Switched to faster minio/sha256-simd implementation (#2320)

master
Frank 8 years ago committed by Harshavardhana
parent dcc3463e48
commit f239fcac67
  1. 2
      signature-v4-utils.go
  2. 2
      signature-v4.go
  3. 2
      signature-verify-reader.go
  4. 202
      vendor/github.com/minio/sha256-simd/LICENSE
  5. 153
      vendor/github.com/minio/sha256-simd/README.md
  6. 32
      vendor/github.com/minio/sha256-simd/appveyor.yml
  7. 55
      vendor/github.com/minio/sha256-simd/cpuid.go
  8. 24
      vendor/github.com/minio/sha256-simd/cpuid_386.go
  9. 33
      vendor/github.com/minio/sha256-simd/cpuid_386.s
  10. 24
      vendor/github.com/minio/sha256-simd/cpuid_amd64.go
  11. 34
      vendor/github.com/minio/sha256-simd/cpuid_amd64.s
  12. 33
      vendor/github.com/minio/sha256-simd/cpuid_arm64.go
  13. 171
      vendor/github.com/minio/sha256-simd/sha256.go
  14. 31
      vendor/github.com/minio/sha256-simd/sha256blockAvx2_amd64.go
  15. 1442
      vendor/github.com/minio/sha256-simd/sha256blockAvx2_amd64.s
  16. 31
      vendor/github.com/minio/sha256-simd/sha256blockAvx_amd64.go
  17. 409
      vendor/github.com/minio/sha256-simd/sha256blockAvx_amd64.s
  18. 31
      vendor/github.com/minio/sha256-simd/sha256blockSsse_amd64.go
  19. 430
      vendor/github.com/minio/sha256-simd/sha256blockSsse_amd64.s
  20. 21
      vendor/github.com/minio/sha256-simd/sha256block_amd64.go
  21. 36
      vendor/github.com/minio/sha256-simd/sha256block_arm64.go
  22. 193
      vendor/github.com/minio/sha256-simd/sha256block_arm64.s
  23. 136
      vendor/github.com/minio/sha256-simd/sha256block_noasm.go
  24. 6
      vendor/vendor.json

@ -18,8 +18,8 @@ package main
import (
"crypto/hmac"
"crypto/sha256"
"encoding/hex"
"github.com/minio/sha256-simd"
"net/http"
"regexp"
"strings"

@ -26,8 +26,8 @@ package main
import (
"bytes"
"crypto/sha256"
"encoding/hex"
"github.com/minio/sha256-simd"
"net/http"
"net/url"
"sort"

@ -17,9 +17,9 @@
package main
import (
"crypto/sha256"
"encoding/hex"
"fmt"
"github.com/minio/sha256-simd"
"hash"
"io"
"net/http"

@ -0,0 +1,202 @@
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [yyyy] [name of copyright owner]
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.

@ -0,0 +1,153 @@
# sha256-simd
Accelerate SHA256 computations in pure Go for both Intel (AVX2, AVX, SSE) as well as ARM (arm64) platforms.
## Introduction
This package is designed as a drop-in replacement for `crypto/sha256`. For Intel CPUs it has three flavors for AVX2, AVX and SSE whereby the fastest method is automatically chosen depending on CPU capabilities. For ARM CPUs with the Cryptography Extensions advantage is taken of the SHA2 instructions resulting in a massive performance improvement.
This package uses Golang assembly and as such does not depend on cgo. The Intel versions are based on the implementations as described in "Fast SHA-256 Implementations on Intel Architecture Processors" by J. Guilford et al.
## Performance
Below is the speed in MB/s for a single core (ranked fast to slow) as well as the factor of improvement over `crypto/sha256` (when applicable).
| Processor | Package | Speed | Improvement |
| --------------------------------- | ---------------------------- | -----------:| -----------:|
| 1.2 GHz ARM Cortex-A53 | minio/sha256-simd (ARM64) | 638.2 MB/s | 105x |
| 2.4 GHz Intel Xeon CPU E5-2620 v3 | minio/sha256-simd (AVX2) (*) | 355.0 MB/s | 1.88x |
| 2.4 GHz Intel Xeon CPU E5-2620 v3 | minio/sha256-simd (AVX) | 306.0 MB/s | 1.62x |
| 2.4 GHz Intel Xeon CPU E5-2620 v3 | minio/sha256-simd (SSE) | 298.7 MB/s | 1.58x |
| 2.4 GHz Intel Xeon CPU E5-2620 v3 | crypto/sha256 | 189.2 MB/s | |
| 1.2 GHz ARM Cortex-A53 | crypto/sha256 | 6.1 MB/s | |
(*) Measured with the "unrolled"/"demacro-ed" AVX2 version. Due to some Golang assembly restrictions the AVX2 version that uses `defines` loses about 15% performance. The optimized version is contained in the git history so for maximum speed you want to do this after getting: `git cat-file blob 586b6e > sha256blockAvx2_amd64.s` (or vendor it for your project; see [here](https://github.com/minio/sha256-simd/blob/13b11bdf9b0580a756a111492d2ae382bab7ec79/sha256blockAvx2_amd64.s) to view it in its full glory).
See further down for detailed performance.
## Comparison to other hashing techniques
As measured on Intel Xeon (same as above) with AVX2 version:
| Method | Package | Speed |
| ------- | -------------------| --------:|
| BLAKE2B | [minio/blake2b-simd](https://github.com/minio/blake2b-simd) | 851 MB/s |
| MD5 | crypto/md5 | 607 MB/s |
| SHA1 | crypto/sha1 | 522 MB/s |
| SHA256 | minio/sha256-simd | 355 MB/s |
| SHA512 | crypto/sha512 | 306 MB/s |
asm2plan9s
----------
In order to be able to work more easily with AVX2/AVX instructions, a separate tool was developed to convert AVX2/AVX instructions into the corresponding BYTE sequence as accepted by Go assembly. See [asm2plan9s](https://github.com/minio/asm2plan9s) for more information.
Why and benefits
----------------
One of the most performance sensitive parts of [Minio](https://minio.io) server (object storage [server](https://github.com/minio/minio) compatible with Amazon S3) is related to SHA256 hash sums calculations. For instance during multi part uploads each part that is uploaded needs to be verified for data integrity by the server. Likewise in order to generated pre-signed URLs check sums must be calculated to ensure their validity.
Other applications that can benefit from enhanced SHA256 performance are deduplication in storage systems, intrusion detection, version control systems, integrity checking, etc.
ARM SHA Extensions
------------------
The 64-bit ARMv8 core has introduced new instructions for SHA1 and SHA2 acceleration as part of the [Cryptography Extensions](http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.ddi0501f/CHDFJBCJ.html). Below you can see a small excerpt highlighting one of the rounds as is done for the SHA256 calculation process (for full code see [sha256block_arm64.s](https://github.com/minio/sha256-simd/blob/master/sha256block_arm64.s)).
```
sha256h q2, q3, v9.4s
sha256h2 q3, q4, v9.4s
sha256su0 v5.4s, v6.4s
rev32 v8.16b, v8.16b
add v9.4s, v7.4s, v18.4s
mov v4.16b, v2.16b
sha256h q2, q3, v10.4s
sha256h2 q3, q4, v10.4s
sha256su0 v6.4s, v7.4s
sha256su1 v5.4s, v7.4s, v8.4s
```
Detailed benchmarks
-------------------
### ARM64
Benchmarks generated on a 1.2 Ghz Quad-Core ARM Cortex A53 equipped [Pine64](https://www.pine64.com/).
```
minio@minio-arm:~/gopath/src/github.com/sha256-simd$ benchcmp golang.txt arm64.txt
benchmark old ns/op new ns/op delta
BenchmarkHash8Bytes-4 11836 1403 -88.15%
BenchmarkHash1K-4 181143 3138 -98.27%
BenchmarkHash8K-4 1365652 14356 -98.95%
BenchmarkHash1M-4 173192200 1642954 -99.05%
benchmark old MB/s new MB/s speedup
BenchmarkHash8Bytes-4 0.68 5.70 8.38x
BenchmarkHash1K-4 5.65 326.30 57.75x
BenchmarkHash8K-4 6.00 570.63 95.11x
BenchmarkHash1M-4 6.05 638.23 105.49x
```
Example performance metrics were generated on Intel(R) Xeon(R) CPU E5-2620 v3 @ 2.40GHz - 6 physical cores, 12 logical cores running Ubuntu GNU/Linux with kernel version 4.4.0-24-generic (vanilla with no optimizations).
### AVX2
```
$ benchcmp go.txt avx2.txt
benchmark old ns/op new ns/op delta
BenchmarkHash8Bytes-12 446 364 -18.39%
BenchmarkHash1K-12 5919 3279 -44.60%
BenchmarkHash8K-12 43791 23655 -45.98%
BenchmarkHash1M-12 5544989 2969305 -46.45%
benchmark old MB/s new MB/s speedup
BenchmarkHash8Bytes-12 17.93 21.96 1.22x
BenchmarkHash1K-12 172.98 312.27 1.81x
BenchmarkHash8K-12 187.07 346.31 1.85x
BenchmarkHash1M-12 189.10 353.14 1.87x
```
### AVX
```
$ benchcmp go.txt avx.txt
benchmark old ns/op new ns/op delta
BenchmarkHash8Bytes-12 446 346 -22.42%
BenchmarkHash1K-12 5919 3701 -37.47%
BenchmarkHash8K-12 43791 27222 -37.84%
BenchmarkHash1M-12 5544989 3426938 -38.20%
benchmark old MB/s new MB/s speedup
BenchmarkHash8Bytes-12 17.93 23.06 1.29x
BenchmarkHash1K-12 172.98 276.64 1.60x
BenchmarkHash8K-12 187.07 300.93 1.61x
BenchmarkHash1M-12 189.10 305.98 1.62x
```
### SSE
```
$ benchcmp go.txt sse.txt
benchmark old ns/op new ns/op delta
BenchmarkHash8Bytes-12 446 362 -18.83%
BenchmarkHash1K-12 5919 3751 -36.63%
BenchmarkHash8K-12 43791 27396 -37.44%
BenchmarkHash1M-12 5544989 3444623 -37.88%
benchmark old MB/s new MB/s speedup
BenchmarkHash8Bytes-12 17.93 22.05 1.23x
BenchmarkHash1K-12 172.98 272.92 1.58x
BenchmarkHash8K-12 187.07 299.01 1.60x
BenchmarkHash1M-12 189.10 304.41 1.61x
```
License
-------
Released under the Apache License v2.0. You can find the complete text in the file LICENSE.
Contributing
------------
Contributions are welcome, please send PRs for any enhancements.

@ -0,0 +1,32 @@
# version format
version: "{build}"
# Operating system (build VM template)
os: Windows Server 2012 R2
# Platform.
platform: x64
clone_folder: c:\gopath\src\github.com\minio\sha256-simd
# environment variables
environment:
GOPATH: c:\gopath
GO15VENDOREXPERIMENT: 1
# scripts that run after cloning repository
install:
- set PATH=%GOPATH%\bin;c:\go\bin;%PATH%
- go version
- go env
# to run your custom scripts instead of automatic MSBuild
build_script:
- go test .
- go test -race .
# to disable automatic tests
test: off
# to disable deployment
deploy: off

@ -0,0 +1,55 @@
// Minio Cloud Storage, (C) 2016 Minio, Inc.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
//
package sha256
// True when SIMD instructions are available.
var avx2 = haveAVX2()
var avx = haveAVX()
var ssse3 = haveSSSE3()
var armSha = haveArmSha()
// haveAVX returns true when there is AVX support
func haveAVX() bool {
_, _, c, _ := cpuid(1)
// Check XGETBV, OXSAVE and AVX bits
if c&(1<<26) != 0 && c&(1<<27) != 0 && c&(1<<28) != 0 {
// Check for OS support
eax, _ := xgetbv(0)
return (eax & 0x6) == 0x6
}
return false
}
// haveAVX2 returns true when there is AVX2 support
func haveAVX2() bool {
mfi, _, _, _ := cpuid(0)
// Check AVX2, AVX2 requires OS support, but BMI1/2 don't.
if mfi >= 7 && haveAVX() {
_, ebx, _, _ := cpuidex(7, 0)
return (ebx & 0x00000020) != 0
}
return false
}
// haveSSSE3 returns true when there is SSSE3 support
func haveSSSE3() bool {
_, _, c, _ := cpuid(1)
return (c & 0x00000200) != 0
}

@ -0,0 +1,24 @@
// Minio Cloud Storage, (C) 2016 Minio, Inc.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
//
package sha256
func cpuid(op uint32) (eax, ebx, ecx, edx uint32)
func cpuidex(op, op2 uint32) (eax, ebx, ecx, edx uint32)
func xgetbv(index uint32) (eax, edx uint32)
func haveArmSha() bool {
return false
}

@ -0,0 +1,33 @@
// Copyright (c) 2015 Klaus Post, released under MIT License. See LICENSE file.
// +build 386,!gccgo
// func cpuid(op uint32) (eax, ebx, ecx, edx uint32)
TEXT ·cpuid(SB), 7, $0
XORL CX, CX
MOVL op+0(FP), AX
CPUID
MOVL AX, eax+4(FP)
MOVL BX, ebx+8(FP)
MOVL CX, ecx+12(FP)
MOVL DX, edx+16(FP)
RET
// func cpuidex(op, op2 uint32) (eax, ebx, ecx, edx uint32)
TEXT ·cpuidex(SB), 7, $0
MOVL op+0(FP), AX
MOVL op2+4(FP), CX
CPUID
MOVL AX, eax+8(FP)
MOVL BX, ebx+12(FP)
MOVL CX, ecx+16(FP)
MOVL DX, edx+20(FP)
RET
// func xgetbv(index uint32) (eax, edx uint32)
TEXT ·xgetbv(SB), 7, $0
MOVL index+0(FP), CX
BYTE $0x0f; BYTE $0x01; BYTE $0xd0 // XGETBV
MOVL AX, eax+4(FP)
MOVL DX, edx+8(FP)
RET

@ -0,0 +1,24 @@
// Minio Cloud Storage, (C) 2016 Minio, Inc.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
//
package sha256
func cpuid(op uint32) (eax, ebx, ecx, edx uint32)
func cpuidex(op, op2 uint32) (eax, ebx, ecx, edx uint32)
func xgetbv(index uint32) (eax, edx uint32)
func haveArmSha() bool {
return false
}

@ -0,0 +1,34 @@
// Copyright (c) 2015 Klaus Post, released under MIT License. See LICENSE file.
// +build amd64,!gccgo
// func cpuid(op uint32) (eax, ebx, ecx, edx uint32)
TEXT ·cpuid(SB), 7, $0
XORQ CX, CX
MOVL op+0(FP), AX
CPUID
MOVL AX, eax+8(FP)
MOVL BX, ebx+12(FP)
MOVL CX, ecx+16(FP)
MOVL DX, edx+20(FP)
RET
// func cpuidex(op, op2 uint32) (eax, ebx, ecx, edx uint32)
TEXT ·cpuidex(SB), 7, $0
MOVL op+0(FP), AX
MOVL op2+4(FP), CX
CPUID
MOVL AX, eax+8(FP)
MOVL BX, ebx+12(FP)
MOVL CX, ecx+16(FP)
MOVL DX, edx+20(FP)
RET
// func xgetbv(index uint32) (eax, edx uint32)
TEXT ·xgetbv(SB), 7, $0
MOVL index+0(FP), CX
BYTE $0x0f; BYTE $0x01; BYTE $0xd0 // XGETBV
MOVL AX, eax+8(FP)
MOVL DX, edx+12(FP)
RET

@ -0,0 +1,33 @@
// Minio Cloud Storage, (C) 2016 Minio, Inc.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
//
package sha256
func cpuid(op uint32) (eax, ebx, ecx, edx uint32) {
return 0, 0, 0, 0
}
func cpuidex(op, op2 uint32) (eax, ebx, ecx, edx uint32) {
return 0, 0, 0, 0
}
func xgetbv(index uint32) (eax, edx uint32) {
return 0, 0
}
func haveArmSha() bool {
// TODO: Implement feature detection for ARM
return true
}

@ -0,0 +1,171 @@
/*
* Minio Cloud Storage, (C) 2016 Minio, Inc.
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package sha256
import (
"crypto/sha256"
"hash"
)
// Size - The size of a SHA256 checksum in bytes.
const Size = 32
// BlockSize - The blocksize of SHA256 in bytes.
const BlockSize = 64
const (
chunk = 64
init0 = 0x6A09E667
init1 = 0xBB67AE85
init2 = 0x3C6EF372
init3 = 0xA54FF53A
init4 = 0x510E527F
init5 = 0x9B05688C
init6 = 0x1F83D9AB
init7 = 0x5BE0CD19
)
// digest represents the partial evaluation of a checksum.
type digest struct {
h [8]uint32
x [chunk]byte
nx int
len uint64
}
// Reset digest back to default
func (d *digest) Reset() {
d.h[0] = init0
d.h[1] = init1
d.h[2] = init2
d.h[3] = init3
d.h[4] = init4
d.h[5] = init5
d.h[6] = init6
d.h[7] = init7
d.nx = 0
d.len = 0
}
func block(dig *digest, p []byte) {
switch true {
case avx2:
blockAvx2Go(dig, p)
case avx:
blockAvxGo(dig, p)
case ssse3:
blockSsseGo(dig, p)
case armSha:
blockArmGo(dig, p)
default:
blockGeneric(dig, p)
}
}
// New returns a new hash.Hash computing the SHA256 checksum.
func New() hash.Hash {
if avx2 || avx || ssse3 || armSha {
d := new(digest)
d.Reset()
return d
} else {
// default back to the standard golang implementation
return sha256.New()
}
}
// Sum256 - single caller sha256 helper
func Sum256(data []byte) [Size]byte {
var d digest
d.Reset()
d.Write(data)
return d.checkSum()
}
// Return size of checksum
func (d *digest) Size() int { return Size }
// Return blocksize of checksum
func (d *digest) BlockSize() int { return BlockSize }
// Write to digest
func (d *digest) Write(p []byte) (nn int, err error) {
nn = len(p)
d.len += uint64(nn)
if d.nx > 0 {
n := copy(d.x[d.nx:], p)
d.nx += n
if d.nx == chunk {
block(d, d.x[:])
d.nx = 0
}
p = p[n:]
}
if len(p) >= chunk {
n := len(p) &^ (chunk - 1)
block(d, p[:n])
p = p[n:]
}
if len(p) > 0 {
d.nx = copy(d.x[:], p)
}
return
}
// Return sha256 sum in bytes
func (d *digest) Sum(in []byte) []byte {
// Make a copy of d0 so that caller can keep writing and summing.
d0 := *d
hash := d0.checkSum()
return append(in, hash[:]...)
}
// Intermediate checksum function
func (d *digest) checkSum() [Size]byte {
len := d.len
// Padding. Add a 1 bit and 0 bits until 56 bytes mod 64.
var tmp [64]byte
tmp[0] = 0x80
if len%64 < 56 {
d.Write(tmp[0 : 56-len%64])
} else {
d.Write(tmp[0 : 64+56-len%64])
}
// Length in bits.
len <<= 3
for i := uint(0); i < 8; i++ {
tmp[i] = byte(len >> (56 - 8*i))
}
d.Write(tmp[0:8])
if d.nx != 0 {
panic("d.nx != 0")
}
h := d.h[:]
var digest [Size]byte
for i, s := range h {
digest[i*4] = byte(s >> 24)
digest[i*4+1] = byte(s >> 16)
digest[i*4+2] = byte(s >> 8)
digest[i*4+3] = byte(s)
}
return digest
}

@ -0,0 +1,31 @@
//+build !noasm
/*
* Minio Cloud Storage, (C) 2016 Minio, Inc.
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package sha256
//go:noescape
func blockAvx2(h []uint32, message []uint8)
func blockAvx2Go(dig *digest, p []byte) {
h := []uint32{dig.h[0], dig.h[1], dig.h[2], dig.h[3], dig.h[4], dig.h[5], dig.h[6], dig.h[7]}
blockAvx2(h[:], p[:])
dig.h[0], dig.h[1], dig.h[2], dig.h[3], dig.h[4], dig.h[5], dig.h[6], dig.h[7] = h[0], h[1], h[2], h[3], h[4], h[5], h[6], h[7]
}

File diff suppressed because it is too large Load Diff

@ -0,0 +1,31 @@
//+build !noasm
/*
* Minio Cloud Storage, (C) 2016 Minio, Inc.
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package sha256
//go:noescape
func blockAvx(h []uint32, message []uint8, reserved0, reserved1, reserved2, reserved3 uint64)
func blockAvxGo(dig *digest, p []byte) {
h := []uint32{dig.h[0], dig.h[1], dig.h[2], dig.h[3], dig.h[4], dig.h[5], dig.h[6], dig.h[7]}
blockAvx(h[:], p[:], 0, 0, 0, 0)
dig.h[0], dig.h[1], dig.h[2], dig.h[3], dig.h[4], dig.h[5], dig.h[6], dig.h[7] = h[0], h[1], h[2], h[3], h[4], h[5], h[6], h[7]
}

@ -0,0 +1,409 @@
//+build !noasm !appengine
// SHA256 implementation for AVX
//
// Minio Cloud Storage, (C) 2016 Minio, Inc.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
//
//
// This code is based on an Intel White-Paper:
// "Fast SHA-256 Implementations on Intel Architecture Processors"
//
// together with the reference implementation from the following authors:
// James Guilford <james.guilford@intel.com>
// Kirk Yap <kirk.s.yap@intel.com>
// Tim Chen <tim.c.chen@linux.intel.com>
//
// For Golang it has been converted to Plan 9 assembly with the help of
// github.com/minio/asm2plan9s to assemble Intel instructions to their Plan9
// equivalents
//
#include "textflag.h"
#define ROTATE_XS \
MOVOU X4, X15 \
MOVOU X5, X4 \
MOVOU X6, X5 \
MOVOU X7, X6 \
MOVOU X15, X7
// compute s0 four at a time and s1 two at a time
// compute W[-16] + W[-7] 4 at a time
#define FOUR_ROUNDS_AND_SCHED(a, b, c, d, e, f, g, h) \
MOVL e, R13 \ /* y0 = e */
ROLL $18, R13 \ /* y0 = e >> (25-11) */
MOVL a, R14 \ /* y1 = a */
LONG $0x0f41e3c4; WORD $0x04c6 \ // VPALIGNR XMM0,XMM7,XMM6,0x4 /* XTMP0 = W[-7] */
ROLL $23, R14 \ /* y1 = a >> (22-13) */
XORL e, R13 \ /* y0 = e ^ (e >> (25-11)) */
MOVL f, R15 \ /* y2 = f */
ROLL $27, R13 \ /* y0 = (e >> (11-6)) ^ (e >> (25-6)) */
XORL a, R14 \ /* y1 = a ^ (a >> (22-13) */
XORL g, R15 \ /* y2 = f^g */
LONG $0xc4fef9c5 \ // VPADDD XMM0,XMM0,XMM4 /* XTMP0 = W[-7] + W[-16] */
XORL e, R13 \ /* y0 = e ^ (e >> (11-6)) ^ (e >> (25-6) ) */
ANDL e, R15 \ /* y2 = (f^g)&e */
ROLL $21, R14 \ /* y1 = (a >> (13-2)) ^ (a >> (22-2)) */
\ /* */
\ /* compute s0 */
\ /* */
LONG $0x0f51e3c4; WORD $0x04cc \ // VPALIGNR XMM1,XMM5,XMM4,0x4 /* XTMP1 = W[-15] */
XORL a, R14 \ /* y1 = a ^ (a >> (13-2)) ^ (a >> (22-2)) */
ROLL $26, R13 \ /* y0 = S1 = (e>>6) & (e>>11) ^ (e>>25) */
XORL g, R15 \ /* y2 = CH = ((f^g)&e)^g */
ROLL $30, R14 \ /* y1 = S0 = (a>>2) ^ (a>>13) ^ (a>>22) */
ADDL R13, R15 \ /* y2 = S1 + CH */
ADDL _xfer+48(FP), R15 \ /* y2 = k + w + S1 + CH */
MOVL a, R13 \ /* y0 = a */
ADDL R15, h \ /* h = h + S1 + CH + k + w */
\ /* ROTATE_ARGS */
MOVL a, R15 \ /* y2 = a */
LONG $0xd172e9c5; BYTE $0x07 \ // VPSRLD XMM2,XMM1,0x7 /* */
ORL c, R13 \ /* y0 = a|c */
ADDL h, d \ /* d = d + h + S1 + CH + k + w */
ANDL c, R15 \ /* y2 = a&c */
LONG $0xf172e1c5; BYTE $0x19 \ // VPSLLD XMM3,XMM1,0x19 /* */
ANDL b, R13 \ /* y0 = (a|c)&b */
ADDL R14, h \ /* h = h + S1 + CH + k + w + S0 */
LONG $0xdaebe1c5 \ // VPOR XMM3,XMM3,XMM2 /* XTMP1 = W[-15] MY_ROR 7 */
ORL R15, R13 \ /* y0 = MAJ = (a|c)&b)|(a&c) */
ADDL R13, h \ /* h = h + S1 + CH + k + w + S0 + MAJ */
\ /* ROTATE_ARGS */
MOVL d, R13 \ /* y0 = e */
MOVL h, R14 \ /* y1 = a */
ROLL $18, R13 \ /* y0 = e >> (25-11) */
XORL d, R13 \ /* y0 = e ^ (e >> (25-11)) */
MOVL e, R15 \ /* y2 = f */
ROLL $23, R14 \ /* y1 = a >> (22-13) */
LONG $0xd172e9c5; BYTE $0x12 \ // VPSRLD XMM2,XMM1,0x12 /* */
XORL h, R14 \ /* y1 = a ^ (a >> (22-13) */
ROLL $27, R13 \ /* y0 = (e >> (11-6)) ^ (e >> (25-6)) */
XORL f, R15 \ /* y2 = f^g */
LONG $0xd172b9c5; BYTE $0x03 \ // VPSRLD XMM8,XMM1,0x3 /* XTMP4 = W[-15] >> 3 */
ROLL $21, R14 \ /* y1 = (a >> (13-2)) ^ (a >> (22-2)) */
XORL d, R13 \ /* y0 = e ^ (e >> (11-6)) ^ (e >> (25-6)) */
ANDL d, R15 \ /* y2 = (f^g)&e */
ROLL $26, R13 \ /* y0 = S1 = (e>>6) & (e>>11) ^ (e>>25) */
LONG $0xf172f1c5; BYTE $0x0e \ // VPSLLD XMM1,XMM1,0xe /* */
XORL h, R14 \ /* y1 = a ^ (a >> (13-2)) ^ (a >> (22-2)) */
XORL f, R15 \ /* y2 = CH = ((f^g)&e)^g */
LONG $0xd9efe1c5 \ // VPXOR XMM3,XMM3,XMM1 /* */
ADDL R13, R15 \ /* y2 = S1 + CH */
ADDL _xfer+52(FP), R15 \ /* y2 = k + w + S1 + CH */
ROLL $30, R14 \ /* y1 = S0 = (a>>2) ^ (a>>13) ^ (a>>22) */
LONG $0xdaefe1c5 \ // VPXOR XMM3,XMM3,XMM2 /* XTMP1 = W[-15] MY_ROR 7 ^ W[-15] MY_ROR */
MOVL h, R13 \ /* y0 = a */
ADDL R15, g \ /* h = h + S1 + CH + k + w */
MOVL h, R15 \ /* y2 = a */
LONG $0xef61c1c4; BYTE $0xc8 \ // VPXOR XMM1,XMM3,XMM8 /* XTMP1 = s0 */
ORL b, R13 \ /* y0 = a|c */
ADDL g, c \ /* d = d + h + S1 + CH + k + w */
ANDL b, R15 \ /* y2 = a&c */
\ /* */
\ /* compute low s1 */
\ /* */
LONG $0xd770f9c5; BYTE $0xfa \ // VPSHUFD XMM2,XMM7,0xfa /* XTMP2 = W[-2] {BBAA} */
ANDL a, R13 \ /* y0 = (a|c)&b */
ADDL R14, g \ /* h = h + S1 + CH + k + w + S0 */
LONG $0xc1fef9c5 \ // VPADDD XMM0,XMM0,XMM1 /* XTMP0 = W[-16] + W[-7] + s0 */
ORL R15, R13 \ /* y0 = MAJ = (a|c)&b)|(a&c) */
ADDL R13, g \ /* h = h + S1 + CH + k + w + S0 + MAJ */
\ /* ROTATE_ARGS */
MOVL c, R13 \ /* y0 = e */
MOVL g, R14 \ /* y1 = a */
ROLL $18, R13 \ /* y0 = e >> (25-11) */
XORL c, R13 \ /* y0 = e ^ (e >> (25-11)) */
ROLL $23, R14 \ /* y1 = a >> (22-13) */
MOVL d, R15 \ /* y2 = f */
XORL g, R14 \ /* y1 = a ^ (a >> (22-13) */
ROLL $27, R13 \ /* y0 = (e >> (11-6)) ^ (e >> (25-6)) */
LONG $0xd272b9c5; BYTE $0x0a \ // VPSRLD XMM8,XMM2,0xa /* XTMP4 = W[-2] >> 10 {BBAA} */
XORL e, R15 \ /* y2 = f^g */
LONG $0xd273e1c5; BYTE $0x13 \ // VPSRLQ XMM3,XMM2,0x13 /* XTMP3 = W[-2] MY_ROR 19 {xBxA} */
XORL c, R13 \ /* y0 = e ^ (e >> (11-6)) ^ (e >> (25-6)) */
ANDL c, R15 \ /* y2 = (f^g)&e */
LONG $0xd273e9c5; BYTE $0x11 \ // VPSRLQ XMM2,XMM2,0x11 /* XTMP2 = W[-2] MY_ROR 17 {xBxA} */
ROLL $21, R14 \ /* y1 = (a >> (13-2)) ^ (a >> (22-2)) */
XORL g, R14 \ /* y1 = a ^ (a >> (13-2)) ^ (a >> (22-2)) */
XORL e, R15 \ /* y2 = CH = ((f^g)&e)^g */
ROLL $26, R13 \ /* y0 = S1 = (e>>6) & (e>>11) ^ (e>>25) */
LONG $0xd3efe9c5 \ // VPXOR XMM2,XMM2,XMM3 /* */
ADDL R13, R15 \ /* y2 = S1 + CH */
ROLL $30, R14 \ /* y1 = S0 = (a>>2) ^ (a>>13) ^ (a>>22) */
ADDL _xfer+56(FP), R15 \ /* y2 = k + w + S1 + CH */
LONG $0xc2ef39c5 \ // VPXOR XMM8,XMM8,XMM2 /* XTMP4 = s1 {xBxA} */
MOVL g, R13 \ /* y0 = a */
ADDL R15, f \ /* h = h + S1 + CH + k + w */
MOVL g, R15 \ /* y2 = a */
LONG $0x003942c4; BYTE $0xc2 \ // VPSHUFB XMM8,XMM8,XMM10 /* XTMP4 = s1 {00BA} */
ORL a, R13 \ /* y0 = a|c */
ADDL f, b \ /* d = d + h + S1 + CH + k + w */
ANDL a, R15 \ /* y2 = a&c */
LONG $0xfe79c1c4; BYTE $0xc0 \ // VPADDD XMM0,XMM0,XMM8 /* XTMP0 = {..., ..., W[1], W[0]} */
ANDL h, R13 \ /* y0 = (a|c)&b */
ADDL R14, f \ /* h = h + S1 + CH + k + w + S0 */
\ /* */
\ /* compute high s1 */
\ /* */
LONG $0xd070f9c5; BYTE $0x50 \ // VPSHUFD XMM2,XMM0,0x50 /* XTMP2 = W[-2] {DDCC} */
ORL R15, R13 \ /* y0 = MAJ = (a|c)&b)|(a&c) */
ADDL R13, f \ /* h = h + S1 + CH + k + w + S0 + MAJ */
\ /* ROTATE_ARGS */
MOVL b, R13 \ /* y0 = e */
ROLL $18, R13 \ /* y0 = e >> (25-11) */
MOVL f, R14 \ /* y1 = a */
ROLL $23, R14 \ /* y1 = a >> (22-13) */
XORL b, R13 \ /* y0 = e ^ (e >> (25-11)) */
MOVL c, R15 \ /* y2 = f */
ROLL $27, R13 \ /* y0 = (e >> (11-6)) ^ (e >> (25-6)) */
LONG $0xd272a1c5; BYTE $0x0a \ // VPSRLD XMM11,XMM2,0xa /* XTMP5 = W[-2] >> 10 {DDCC} */
XORL f, R14 \ /* y1 = a ^ (a >> (22-13) */
XORL d, R15 \ /* y2 = f^g */
LONG $0xd273e1c5; BYTE $0x13 \ // VPSRLQ XMM3,XMM2,0x13 /* XTMP3 = W[-2] MY_ROR 19 {xDxC} */
XORL b, R13 \ /* y0 = e ^ (e >> (11-6)) ^ (e >> (25-6)) */
ANDL b, R15 \ /* y2 = (f^g)&e */
ROLL $21, R14 \ /* y1 = (a >> (13-2)) ^ (a >> (22-2)) */
LONG $0xd273e9c5; BYTE $0x11 \ // VPSRLQ XMM2,XMM2,0x11 /* XTMP2 = W[-2] MY_ROR 17 {xDxC} */
XORL f, R14 \ /* y1 = a ^ (a >> (13-2)) ^ (a >> (22-2)) */
ROLL $26, R13 \ /* y0 = S1 = (e>>6) & (e>>11) ^ (e>>25) */
XORL d, R15 \ /* y2 = CH = ((f^g)&e)^g */
LONG $0xd3efe9c5 \ // VPXOR XMM2,XMM2,XMM3 /* */
ROLL $30, R14 \ /* y1 = S0 = (a>>2) ^ (a>>13) ^ (a>>22) */
ADDL R13, R15 \ /* y2 = S1 + CH */
ADDL _xfer+60(FP), R15 \ /* y2 = k + w + S1 + CH */
LONG $0xdaef21c5 \ // VPXOR XMM11,XMM11,XMM2 /* XTMP5 = s1 {xDxC} */
MOVL f, R13 \ /* y0 = a */
ADDL R15, e \ /* h = h + S1 + CH + k + w */
MOVL f, R15 \ /* y2 = a */
LONG $0x002142c4; BYTE $0xdc \ // VPSHUFB XMM11,XMM11,XMM12 /* XTMP5 = s1 {DC00} */
ORL h, R13 \ /* y0 = a|c */
ADDL e, a \ /* d = d + h + S1 + CH + k + w */
ANDL h, R15 \ /* y2 = a&c */
LONG $0xe0fea1c5 \ // VPADDD XMM4,XMM11,XMM0 /* X0 = {W[3], W[2], W[1], W[0]} */
ANDL g, R13 \ /* y0 = (a|c)&b */
ADDL R14, e \ /* h = h + S1 + CH + k + w + S0 */
ORL R15, R13 \ /* y0 = MAJ = (a|c)&b)|(a&c) */
ADDL R13, e \ /* h = h + S1 + CH + k + w + S0 + MAJ */
\ /* ROTATE_ARGS */
ROTATE_XS
#define DO_ROUND(a, b, c, d, e, f, g, h, offset) \
MOVL e, R13 \ /* y0 = e */
ROLL $18, R13 \ /* y0 = e >> (25-11) */
MOVL a, R14 \ /* y1 = a */
XORL e, R13 \ /* y0 = e ^ (e >> (25-11)) */
ROLL $23, R14 \ /* y1 = a >> (22-13) */
MOVL f, R15 \ /* y2 = f */
XORL a, R14 \ /* y1 = a ^ (a >> (22-13) */
ROLL $27, R13 \ /* y0 = (e >> (11-6)) ^ (e >> (25-6)) */
XORL g, R15 \ /* y2 = f^g */
XORL e, R13 \ /* y0 = e ^ (e >> (11-6)) ^ (e >> (25-6)) */
ROLL $21, R14 \ /* y1 = (a >> (13-2)) ^ (a >> (22-2)) */
ANDL e, R15 \ /* y2 = (f^g)&e */
XORL a, R14 \ /* y1 = a ^ (a >> (13-2)) ^ (a >> (22-2)) */
ROLL $26, R13 \ /* y0 = S1 = (e>>6) & (e>>11) ^ (e>>25) */
XORL g, R15 \ /* y2 = CH = ((f^g)&e)^g */
ADDL R13, R15 \ /* y2 = S1 + CH */
ROLL $30, R14 \ /* y1 = S0 = (a>>2) ^ (a>>13) ^ (a>>22) */
ADDL _xfer+offset(FP), R15 \ /* y2 = k + w + S1 + CH */
MOVL a, R13 \ /* y0 = a */
ADDL R15, h \ /* h = h + S1 + CH + k + w */
MOVL a, R15 \ /* y2 = a */
ORL c, R13 \ /* y0 = a|c */
ADDL h, d \ /* d = d + h + S1 + CH + k + w */
ANDL c, R15 \ /* y2 = a&c */
ANDL b, R13 \ /* y0 = (a|c)&b */
ADDL R14, h \ /* h = h + S1 + CH + k + w + S0 */
ORL R15, R13 \ /* y0 = MAJ = (a|c)&b)|(a&c) */
ADDL R13, h /* h = h + S1 + CH + k + w + S0 + MAJ */
// func blockAvx(h []uint32, message []uint8, reserved0, reserved1, reserved2, reserved3 uint64)
TEXT ·blockAvx(SB), 7, $0
MOVQ h+0(FP), SI // SI: &h
MOVQ message+24(FP), R8 // &message
MOVQ lenmessage+32(FP), R9 // length of message
CMPQ R9, $0
JEQ done_hash
ADDQ R8, R9
MOVQ R9, _inp_end+64(FP) // store end of message
// Register definition
// a --> eax
// b --> ebx
// c --> ecx
// d --> r8d
// e --> edx
// f --> r9d
// g --> r10d
// h --> r11d
//
// y0 --> r13d
// y1 --> r14d
// y2 --> r15d
MOVL (0*4)(SI), AX // a = H0
MOVL (1*4)(SI), BX // b = H1
MOVL (2*4)(SI), CX // c = H2
MOVL (3*4)(SI), R8 // d = H3
MOVL (4*4)(SI), DX // e = H4
MOVL (5*4)(SI), R9 // f = H5
MOVL (6*4)(SI), R10 // g = H6
MOVL (7*4)(SI), R11 // h = H7
MOVOU bflipMask<>(SB), X13
MOVOU shuf00BA<>(SB), X10 // shuffle xBxA -> 00BA
MOVOU shufDC00<>(SB), X12 // shuffle xDxC -> DC00
MOVQ message+24(FP), SI // SI: &message
loop0:
LEAQ constants<>(SB), BP
// byte swap first 16 dwords
MOVOU 0*16(SI), X4
LONG $0x0059c2c4; BYTE $0xe5 // VPSHUFB XMM4, XMM4, XMM13
MOVOU 1*16(SI), X5
LONG $0x0051c2c4; BYTE $0xed // VPSHUFB XMM5, XMM5, XMM13
MOVOU 2*16(SI), X6
LONG $0x0049c2c4; BYTE $0xf5 // VPSHUFB XMM6, XMM6, XMM13
MOVOU 3*16(SI), X7
LONG $0x0041c2c4; BYTE $0xfd // VPSHUFB XMM7, XMM7, XMM13
MOVQ SI, _inp+72(FP)
MOVD $0x3, DI
// schedule 48 input dwords, by doing 3 rounds of 16 each
loop1:
LONG $0x4dfe59c5; BYTE $0x00 // VPADDD XMM9, XMM4, 0[RBP] /* Add 1st constant to first part of message */
MOVOU X9, _xfer+48(FP)
FOUR_ROUNDS_AND_SCHED(AX, BX, CX, R8, DX, R9, R10, R11)
LONG $0x4dfe59c5; BYTE $0x10 // VPADDD XMM9, XMM4, 16[RBP] /* Add 2nd constant to message */
MOVOU X9, _xfer+48(FP)
FOUR_ROUNDS_AND_SCHED(DX, R9, R10, R11, AX, BX, CX, R8)
LONG $0x4dfe59c5; BYTE $0x20 // VPADDD XMM9, XMM4, 32[RBP] /* Add 3rd constant to message */
MOVOU X9, _xfer+48(FP)
FOUR_ROUNDS_AND_SCHED(AX, BX, CX, R8, DX, R9, R10, R11)
LONG $0x4dfe59c5; BYTE $0x30 // VPADDD XMM9, XMM4, 48[RBP] /* Add 4th constant to message */
MOVOU X9, _xfer+48(FP)
ADDQ $64, BP
FOUR_ROUNDS_AND_SCHED(DX, R9, R10, R11, AX, BX, CX, R8)
SUBQ $1, DI
JNE loop1
MOVD $0x2, DI
loop2:
LONG $0x4dfe59c5; BYTE $0x00 // VPADDD XMM9, XMM4, 0[RBP] /* Add 1st constant to first part of message */
MOVOU X9, _xfer+48(FP)
DO_ROUND( AX, BX, CX, R8, DX, R9, R10, R11, 48)
DO_ROUND(R11, AX, BX, CX, R8, DX, R9, R10, 52)
DO_ROUND(R10, R11, AX, BX, CX, R8, DX, R9, 56)
DO_ROUND( R9, R10, R11, AX, BX, CX, R8, DX, 60)
LONG $0x4dfe51c5; BYTE $0x10 // VPADDD XMM9, XMM5, 16[RBP] /* Add 2nd constant to message */
MOVOU X9, _xfer+48(FP)
ADDQ $32, BP
DO_ROUND( DX, R9, R10, R11, AX, BX, CX, R8, 48)
DO_ROUND( R8, DX, R9, R10, R11, AX, BX, CX, 52)
DO_ROUND( CX, R8, DX, R9, R10, R11, AX, BX, 56)
DO_ROUND( BX, CX, R8, DX, R9, R10, R11, AX, 60)
MOVOU X6, X4
MOVOU X7, X5
SUBQ $1, DI
JNE loop2
MOVQ h+0(FP), SI // SI: &h
ADDL (0*4)(SI), AX // H0 = a + H0
MOVL AX, (0*4)(SI)
ADDL (1*4)(SI), BX // H1 = b + H1
MOVL BX, (1*4)(SI)
ADDL (2*4)(SI), CX // H2 = c + H2
MOVL CX, (2*4)(SI)
ADDL (3*4)(SI), R8 // H3 = d + H3
MOVL R8, (3*4)(SI)
ADDL (4*4)(SI), DX // H4 = e + H4
MOVL DX, (4*4)(SI)
ADDL (5*4)(SI), R9 // H5 = f + H5
MOVL R9, (5*4)(SI)
ADDL (6*4)(SI), R10 // H6 = g + H6
MOVL R10, (6*4)(SI)
ADDL (7*4)(SI), R11 // H7 = h + H7
MOVL R11, (7*4)(SI)
MOVQ _inp+72(FP), SI
ADDQ $64, SI
CMPQ _inp_end+64(FP), SI
JNE loop0
done_hash:
RET
// Constants table
DATA constants<>+0x0(SB)/8, $0x71374491428a2f98
DATA constants<>+0x8(SB)/8, $0xe9b5dba5b5c0fbcf
DATA constants<>+0x10(SB)/8, $0x59f111f13956c25b
DATA constants<>+0x18(SB)/8, $0xab1c5ed5923f82a4
DATA constants<>+0x20(SB)/8, $0x12835b01d807aa98
DATA constants<>+0x28(SB)/8, $0x550c7dc3243185be
DATA constants<>+0x30(SB)/8, $0x80deb1fe72be5d74
DATA constants<>+0x38(SB)/8, $0xc19bf1749bdc06a7
DATA constants<>+0x40(SB)/8, $0xefbe4786e49b69c1
DATA constants<>+0x48(SB)/8, $0x240ca1cc0fc19dc6
DATA constants<>+0x50(SB)/8, $0x4a7484aa2de92c6f
DATA constants<>+0x58(SB)/8, $0x76f988da5cb0a9dc
DATA constants<>+0x60(SB)/8, $0xa831c66d983e5152
DATA constants<>+0x68(SB)/8, $0xbf597fc7b00327c8
DATA constants<>+0x70(SB)/8, $0xd5a79147c6e00bf3
DATA constants<>+0x78(SB)/8, $0x1429296706ca6351
DATA constants<>+0x80(SB)/8, $0x2e1b213827b70a85
DATA constants<>+0x88(SB)/8, $0x53380d134d2c6dfc
DATA constants<>+0x90(SB)/8, $0x766a0abb650a7354
DATA constants<>+0x98(SB)/8, $0x92722c8581c2c92e
DATA constants<>+0xa0(SB)/8, $0xa81a664ba2bfe8a1
DATA constants<>+0xa8(SB)/8, $0xc76c51a3c24b8b70
DATA constants<>+0xb0(SB)/8, $0xd6990624d192e819
DATA constants<>+0xb8(SB)/8, $0x106aa070f40e3585
DATA constants<>+0xc0(SB)/8, $0x1e376c0819a4c116
DATA constants<>+0xc8(SB)/8, $0x34b0bcb52748774c
DATA constants<>+0xd0(SB)/8, $0x4ed8aa4a391c0cb3
DATA constants<>+0xd8(SB)/8, $0x682e6ff35b9cca4f
DATA constants<>+0xe0(SB)/8, $0x78a5636f748f82ee
DATA constants<>+0xe8(SB)/8, $0x8cc7020884c87814
DATA constants<>+0xf0(SB)/8, $0xa4506ceb90befffa
DATA constants<>+0xf8(SB)/8, $0xc67178f2bef9a3f7
DATA bflipMask<>+0x00(SB)/8, $0x0405060700010203
DATA bflipMask<>+0x08(SB)/8, $0x0c0d0e0f08090a0b
DATA shuf00BA<>+0x00(SB)/8, $0x0b0a090803020100
DATA shuf00BA<>+0x08(SB)/8, $0xFFFFFFFFFFFFFFFF
DATA shufDC00<>+0x00(SB)/8, $0xFFFFFFFFFFFFFFFF
DATA shufDC00<>+0x08(SB)/8, $0x0b0a090803020100
GLOBL constants<>(SB), 8, $256
GLOBL bflipMask<>(SB), (NOPTR+RODATA), $16
GLOBL shuf00BA<>(SB), (NOPTR+RODATA), $16
GLOBL shufDC00<>(SB), (NOPTR+RODATA), $16

@ -0,0 +1,31 @@
//+build !noasm
/*
* Minio Cloud Storage, (C) 2016 Minio, Inc.
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package sha256
//go:noescape
func blockSsse(h []uint32, message []uint8, reserved0, reserved1, reserved2, reserved3 uint64)
func blockSsseGo(dig *digest, p []byte) {
h := []uint32{dig.h[0], dig.h[1], dig.h[2], dig.h[3], dig.h[4], dig.h[5], dig.h[6], dig.h[7]}
blockSsse(h[:], p[:], 0, 0, 0, 0)
dig.h[0], dig.h[1], dig.h[2], dig.h[3], dig.h[4], dig.h[5], dig.h[6], dig.h[7] = h[0], h[1], h[2], h[3], h[4], h[5], h[6], h[7]
}

@ -0,0 +1,430 @@
//+build !noasm !appengine
// SHA256 implementation for SSSE3
//
// Minio Cloud Storage, (C) 2016 Minio, Inc.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
//
//
// This code is based on an Intel White-Paper:
// "Fast SHA-256 Implementations on Intel Architecture Processors"
//
// together with the reference implementation from the following authors:
// James Guilford <james.guilford@intel.com>
// Kirk Yap <kirk.s.yap@intel.com>
// Tim Chen <tim.c.chen@linux.intel.com>
//
// For Golang it has been converted to Plan 9 assembly with the help of
// github.com/minio/asm2plan9s to assemble Intel instructions to their Plan9
// equivalents
//
#include "textflag.h"
#define ROTATE_XS \
MOVOU X4, X15 \
MOVOU X5, X4 \
MOVOU X6, X5 \
MOVOU X7, X6 \
MOVOU X15, X7
// compute s0 four at a time and s1 two at a time
// compute W[-16] + W[-7] 4 at a time
#define FOUR_ROUNDS_AND_SCHED(a, b, c, d, e, f, g, h) \
MOVL e, R13 \ /* y0 = e */
ROLL $18, R13 \ /* y0 = e >> (25-11) */
MOVL a, R14 \ /* y1 = a */
MOVOU X7, X0 \
LONG $0x0f3a0f66; WORD $0x04c6 \ // PALIGNR XMM0,XMM6,0x4 /* XTMP0 = W[-7] */
ROLL $23, R14 \ /* y1 = a >> (22-13) */
XORL e, R13 \ /* y0 = e ^ (e >> (25-11)) */
MOVL f, R15 \ /* y2 = f */
ROLL $27, R13 \ /* y0 = (e >> (11-6)) ^ (e >> (25-6)) */
XORL a, R14 \ /* y1 = a ^ (a >> (22-13) */
XORL g, R15 \ /* y2 = f^g */
LONG $0xc4fe0f66 \ // PADDD XMM0,XMM4 /* XTMP0 = W[-7] + W[-16] */
XORL e, R13 \ /* y0 = e ^ (e >> (11-6)) ^ (e >> (25-6) ) */
ANDL e, R15 \ /* y2 = (f^g)&e */
ROLL $21, R14 \ /* y1 = (a >> (13-2)) ^ (a >> (22-2)) */
\ /* */
\ /* compute s0 */
\ /* */
MOVOU X5, X1 \
LONG $0x0f3a0f66; WORD $0x04cc \ // PALIGNR XMM1,XMM4,0x4 /* XTMP1 = W[-15] */
XORL a, R14 \ /* y1 = a ^ (a >> (13-2)) ^ (a >> (22-2)) */
ROLL $26, R13 \ /* y0 = S1 = (e>>6) & (e>>11) ^ (e>>25) */
XORL g, R15 \ /* y2 = CH = ((f^g)&e)^g */
ROLL $30, R14 \ /* y1 = S0 = (a>>2) ^ (a>>13) ^ (a>>22) */
ADDL R13, R15 \ /* y2 = S1 + CH */
ADDL _xfer+48(FP), R15 \ /* y2 = k + w + S1 + CH */
MOVL a, R13 \ /* y0 = a */
ADDL R15, h \ /* h = h + S1 + CH + k + w */
\ /* ROTATE_ARGS */
MOVL a, R15 \ /* y2 = a */
MOVOU X1, X2 \
LONG $0xd2720f66; BYTE $0x07 \ // PSRLD XMM2,0x7 /* */
ORL c, R13 \ /* y0 = a|c */
ADDL h, d \ /* d = d + h + S1 + CH + k + w */
ANDL c, R15 \ /* y2 = a&c */
MOVOU X1, X3 \
LONG $0xf3720f66; BYTE $0x19 \ // PSLLD XMM3,0x19 /* */
ANDL b, R13 \ /* y0 = (a|c)&b */
ADDL R14, h \ /* h = h + S1 + CH + k + w + S0 */
LONG $0xdaeb0f66 \ // POR XMM3,XMM2 /* XTMP1 = W[-15] MY_ROR 7 */
ORL R15, R13 \ /* y0 = MAJ = (a|c)&b)|(a&c) */
ADDL R13, h \ /* h = h + S1 + CH + k + w + S0 + MAJ */
\ /* ROTATE_ARGS */
MOVL d, R13 \ /* y0 = e */
MOVL h, R14 \ /* y1 = a */
ROLL $18, R13 \ /* y0 = e >> (25-11) */
XORL d, R13 \ /* y0 = e ^ (e >> (25-11)) */
MOVL e, R15 \ /* y2 = f */
ROLL $23, R14 \ /* y1 = a >> (22-13) */
MOVOU X1, X2 \
LONG $0xd2720f66; BYTE $0x12 \ // PSRLD XMM2,0x12 /* */
XORL h, R14 \ /* y1 = a ^ (a >> (22-13) */
ROLL $27, R13 \ /* y0 = (e >> (11-6)) ^ (e >> (25-6)) */
XORL f, R15 \ /* y2 = f^g */
MOVOU X1, X8 \
LONG $0x720f4166; WORD $0x03d0 \ // PSRLD XMM8,0x3 /* XTMP4 = W[-15] >> 3 */
ROLL $21, R14 \ /* y1 = (a >> (13-2)) ^ (a >> (22-2)) */
XORL d, R13 \ /* y0 = e ^ (e >> (11-6)) ^ (e >> (25-6)) */
ANDL d, R15 \ /* y2 = (f^g)&e */
ROLL $26, R13 \ /* y0 = S1 = (e>>6) & (e>>11) ^ (e>>25) */
LONG $0xf1720f66; BYTE $0x0e \ // PSLLD XMM1,0xe /* */
XORL h, R14 \ /* y1 = a ^ (a >> (13-2)) ^ (a >> (22-2)) */
XORL f, R15 \ /* y2 = CH = ((f^g)&e)^g */
LONG $0xd9ef0f66 \ // PXOR XMM3,XMM1 /* */
ADDL R13, R15 \ /* y2 = S1 + CH */
ADDL _xfer+52(FP), R15 \ /* y2 = k + w + S1 + CH */
ROLL $30, R14 \ /* y1 = S0 = (a>>2) ^ (a>>13) ^ (a>>22) */
LONG $0xdaef0f66 \ // PXOR XMM3,XMM2 /* XTMP1 = W[-15] MY_ROR 7 ^ W[-15] MY_ROR */
MOVL h, R13 \ /* y0 = a */
ADDL R15, g \ /* h = h + S1 + CH + k + w */
MOVL h, R15 \ /* y2 = a */
MOVOU X3, X1 \
LONG $0xef0f4166; BYTE $0xc8 \ // PXOR XMM1,XMM8 /* XTMP1 = s0 */
ORL b, R13 \ /* y0 = a|c */
ADDL g, c \ /* d = d + h + S1 + CH + k + w */
ANDL b, R15 \ /* y2 = a&c */
\ /* */
\ /* compute low s1 */
\ /* */
LONG $0xd7700f66; BYTE $0xfa \ // PSHUFD XMM2,XMM7,0xfa /* XTMP2 = W[-2] {BBAA} */
ANDL a, R13 \ /* y0 = (a|c)&b */
ADDL R14, g \ /* h = h + S1 + CH + k + w + S0 */
LONG $0xc1fe0f66 \ // PADDD XMM0,XMM1 /* XTMP0 = W[-16] + W[-7] + s0 */
ORL R15, R13 \ /* y0 = MAJ = (a|c)&b)|(a&c) */
ADDL R13, g \ /* h = h + S1 + CH + k + w + S0 + MAJ */
\ /* ROTATE_ARGS */
MOVL c, R13 \ /* y0 = e */
MOVL g, R14 \ /* y1 = a */
ROLL $18, R13 \ /* y0 = e >> (25-11) */
XORL c, R13 \ /* y0 = e ^ (e >> (25-11)) */
ROLL $23, R14 \ /* y1 = a >> (22-13) */
MOVL d, R15 \ /* y2 = f */
XORL g, R14 \ /* y1 = a ^ (a >> (22-13) */
ROLL $27, R13 \ /* y0 = (e >> (11-6)) ^ (e >> (25-6)) */
MOVOU X2, X8 \
LONG $0x720f4166; WORD $0x0ad0 \ // PSRLD XMM8,0xa /* XTMP4 = W[-2] >> 10 {BBAA} */
XORL e, R15 \ /* y2 = f^g */
MOVOU X2, X3 \
LONG $0xd3730f66; BYTE $0x13 \ // PSRLQ XMM3,0x13 /* XTMP3 = W[-2] MY_ROR 19 {xBxA} */
XORL c, R13 \ /* y0 = e ^ (e >> (11-6)) ^ (e >> (25-6)) */
ANDL c, R15 \ /* y2 = (f^g)&e */
LONG $0xd2730f66; BYTE $0x11 \ // PSRLQ XMM2,0x11 /* XTMP2 = W[-2] MY_ROR 17 {xBxA} */
ROLL $21, R14 \ /* y1 = (a >> (13-2)) ^ (a >> (22-2)) */
XORL g, R14 \ /* y1 = a ^ (a >> (13-2)) ^ (a >> (22-2)) */
XORL e, R15 \ /* y2 = CH = ((f^g)&e)^g */
ROLL $26, R13 \ /* y0 = S1 = (e>>6) & (e>>11) ^ (e>>25) */
LONG $0xd3ef0f66 \ // PXOR XMM2,XMM3 /* */
ADDL R13, R15 \ /* y2 = S1 + CH */
ROLL $30, R14 \ /* y1 = S0 = (a>>2) ^ (a>>13) ^ (a>>22) */
ADDL _xfer+56(FP), R15 \ /* y2 = k + w + S1 + CH */
LONG $0xef0f4466; BYTE $0xc2 \ // PXOR XMM8,XMM2 /* XTMP4 = s1 {xBxA} */
MOVL g, R13 \ /* y0 = a */
ADDL R15, f \ /* h = h + S1 + CH + k + w */
MOVL g, R15 \ /* y2 = a */
LONG $0x380f4566; WORD $0xc200 \ // PSHUFB XMM8,XMM10 /* XTMP4 = s1 {00BA} */
ORL a, R13 \ /* y0 = a|c */
ADDL f, b \ /* d = d + h + S1 + CH + k + w */
ANDL a, R15 \ /* y2 = a&c */
LONG $0xfe0f4166; BYTE $0xc0 \ // PADDD XMM0,XMM8 /* XTMP0 = {..., ..., W[1], W[0]} */
ANDL h, R13 \ /* y0 = (a|c)&b */
ADDL R14, f \ /* h = h + S1 + CH + k + w + S0 */
\ /* */
\ /* compute high s1 */
\ /* */
LONG $0xd0700f66; BYTE $0x50 \ // PSHUFD XMM2,XMM0,0x50 /* XTMP2 = W[-2] {DDCC} */
ORL R15, R13 \ /* y0 = MAJ = (a|c)&b)|(a&c) */
ADDL R13, f \ /* h = h + S1 + CH + k + w + S0 + MAJ */
\ /* ROTATE_ARGS */
MOVL b, R13 \ /* y0 = e */
ROLL $18, R13 \ /* y0 = e >> (25-11) */
MOVL f, R14 \ /* y1 = a */
ROLL $23, R14 \ /* y1 = a >> (22-13) */
XORL b, R13 \ /* y0 = e ^ (e >> (25-11)) */
MOVL c, R15 \ /* y2 = f */
ROLL $27, R13 \ /* y0 = (e >> (11-6)) ^ (e >> (25-6)) */
MOVOU X2, X11 \
LONG $0x720f4166; WORD $0x0ad3 \ // PSRLD XMM11,0xa /* XTMP5 = W[-2] >> 10 {DDCC} */
XORL f, R14 \ /* y1 = a ^ (a >> (22-13) */
XORL d, R15 \ /* y2 = f^g */
MOVOU X2, X3 \
LONG $0xd3730f66; BYTE $0x13 \ // PSRLQ XMM3,0x13 /* XTMP3 = W[-2] MY_ROR 19 {xDxC} */
XORL b, R13 \ /* y0 = e ^ (e >> (11-6)) ^ (e >> (25-6)) */
ANDL b, R15 \ /* y2 = (f^g)&e */
ROLL $21, R14 \ /* y1 = (a >> (13-2)) ^ (a >> (22-2)) */
LONG $0xd2730f66; BYTE $0x11 \ // PSRLQ XMM2,0x11 /* XTMP2 = W[-2] MY_ROR 17 {xDxC} */
XORL f, R14 \ /* y1 = a ^ (a >> (13-2)) ^ (a >> (22-2)) */
ROLL $26, R13 \ /* y0 = S1 = (e>>6) & (e>>11) ^ (e>>25) */
XORL d, R15 \ /* y2 = CH = ((f^g)&e)^g */
LONG $0xd3ef0f66 \ // PXOR XMM2,XMM3 /* */
ROLL $30, R14 \ /* y1 = S0 = (a>>2) ^ (a>>13) ^ (a>>22) */
ADDL R13, R15 \ /* y2 = S1 + CH */
ADDL _xfer+60(FP), R15 \ /* y2 = k + w + S1 + CH */
LONG $0xef0f4466; BYTE $0xda \ // PXOR XMM11,XMM2 /* XTMP5 = s1 {xDxC} */
MOVL f, R13 \ /* y0 = a */
ADDL R15, e \ /* h = h + S1 + CH + k + w */
MOVL f, R15 \ /* y2 = a */
LONG $0x380f4566; WORD $0xdc00 \ // PSHUFB XMM11,XMM12 /* XTMP5 = s1 {DC00} */
ORL h, R13 \ /* y0 = a|c */
ADDL e, a \ /* d = d + h + S1 + CH + k + w */
ANDL h, R15 \ /* y2 = a&c */
MOVOU X11, X4 \
LONG $0xe0fe0f66 \ // PADDD XMM4,XMM0 /* X0 = {W[3], W[2], W[1], W[0]} */
ANDL g, R13 \ /* y0 = (a|c)&b */
ADDL R14, e \ /* h = h + S1 + CH + k + w + S0 */
ORL R15, R13 \ /* y0 = MAJ = (a|c)&b)|(a&c) */
ADDL R13, e \ /* h = h + S1 + CH + k + w + S0 + MAJ */
\ /* ROTATE_ARGS */
ROTATE_XS
#define DO_ROUND(a, b, c, d, e, f, g, h, offset) \
MOVL e, R13 \ /* y0 = e */
ROLL $18, R13 \ /* y0 = e >> (25-11) */
MOVL a, R14 \ /* y1 = a */
XORL e, R13 \ /* y0 = e ^ (e >> (25-11)) */
ROLL $23, R14 \ /* y1 = a >> (22-13) */
MOVL f, R15 \ /* y2 = f */
XORL a, R14 \ /* y1 = a ^ (a >> (22-13) */
ROLL $27, R13 \ /* y0 = (e >> (11-6)) ^ (e >> (25-6)) */
XORL g, R15 \ /* y2 = f^g */
XORL e, R13 \ /* y0 = e ^ (e >> (11-6)) ^ (e >> (25-6)) */
ROLL $21, R14 \ /* y1 = (a >> (13-2)) ^ (a >> (22-2)) */
ANDL e, R15 \ /* y2 = (f^g)&e */
XORL a, R14 \ /* y1 = a ^ (a >> (13-2)) ^ (a >> (22-2)) */
ROLL $26, R13 \ /* y0 = S1 = (e>>6) & (e>>11) ^ (e>>25) */
XORL g, R15 \ /* y2 = CH = ((f^g)&e)^g */
ADDL R13, R15 \ /* y2 = S1 + CH */
ROLL $30, R14 \ /* y1 = S0 = (a>>2) ^ (a>>13) ^ (a>>22) */
ADDL _xfer+offset(FP), R15 \ /* y2 = k + w + S1 + CH */
MOVL a, R13 \ /* y0 = a */
ADDL R15, h \ /* h = h + S1 + CH + k + w */
MOVL a, R15 \ /* y2 = a */
ORL c, R13 \ /* y0 = a|c */
ADDL h, d \ /* d = d + h + S1 + CH + k + w */
ANDL c, R15 \ /* y2 = a&c */
ANDL b, R13 \ /* y0 = (a|c)&b */
ADDL R14, h \ /* h = h + S1 + CH + k + w + S0 */
ORL R15, R13 \ /* y0 = MAJ = (a|c)&b)|(a&c) */
ADDL R13, h /* h = h + S1 + CH + k + w + S0 + MAJ */
// func blockSsse(h []uint32, message []uint8, reserved0, reserved1, reserved2, reserved3 uint64)
TEXT ·blockSsse(SB), 7, $0
MOVQ h+0(FP), SI // SI: &h
MOVQ message+24(FP), R8 // &message
MOVQ lenmessage+32(FP), R9 // length of message
CMPQ R9, $0
JEQ done_hash
ADDQ R8, R9
MOVQ R9, _inp_end+64(FP) // store end of message
// Register definition
// a --> eax
// b --> ebx
// c --> ecx
// d --> r8d
// e --> edx
// f --> r9d
// g --> r10d
// h --> r11d
//
// y0 --> r13d
// y1 --> r14d
// y2 --> r15d
MOVL (0*4)(SI), AX // a = H0
MOVL (1*4)(SI), BX // b = H1
MOVL (2*4)(SI), CX // c = H2
MOVL (3*4)(SI), R8 // d = H3
MOVL (4*4)(SI), DX // e = H4
MOVL (5*4)(SI), R9 // f = H5
MOVL (6*4)(SI), R10 // g = H6
MOVL (7*4)(SI), R11 // h = H7
MOVOU bflipMask<>(SB), X13
MOVOU shuf00BA<>(SB), X10 // shuffle xBxA -> 00BA
MOVOU shufDC00<>(SB), X12 // shuffle xDxC -> DC00
MOVQ message+24(FP), SI // SI: &message
loop0:
LEAQ constants<>(SB), BP
// byte swap first 16 dwords
MOVOU 0*16(SI), X4
LONG $0x380f4166; WORD $0xe500 // PSHUFB XMM4, XMM13
MOVOU 1*16(SI), X5
LONG $0x380f4166; WORD $0xed00 // PSHUFB XMM5, XMM13
MOVOU 2*16(SI), X6
LONG $0x380f4166; WORD $0xf500 // PSHUFB XMM6, XMM13
MOVOU 3*16(SI), X7
LONG $0x380f4166; WORD $0xfd00 // PSHUFB XMM7, XMM13
MOVQ SI, _inp+72(FP)
MOVD $0x3, DI
// Align
// nop WORD PTR [rax+rax*1+0x0]
// schedule 48 input dwords, by doing 3 rounds of 16 each
loop1:
MOVOU X4, X9
LONG $0xfe0f4466; WORD $0x004d // PADDD XMM9, 0[RBP] /* Add 1st constant to first part of message */
MOVOU X9, _xfer+48(FP)
FOUR_ROUNDS_AND_SCHED(AX, BX, CX, R8, DX, R9, R10, R11)
MOVOU X4, X9
LONG $0xfe0f4466; WORD $0x104d // PADDD XMM9, 16[RBP] /* Add 2nd constant to message */
MOVOU X9, _xfer+48(FP)
FOUR_ROUNDS_AND_SCHED(DX, R9, R10, R11, AX, BX, CX, R8)
MOVOU X4, X9
LONG $0xfe0f4466; WORD $0x204d // PADDD XMM9, 32[RBP] /* Add 3rd constant to message */
MOVOU X9, _xfer+48(FP)
FOUR_ROUNDS_AND_SCHED(AX, BX, CX, R8, DX, R9, R10, R11)
MOVOU X4, X9
LONG $0xfe0f4466; WORD $0x304d // PADDD XMM9, 48[RBP] /* Add 4th constant to message */
MOVOU X9, _xfer+48(FP)
ADDQ $64, BP
FOUR_ROUNDS_AND_SCHED(DX, R9, R10, R11, AX, BX, CX, R8)
SUBQ $1, DI
JNE loop1
MOVD $0x2, DI
loop2:
MOVOU X4, X9
LONG $0xfe0f4466; WORD $0x004d // PADDD XMM9, 0[RBP] /* Add 1st constant to first part of message */
MOVOU X9, _xfer+48(FP)
DO_ROUND( AX, BX, CX, R8, DX, R9, R10, R11, 48)
DO_ROUND(R11, AX, BX, CX, R8, DX, R9, R10, 52)
DO_ROUND(R10, R11, AX, BX, CX, R8, DX, R9, 56)
DO_ROUND( R9, R10, R11, AX, BX, CX, R8, DX, 60)
MOVOU X5, X9
LONG $0xfe0f4466; WORD $0x104d // PADDD XMM9, 16[RBP] /* Add 2nd constant to message */
MOVOU X9, _xfer+48(FP)
ADDQ $32, BP
DO_ROUND( DX, R9, R10, R11, AX, BX, CX, R8, 48)
DO_ROUND( R8, DX, R9, R10, R11, AX, BX, CX, 52)
DO_ROUND( CX, R8, DX, R9, R10, R11, AX, BX, 56)
DO_ROUND( BX, CX, R8, DX, R9, R10, R11, AX, 60)
MOVOU X6, X4
MOVOU X7, X5
SUBQ $1, DI
JNE loop2
MOVQ h+0(FP), SI // SI: &h
ADDL (0*4)(SI), AX // H0 = a + H0
MOVL AX, (0*4)(SI)
ADDL (1*4)(SI), BX // H1 = b + H1
MOVL BX, (1*4)(SI)
ADDL (2*4)(SI), CX // H2 = c + H2
MOVL CX, (2*4)(SI)
ADDL (3*4)(SI), R8 // H3 = d + H3
MOVL R8, (3*4)(SI)
ADDL (4*4)(SI), DX // H4 = e + H4
MOVL DX, (4*4)(SI)
ADDL (5*4)(SI), R9 // H5 = f + H5
MOVL R9, (5*4)(SI)
ADDL (6*4)(SI), R10 // H6 = g + H6
MOVL R10, (6*4)(SI)
ADDL (7*4)(SI), R11 // H7 = h + H7
MOVL R11, (7*4)(SI)
MOVQ _inp+72(FP), SI
ADDQ $64, SI
CMPQ _inp_end+64(FP), SI
JNE loop0
done_hash:
RET
// Constants table
DATA constants<>+0x0(SB)/8, $0x71374491428a2f98
DATA constants<>+0x8(SB)/8, $0xe9b5dba5b5c0fbcf
DATA constants<>+0x10(SB)/8, $0x59f111f13956c25b
DATA constants<>+0x18(SB)/8, $0xab1c5ed5923f82a4
DATA constants<>+0x20(SB)/8, $0x12835b01d807aa98
DATA constants<>+0x28(SB)/8, $0x550c7dc3243185be
DATA constants<>+0x30(SB)/8, $0x80deb1fe72be5d74
DATA constants<>+0x38(SB)/8, $0xc19bf1749bdc06a7
DATA constants<>+0x40(SB)/8, $0xefbe4786e49b69c1
DATA constants<>+0x48(SB)/8, $0x240ca1cc0fc19dc6
DATA constants<>+0x50(SB)/8, $0x4a7484aa2de92c6f
DATA constants<>+0x58(SB)/8, $0x76f988da5cb0a9dc
DATA constants<>+0x60(SB)/8, $0xa831c66d983e5152
DATA constants<>+0x68(SB)/8, $0xbf597fc7b00327c8
DATA constants<>+0x70(SB)/8, $0xd5a79147c6e00bf3
DATA constants<>+0x78(SB)/8, $0x1429296706ca6351
DATA constants<>+0x80(SB)/8, $0x2e1b213827b70a85
DATA constants<>+0x88(SB)/8, $0x53380d134d2c6dfc
DATA constants<>+0x90(SB)/8, $0x766a0abb650a7354
DATA constants<>+0x98(SB)/8, $0x92722c8581c2c92e
DATA constants<>+0xa0(SB)/8, $0xa81a664ba2bfe8a1
DATA constants<>+0xa8(SB)/8, $0xc76c51a3c24b8b70
DATA constants<>+0xb0(SB)/8, $0xd6990624d192e819
DATA constants<>+0xb8(SB)/8, $0x106aa070f40e3585
DATA constants<>+0xc0(SB)/8, $0x1e376c0819a4c116
DATA constants<>+0xc8(SB)/8, $0x34b0bcb52748774c
DATA constants<>+0xd0(SB)/8, $0x4ed8aa4a391c0cb3
DATA constants<>+0xd8(SB)/8, $0x682e6ff35b9cca4f
DATA constants<>+0xe0(SB)/8, $0x78a5636f748f82ee
DATA constants<>+0xe8(SB)/8, $0x8cc7020884c87814
DATA constants<>+0xf0(SB)/8, $0xa4506ceb90befffa
DATA constants<>+0xf8(SB)/8, $0xc67178f2bef9a3f7
DATA bflipMask<>+0x00(SB)/8, $0x0405060700010203
DATA bflipMask<>+0x08(SB)/8, $0x0c0d0e0f08090a0b
DATA shuf00BA<>+0x00(SB)/8, $0x0b0a090803020100
DATA shuf00BA<>+0x08(SB)/8, $0xFFFFFFFFFFFFFFFF
DATA shufDC00<>+0x00(SB)/8, $0xFFFFFFFFFFFFFFFF
DATA shufDC00<>+0x08(SB)/8, $0x0b0a090803020100
GLOBL constants<>(SB), 8, $256
GLOBL bflipMask<>(SB), (NOPTR+RODATA), $16
GLOBL shuf00BA<>(SB), (NOPTR+RODATA), $16
GLOBL shufDC00<>(SB), (NOPTR+RODATA), $16

@ -0,0 +1,21 @@
//+build !noasm
/*
* Minio Cloud Storage, (C) 2016 Minio, Inc.
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package sha256
func blockArmGo(dig *digest, p []byte) {}

@ -0,0 +1,36 @@
//+build !noasm
/*
* Minio Cloud Storage, (C) 2016 Minio, Inc.
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package sha256
func blockAvx2Go(dig *digest, p []byte) {}
func blockAvxGo(dig *digest, p []byte) {}
func blockSsseGo(dig *digest, p []byte) {}
//go:noescape
func blockArm(h []uint32, message []uint8)
func blockArmGo(dig *digest, p []byte) {
h := []uint32{dig.h[0], dig.h[1], dig.h[2], dig.h[3], dig.h[4], dig.h[5], dig.h[6], dig.h[7]}
blockArm(h[:], p[:])
dig.h[0], dig.h[1], dig.h[2], dig.h[3], dig.h[4], dig.h[5], dig.h[6], dig.h[7] = h[0], h[1], h[2], h[3], h[4],
h[5], h[6], h[7]
}

@ -0,0 +1,193 @@
//+build !noasm !appengine
// ARM64 version of SHA256
//
// Minio Cloud Storage, (C) 2016 Minio, Inc.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
//
//
// Based on implementaion as found in https://github.com/jocover/sha256-armv8
//
// Use github.com/minio/asm2plan9s on this file to assemble ARM instructions to
// their Plan9 equivalents
//
TEXT ·blockArm(SB), 7, $0
MOVD h+0(FP), R0
MOVD message+24(FP), R1
MOVD lenmessage+32(FP), R2 // length of message
SUBS $64, R2
BMI complete
// Load constants table pointer
MOVD $·constants(SB), R3
// Cache constants table in registers v16 - v31
WORD $0x4cdf2870 // ld1 {v16.4s-v19.4s}, [x3], #64
WORD $0x4cdf7800 // ld1 {v0.4s}, [x0], #16
WORD $0x4cdf2874 // ld1 {v20.4s-v23.4s}, [x3], #64
WORD $0x4c407801 // ld1 {v1.4s}, [x0]
WORD $0x4cdf2878 // ld1 {v24.4s-v27.4s}, [x3], #64
WORD $0xd1004000 // sub x0, x0, #0x10
WORD $0x4cdf287c // ld1 {v28.4s-v31.4s}, [x3], #64
loop:
// Main loop
WORD $0x4cdf2025 // ld1 {v5.16b-v8.16b}, [x1], #64
WORD $0x4ea01c02 // mov v2.16b, v0.16b
WORD $0x4ea11c23 // mov v3.16b, v1.16b
WORD $0x6e2008a5 // rev32 v5.16b, v5.16b
WORD $0x6e2008c6 // rev32 v6.16b, v6.16b
WORD $0x4eb084a9 // add v9.4s, v5.4s, v16.4s
WORD $0x6e2008e7 // rev32 v7.16b, v7.16b
WORD $0x4eb184ca // add v10.4s, v6.4s, v17.4s
WORD $0x4ea21c44 // mov v4.16b, v2.16b
WORD $0x5e094062 // sha256h q2, q3, v9.4s
WORD $0x5e095083 // sha256h2 q3, q4, v9.4s
WORD $0x5e2828c5 // sha256su0 v5.4s, v6.4s
WORD $0x6e200908 // rev32 v8.16b, v8.16b
WORD $0x4eb284e9 // add v9.4s, v7.4s, v18.4s
WORD $0x4ea21c44 // mov v4.16b, v2.16b
WORD $0x5e0a4062 // sha256h q2, q3, v10.4s
WORD $0x5e0a5083 // sha256h2 q3, q4, v10.4s
WORD $0x5e2828e6 // sha256su0 v6.4s, v7.4s
WORD $0x5e0860e5 // sha256su1 v5.4s, v7.4s, v8.4s
WORD $0x4eb3850a // add v10.4s, v8.4s, v19.4s
WORD $0x4ea21c44 // mov v4.16b, v2.16b
WORD $0x5e094062 // sha256h q2, q3, v9.4s
WORD $0x5e095083 // sha256h2 q3, q4, v9.4s
WORD $0x5e282907 // sha256su0 v7.4s, v8.4s
WORD $0x5e056106 // sha256su1 v6.4s, v8.4s, v5.4s
WORD $0x4eb484a9 // add v9.4s, v5.4s, v20.4s
WORD $0x4ea21c44 // mov v4.16b, v2.16b
WORD $0x5e0a4062 // sha256h q2, q3, v10.4s
WORD $0x5e0a5083 // sha256h2 q3, q4, v10.4s
WORD $0x5e2828a8 // sha256su0 v8.4s, v5.4s
WORD $0x5e0660a7 // sha256su1 v7.4s, v5.4s, v6.4s
WORD $0x4eb584ca // add v10.4s, v6.4s, v21.4s
WORD $0x4ea21c44 // mov v4.16b, v2.16b
WORD $0x5e094062 // sha256h q2, q3, v9.4s
WORD $0x5e095083 // sha256h2 q3, q4, v9.4s
WORD $0x5e2828c5 // sha256su0 v5.4s, v6.4s
WORD $0x5e0760c8 // sha256su1 v8.4s, v6.4s, v7.4s
WORD $0x4eb684e9 // add v9.4s, v7.4s, v22.4s
WORD $0x4ea21c44 // mov v4.16b, v2.16b
WORD $0x5e0a4062 // sha256h q2, q3, v10.4s
WORD $0x5e0a5083 // sha256h2 q3, q4, v10.4s
WORD $0x5e2828e6 // sha256su0 v6.4s, v7.4s
WORD $0x5e0860e5 // sha256su1 v5.4s, v7.4s, v8.4s
WORD $0x4eb7850a // add v10.4s, v8.4s, v23.4s
WORD $0x4ea21c44 // mov v4.16b, v2.16b
WORD $0x5e094062 // sha256h q2, q3, v9.4s
WORD $0x5e095083 // sha256h2 q3, q4, v9.4s
WORD $0x5e282907 // sha256su0 v7.4s, v8.4s
WORD $0x5e056106 // sha256su1 v6.4s, v8.4s, v5.4s
WORD $0x4eb884a9 // add v9.4s, v5.4s, v24.4s
WORD $0x4ea21c44 // mov v4.16b, v2.16b
WORD $0x5e0a4062 // sha256h q2, q3, v10.4s
WORD $0x5e0a5083 // sha256h2 q3, q4, v10.4s
WORD $0x5e2828a8 // sha256su0 v8.4s, v5.4s
WORD $0x5e0660a7 // sha256su1 v7.4s, v5.4s, v6.4s
WORD $0x4eb984ca // add v10.4s, v6.4s, v25.4s
WORD $0x4ea21c44 // mov v4.16b, v2.16b
WORD $0x5e094062 // sha256h q2, q3, v9.4s
WORD $0x5e095083 // sha256h2 q3, q4, v9.4s
WORD $0x5e2828c5 // sha256su0 v5.4s, v6.4s
WORD $0x5e0760c8 // sha256su1 v8.4s, v6.4s, v7.4s
WORD $0x4eba84e9 // add v9.4s, v7.4s, v26.4s
WORD $0x4ea21c44 // mov v4.16b, v2.16b
WORD $0x5e0a4062 // sha256h q2, q3, v10.4s
WORD $0x5e0a5083 // sha256h2 q3, q4, v10.4s
WORD $0x5e2828e6 // sha256su0 v6.4s, v7.4s
WORD $0x5e0860e5 // sha256su1 v5.4s, v7.4s, v8.4s
WORD $0x4ebb850a // add v10.4s, v8.4s, v27.4s
WORD $0x4ea21c44 // mov v4.16b, v2.16b
WORD $0x5e094062 // sha256h q2, q3, v9.4s
WORD $0x5e095083 // sha256h2 q3, q4, v9.4s
WORD $0x5e282907 // sha256su0 v7.4s, v8.4s
WORD $0x5e056106 // sha256su1 v6.4s, v8.4s, v5.4s
WORD $0x4ebc84a9 // add v9.4s, v5.4s, v28.4s
WORD $0x4ea21c44 // mov v4.16b, v2.16b
WORD $0x5e0a4062 // sha256h q2, q3, v10.4s
WORD $0x5e0a5083 // sha256h2 q3, q4, v10.4s
WORD $0x5e2828a8 // sha256su0 v8.4s, v5.4s
WORD $0x5e0660a7 // sha256su1 v7.4s, v5.4s, v6.4s
WORD $0x4ebd84ca // add v10.4s, v6.4s, v29.4s
WORD $0x4ea21c44 // mov v4.16b, v2.16b
WORD $0x5e094062 // sha256h q2, q3, v9.4s
WORD $0x5e095083 // sha256h2 q3, q4, v9.4s
WORD $0x5e0760c8 // sha256su1 v8.4s, v6.4s, v7.4s
WORD $0x4ebe84e9 // add v9.4s, v7.4s, v30.4s
WORD $0x4ea21c44 // mov v4.16b, v2.16b
WORD $0x5e0a4062 // sha256h q2, q3, v10.4s
WORD $0x5e0a5083 // sha256h2 q3, q4, v10.4s
WORD $0x4ebf850a // add v10.4s, v8.4s, v31.4s
WORD $0x4ea21c44 // mov v4.16b, v2.16b
WORD $0x5e094062 // sha256h q2, q3, v9.4s
WORD $0x5e095083 // sha256h2 q3, q4, v9.4s
WORD $0x4ea21c44 // mov v4.16b, v2.16b
WORD $0x5e0a4062 // sha256h q2, q3, v10.4s
WORD $0x5e0a5083 // sha256h2 q3, q4, v10.4s
WORD $0x4ea38421 // add v1.4s, v1.4s, v3.4s
WORD $0x4ea28400 // add v0.4s, v0.4s, v2.4s
SUBS $64, R2
BPL loop
// Store result
WORD $0x4c00a800 // st1 {v0.4s, v1.4s}, [x0]
complete:
RET
// Constants table
DATA ·constants+0x0(SB)/8, $0x71374491428a2f98
DATA ·constants+0x8(SB)/8, $0xe9b5dba5b5c0fbcf
DATA ·constants+0x10(SB)/8, $0x59f111f13956c25b
DATA ·constants+0x18(SB)/8, $0xab1c5ed5923f82a4
DATA ·constants+0x20(SB)/8, $0x12835b01d807aa98
DATA ·constants+0x28(SB)/8, $0x550c7dc3243185be
DATA ·constants+0x30(SB)/8, $0x80deb1fe72be5d74
DATA ·constants+0x38(SB)/8, $0xc19bf1749bdc06a7
DATA ·constants+0x40(SB)/8, $0xefbe4786e49b69c1
DATA ·constants+0x48(SB)/8, $0x240ca1cc0fc19dc6
DATA ·constants+0x50(SB)/8, $0x4a7484aa2de92c6f
DATA ·constants+0x58(SB)/8, $0x76f988da5cb0a9dc
DATA ·constants+0x60(SB)/8, $0xa831c66d983e5152
DATA ·constants+0x68(SB)/8, $0xbf597fc7b00327c8
DATA ·constants+0x70(SB)/8, $0xd5a79147c6e00bf3
DATA ·constants+0x78(SB)/8, $0x1429296706ca6351
DATA ·constants+0x80(SB)/8, $0x2e1b213827b70a85
DATA ·constants+0x88(SB)/8, $0x53380d134d2c6dfc
DATA ·constants+0x90(SB)/8, $0x766a0abb650a7354
DATA ·constants+0x98(SB)/8, $0x92722c8581c2c92e
DATA ·constants+0xa0(SB)/8, $0xa81a664ba2bfe8a1
DATA ·constants+0xa8(SB)/8, $0xc76c51a3c24b8b70
DATA ·constants+0xb0(SB)/8, $0xd6990624d192e819
DATA ·constants+0xb8(SB)/8, $0x106aa070f40e3585
DATA ·constants+0xc0(SB)/8, $0x1e376c0819a4c116
DATA ·constants+0xc8(SB)/8, $0x34b0bcb52748774c
DATA ·constants+0xd0(SB)/8, $0x4ed8aa4a391c0cb3
DATA ·constants+0xd8(SB)/8, $0x682e6ff35b9cca4f
DATA ·constants+0xe0(SB)/8, $0x78a5636f748f82ee
DATA ·constants+0xe8(SB)/8, $0x8cc7020884c87814
DATA ·constants+0xf0(SB)/8, $0xa4506ceb90befffa
DATA ·constants+0xf8(SB)/8, $0xc67178f2bef9a3f7
GLOBL ·constants(SB), 8, $256

@ -0,0 +1,136 @@
//+build !arm64 !amd64 noasm appengine
/*
* Minio Cloud Storage, (C) 2016 Minio, Inc.
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package sha256
func blockGeneric(dig *digest, p []byte) {
var w [64]uint32
h0, h1, h2, h3, h4, h5, h6, h7 := dig.h[0], dig.h[1], dig.h[2], dig.h[3], dig.h[4], dig.h[5], dig.h[6], dig.h[7]
for len(p) >= chunk {
// Can interlace the computation of w with the
// rounds below if needed for speed.
for i := 0; i < 16; i++ {
j := i * 4
w[i] = uint32(p[j])<<24 | uint32(p[j+1])<<16 | uint32(p[j+2])<<8 | uint32(p[j+3])
}
for i := 16; i < 64; i++ {
v1 := w[i-2]
t1 := (v1>>17 | v1<<(32-17)) ^ (v1>>19 | v1<<(32-19)) ^ (v1 >> 10)
v2 := w[i-15]
t2 := (v2>>7 | v2<<(32-7)) ^ (v2>>18 | v2<<(32-18)) ^ (v2 >> 3)
w[i] = t1 + w[i-7] + t2 + w[i-16]
}
a, b, c, d, e, f, g, h := h0, h1, h2, h3, h4, h5, h6, h7
for i := 0; i < 64; i++ {
t1 := h + ((e>>6 | e<<(32-6)) ^ (e>>11 | e<<(32-11)) ^ (e>>25 | e<<(32-25))) + ((e & f) ^ (^e & g)) + _K[i] + w[i]
t2 := ((a>>2 | a<<(32-2)) ^ (a>>13 | a<<(32-13)) ^ (a>>22 | a<<(32-22))) + ((a & b) ^ (a & c) ^ (b & c))
h = g
g = f
f = e
e = d + t1
d = c
c = b
b = a
a = t1 + t2
}
h0 += a
h1 += b
h2 += c
h3 += d
h4 += e
h5 += f
h6 += g
h7 += h
p = p[chunk:]
}
dig.h[0], dig.h[1], dig.h[2], dig.h[3], dig.h[4], dig.h[5], dig.h[6], dig.h[7] = h0, h1, h2, h3, h4, h5, h6, h7
}
var _K = []uint32{
0x428a2f98,
0x71374491,
0xb5c0fbcf,
0xe9b5dba5,
0x3956c25b,
0x59f111f1,
0x923f82a4,
0xab1c5ed5,
0xd807aa98,
0x12835b01,
0x243185be,
0x550c7dc3,
0x72be5d74,
0x80deb1fe,
0x9bdc06a7,
0xc19bf174,
0xe49b69c1,
0xefbe4786,
0x0fc19dc6,
0x240ca1cc,
0x2de92c6f,
0x4a7484aa,
0x5cb0a9dc,
0x76f988da,
0x983e5152,
0xa831c66d,
0xb00327c8,
0xbf597fc7,
0xc6e00bf3,
0xd5a79147,
0x06ca6351,
0x14292967,
0x27b70a85,
0x2e1b2138,
0x4d2c6dfc,
0x53380d13,
0x650a7354,
0x766a0abb,
0x81c2c92e,
0x92722c85,
0xa2bfe8a1,
0xa81a664b,
0xc24b8b70,
0xc76c51a3,
0xd192e819,
0xd6990624,
0xf40e3585,
0x106aa070,
0x19a4c116,
0x1e376c08,
0x2748774c,
0x34b0bcb5,
0x391c0cb3,
0x4ed8aa4a,
0x5b9cca4f,
0x682e6ff3,
0x748f82ee,
0x78a5636f,
0x84c87814,
0x8cc70208,
0x90befffa,
0xa4506ceb,
0xbef9a3f7,
0xc67178f2,
}

@ -118,6 +118,12 @@
"revision": "5e2117cd32d677a36dcd8c9c83776a065555653b",
"revisionTime": "2016-07-24T00:05:56Z"
},
{
"checksumSHA1": "pGgL9xre+/LmNfZV7rNE8uyAovQ=",
"path": "github.com/minio/sha256-simd",
"revision": "8058cafa697e657caa0beb136bd3cbda50fc4496",
"revisionTime": "2016-07-28T21:10:57Z"
},
{
"path": "github.com/pkg/profile",
"revision": "c78aac22bd43883fd2817833b982153dcac17b3b",

Loading…
Cancel
Save