveopt
bugs : cpu_meltdown spectre_v1 spectre_v2 spec_store_bypass l1tf mds swapgs
bogomips : 4789.03
clflush size : 64
cache_alignment : 64
address sizes : 46 bits physical, 48 bits virtual
power management:
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment