ARM64 assembly pack: add ThunderX2 results.

Reviewed-by: Tim Hudson <tjh@openssl.org>
Reviewed-by: Richard Levitte <levitte@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/8776)
This commit is contained in:
Andy Polyakov 2019-04-17 21:08:13 +02:00
parent ad7e17dd6c
commit 6465321e40
8 changed files with 8 additions and 0 deletions

View file

@ -36,6 +36,7 @@
# Denver 1.96 0.86 0.80 # Denver 1.96 0.86 0.80
# Mongoose 1.33 1.20 1.20 # Mongoose 1.33 1.20 1.20
# Kryo 1.26 0.94 1.00 # Kryo 1.26 0.94 1.00
# ThunderX2 5.95 1.53 1.55
# #
# (*) original 3.64/1.34/1.32 results were for r0p0 revision # (*) original 3.64/1.34/1.32 results were for r0p0 revision
# and are still same even for updated module; # and are still same even for updated module;

View file

@ -30,6 +30,7 @@
# Denver(***) 16.6(**) 15.1/17.8(**) [8.80/9.93 ] # Denver(***) 16.6(**) 15.1/17.8(**) [8.80/9.93 ]
# Apple A7(***) 22.7(**) 10.9/14.3 [8.45/10.0 ] # Apple A7(***) 22.7(**) 10.9/14.3 [8.45/10.0 ]
# Mongoose(***) 26.3(**) 21.0/25.0(**) [13.3/16.8 ] # Mongoose(***) 26.3(**) 21.0/25.0(**) [13.3/16.8 ]
# ThunderX2(***) 39.4(**) 33.8/48.6(**)
# #
# (*) ECB denotes approximate result for parallelizable modes # (*) ECB denotes approximate result for parallelizable modes
# such as CBC decrypt, CTR, etc.; # such as CBC decrypt, CTR, etc.;

View file

@ -29,6 +29,7 @@
# X-Gene 9.50/+46% 8.82 8.89(*) # X-Gene 9.50/+46% 8.82 8.89(*)
# Mongoose 8.00/+44% 3.64 3.25 # Mongoose 8.00/+44% 3.64 3.25
# Kryo 8.17/+50% 4.83 4.65 # Kryo 8.17/+50% 4.83 4.65
# ThunderX2 7.26/+48% 7.91 4.30
# #
# (*) it's expected that doubling interleave factor doesn't help # (*) it's expected that doubling interleave factor doesn't help
# all processors, only those with higher NEON latency and # all processors, only those with higher NEON latency and

View file

@ -42,6 +42,7 @@
# Denver 0.51 0.65 6.02 # Denver 0.51 0.65 6.02
# Mongoose 0.65 1.10 8.06 # Mongoose 0.65 1.10 8.06
# Kryo 0.76 1.16 8.00 # Kryo 0.76 1.16 8.00
# ThunderX2 1.05
# #
# (*) presented for reference/comparison purposes; # (*) presented for reference/comparison purposes;

View file

@ -29,6 +29,7 @@
# X-Gene 2.13/+68% 2.27 # X-Gene 2.13/+68% 2.27
# Mongoose 1.77/+75% 1.12 # Mongoose 1.77/+75% 1.12
# Kryo 2.70/+55% 1.13 # Kryo 2.70/+55% 1.13
# ThunderX2 1.17/+95% 1.36
# #
# (*) estimate based on resources availability is less than 1.0, # (*) estimate based on resources availability is less than 1.0,
# i.e. measured result is worse than expected, presumably binary # i.e. measured result is worse than expected, presumably binary

View file

@ -51,6 +51,7 @@
# Kryo 12 # Kryo 12
# Denver 7.8 # Denver 7.8
# Apple A7 7.2 # Apple A7 7.2
# ThunderX2 9.7
# #
# (*) Corresponds to SHA3-256. No improvement coefficients are listed # (*) Corresponds to SHA3-256. No improvement coefficients are listed
# because they vary too much from compiler to compiler. Newer # because they vary too much from compiler to compiler. Newer

View file

@ -27,6 +27,7 @@
# X-Gene 8.80 (+200%) # X-Gene 8.80 (+200%)
# Mongoose 2.05 6.50 (+160%) # Mongoose 2.05 6.50 (+160%)
# Kryo 1.88 8.00 (+90%) # Kryo 1.88 8.00 (+90%)
# ThunderX2 2.64 6.36 (+150%)
# #
# (*) Software results are presented mostly for reference purposes. # (*) Software results are presented mostly for reference purposes.
# (**) Keep in mind that Denver relies on binary translation, which # (**) Keep in mind that Denver relies on binary translation, which

View file

@ -28,6 +28,7 @@
# X-Gene 20.0 (+100%) 12.8 (+300%(***)) # X-Gene 20.0 (+100%) 12.8 (+300%(***))
# Mongoose 2.36 13.0 (+50%) 8.36 (+33%) # Mongoose 2.36 13.0 (+50%) 8.36 (+33%)
# Kryo 1.92 17.4 (+30%) 11.2 (+8%) # Kryo 1.92 17.4 (+30%) 11.2 (+8%)
# ThunderX2 2.54 13.2 (+40%) 8.40 (+18%)
# #
# (*) Software SHA256 results are of lesser relevance, presented # (*) Software SHA256 results are of lesser relevance, presented
# mostly for informational purposes. # mostly for informational purposes.