x/crypto/chacha20poly1305: linux/arm64 Go 1.9 performance is 3X slower than OpenSSL #22809

williamweixiao · 2017-11-19T12:26:54Z

Please answer these questions before submitting your issue. Thanks!

What version of Go are you using (`go version`)?

go version go1.9.2 linux/arm64

Does this issue reproduce with the latest release?

yes

What operating system and processor architecture are you using (`go env`)?

GOARCH="arm64"
GOBIN=""
GOEXE=""
GOHOSTARCH="arm64"
GOHOSTOS="linux"
GOOS="linux"
GOPATH=""
GORACE=""
GOROOT="/usr/lib/go-1.6"
GOTOOLDIR="/usr/lib/go-1.6/pkg/tool/linux_arm64"
GO15VENDOREXPERIMENT="1"
CC="gcc"
GOGCCFLAGS="-fPIC -pthread -fmessage-length=0"
CXX="g++"
CGO_ENABLED="1"

What did you do?

go test vendor/golang_org/x/crypto/chacha20poly1305 -bench .

What did you expect to see?

Performance can be on par with OpenSSL (https://blog.cloudflare.com/content/images/2017/11/sym_key_1_core.png)

What did you see instead?

3X slower than OpenSSL( https://blog.cloudflare.com/content/images/2017/11/go_sym_key_1_core.png)

The text was updated successfully, but these errors were encountered:

gopherbot · 2018-04-09T18:03:06Z

Change https://golang.org/cl/105895 mentions this issue: crypto/poly1305: arm64 implementation using multiword arithmetic

gopherbot · 2018-04-09T18:44:27Z

Change https://golang.org/cl/105896 mentions this issue: crypto/poly1305: arm64 implementation using multiword arithmetic

gopherbot · 2018-04-19T13:21:25Z

Change https://golang.org/cl/107628 mentions this issue: internal/chacha20: add arm64 SIMD implementation

vielmetti · 2018-06-26T23:21:01Z

Substantial perf improvements on Cavium ThunderX going from go 1.10.2 to go1.11beta1, but not 3x faster.

ed@ed-2a-bcc-llvm:~$ go version
go version go1.10.2 linux/arm64
ed@ed-2a-bcc-llvm:~$ go test vendor/golang_org/x/crypto/chacha20poly1305 -bench .
goos: linux
goarch: arm64
pkg: vendor/golang_org/x/crypto/chacha20poly1305
BenchmarkChacha20Poly1305Open_64-96               500000              3047 ns/op          21.00 MB/s
BenchmarkChacha20Poly1305Seal_64-96               500000              2920 ns/op          21.91 MB/s
BenchmarkChacha20Poly1305Open_1350-96              50000             30990 ns/op          43.56 MB/s
BenchmarkChacha20Poly1305Seal_1350-96              50000             30890 ns/op          43.70 MB/s
BenchmarkChacha20Poly1305Open_8K-96                10000            173794 ns/op          47.14 MB/s
BenchmarkChacha20Poly1305Seal_8K-96                10000            173907 ns/op          47.11 MB/s
PASS
ok      vendor/golang_org/x/crypto/chacha20poly1305     10.538s
ed@ed-2a-bcc-llvm:~$ 
ed@ed-2a-bcc-llvm:~$ ~/go/bin/go1.11beta1 test vendor/golang_org/x/crypto/chacha20poly1305 -bench .
goos: linux
goarch: arm64
pkg: vendor/golang_org/x/crypto/chacha20poly1305
BenchmarkChacha20Poly1305Open_64-96              1000000              2249 ns/op          28.45 MB/s
BenchmarkChacha20Poly1305Seal_64-96              1000000              2245 ns/op          28.50 MB/s
BenchmarkChacha20Poly1305Open_1350-96             100000             19541 ns/op          69.08 MB/s
BenchmarkChacha20Poly1305Seal_1350-96             100000             19439 ns/op          69.45 MB/s
BenchmarkChacha20Poly1305Open_8K-96                10000            105547 ns/op          77.61 MB/s
BenchmarkChacha20Poly1305Seal_8K-96                10000            105938 ns/op          77.33 MB/s
PASS
ok      vendor/golang_org/x/crypto/chacha20poly1305     11.173s

mengzhuo · 2018-06-29T07:02:43Z

@vielmetti internal/chacha20 won't be merged into go1.11 since it's frozen.

vielmetti · 2018-06-29T12:26:30Z

Thanks @mengzhuo . Can we get this onto the go1.12 roster then? It's currently marked as "Unplanned".

ianlancetaylor · 2018-06-29T13:32:59Z

I changed the milestone, but note that that doesn't cause the work to be done. This is an open source project so the best way to get something done is to volunteer to do it. Thanks.

vielmetti · 2018-06-29T14:39:23Z

Noted at https://go-review.googlesource.com/c/crypto/+/107628

"If you prioritize arm64 chacha and arm64 poly, it will see production use super soon after."

It appears from comments on that patch that the coding work has largely been done but there are constraints on the availability of reviewers for arm64 assembly.

vielmetti · 2018-08-23T19:21:57Z

Who is reviewing arm64 assembly these days, @ianlancetaylor , and can they use qualified help? I'm happy to help recruit qualified reviewers from the arm64 Go community if I know the qualifications.

ianlancetaylor · 2018-08-23T19:26:10Z

At present arm64 assembly is typically reviewed by the tireless @cherrymui . I'm sure @benshi001 would also have good input.

zx2c4 · 2019-01-03T17:28:58Z

@FiloSottile This was marked for 1.12. Things still on target for that?

vielmetti · 2019-02-05T21:04:53Z

This issue is marked currently as "help wanted". What is the nature of the help desired?

ianlancetaylor · 2019-02-06T04:20:11Z

@vielmetti Figuring out how to make the code run faster.

One of the meanings of the "help wanted" label is "we would like this to happen but nobody is working on it."

zx2c4 · 2019-02-06T04:24:54Z

"we would like this to happen but nobody is working on it."

Pretty sure somebody was working on it, but then CL just didn't get much of a review. Until today, that is.

ianlancetaylor · 2019-02-06T04:30:37Z

@zx2c4 The "help wanted" label was added before any of the CLs were sent. But I should have been clearer in my response; my apologies.

Inspired by Vectorization of ChaCha Stream Cipher https://eprint.iacr.org/2013/759.pdf name old time/op new time/op delta ChaCha20/32 690ns ± 0% 872ns ± 0% +26.38% (p=0.000 n=10+10) ChaCha20/63 750ns ± 0% 987ns ± 0% +31.53% (p=0.000 n=10+10) ChaCha20/64 674ns ± 0% 879ns ± 0% +30.42% (p=0.000 n=8+10) ChaCha20/256 2.28µs ± 0% 0.82µs ± 0% -64.13% (p=0.000 n=10+10) ChaCha20/1024 8.64µs ± 0% 2.92µs ± 0% -66.15% (p=0.000 n=9+9) ChaCha20/1350 11.9µs ± 0% 4.5µs ± 0% -62.51% (p=0.000 n=10+8) ChaCha20/65536 554µs ± 0% 181µs ± 0% -67.33% (p=0.000 n=10+10) name old speed new speed delta ChaCha20/32 46.3MB/s ± 0% 36.7MB/s ± 0% -20.87% (p=0.000 n=10+9) ChaCha20/63 83.9MB/s ± 0% 63.8MB/s ± 0% -23.97% (p=0.000 n=10+10) ChaCha20/64 94.9MB/s ± 0% 72.8MB/s ± 0% -23.31% (p=0.000 n=10+10) ChaCha20/256 112MB/s ± 0% 312MB/s ± 0% +178.74% (p=0.000 n=10+10) ChaCha20/1024 119MB/s ± 0% 350MB/s ± 0% +195.31% (p=0.000 n=10+9) ChaCha20/1350 114MB/s ± 0% 303MB/s ± 0% +166.73% (p=0.000 n=8+8) ChaCha20/65536 118MB/s ± 0% 362MB/s ± 0% +206.12% (p=0.000 n=10+10) Updates golang/go#22809 Change-Id: I487487faa2ae4ff29de6fd8eb1317740c2939c10 Reviewed-on: https://go-review.googlesource.com/c/107628 Reviewed-by: Filippo Valsorda <filippo@golang.org>

rfjakob · 2020-04-11T15:33:31Z

Looks this has been done via https://github.com/golang/crypto/blob/master/chacha20/chacha_arm64.s .

mengzhuo · 2020-12-16T04:09:47Z

Could someone close this issue? Apparently it's done.

williamweixiao mentioned this issue Nov 19, 2017

crypto/tls: linux/arm64 Go 1.8 performance is slow, max 12.5 MB/sec #19840

Closed

titanous added help wanted NeedsFix The path to resolution is known, but the work has not been done. Performance labels Nov 21, 2017

titanous added this to the Unplanned milestone Nov 21, 2017

bradfitz mentioned this issue Feb 7, 2018

net/http: Slow HTTPS #23727

Closed

dmitshur changed the title ~~crypto/chacha20poly1305: linux/arm64 Go 1.9 performance is 3X slower than OpenSSL~~ x/crypto/chacha20poly1305: linux/arm64 Go 1.9 performance is 3X slower than OpenSSL Mar 20, 2018

ianlancetaylor modified the milestones: Unplanned, Go1.12 Jun 29, 2018

zx2c4 mentioned this issue Dec 28, 2018

ChaCha20Poly1305 is slow on ARM64 #29440

Closed

andybons modified the milestones: Go1.12, Go1.13 Feb 12, 2019

vielmetti mentioned this issue Mar 29, 2019

plugin/forward: maxes out CPU (TLS connection negotiating) coredns/coredns#2624

Closed

andybons removed this from the Go1.13 milestone Jul 8, 2019

andybons added this to the Go1.14 milestone Jul 8, 2019

rsc modified the milestones: Go1.14, Backlog Oct 9, 2019

DavyLandman mentioned this issue Apr 10, 2020

Feature Request: encryption primitives for devices without AES cpu instructions rfjakob/gocryptfs#452

Closed

ianlancetaylor closed this as completed Dec 16, 2020

golang locked and limited conversation to collaborators Dec 16, 2021

gopherbot added the FrozenDueToAge label Dec 16, 2021

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

x/crypto/chacha20poly1305: linux/arm64 Go 1.9 performance is 3X slower than OpenSSL #22809

x/crypto/chacha20poly1305: linux/arm64 Go 1.9 performance is 3X slower than OpenSSL #22809

williamweixiao commented Nov 19, 2017

gopherbot commented Apr 9, 2018

gopherbot commented Apr 9, 2018

gopherbot commented Apr 19, 2018

vielmetti commented Jun 26, 2018

mengzhuo commented Jun 29, 2018

vielmetti commented Jun 29, 2018

ianlancetaylor commented Jun 29, 2018

vielmetti commented Jun 29, 2018

vielmetti commented Aug 23, 2018

ianlancetaylor commented Aug 23, 2018

zx2c4 commented Jan 3, 2019

vielmetti commented Feb 5, 2019

ianlancetaylor commented Feb 6, 2019

zx2c4 commented Feb 6, 2019

ianlancetaylor commented Feb 6, 2019

rfjakob commented Apr 11, 2020

mengzhuo commented Dec 16, 2020 •

edited

x/crypto/chacha20poly1305: linux/arm64 Go 1.9 performance is 3X slower than OpenSSL #22809

x/crypto/chacha20poly1305: linux/arm64 Go 1.9 performance is 3X slower than OpenSSL #22809

Comments

williamweixiao commented Nov 19, 2017

What version of Go are you using (go version)?

Does this issue reproduce with the latest release?

What operating system and processor architecture are you using (go env)?

What did you do?

What did you expect to see?

What did you see instead?

gopherbot commented Apr 9, 2018

gopherbot commented Apr 9, 2018

gopherbot commented Apr 19, 2018

vielmetti commented Jun 26, 2018

mengzhuo commented Jun 29, 2018

vielmetti commented Jun 29, 2018

ianlancetaylor commented Jun 29, 2018

vielmetti commented Jun 29, 2018

vielmetti commented Aug 23, 2018

ianlancetaylor commented Aug 23, 2018

zx2c4 commented Jan 3, 2019

vielmetti commented Feb 5, 2019

ianlancetaylor commented Feb 6, 2019

zx2c4 commented Feb 6, 2019

ianlancetaylor commented Feb 6, 2019

rfjakob commented Apr 11, 2020

mengzhuo commented Dec 16, 2020 • edited

What version of Go are you using (`go version`)?

What operating system and processor architecture are you using (`go env`)?

mengzhuo commented Dec 16, 2020 •

edited